[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3_LTO - Build # 9 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit 0237dbfdd38053cc190f814b6f92e311ae3509c6
Author: Chuanqi Xu <yedeng.yd(a)linux.alibaba.com>
Date: Tue Jul 27 13:13:39 2021 +0800
[Coroutine] Record the elided coroutines
Reviewed By: lxfind
Differential Revision: https://reviews.llvm.org/D105606
</cut>
Results regressed to (for first_bad == 0237dbfdd38053cc190f814b6f92e311ae3509c6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-0237dbfdd38053cc190f814b6f92e311ae3509c6/results_id:
1
# 458.sjeng,sjeng_base.default regressed by 104
from (for last_good == dbefcde6da1b58eb181dcbd8d7913175b2ec8350)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-dbefcde6da1b58eb181dcbd8d7913175b2ec8350/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/4264
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/4262
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-0237dbfdd38053cc190f814b6f92e311ae3509c6
cd investigate-llvm-0237dbfdd38053cc190f814b6f92e311ae3509c6
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 0237dbfdd38053cc190f814b6f92e311ae3509c6
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dbefcde6da1b58eb181dcbd8d7913175b2ec8350
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 0237dbfdd38053cc190f814b6f92e311ae3509c6
Author: Chuanqi Xu <yedeng.yd(a)linux.alibaba.com>
Date: Tue Jul 27 13:13:39 2021 +0800
[Coroutine] Record the elided coroutines
Reviewed By: lxfind
Differential Revision: https://reviews.llvm.org/D105606
---
llvm/lib/Transforms/Coroutines/CoroElide.cpp | 28 ++++++++++++++++++++++
.../{coro-elide-count.ll => coro-elide-stat.ll} | 7 ++++++
2 files changed, 35 insertions(+)
diff --git a/llvm/lib/Transforms/Coroutines/CoroElide.cpp b/llvm/lib/Transforms/Coroutines/CoroElide.cpp
index d35a5de6d4bd..84bebb7bf42d 100644
--- a/llvm/lib/Transforms/Coroutines/CoroElide.cpp
+++ b/llvm/lib/Transforms/Coroutines/CoroElide.cpp
@@ -17,6 +17,7 @@
#include "llvm/InitializePasses.h"
#include "llvm/Pass.h"
#include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/FileSystem.h"
using namespace llvm;
@@ -24,6 +25,12 @@ using namespace llvm;
STATISTIC(NumOfCoroElided, "The # of coroutine get elided.");
+#ifndef NDEBUG
+static cl::opt<std::string> CoroElideInfoOutputFilename(
+ "coro-elide-info-output-file", cl::value_desc("filename"),
+ cl::desc("File to record the coroutines got elided"), cl::Hidden);
+#endif
+
namespace {
// Created on demand if the coro-elide pass has work to do.
struct Lowerer : coro::LowererBase {
@@ -121,6 +128,21 @@ static Instruction *getFirstNonAllocaInTheEntryBlock(Function *F) {
llvm_unreachable("no terminator in the entry block");
}
+#ifndef NDEBUG
+static std::unique_ptr<raw_fd_ostream> getOrCreateLogFile() {
+ assert(!CoroElideInfoOutputFilename.empty() &&
+ "coro-elide-info-output-file shouldn't be empty");
+ std::error_code EC;
+ auto Result = std::make_unique<raw_fd_ostream>(CoroElideInfoOutputFilename,
+ EC, sys::fs::OF_Append);
+ if (!EC)
+ return Result;
+ llvm::errs() << "Error opening coro-elide-info-output-file '"
+ << CoroElideInfoOutputFilename << " for appending!\n";
+ return std::make_unique<raw_fd_ostream>(2, false); // stderr.
+}
+#endif
+
// To elide heap allocations we need to suppress code blocks guarded by
// llvm.coro.alloc and llvm.coro.free instructions.
void Lowerer::elideHeapAllocations(Function *F, uint64_t FrameSize,
@@ -344,6 +366,12 @@ bool Lowerer::processCoroId(CoroIdInst *CoroId, AAResults &AA,
FrameSizeAndAlign.second, AA);
coro::replaceCoroFree(CoroId, /*Elide=*/true);
NumOfCoroElided++;
+#ifndef NDEBUG
+ if (!CoroElideInfoOutputFilename.empty())
+ *getOrCreateLogFile()
+ << "Elide " << CoroId->getCoroutine()->getName() << " in "
+ << CoroId->getFunction()->getName() << "\n";
+#endif
}
return true;
diff --git a/llvm/test/Transforms/Coroutines/coro-elide-count.ll b/llvm/test/Transforms/Coroutines/coro-elide-stat.ll
similarity index 92%
rename from llvm/test/Transforms/Coroutines/coro-elide-count.ll
rename to llvm/test/Transforms/Coroutines/coro-elide-stat.ll
index ae40a74f41d5..e92d484786c5 100644
--- a/llvm/test/Transforms/Coroutines/coro-elide-count.ll
+++ b/llvm/test/Transforms/Coroutines/coro-elide-stat.ll
@@ -4,8 +4,15 @@
; RUN: opt < %s -S \
; RUN: -passes='cgscc(repeat<2>(inline,function(coro-elide,dce)))' -stats 2>&1 \
; RUN: | FileCheck %s
+; RUN: opt < %s --disable-output \
+; RUN: -passes='cgscc(repeat<2>(inline,function(coro-elide,dce)))' \
+; RUN: -coro-elide-info-output-file=%t && \
+; RUN: cat %t \
+; RUN: | FileCheck %s --check-prefix=FILE
; CHECK: 2 coro-elide - The # of coroutine get elided.
+; FILE: Elide f in callResume
+; FILE: Elide f in callResumeMultiRetDommmed
declare void @print(i32) nounwind
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3_LTO - Build # 8 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3_LTO
Culprit:
<cut>
commit bb1e5399e4586239d6424f5eea5a9f06c52ebe9b
Author: Vitaly Buka <vitalybuka(a)google.com>
Date: Fri Apr 2 00:58:09 2021 -0700
[NFC][scudo] Inline some functions into ScudoPrimaryTest
</cut>
Results regressed to (for first_bad == bb1e5399e4586239d6424f5eea5a9f06c52ebe9b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-bb1e5399e4586239d6424f5eea5a9f06c52ebe9b/results_id:
1
# 462.libquantum,libquantum_base.default regressed by 105
from (for last_good == f343a730596b6b02039a91d71dc16c113d09cfe6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-baseline/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/baseline-llvm-release-arm-spec2k6-O3_LTO/4201
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3_LTO/4234
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-bb1e5399e4586239d6424f5eea5a9f06c52ebe9b
cd investigate-llvm-bb1e5399e4586239d6424f5eea5a9f06c52ebe9b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach bb1e5399e4586239d6424f5eea5a9f06c52ebe9b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach f343a730596b6b02039a91d71dc16c113d09cfe6
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit bb1e5399e4586239d6424f5eea5a9f06c52ebe9b
Author: Vitaly Buka <vitalybuka(a)google.com>
Date: Fri Apr 2 00:58:09 2021 -0700
[NFC][scudo] Inline some functions into ScudoPrimaryTest
---
.../lib/scudo/standalone/tests/primary_test.cpp | 173 +++++++++------------
1 file changed, 71 insertions(+), 102 deletions(-)
diff --git a/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp b/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp
index 07f3d6b77c17..2707985b5c72 100644
--- a/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp
+++ b/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp
@@ -21,37 +21,6 @@
// 32-bit architectures. It's not something we want to encourage, but we still
// should ensure the tests pass.
-template <typename Primary> static void testPrimary() {
- const scudo::uptr NumberOfAllocations = 32U;
- auto Deleter = [](Primary *P) {
- P->unmapTestOnly();
- delete P;
- };
- std::unique_ptr<Primary, decltype(Deleter)> Allocator(new Primary, Deleter);
- Allocator->init(/*ReleaseToOsInterval=*/-1);
- typename Primary::CacheT Cache;
- Cache.init(nullptr, Allocator.get());
- for (scudo::uptr I = 0; I <= 16U; I++) {
- const scudo::uptr Size = 1UL << I;
- if (!Primary::canAllocate(Size))
- continue;
- const scudo::uptr ClassId = Primary::SizeClassMap::getClassIdBySize(Size);
- void *Pointers[NumberOfAllocations];
- for (scudo::uptr J = 0; J < NumberOfAllocations; J++) {
- void *P = Cache.allocate(ClassId);
- memset(P, 'B', Size);
- Pointers[J] = P;
- }
- for (scudo::uptr J = 0; J < NumberOfAllocations; J++)
- Cache.deallocate(ClassId, Pointers[J]);
- }
- Cache.destroy(nullptr);
- Allocator->releaseToOS();
- scudo::ScopedString Str(1024);
- Allocator->getStats(&Str);
- Str.output();
-}
-
struct TestConfig1 {
static const scudo::uptr PrimaryRegionSizeLog = 18U;
static const scudo::s32 PrimaryMinReleaseToOsIntervalMs = INT32_MIN;
@@ -84,13 +53,16 @@ struct Config : public BaseConfig {
using SizeClassMap = SizeClassMapT;
};
-template <typename BaseConfig, typename SizeClassMapT> struct MakeAllocator {
- using Value = scudo::SizeClassAllocator64<Config<BaseConfig, SizeClassMapT>>;
-};
-
+template <typename BaseConfig, typename SizeClassMapT>
+struct SizeClassAllocator
+ : public scudo::SizeClassAllocator64<Config<BaseConfig, SizeClassMapT>> {};
template <typename SizeClassMapT>
-struct MakeAllocator<TestConfig1, SizeClassMapT> {
- using Value = scudo::SizeClassAllocator32<Config<TestConfig1, SizeClassMapT>>;
+struct SizeClassAllocator<TestConfig1, SizeClassMapT>
+ : public scudo::SizeClassAllocator32<Config<TestConfig1, SizeClassMapT>> {};
+
+template <typename BaseConfig, typename SizeClassMapT>
+struct TestAllocator : public SizeClassAllocator<BaseConfig, SizeClassMapT> {
+ ~TestAllocator() { this->unmapTestOnly(); }
};
namespace testing {
@@ -114,8 +86,31 @@ using ScudoPrimaryTestTypes = testing::Types<
TYPED_TEST_CASE(ScudoPrimaryTest, ScudoPrimaryTestTypes);
TYPED_TEST(ScudoPrimaryTest, BasicPrimary) {
- using SizeClassMap = scudo::DefaultSizeClassMap;
- testPrimary<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
+ using Primary = TestAllocator<TypeParam, scudo::DefaultSizeClassMap>;
+ std::unique_ptr<Primary> Allocator(new Primary);
+ Allocator->init(/*ReleaseToOsInterval=*/-1);
+ typename Primary::CacheT Cache;
+ Cache.init(nullptr, Allocator.get());
+ const scudo::uptr NumberOfAllocations = 32U;
+ for (scudo::uptr I = 0; I <= 16U; I++) {
+ const scudo::uptr Size = 1UL << I;
+ if (!Primary::canAllocate(Size))
+ continue;
+ const scudo::uptr ClassId = Primary::SizeClassMap::getClassIdBySize(Size);
+ void *Pointers[NumberOfAllocations];
+ for (scudo::uptr J = 0; J < NumberOfAllocations; J++) {
+ void *P = Cache.allocate(ClassId);
+ memset(P, 'B', Size);
+ Pointers[J] = P;
+ }
+ for (scudo::uptr J = 0; J < NumberOfAllocations; J++)
+ Cache.deallocate(ClassId, Pointers[J]);
+ }
+ Cache.destroy(nullptr);
+ Allocator->releaseToOS();
+ scudo::ScopedString Str(1024);
+ Allocator->getStats(&Str);
+ Str.output();
}
struct SmallRegionsConfig {
@@ -166,12 +161,9 @@ TEST(ScudoPrimaryTest, Primary64OOM) {
Allocator.unmapTestOnly();
}
-template <typename Primary> static void testIteratePrimary() {
- auto Deleter = [](Primary *P) {
- P->unmapTestOnly();
- delete P;
- };
- std::unique_ptr<Primary, decltype(Deleter)> Allocator(new Primary, Deleter);
+TYPED_TEST(ScudoPrimaryTest, PrimaryIterate) {
+ using Primary = TestAllocator<TypeParam, scudo::DefaultSizeClassMap>;
+ std::unique_ptr<Primary> Allocator(new Primary);
Allocator->init(/*ReleaseToOsInterval=*/-1);
typename Primary::CacheT Cache;
Cache.init(nullptr, Allocator.get());
@@ -205,50 +197,40 @@ template <typename Primary> static void testIteratePrimary() {
Str.output();
}
-TYPED_TEST(ScudoPrimaryTest, PrimaryIterate) {
- using SizeClassMap = scudo::DefaultSizeClassMap;
- testIteratePrimary<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
-}
-
-static std::mutex Mutex;
-static std::condition_variable Cv;
-static bool Ready;
-
-template <typename Primary> static void performAllocations(Primary *Allocator) {
- static thread_local typename Primary::CacheT Cache;
- Cache.init(nullptr, Allocator);
- std::vector<std::pair<scudo::uptr, void *>> V;
- {
- std::unique_lock<std::mutex> Lock(Mutex);
- while (!Ready)
- Cv.wait(Lock);
- }
- for (scudo::uptr I = 0; I < 256U; I++) {
- const scudo::uptr Size = std::rand() % Primary::SizeClassMap::MaxSize / 4;
- const scudo::uptr ClassId = Primary::SizeClassMap::getClassIdBySize(Size);
- void *P = Cache.allocate(ClassId);
- if (P)
- V.push_back(std::make_pair(ClassId, P));
- }
- while (!V.empty()) {
- auto Pair = V.back();
- Cache.deallocate(Pair.first, Pair.second);
- V.pop_back();
- }
- Cache.destroy(nullptr);
-}
-
-template <typename Primary> static void testPrimaryThreaded() {
- Ready = false;
- auto Deleter = [](Primary *P) {
- P->unmapTestOnly();
- delete P;
- };
- std::unique_ptr<Primary, decltype(Deleter)> Allocator(new Primary, Deleter);
+TYPED_TEST(ScudoPrimaryTest, PrimaryThreaded) {
+ using Primary = TestAllocator<TypeParam, scudo::SvelteSizeClassMap>;
+ std::unique_ptr<Primary> Allocator(new Primary);
Allocator->init(/*ReleaseToOsInterval=*/-1);
+ std::mutex Mutex;
+ std::condition_variable Cv;
+ bool Ready = false;
std::thread Threads[32];
for (scudo::uptr I = 0; I < ARRAY_SIZE(Threads); I++)
- Threads[I] = std::thread(performAllocations<Primary>, Allocator.get());
+ Threads[I] = std::thread([&]() {
+ static thread_local typename Primary::CacheT Cache;
+ Cache.init(nullptr, Allocator.get());
+ std::vector<std::pair<scudo::uptr, void *>> V;
+ {
+ std::unique_lock<std::mutex> Lock(Mutex);
+ while (!Ready)
+ Cv.wait(Lock);
+ }
+ for (scudo::uptr I = 0; I < 256U; I++) {
+ const scudo::uptr Size =
+ std::rand() % Primary::SizeClassMap::MaxSize / 4;
+ const scudo::uptr ClassId =
+ Primary::SizeClassMap::getClassIdBySize(Size);
+ void *P = Cache.allocate(ClassId);
+ if (P)
+ V.push_back(std::make_pair(ClassId, P));
+ }
+ while (!V.empty()) {
+ auto Pair = V.back();
+ Cache.deallocate(Pair.first, Pair.second);
+ V.pop_back();
+ }
+ Cache.destroy(nullptr);
+ });
{
std::unique_lock<std::mutex> Lock(Mutex);
Ready = true;
@@ -262,20 +244,12 @@ template <typename Primary> static void testPrimaryThreaded() {
Str.output();
}
-TYPED_TEST(ScudoPrimaryTest, PrimaryThreaded) {
- using SizeClassMap = scudo::SvelteSizeClassMap;
- testPrimaryThreaded<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
-}
-
// Through a simple allocation that spans two pages, verify that releaseToOS
// actually releases some bytes (at least one page worth). This is a regression
// test for an error in how the release criteria were computed.
-template <typename Primary> static void testReleaseToOS() {
- auto Deleter = [](Primary *P) {
- P->unmapTestOnly();
- delete P;
- };
- std::unique_ptr<Primary, decltype(Deleter)> Allocator(new Primary, Deleter);
+TYPED_TEST(ScudoPrimaryTest, ReleaseToOS) {
+ using Primary = TestAllocator<TypeParam, scudo::DefaultSizeClassMap>;
+ std::unique_ptr<Primary> Allocator(new Primary);
Allocator->init(/*ReleaseToOsInterval=*/-1);
typename Primary::CacheT Cache;
Cache.init(nullptr, Allocator.get());
@@ -288,8 +262,3 @@ template <typename Primary> static void testReleaseToOS() {
Cache.destroy(nullptr);
EXPECT_GT(Allocator->releaseToOS(), 0U);
}
-
-TYPED_TEST(ScudoPrimaryTest, ReleaseToOS) {
- using SizeClassMap = scudo::DefaultSizeClassMap;
- testReleaseToOS<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
-}
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3_LTO - Build # 8 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b
Author: Carl Ritson <carl.ritson(a)amd.com>
Date: Tue May 11 12:14:01 2021 +0900
[AMDGPU] Pre-commit tests for D102211
</cut>
Results regressed to (for first_bad == ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b/results_id:
1
# 473.astar,astar_base.default regressed by 104
from (for last_good == d8ec2b183e9243366e3a0cd1116dbe879856b333)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-d8ec2b183e9243366e3a0cd1116dbe879856b333/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/4218
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/4219
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b
cd investigate-llvm-ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach d8ec2b183e9243366e3a0cd1116dbe879856b333
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit ad558a4ff7cd61081cfeaabff1dbc8c0a9afa92b
Author: Carl Ritson <carl.ritson(a)amd.com>
Date: Tue May 11 12:14:01 2021 +0900
[AMDGPU] Pre-commit tests for D102211
---
llvm/test/CodeGen/AMDGPU/hard-clauses.mir | 36 +++++++++++++++++++++++++++++++
1 file changed, 36 insertions(+)
diff --git a/llvm/test/CodeGen/AMDGPU/hard-clauses.mir b/llvm/test/CodeGen/AMDGPU/hard-clauses.mir
index 506f9a77c177..e6ca33341bfb 100644
--- a/llvm/test/CodeGen/AMDGPU/hard-clauses.mir
+++ b/llvm/test/CodeGen/AMDGPU/hard-clauses.mir
@@ -209,3 +209,39 @@ body: |
$vgpr79 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 316, 0, 0, 0, implicit $exec
$vgpr80 = BUFFER_LOAD_DWORD_OFFEN $vgpr0, $sgpr0_sgpr1_sgpr2_sgpr3, 0, 320, 0, 0, 0, implicit $exec
...
+
+---
+name: mimg_nsa
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
+ ; CHECK-LABEL: name: mimg_nsa
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
+ ; CHECK: BUNDLE implicit-def $vgpr10_vgpr11_vgpr12_vgpr13, implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr13, implicit-def $vgpr13_lo16, implicit-def $vgpr13_hi16, implicit-def $vgpr10_vgpr11, implicit-def $vgpr10_vgpr11_vgpr12, implicit-def $vgpr11_vgpr12, implicit-def $vgpr11_vgpr12_vgpr13, implicit-def $vgpr12_vgpr13, implicit-def $vgpr20_vgpr21_vgpr22_vgpr23, implicit-def $vgpr20, implicit-def $vgpr20_lo16, implicit-def $vgpr20_hi16, implicit-def $vgpr21, implicit-def $vgpr21_lo16, implicit-def $vgpr21_hi16, implicit-def $vgpr22, implicit-def $vgpr22_lo16, implicit-def $vgpr22_hi16, implicit-def $vgpr23, implicit-def $vgpr23_lo16, implicit-def $vgpr23_hi16, implicit-def $vgpr20_vgpr21, implicit-def $vgpr20_vgpr21_vgpr22, implicit-def $vgpr21_vgpr22, implicit-def $vgpr21_vgpr22_vgpr23, implicit-def $vgpr22_vgpr23, implicit $vgpr3, implicit $vgpr8, implicit $vgpr7, implicit $vgpr5, implicit $vgpr4, implicit $vgpr6, implicit $vgpr0, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, implicit $sgpr8_sgpr9_sgpr10_sgpr11, implicit $exec {
+ ; CHECK: S_CLAUSE 1
+ ; CHECK: $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+ ; CHECK: $vgpr20_vgpr21_vgpr22_vgpr23 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+ ; CHECK: }
+ $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+ $vgpr20_vgpr21_vgpr22_vgpr23 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+...
+
+---
+name: mimg_nsa_mixed
+tracksRegLiveness: true
+body: |
+ bb.0:
+ liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
+ ; CHECK-LABEL: name: mimg_nsa_mixed
+ ; CHECK: liveins: $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, $vgpr0, $vgpr1, $vgpr2, $vgpr3, $vgpr4, $vgpr5, $vgpr6, $vgpr7, $vgpr8
+ ; CHECK: BUNDLE implicit-def $vgpr10_vgpr11_vgpr12_vgpr13, implicit-def $vgpr10, implicit-def $vgpr10_lo16, implicit-def $vgpr10_hi16, implicit-def $vgpr11, implicit-def $vgpr11_lo16, implicit-def $vgpr11_hi16, implicit-def $vgpr12, implicit-def $vgpr12_lo16, implicit-def $vgpr12_hi16, implicit-def $vgpr13, implicit-def $vgpr13_lo16, implicit-def $vgpr13_hi16, implicit-def $vgpr10_vgpr11, implicit-def $vgpr10_vgpr11_vgpr12, implicit-def $vgpr11_vgpr12, implicit-def $vgpr11_vgpr12_vgpr13, implicit-def $vgpr12_vgpr13, implicit-def $vgpr14, implicit-def $vgpr14_lo16, implicit-def $vgpr14_hi16, implicit-def $vgpr20_vgpr21_vgpr22_vgpr23, implicit-def $vgpr20, implicit-def $vgpr20_lo16, implicit-def $vgpr20_hi16, implicit-def $vgpr21, implicit-def $vgpr21_lo16, implicit-def $vgpr21_hi16, implicit-def $vgpr22, implicit-def $vgpr22_lo16, implicit-def $vgpr22_hi16, implicit-def $vgpr23, implicit-def $vgpr23_lo16, implicit-def $vgpr23_hi16, implicit-def $vgpr20_vgpr21, implicit-def $vgpr20_vgpr21_vgpr22, implicit-def $vgpr21_vgpr22, implicit-def $vgpr21_vgpr22_vgpr23, implicit-def $vgpr22_vgpr23, implicit $vgpr3, implicit $vgpr8, implicit $vgpr7, implicit $vgpr5, implicit $vgpr4, implicit $vgpr6, implicit $vgpr0, implicit $vgpr2, implicit $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, implicit $sgpr8_sgpr9_sgpr10_sgpr11, implicit $exec, implicit $vgpr5_vgpr6 {
+ ; CHECK: S_CLAUSE 2
+ ; CHECK: $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+ ; CHECK: $vgpr14 = IMAGE_SAMPLE_LZ_V1_V2_gfx10 $vgpr5_vgpr6, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load 16 from custom "ImageResource")
+ ; CHECK: $vgpr20_vgpr21_vgpr22_vgpr23 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+ ; CHECK: }
+ $vgpr10_vgpr11_vgpr12_vgpr13 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+ $vgpr14 = IMAGE_SAMPLE_LZ_V1_V2_gfx10 $vgpr5_vgpr6, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 1, 1, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (dereferenceable load 16 from custom "ImageResource")
+ $vgpr20_vgpr21_vgpr22_vgpr23 = IMAGE_SAMPLE_D_V4_V9_nsa_gfx10 $vgpr3, $vgpr8, $vgpr7, $vgpr5, $vgpr4, $vgpr6, $vgpr0, $vgpr2, $vgpr2, $sgpr0_sgpr1_sgpr2_sgpr3_sgpr4_sgpr5_sgpr6_sgpr7, $sgpr8_sgpr9_sgpr10_sgpr11, 15, 2, 0, 0, 0, 0, 0, 0, 0, implicit $exec :: (load 16)
+...
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3 - Build # 11 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3
Culprit:
<cut>
commit 99203f2004d031f2ef22f01e3c569d2775de1836
Author: Alexey Bataev <a.bataev(a)outlook.com>
Date: Tue Mar 23 13:22:58 2021 -0700
[Analysis]Add getPointersDiff function to improve compile time.
Added getPointersDiff function to LoopAccessAnalysis and used it instead
direct calculatoin of the distance between pointers and/or
isConsecutiveAccess function in SLP vectorizer to improve compile time
and detection of stores consecutive chains.
Part of D57059
Differential Revision: https://reviews.llvm.org/D98967
</cut>
Results regressed to (for first_bad == 99203f2004d031f2ef22f01e3c569d2775de1836)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-99203f2004d031f2ef22f01e3c569d2775de1836/results_id:
1
# 458.sjeng,sjeng_base.default regressed by 103
from (for last_good == 4157a079afbf7fa5c3ce3ac0e9f4541f89188ae2)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-4157a079afbf7fa5c3ce3ac0e9f4541f89188ae2/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/4192
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/4194
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-99203f2004d031f2ef22f01e3c569d2775de1836
cd investigate-llvm-99203f2004d031f2ef22f01e3c569d2775de1836
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 99203f2004d031f2ef22f01e3c569d2775de1836
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 4157a079afbf7fa5c3ce3ac0e9f4541f89188ae2
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 99203f2004d031f2ef22f01e3c569d2775de1836
Author: Alexey Bataev <a.bataev(a)outlook.com>
Date: Tue Mar 23 13:22:58 2021 -0700
[Analysis]Add getPointersDiff function to improve compile time.
Added getPointersDiff function to LoopAccessAnalysis and used it instead
direct calculatoin of the distance between pointers and/or
isConsecutiveAccess function in SLP vectorizer to improve compile time
and detection of stores consecutive chains.
Part of D57059
Differential Revision: https://reviews.llvm.org/D98967
---
llvm/include/llvm/Analysis/LoopAccessAnalysis.h | 9 +
llvm/lib/Analysis/LoopAccessAnalysis.cpp | 198 ++++++++++------------
llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp | 79 ++++++---
llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll | 17 +-
4 files changed, 163 insertions(+), 140 deletions(-)
diff --git a/llvm/include/llvm/Analysis/LoopAccessAnalysis.h b/llvm/include/llvm/Analysis/LoopAccessAnalysis.h
index 13fbe884eddf..39acfd5bbbee 100644
--- a/llvm/include/llvm/Analysis/LoopAccessAnalysis.h
+++ b/llvm/include/llvm/Analysis/LoopAccessAnalysis.h
@@ -679,6 +679,15 @@ int64_t getPtrStride(PredicatedScalarEvolution &PSE, Value *Ptr, const Loop *Lp,
const ValueToValueMap &StridesMap = ValueToValueMap(),
bool Assume = false, bool ShouldCheckWrap = true);
+/// Returns the distance between the pointers \p PtrA and \p PtrB iff they are
+/// compatible and it is possible to calculate the distance between them. This
+/// is a simple API that does not depend on the analysis pass.
+/// \param StrictCheck Ensure that the calculated distance matches the
+/// type-based one after all the bitcasts removal in the provided pointers.
+Optional<int> getPointersDiff(Value *PtrA, Value *PtrB, const DataLayout &DL,
+ ScalarEvolution &SE, bool StrictCheck = false,
+ bool CheckType = true);
+
/// Attempt to sort the pointers in \p VL and return the sorted indices
/// in \p SortedIndices, if reordering is required.
///
diff --git a/llvm/lib/Analysis/LoopAccessAnalysis.cpp b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
index e632fe25c24c..997d4474a448 100644
--- a/llvm/lib/Analysis/LoopAccessAnalysis.cpp
+++ b/llvm/lib/Analysis/LoopAccessAnalysis.cpp
@@ -1124,139 +1124,123 @@ int64_t llvm::getPtrStride(PredicatedScalarEvolution &PSE, Value *Ptr,
return Stride;
}
+Optional<int> llvm::getPointersDiff(Value *PtrA, Value *PtrB,
+ const DataLayout &DL, ScalarEvolution &SE,
+ bool StrictCheck, bool CheckType) {
+ assert(PtrA && PtrB && "Expected non-nullptr pointers.");
+ // Make sure that A and B are different pointers.
+ if (PtrA == PtrB)
+ return 0;
+
+ // Make sure that PtrA and PtrB have the same type if required
+ if (CheckType && PtrA->getType() != PtrB->getType())
+ return None;
+
+ unsigned ASA = PtrA->getType()->getPointerAddressSpace();
+ unsigned ASB = PtrB->getType()->getPointerAddressSpace();
+
+ // Check that the address spaces match.
+ if (ASA != ASB)
+ return None;
+ unsigned IdxWidth = DL.getIndexSizeInBits(ASA);
+
+ APInt OffsetA(IdxWidth, 0), OffsetB(IdxWidth, 0);
+ Value *PtrA1 = PtrA->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetA);
+ Value *PtrB1 = PtrB->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetB);
+
+ int Val;
+ if (PtrA1 == PtrB1) {
+ // Retrieve the address space again as pointer stripping now tracks through
+ // `addrspacecast`.
+ ASA = cast<PointerType>(PtrA1->getType())->getAddressSpace();
+ ASB = cast<PointerType>(PtrB1->getType())->getAddressSpace();
+ // Check that the address spaces match and that the pointers are valid.
+ if (ASA != ASB)
+ return None;
+
+ IdxWidth = DL.getIndexSizeInBits(ASA);
+ OffsetA = OffsetA.sextOrTrunc(IdxWidth);
+ OffsetB = OffsetB.sextOrTrunc(IdxWidth);
+
+ OffsetB -= OffsetA;
+ Val = OffsetB.getSExtValue();
+ } else {
+ // Otherwise compute the distance with SCEV between the base pointers.
+ const SCEV *PtrSCEVA = SE.getSCEV(PtrA);
+ const SCEV *PtrSCEVB = SE.getSCEV(PtrB);
+ const auto *Diff =
+ dyn_cast<SCEVConstant>(SE.getMinusSCEV(PtrSCEVB, PtrSCEVA));
+ if (!Diff)
+ return None;
+ Val = Diff->getAPInt().getSExtValue();
+ }
+ Type *Ty = cast<PointerType>(PtrA->getType())->getElementType();
+ int Size = DL.getTypeStoreSize(Ty);
+ int Dist = Val / Size;
+
+ // Ensure that the calculated distance matches the type-based one after all
+ // the bitcasts removal in the provided pointers.
+ if (!StrictCheck || Dist * Size == Val)
+ return Dist;
+ return None;
+}
+
bool llvm::sortPtrAccesses(ArrayRef<Value *> VL, const DataLayout &DL,
ScalarEvolution &SE,
SmallVectorImpl<unsigned> &SortedIndices) {
assert(llvm::all_of(
VL, [](const Value *V) { return V->getType()->isPointerTy(); }) &&
"Expected list of pointer operands.");
- SmallVector<std::pair<int64_t, Value *>, 4> OffValPairs;
- OffValPairs.reserve(VL.size());
-
// Walk over the pointers, and map each of them to an offset relative to
// first pointer in the array.
Value *Ptr0 = VL[0];
- const SCEV *Scev0 = SE.getSCEV(Ptr0);
- Value *Obj0 = getUnderlyingObject(Ptr0);
-
- llvm::SmallSet<int64_t, 4> Offsets;
- for (auto *Ptr : VL) {
- // TODO: Outline this code as a special, more time consuming, version of
- // computeConstantDifference() function.
- if (Ptr->getType()->getPointerAddressSpace() !=
- Ptr0->getType()->getPointerAddressSpace())
- return false;
- // If a pointer refers to a different underlying object, bail - the
- // pointers are by definition incomparable.
- Value *CurrObj = getUnderlyingObject(Ptr);
- if (CurrObj != Obj0)
- return false;
- const SCEV *Scev = SE.getSCEV(Ptr);
- const auto *Diff = dyn_cast<SCEVConstant>(SE.getMinusSCEV(Scev, Scev0));
- // The pointers may not have a constant offset from each other, or SCEV
- // may just not be smart enough to figure out they do. Regardless,
- // there's nothing we can do.
+ using DistOrdPair = std::pair<int64_t, int>;
+ auto Compare = [](const DistOrdPair &L, const DistOrdPair &R) {
+ return L.first < R.first;
+ };
+ std::set<DistOrdPair, decltype(Compare)> Offsets(Compare);
+ Offsets.emplace(0, 0);
+ int Cnt = 1;
+ bool IsConsecutive = true;
+ for (auto *Ptr : VL.drop_front()) {
+ Optional<int> Diff = getPointersDiff(Ptr0, Ptr, DL, SE);
if (!Diff)
return false;
// Check if the pointer with the same offset is found.
- int64_t Offset = Diff->getAPInt().getSExtValue();
- if (!Offsets.insert(Offset).second)
+ int64_t Offset = *Diff;
+ auto Res = Offsets.emplace(Offset, Cnt);
+ if (!Res.second)
return false;
- OffValPairs.emplace_back(Offset, Ptr);
+ // Consecutive order if the inserted element is the last one.
+ IsConsecutive = IsConsecutive && std::next(Res.first) == Offsets.end();
+ ++Cnt;
}
SortedIndices.clear();
- SortedIndices.resize(VL.size());
- std::iota(SortedIndices.begin(), SortedIndices.end(), 0);
-
- // Sort the memory accesses and keep the order of their uses in UseOrder.
- llvm::stable_sort(SortedIndices, [&](unsigned Left, unsigned Right) {
- return OffValPairs[Left].first < OffValPairs[Right].first;
- });
-
- // Check if the order is consecutive already.
- if (llvm::all_of(SortedIndices, [&SortedIndices](const unsigned I) {
- return I == SortedIndices[I];
- }))
- SortedIndices.clear();
-
+ if (!IsConsecutive) {
+ // Fill SortedIndices array only if it is non-consecutive.
+ SortedIndices.resize(VL.size());
+ Cnt = 0;
+ for (const std::pair<int64_t, int> &Pair : Offsets) {
+ IsConsecutive = IsConsecutive && Cnt == Pair.second;
+ SortedIndices[Cnt] = Pair.second;
+ ++Cnt;
+ }
+ }
return true;
}
-/// Take the address space operand from the Load/Store instruction.
-/// Returns -1 if this is not a valid Load/Store instruction.
-static unsigned getAddressSpaceOperand(Value *I) {
- if (LoadInst *L = dyn_cast<LoadInst>(I))
- return L->getPointerAddressSpace();
- if (StoreInst *S = dyn_cast<StoreInst>(I))
- return S->getPointerAddressSpace();
- return -1;
-}
-
/// Returns true if the memory operations \p A and \p B are consecutive.
bool llvm::isConsecutiveAccess(Value *A, Value *B, const DataLayout &DL,
ScalarEvolution &SE, bool CheckType) {
Value *PtrA = getLoadStorePointerOperand(A);
Value *PtrB = getLoadStorePointerOperand(B);
- unsigned ASA = getAddressSpaceOperand(A);
- unsigned ASB = getAddressSpaceOperand(B);
-
- // Check that the address spaces match and that the pointers are valid.
- if (!PtrA || !PtrB || (ASA != ASB))
- return false;
-
- // Make sure that A and B are different pointers.
- if (PtrA == PtrB)
- return false;
-
- // Make sure that A and B have the same type if required.
- if (CheckType && PtrA->getType() != PtrB->getType())
+ if (!PtrA || !PtrB)
return false;
-
- unsigned IdxWidth = DL.getIndexSizeInBits(ASA);
- Type *Ty = cast<PointerType>(PtrA->getType())->getElementType();
-
- APInt OffsetA(IdxWidth, 0), OffsetB(IdxWidth, 0);
- PtrA = PtrA->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetA);
- PtrB = PtrB->stripAndAccumulateInBoundsConstantOffsets(DL, OffsetB);
-
- // Retrieve the address space again as pointer stripping now tracks through
- // `addrspacecast`.
- ASA = cast<PointerType>(PtrA->getType())->getAddressSpace();
- ASB = cast<PointerType>(PtrB->getType())->getAddressSpace();
- // Check that the address spaces match and that the pointers are valid.
- if (ASA != ASB)
- return false;
-
- IdxWidth = DL.getIndexSizeInBits(ASA);
- OffsetA = OffsetA.sextOrTrunc(IdxWidth);
- OffsetB = OffsetB.sextOrTrunc(IdxWidth);
-
- APInt Size(IdxWidth, DL.getTypeStoreSize(Ty));
-
- // OffsetDelta = OffsetB - OffsetA;
- const SCEV *OffsetSCEVA = SE.getConstant(OffsetA);
- const SCEV *OffsetSCEVB = SE.getConstant(OffsetB);
- const SCEV *OffsetDeltaSCEV = SE.getMinusSCEV(OffsetSCEVB, OffsetSCEVA);
- const APInt &OffsetDelta = cast<SCEVConstant>(OffsetDeltaSCEV)->getAPInt();
-
- // Check if they are based on the same pointer. That makes the offsets
- // sufficient.
- if (PtrA == PtrB)
- return OffsetDelta == Size;
-
- // Compute the necessary base pointer delta to have the necessary final delta
- // equal to the size.
- // BaseDelta = Size - OffsetDelta;
- const SCEV *SizeSCEV = SE.getConstant(Size);
- const SCEV *BaseDelta = SE.getMinusSCEV(SizeSCEV, OffsetDeltaSCEV);
-
- // Otherwise compute the distance with SCEV between the base pointers.
- const SCEV *PtrSCEVA = SE.getSCEV(PtrA);
- const SCEV *PtrSCEVB = SE.getSCEV(PtrB);
- const SCEV *X = SE.getAddExpr(PtrSCEVA, BaseDelta);
- return X == PtrSCEVB;
+ Optional<int> Diff =
+ getPointersDiff(PtrA, PtrB, DL, SE, /*StrictCheck=*/true, CheckType);
+ return Diff && *Diff == 1;
}
MemoryDepChecker::VectorizationSafetyStatus
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index 385b6f30dc0f..78d2ea0032db 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -941,10 +941,16 @@ public:
ScalarEvolution &SE) {
auto *LI1 = dyn_cast<LoadInst>(V1);
auto *LI2 = dyn_cast<LoadInst>(V2);
- if (LI1 && LI2)
- return isConsecutiveAccess(LI1, LI2, DL, SE)
- ? VLOperands::ScoreConsecutiveLoads
- : VLOperands::ScoreFail;
+ if (LI1 && LI2) {
+ if (LI1->getParent() != LI2->getParent())
+ return VLOperands::ScoreFail;
+
+ Optional<int> Dist =
+ getPointersDiff(LI1->getPointerOperand(), LI2->getPointerOperand(),
+ DL, SE, /*StrictCheck=*/true);
+ return (Dist && *Dist == 1) ? VLOperands::ScoreConsecutiveLoads
+ : VLOperands::ScoreFail;
+ }
auto *C1 = dyn_cast<Constant>(V1);
auto *C2 = dyn_cast<Constant>(V2);
@@ -2871,13 +2877,9 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth,
Ptr0 = PointerOps[CurrentOrder.front()];
PtrN = PointerOps[CurrentOrder.back()];
}
- const SCEV *Scev0 = SE->getSCEV(Ptr0);
- const SCEV *ScevN = SE->getSCEV(PtrN);
- const auto *Diff =
- dyn_cast<SCEVConstant>(SE->getMinusSCEV(ScevN, Scev0));
- uint64_t Size = DL->getTypeAllocSize(ScalarTy);
+ Optional<int> Diff = getPointersDiff(Ptr0, PtrN, *DL, *SE);
// Check that the sorted loads are consecutive.
- if (Diff && Diff->getAPInt() == (VL.size() - 1) * Size) {
+ if (static_cast<unsigned>(*Diff) == VL.size() - 1) {
if (CurrentOrder.empty()) {
// Original loads are consecutive and does not require reordering.
++NumOpsWantToKeepOriginalOrder;
@@ -3150,13 +3152,9 @@ void BoUpSLP::buildTree_rec(ArrayRef<Value *> VL, unsigned Depth,
Ptr0 = PointerOps[CurrentOrder.front()];
PtrN = PointerOps[CurrentOrder.back()];
}
- const SCEV *Scev0 = SE->getSCEV(Ptr0);
- const SCEV *ScevN = SE->getSCEV(PtrN);
- const auto *Diff =
- dyn_cast<SCEVConstant>(SE->getMinusSCEV(ScevN, Scev0));
- uint64_t Size = DL->getTypeAllocSize(ScalarTy);
+ Optional<int> Dist = getPointersDiff(Ptr0, PtrN, *DL, *SE);
// Check that the sorted pointer operands are consecutive.
- if (Diff && Diff->getAPInt() == (VL.size() - 1) * Size) {
+ if (static_cast<unsigned>(*Dist) == VL.size() - 1) {
if (CurrentOrder.empty()) {
// Original stores are consecutive and does not require reordering.
++NumOpsWantToKeepOriginalOrder;
@@ -6107,20 +6105,41 @@ bool SLPVectorizerPass::vectorizeStores(ArrayRef<StoreInst *> Stores,
int E = Stores.size();
SmallBitVector Tails(E, false);
- SmallVector<int, 16> ConsecutiveChain(E, E + 1);
int MaxIter = MaxStoreLookup.getValue();
+ SmallVector<std::pair<int, int>, 16> ConsecutiveChain(
+ E, std::make_pair(E, INT_MAX));
+ SmallVector<SmallBitVector, 4> CheckedPairs(E, SmallBitVector(E, false));
int IterCnt;
auto &&FindConsecutiveAccess = [this, &Stores, &Tails, &IterCnt, MaxIter,
+ &CheckedPairs,
&ConsecutiveChain](int K, int Idx) {
if (IterCnt >= MaxIter)
return true;
+ if (CheckedPairs[Idx].test(K))
+ return ConsecutiveChain[K].second == 1 &&
+ ConsecutiveChain[K].first == Idx;
++IterCnt;
- if (!isConsecutiveAccess(Stores[K], Stores[Idx], *DL, *SE))
+ CheckedPairs[Idx].set(K);
+ CheckedPairs[K].set(Idx);
+ Optional<int> Diff = getPointersDiff(Stores[K]->getPointerOperand(),
+ Stores[Idx]->getPointerOperand(), *DL,
+ *SE, /*StrictCheck=*/true);
+ if (!Diff || *Diff == 0)
+ return false;
+ int Val = *Diff;
+ if (Val < 0) {
+ if (ConsecutiveChain[Idx].second > -Val) {
+ Tails.set(K);
+ ConsecutiveChain[Idx] = std::make_pair(K, -Val);
+ }
+ return false;
+ }
+ if (ConsecutiveChain[K].second <= Val)
return false;
Tails.set(Idx);
- ConsecutiveChain[K] = Idx;
- return true;
+ ConsecutiveChain[K] = std::make_pair(Idx, Val);
+ return Val == 1;
};
// Do a quadratic search on all of the given stores in reverse order and find
// all of the pairs of stores that follow each other.
@@ -6140,17 +6159,31 @@ bool SLPVectorizerPass::vectorizeStores(ArrayRef<StoreInst *> Stores,
// For stores that start but don't end a link in the chain:
for (int Cnt = E; Cnt > 0; --Cnt) {
int I = Cnt - 1;
- if (ConsecutiveChain[I] == E + 1 || Tails.test(I))
+ if (ConsecutiveChain[I].first == E || Tails.test(I))
continue;
// We found a store instr that starts a chain. Now follow the chain and try
// to vectorize it.
BoUpSLP::ValueList Operands;
// Collect the chain into a list.
- while (I != E + 1 && !VectorizedStores.count(Stores[I])) {
+ while (I != E && !VectorizedStores.count(Stores[I])) {
Operands.push_back(Stores[I]);
+ Tails.set(I);
+ if (ConsecutiveChain[I].second != 1) {
+ // Mark the new end in the chain and go back, if required. It might be
+ // required if the original stores come in reversed order, for example.
+ if (ConsecutiveChain[I].first != E &&
+ Tails.test(ConsecutiveChain[I].first) &&
+ !VectorizedStores.count(Stores[ConsecutiveChain[I].first])) {
+ Tails.reset(ConsecutiveChain[I].first);
+ if (Cnt < ConsecutiveChain[I].first + 2)
+ Cnt = ConsecutiveChain[I].first + 2;
+ }
+ break;
+ }
// Move to the next value in the chain.
- I = ConsecutiveChain[I];
+ I = ConsecutiveChain[I].first;
}
+ assert(!Operands.empty() && "Expected non-empty list of stores.");
unsigned MaxVecRegSize = R.getMaxVecRegSize();
unsigned EltSize = R.getVectorElementSize(Operands[0]);
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll b/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll
index 267cf1a02c29..e28362894910 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/pr35497.ll
@@ -1,7 +1,7 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -slp-vectorizer -slp-vectorizer -mattr=+sse2 -S | FileCheck %s --check-prefix=SSE
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -slp-vectorizer -slp-vectorizer -mattr=+avx -S | FileCheck %s --check-prefix=AVX
-; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -slp-vectorizer -slp-vectorizer -mattr=+avx2 -S | FileCheck %s --check-prefix=AVX
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -slp-vectorizer -mattr=+sse2 -S | FileCheck %s --check-prefix=SSE
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -slp-vectorizer -mattr=+avx -S | FileCheck %s --check-prefix=AVX
+; RUN: opt < %s -mtriple=x86_64-unknown-linux-gnu -slp-vectorizer -mattr=+avx2 -S | FileCheck %s --check-prefix=AVX
%class.1 = type { %class.2 }
%class.2 = type { %"class.3" }
@@ -117,13 +117,10 @@ define void @pr35497() local_unnamed_addr #0 {
; AVX-NEXT: [[ARRAYIDX2_6:%.*]] = getelementptr inbounds [0 x i64], [0 x i64]* undef, i64 0, i64 0
; AVX-NEXT: [[TMP10:%.*]] = bitcast i64* [[ARRAYIDX2_6]] to <2 x i64>*
; AVX-NEXT: store <2 x i64> [[TMP4]], <2 x i64>* [[TMP10]], align 1
-; AVX-NEXT: [[TMP11:%.*]] = extractelement <2 x i64> [[TMP4]], i32 0
-; AVX-NEXT: [[TMP12:%.*]] = insertelement <2 x i64> poison, i64 [[TMP11]], i32 0
-; AVX-NEXT: [[TMP13:%.*]] = insertelement <2 x i64> [[TMP12]], i64 [[TMP5]], i32 1
-; AVX-NEXT: [[TMP14:%.*]] = lshr <2 x i64> [[TMP13]], <i64 6, i64 6>
-; AVX-NEXT: [[TMP15:%.*]] = add nuw nsw <2 x i64> [[TMP9]], [[TMP14]]
-; AVX-NEXT: [[TMP16:%.*]] = bitcast i64* [[ARRAYIDX2_2]] to <2 x i64>*
-; AVX-NEXT: store <2 x i64> [[TMP15]], <2 x i64>* [[TMP16]], align 1
+; AVX-NEXT: [[TMP11:%.*]] = lshr <2 x i64> [[TMP4]], <i64 6, i64 6>
+; AVX-NEXT: [[TMP12:%.*]] = add nuw nsw <2 x i64> [[TMP9]], [[TMP11]]
+; AVX-NEXT: [[TMP13:%.*]] = bitcast i64* [[ARRAYIDX2_2]] to <2 x i64>*
+; AVX-NEXT: store <2 x i64> [[TMP12]], <2 x i64>* [[TMP13]], align 1
; AVX-NEXT: ret void
;
entry:
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O2_LTO - Build # 24 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2_LTO
Culprit:
<cut>
commit 643ce61fb3c2c730b7ecead4a489eaeef3f053ea
Author: Akira Hatanaka <ahatanaka(a)apple.com>
Date: Wed Aug 11 12:55:28 2021 -0700
[ObjC][ARC] Don't form a StoreStrong call if it is unsafe to move the
release call
findSafeStoreForStoreStrongContraction checks whether it's safe to move
the release call to the store by inspecting all instructions between the
two, but was ignoring retain instructions. This was causing objects to
be released and deallocated before they were retained.
rdar://81668577
</cut>
Results regressed to (for first_bad == 643ce61fb3c2c730b7ecead4a489eaeef3f053ea)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO artifacts/build-643ce61fb3c2c730b7ecead4a489eaeef3f053ea/results_id:
1
# 433.milc,milc_base.default regressed by 103
from (for last_good == 767496d19cb9a1fbba57ff08095faa161998ee36)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO artifacts/build-767496d19cb9a1fbba57ff08095faa161998ee36/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2_LTO/4172
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2_LTO/4171
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-643ce61fb3c2c730b7ecead4a489eaeef3f053ea
cd investigate-llvm-643ce61fb3c2c730b7ecead4a489eaeef3f053ea
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 643ce61fb3c2c730b7ecead4a489eaeef3f053ea
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 767496d19cb9a1fbba57ff08095faa161998ee36
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 643ce61fb3c2c730b7ecead4a489eaeef3f053ea
Author: Akira Hatanaka <ahatanaka(a)apple.com>
Date: Wed Aug 11 12:55:28 2021 -0700
[ObjC][ARC] Don't form a StoreStrong call if it is unsafe to move the
release call
findSafeStoreForStoreStrongContraction checks whether it's safe to move
the release call to the store by inspecting all instructions between the
two, but was ignoring retain instructions. This was causing objects to
be released and deallocated before they were retained.
rdar://81668577
---
llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp | 21 ++++++++++++---------
.../test/Transforms/ObjCARC/contract-storestrong.ll | 19 +++++++++++++++++++
2 files changed, 31 insertions(+), 9 deletions(-)
diff --git a/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp b/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp
index 62161b5b6b40..577973c80601 100644
--- a/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp
+++ b/llvm/lib/Transforms/ObjCARC/ObjCARCContract.cpp
@@ -226,13 +226,6 @@ static StoreInst *findSafeStoreForStoreStrongContraction(LoadInst *Load,
// of Inst.
ARCInstKind Class = GetBasicARCInstKind(Inst);
- // If Inst is an unrelated retain, we don't care about it.
- //
- // TODO: This is one area where the optimization could be made more
- // aggressive.
- if (IsRetain(Class))
- continue;
-
// If we have seen the store, but not the release...
if (Store) {
// We need to make sure that it is safe to move the release from its
@@ -248,8 +241,18 @@ static StoreInst *findSafeStoreForStoreStrongContraction(LoadInst *Load,
return nullptr;
}
- // Ok, now we know we have not seen a store yet. See if Inst can write to
- // our load location, if it can not, just ignore the instruction.
+ // Ok, now we know we have not seen a store yet.
+
+ // If Inst is a retain, we don't care about it as it doesn't prevent moving
+ // the load to the store.
+ //
+ // TODO: This is one area where the optimization could be made more
+ // aggressive.
+ if (IsRetain(Class))
+ continue;
+
+ // See if Inst can write to our load location, if it can not, just ignore
+ // the instruction.
if (!isModSet(AA->getModRefInfo(Inst, Loc)))
continue;
diff --git a/llvm/test/Transforms/ObjCARC/contract-storestrong.ll b/llvm/test/Transforms/ObjCARC/contract-storestrong.ll
index eff0a6fdf900..9c45e3334d83 100644
--- a/llvm/test/Transforms/ObjCARC/contract-storestrong.ll
+++ b/llvm/test/Transforms/ObjCARC/contract-storestrong.ll
@@ -256,6 +256,25 @@ define i8* @test13(i8* %a0, i8* %a1, i8** %addr, i8* %new) {
ret i8* %retained
}
+; Cannot form a storeStrong call because it's unsafe to move the release call to
+; the store.
+
+; CHECK-LABEL: define void @test14(
+; CHECK: %[[V0:.*]] = load i8*, i8** %a
+; CHECK: %[[V1:.*]] = call i8* @llvm.objc.retain(i8* %p)
+; CHECK: store i8* %[[V1]], i8** %a
+; CHECK: %[[V2:.*]] = call i8* @llvm.objc.retain(i8* %[[V0]])
+; CHECK: call void @llvm.objc.release(i8* %[[V2]])
+
+define void @test14(i8** %a, i8* %p) {
+ %v0 = load i8*, i8** %a, align 8
+ %v1 = call i8* @llvm.objc.retain(i8* %p)
+ store i8* %p, i8** %a, align 8
+ %v2 = call i8* @llvm.objc.retain(i8* %v0)
+ call void @llvm.objc.release(i8* %v0)
+ ret void
+}
+
!0 = !{}
; CHECK: attributes [[NUW]] = { nounwind }
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2_LTO - Build # 11 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2_LTO
Culprit:
<cut>
commit 176379e0c8f9dbde2b357fb3b6a6802b83282e71
Author: Alex Zinenko <zinenko(a)google.com>
Date: Fri Feb 12 12:53:27 2021 +0100
[mlir] Use the interface-based translation for LLVM "intrinsic" dialects
Port the translation of five dialects that define LLVM IR intrinsics
(LLVMAVX512, LLVMArmNeon, LLVMArmSVE, NVVM, ROCDL) to the new dialect
interface-based mechanism. This allows us to remove individual translations
that were created for each of these dialects and just use one common
MLIR-to-LLVM-IR translation that potentially supports all dialects instead,
based on what is registered and including any combination of translatable
dialects. This removal was one of the main goals of the refactoring.
To support the addition of GPU-related metadata, the translation interface is
extended with the `amendOperation` function that allows the interface
implementation to post-process any translated operation with dialect attributes
from the dialect for which the interface is implemented regardless of the
operation's dialect. This is currently applied to "kernel" functions, but can
be used to construct other metadata in dialect-specific ways without
necessarily affecting operations.
Depends On D96591, D96504
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D96592
</cut>
Results regressed to (for first_bad == 176379e0c8f9dbde2b357fb3b6a6802b83282e71)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-176379e0c8f9dbde2b357fb3b6a6802b83282e71/results_id:
1
# 482.sphinx3,sphinx_livepretend_base.default regressed by 109
from (for last_good == 2d728bbff5c688284b8b8306ecfd3000b0ab8bb1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-2d728bbff5c688284b8b8306ecfd3000b0ab8bb1/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2_LTO/4128
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2_LTO/4125
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-176379e0c8f9dbde2b357fb3b6a6802b83282e71
cd investigate-llvm-176379e0c8f9dbde2b357fb3b6a6802b83282e71
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 176379e0c8f9dbde2b357fb3b6a6802b83282e71
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 2d728bbff5c688284b8b8306ecfd3000b0ab8bb1
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 176379e0c8f9dbde2b357fb3b6a6802b83282e71
Author: Alex Zinenko <zinenko(a)google.com>
Date: Fri Feb 12 12:53:27 2021 +0100
[mlir] Use the interface-based translation for LLVM "intrinsic" dialects
Port the translation of five dialects that define LLVM IR intrinsics
(LLVMAVX512, LLVMArmNeon, LLVMArmSVE, NVVM, ROCDL) to the new dialect
interface-based mechanism. This allows us to remove individual translations
that were created for each of these dialects and just use one common
MLIR-to-LLVM-IR translation that potentially supports all dialects instead,
based on what is registered and including any combination of translatable
dialects. This removal was one of the main goals of the refactoring.
To support the addition of GPU-related metadata, the translation interface is
extended with the `amendOperation` function that allows the interface
implementation to post-process any translated operation with dialect attributes
from the dialect for which the interface is implemented regardless of the
operation's dialect. This is currently applied to "kernel" functions, but can
be used to construct other metadata in dialect-specific ways without
necessarily affecting operations.
Depends On D96591, D96504
Reviewed By: nicolasvasilache
Differential Revision: https://reviews.llvm.org/D96592
---
.../test/Standalone/standalone-translate.mlir | 3 -
mlir/include/mlir/Dialect/LLVMIR/LLVMOpBase.td | 13 ++-
mlir/include/mlir/Dialect/LLVMIR/LLVMOps.td | 3 +-
mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td | 2 +-
mlir/include/mlir/InitAllTranslations.h | 10 --
mlir/include/mlir/Target/LLVMIR.h | 4 +-
.../LLVMAVX512/LLVMAVX512ToLLVMIRTranslation.h | 37 ++++++
.../LLVMArmNeon/LLVMArmNeonToLLVMIRTranslation.h | 37 ++++++
.../LLVMArmSVE/LLVMArmSVEToLLVMIRTranslation.h | 37 ++++++
.../Dialect/LLVMIR/LLVMToLLVMIRTranslation.h | 4 +-
.../LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h | 42 +++++++
.../Dialect/OpenMP/OpenMPToLLVMIRTranslation.h | 4 +-
.../Dialect/ROCDL/ROCDLToLLVMIRTranslation.h | 42 +++++++
.../mlir/Target/LLVMIR/LLVMTranslationInterface.h | 28 ++++-
.../include/mlir/Target/LLVMIR/ModuleTranslation.h | 32 ++++--
mlir/include/mlir/Target/NVVMIR.h | 39 -------
mlir/include/mlir/Target/ROCDLIR.h | 40 -------
mlir/lib/Target/CMakeLists.txt | 107 +----------------
mlir/lib/Target/LLVMIR/ConvertToLLVMIR.cpp | 35 +++++-
mlir/lib/Target/LLVMIR/ConvertToNVVMIR.cpp | 124 --------------------
mlir/lib/Target/LLVMIR/ConvertToROCDLIR.cpp | 127 ---------------------
mlir/lib/Target/LLVMIR/Dialect/CMakeLists.txt | 5 +
.../LLVMIR/Dialect/LLVMAVX512/CMakeLists.txt | 16 +++
.../LLVMAVX512/LLVMAVX512ToLLVMIRTranslation.cpp | 33 ++++++
.../LLVMIR/Dialect/LLVMArmNeon/CMakeLists.txt | 16 +++
.../LLVMArmNeon/LLVMArmNeonToLLVMIRTranslation.cpp | 33 ++++++
.../LLVMIR/Dialect/LLVMArmSVE/CMakeLists.txt | 16 +++
.../LLVMArmSVE/LLVMArmSVEToLLVMIRTranslation.cpp | 33 ++++++
.../Dialect/LLVMIR/LLVMToLLVMIRTranslation.cpp | 71 ++++--------
mlir/lib/Target/LLVMIR/Dialect/NVVM/CMakeLists.txt | 16 +++
.../Dialect/NVVM/NVVMToLLVMIRTranslation.cpp | 67 +++++++++++
.../lib/Target/LLVMIR/Dialect/ROCDL/CMakeLists.txt | 16 +++
.../Dialect/ROCDL/ROCDLToLLVMIRTranslation.cpp | 69 +++++++++++
mlir/lib/Target/LLVMIR/LLVMAVX512Intr.cpp | 65 -----------
mlir/lib/Target/LLVMIR/LLVMArmNeonIntr.cpp | 65 -----------
mlir/lib/Target/LLVMIR/LLVMArmSVEIntr.cpp | 65 -----------
mlir/lib/Target/LLVMIR/ModuleTranslation.cpp | 65 +++++++----
mlir/test/Target/arm-neon.mlir | 2 +-
mlir/test/Target/arm-sve.mlir | 2 +-
mlir/test/Target/avx512.mlir | 2 +-
mlir/test/Target/nvvmir.mlir | 2 +-
mlir/test/Target/rocdl.mlir | 2 +-
mlir/test/lib/Transforms/CMakeLists.txt | 13 ++-
.../lib/Transforms/TestConvertGPUKernelToCubin.cpp | 25 +++-
.../lib/Transforms/TestConvertGPUKernelToHsaco.cpp | 22 +++-
mlir/tools/mlir-cuda-runner/mlir-cuda-runner.cpp | 6 +-
mlir/tools/mlir-rocm-runner/mlir-rocm-runner.cpp | 3 +
mlir/tools/mlir-tblgen/LLVMIRConversionGen.cpp | 10 +-
48 files changed, 750 insertions(+), 760 deletions(-)
diff --git a/mlir/examples/standalone/test/Standalone/standalone-translate.mlir b/mlir/examples/standalone/test/Standalone/standalone-translate.mlir
index 2a096c38e128..16d49785ee16 100644
--- a/mlir/examples/standalone/test/Standalone/standalone-translate.mlir
+++ b/mlir/examples/standalone/test/Standalone/standalone-translate.mlir
@@ -1,8 +1,5 @@
// RUN: standalone-translate --help | FileCheck %s
-// CHECK: --avx512-mlir-to-llvmir
// CHECK: --deserialize-spirv
// CHECK: --import-llvm
// CHECK: --mlir-to-llvmir
-// CHECK: --mlir-to-nvvmir
-// CHECK: --mlir-to-rocdlir
// CHECK: --serialize-spirv
diff --git a/mlir/include/mlir/Dialect/LLVMIR/LLVMOpBase.td b/mlir/include/mlir/Dialect/LLVMIR/LLVMOpBase.td
index ad886e55b4e6..541f7ebfadfa 100644
--- a/mlir/include/mlir/Dialect/LLVMIR/LLVMOpBase.td
+++ b/mlir/include/mlir/Dialect/LLVMIR/LLVMOpBase.td
@@ -219,12 +219,13 @@ class ListIntSubst<string pattern, list<int> values> {
// or result in the operation.
def LLVM_IntrPatterns {
string operand =
- [{convertType(opInst.getOperand($0).getType())}];
+ [{moduleTranslation.convertType(opInst.getOperand($0).getType())}];
string result =
- [{convertType(opInst.getResult($0).getType())}];
+ [{moduleTranslation.convertType(opInst.getResult($0).getType())}];
string structResult =
- [{convertType(opInst.getResult(0).getType().cast<LLVM::LLVMStructType>()
- .getBody()[$0])}];
+ [{moduleTranslation.convertType(
+ opInst.getResult(0).getType().cast<LLVM::LLVMStructType>()
+ .getBody()[$0])}];
}
@@ -259,7 +260,7 @@ class LLVM_IntrOpBase<Dialect dialect, string opName, string enumName,
ListIntSubst<LLVM_IntrPatterns.operand,
overloadedOperands>.lst), ", ") # [{
});
- auto operands = lookupValues(opInst.getOperands());
+ auto operands = moduleTranslation.lookupValues(opInst.getOperands());
}] # !if(!gt(numResults, 0), "$res = ", "")
# [{builder.CreateCall(fn, operands);
}];
@@ -325,7 +326,7 @@ class LLVM_VectorReductionAcc<string mnem>
{ }] # !interleave(ListIntSubst<LLVM_IntrPatterns.operand, [1]>.lst,
", ") # [{
});
- auto operands = lookupValues(opInst.getOperands());
+ auto operands = moduleTranslation.lookupValues(opInst.getOperands());
llvm::FastMathFlags origFM = builder.getFastMathFlags();
llvm::FastMathFlags tempFM = origFM;
tempFM.setAllowReassoc($reassoc);
diff --git a/mlir/include/mlir/Dialect/LLVMIR/LLVMOps.td b/mlir/include/mlir/Dialect/LLVMIR/LLVMOps.td
index 7a2152b9a481..7dca08a43f7a 100644
--- a/mlir/include/mlir/Dialect/LLVMIR/LLVMOps.td
+++ b/mlir/include/mlir/Dialect/LLVMIR/LLVMOps.td
@@ -1083,7 +1083,8 @@ def LLVM_UndefOp : LLVM_Op<"mlir.undef", [NoSideEffect]>,
def LLVM_ConstantOp
: LLVM_Op<"mlir.constant", [NoSideEffect]>,
- LLVM_Builder<"$res = getLLVMConstant($_resultType, $value, $_location);">
+ LLVM_Builder<[{$res = getLLVMConstant($_resultType, $value, $_location,
+ moduleTranslation);}]>
{
let summary = "Defines a constant of LLVM type.";
let description = [{
diff --git a/mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td b/mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td
index d5eec3cebb4a..cfb08ff465a2 100644
--- a/mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td
+++ b/mlir/include/mlir/Dialect/LLVMIR/ROCDLOps.td
@@ -175,7 +175,7 @@ def ROCDL_MubufStoreOp :
LLVM_Type:$glc,
LLVM_Type:$slc)>{
string llvmBuilder = [{
- auto vdataType = convertType(op.vdata().getType());
+ auto vdataType = moduleTranslation.convertType(op.vdata().getType());
createIntrinsicCall(builder,
llvm::Intrinsic::amdgcn_buffer_store, {$vdata, $rsrc, $vindex,
$offset, $glc, $slc}, {vdataType});
diff --git a/mlir/include/mlir/InitAllTranslations.h b/mlir/include/mlir/InitAllTranslations.h
index 16dd113d14cd..fc319c09a8c8 100644
--- a/mlir/include/mlir/InitAllTranslations.h
+++ b/mlir/include/mlir/InitAllTranslations.h
@@ -20,11 +20,6 @@ void registerFromLLVMIRTranslation();
void registerFromSPIRVTranslation();
void registerToLLVMIRTranslation();
void registerToSPIRVTranslation();
-void registerToNVVMIRTranslation();
-void registerToROCDLIRTranslation();
-void registerArmNeonToLLVMIRTranslation();
-void registerAVX512ToLLVMIRTranslation();
-void registerArmSVEToLLVMIRTranslation();
// This function should be called before creating any MLIRContext if one
// expects all the possible translations to be made available to the context
@@ -35,11 +30,6 @@ inline void registerAllTranslations() {
registerFromSPIRVTranslation();
registerToLLVMIRTranslation();
registerToSPIRVTranslation();
- registerToNVVMIRTranslation();
- registerToROCDLIRTranslation();
- registerArmNeonToLLVMIRTranslation();
- registerAVX512ToLLVMIRTranslation();
- registerArmSVEToLLVMIRTranslation();
return true;
}();
(void)initOnce;
diff --git a/mlir/include/mlir/Target/LLVMIR.h b/mlir/include/mlir/Target/LLVMIR.h
index 2050c63df73f..10bec79f3506 100644
--- a/mlir/include/mlir/Target/LLVMIR.h
+++ b/mlir/include/mlir/Target/LLVMIR.h
@@ -28,14 +28,14 @@ namespace mlir {
class DialectRegistry;
class OwningModuleRef;
class MLIRContext;
-class ModuleOp;
+class Operation;
/// Convert the given MLIR module into LLVM IR. The LLVM context is extracted
/// from the registered LLVM IR dialect. In case of error, report it
/// to the error handler registered with the MLIR context, if any (obtained from
/// the MLIR module), and return `nullptr`.
std::unique_ptr<llvm::Module>
-translateModuleToLLVMIR(ModuleOp m, llvm::LLVMContext &llvmContext,
+translateModuleToLLVMIR(Operation *op, llvm::LLVMContext &llvmContext,
StringRef name = "LLVMDialectModule");
/// Convert the given LLVM module into MLIR's LLVM dialect. The LLVM context is
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMAVX512/LLVMAVX512ToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMAVX512/LLVMAVX512ToLLVMIRTranslation.h
new file mode 100644
index 000000000000..e591a95f0357
--- /dev/null
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMAVX512/LLVMAVX512ToLLVMIRTranslation.h
@@ -0,0 +1,37 @@
+//===- LLVMAVX512ToLLVMIRTranslation.h - LLVMAVX512 to LLVM IR --*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the dialect interface for translating the LLVMAVX512
+// dialect to LLVM IR.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_TARGET_LLVMIR_DIALECT_LLVMAVX512_LLVMAVX512TOLLVMIRTRANSLATION_H
+#define MLIR_TARGET_LLVMIR_DIALECT_LLVMAVX512_LLVMAVX512TOLLVMIRTRANSLATION_H
+
+#include "mlir/Target/LLVMIR/LLVMTranslationInterface.h"
+
+namespace mlir {
+
+/// Implementation of the dialect interface that converts operations belonging
+/// to the LLVMAVX512 dialect to LLVM IR.
+class LLVMAVX512DialectLLVMIRTranslationInterface
+ : public LLVMTranslationDialectInterface {
+public:
+ using LLVMTranslationDialectInterface::LLVMTranslationDialectInterface;
+
+ /// Translates the given operation to LLVM IR using the provided IR builder
+ /// and saving the state in `moduleTranslation`.
+ LogicalResult
+ convertOperation(Operation *op, llvm::IRBuilderBase &builder,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+};
+
+} // namespace mlir
+
+#endif // MLIR_TARGET_LLVMIR_DIALECT_LLVMAVX512_LLVMAVX512TOLLVMIRTRANSLATION_H
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMArmNeon/LLVMArmNeonToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMArmNeon/LLVMArmNeonToLLVMIRTranslation.h
new file mode 100644
index 000000000000..7d268d155083
--- /dev/null
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMArmNeon/LLVMArmNeonToLLVMIRTranslation.h
@@ -0,0 +1,37 @@
+//===- LLVMArmNeonToLLVMIRTranslation.h - LLVMArmNeon to LLVMIR -*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the dialect interface for translating the LLVMArmNeon
+// dialect to LLVM IR.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_TARGET_LLVMIR_DIALECT_LLVMARMNEON_LLVMARMNEONTOLLVMIRTRANSLATION_H
+#define MLIR_TARGET_LLVMIR_DIALECT_LLVMARMNEON_LLVMARMNEONTOLLVMIRTRANSLATION_H
+
+#include "mlir/Target/LLVMIR/LLVMTranslationInterface.h"
+
+namespace mlir {
+
+/// Implementation of the dialect interface that converts operations belonging
+/// to the LLVMArmNeon dialect to LLVM IR.
+class LLVMArmNeonDialectLLVMIRTranslationInterface
+ : public LLVMTranslationDialectInterface {
+public:
+ using LLVMTranslationDialectInterface::LLVMTranslationDialectInterface;
+
+ /// Translates the given operation to LLVM IR using the provided IR builder
+ /// and saving the state in `moduleTranslation`.
+ LogicalResult
+ convertOperation(Operation *op, llvm::IRBuilderBase &builder,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+};
+
+} // namespace mlir
+
+#endif // MLIR_TARGET_LLVMIR_DIALECT_LLVMARMNEON_LLVMARMNEONTOLLVMIRTRANSLATION_H
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMArmSVE/LLVMArmSVEToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMArmSVE/LLVMArmSVEToLLVMIRTranslation.h
new file mode 100644
index 000000000000..9d4d05b9b9bd
--- /dev/null
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMArmSVE/LLVMArmSVEToLLVMIRTranslation.h
@@ -0,0 +1,37 @@
+//===- LLVMArmSVEToLLVMIRTranslation.h - LLVMArmSVE to LLVM IR --*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the dialect interface for translating the LLVMArmSVE
+// dialect to LLVM IR.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_TARGET_LLVMIR_DIALECT_LLVMARMSVE_LLVMARMSVETOLLVMIRTRANSLATION_H
+#define MLIR_TARGET_LLVMIR_DIALECT_LLVMARMSVE_LLVMARMSVETOLLVMIRTRANSLATION_H
+
+#include "mlir/Target/LLVMIR/LLVMTranslationInterface.h"
+
+namespace mlir {
+
+/// Implementation of the dialect interface that converts operations belonging
+/// to the LLVMArmSVE dialect to LLVM IR.
+class LLVMArmSVEDialectLLVMIRTranslationInterface
+ : public LLVMTranslationDialectInterface {
+public:
+ using LLVMTranslationDialectInterface::LLVMTranslationDialectInterface;
+
+ /// Translates the given operation to LLVM IR using the provided IR builder
+ /// and saving the state in `moduleTranslation`.
+ LogicalResult
+ convertOperation(Operation *op, llvm::IRBuilderBase &builder,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+};
+
+} // namespace mlir
+
+#endif // MLIR_TARGET_LLVMIR_DIALECT_LLVMARMSVE_LLVMARMSVETOLLVMIRTRANSLATION_H
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h
index 8b72cedf1ff2..2af76e092917 100644
--- a/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h
@@ -18,8 +18,8 @@
namespace mlir {
-/// Implementation of the dialect interface that converts operations beloning to
-/// the LLVM dialect to LLVM IR.
+/// Implementation of the dialect interface that converts operations belonging
+/// to the LLVM dialect to LLVM IR.
class LLVMDialectLLVMIRTranslationInterface
: public LLVMTranslationDialectInterface {
public:
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h
new file mode 100644
index 000000000000..3a8a01df84b0
--- /dev/null
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h
@@ -0,0 +1,42 @@
+//===- NVVMToLLVMIRTranslation.h - NVVM to LLVM IR --------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the dialect interface for translating the NVVM
+// dialect to LLVM IR.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_TARGET_LLVMIR_DIALECT_NVVM_NVVMTOLLVMIRTRANSLATION_H
+#define MLIR_TARGET_LLVMIR_DIALECT_NVVM_NVVMTOLLVMIRTRANSLATION_H
+
+#include "mlir/Target/LLVMIR/LLVMTranslationInterface.h"
+
+namespace mlir {
+
+/// Implementation of the dialect interface that converts operations belonging
+/// to the NVVM dialect to LLVM IR.
+class NVVMDialectLLVMIRTranslationInterface
+ : public LLVMTranslationDialectInterface {
+public:
+ using LLVMTranslationDialectInterface::LLVMTranslationDialectInterface;
+
+ /// Translates the given operation to LLVM IR using the provided IR builder
+ /// and saving the state in `moduleTranslation`.
+ LogicalResult
+ convertOperation(Operation *op, llvm::IRBuilderBase &builder,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+
+ /// Attaches module-level metadata for functions marked as kernels.
+ LogicalResult
+ amendOperation(Operation *op, NamedAttribute attribute,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+};
+
+} // namespace mlir
+
+#endif // MLIR_TARGET_LLVMIR_DIALECT_NVVM_NVVMTOLLVMIRTRANSLATION_H
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.h
index 7d9eeea9462e..07721d089689 100644
--- a/mlir/include/mlir/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.h
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.h
@@ -18,8 +18,8 @@
namespace mlir {
-/// Implementation of the dialect interface that converts operations beloning to
-/// the OpenMP dialect to LLVM IR.
+/// Implementation of the dialect interface that converts operations belonging
+/// to the OpenMP dialect to LLVM IR.
class OpenMPDialectLLVMIRTranslationInterface
: public LLVMTranslationDialectInterface {
public:
diff --git a/mlir/include/mlir/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.h b/mlir/include/mlir/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.h
new file mode 100644
index 000000000000..e2211a59098f
--- /dev/null
+++ b/mlir/include/mlir/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.h
@@ -0,0 +1,42 @@
+//===- ROCDLToLLVMIRTranslation.h - ROCDL to LLVM IR ------------*- C++ -*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+// This file implements the dialect interface for translating the ROCDL
+// dialect to LLVM IR.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef MLIR_TARGET_LLVMIR_DIALECT_ROCDL_ROCDLTOLLVMIRTRANSLATION_H
+#define MLIR_TARGET_LLVMIR_DIALECT_ROCDL_ROCDLTOLLVMIRTRANSLATION_H
+
+#include "mlir/Target/LLVMIR/LLVMTranslationInterface.h"
+
+namespace mlir {
+
+/// Implementation of the dialect interface that converts operations belonging
+/// to the ROCDL dialect to LLVM IR.
+class ROCDLDialectLLVMIRTranslationInterface
+ : public LLVMTranslationDialectInterface {
+public:
+ using LLVMTranslationDialectInterface::LLVMTranslationDialectInterface;
+
+ /// Translates the given operation to LLVM IR using the provided IR builder
+ /// and saving the state in `moduleTranslation`.
+ LogicalResult
+ convertOperation(Operation *op, llvm::IRBuilderBase &builder,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+
+ /// Attaches module-level metadata for functions marked as kernels.
+ LogicalResult
+ amendOperation(Operation *op, NamedAttribute attribute,
+ LLVM::ModuleTranslation &moduleTranslation) const final;
+};
+
+} // namespace mlir
+
+#endif // MLIR_TARGET_LLVMIR_DIALECT_ROCDL_ROCDLTOLLVMIRTRANSLATION_H
diff --git a/mlir/include/mlir/Target/LLVMIR/LLVMTranslationInterface.h b/mlir/include/mlir/Target/LLVMIR/LLVMTranslationInterface.h
index 0063beac2977..0c563e6e7d39 100644
--- a/mlir/include/mlir/Target/LLVMIR/LLVMTranslationInterface.h
+++ b/mlir/include/mlir/Target/LLVMIR/LLVMTranslationInterface.h
@@ -13,12 +13,14 @@
#ifndef MLIR_TARGET_LLVMIR_LLVMTRANSLATIONINTERFACE_H
#define MLIR_TARGET_LLVMIR_LLVMTRANSLATIONINTERFACE_H
+#include "mlir/IR/Attributes.h"
#include "mlir/IR/DialectInterface.h"
+#include "mlir/IR/Identifier.h"
#include "mlir/Support/LogicalResult.h"
namespace llvm {
class IRBuilderBase;
-}
+} // namespace llvm
namespace mlir {
namespace LLVM {
@@ -43,6 +45,18 @@ public:
LLVM::ModuleTranslation &moduleTranslation) const {
return failure();
}
+
+ /// Hook for derived dialect interface to act on an operation that has dialect
+ /// attributes from the derived dialect (the operation itself may be from a
+ /// different dialect). This gets called after the operation has been
+ /// translated. The hook is expected to use moduleTranslation to look up the
+ /// translation results and amend the corresponding IR constructs. Does
+ /// nothing and succeeds by default.
+ virtual LogicalResult
+ amendOperation(Operation *op, NamedAttribute attribute,
+ LLVM::ModuleTranslation &moduleTranslation) const {
+ return success();
+ }
};
/// Interface collection for translation to LLVM IR, dispatches to a concrete
@@ -61,6 +75,18 @@ public:
return iface->convertOperation(op, builder, moduleTranslation);
return failure();
}
+
+ /// Acts on the given operation using the interface implemented by the dialect
+ /// of one of the operation's dialect attributes.
+ virtual LogicalResult
+ amendOperation(Operation *op, NamedAttribute attribute,
+ LLVM::ModuleTranslation &moduleTranslation) const {
+ if (const LLVMTranslationDialectInterface *iface =
+ getInterfaceFor(attribute.first.getDialect())) {
+ return iface->amendOperation(op, attribute, moduleTranslation);
+ }
+ return success();
+ }
};
} // namespace mlir
diff --git a/mlir/include/mlir/Target/LLVMIR/ModuleTranslation.h b/mlir/include/mlir/Target/LLVMIR/ModuleTranslation.h
index 03b7f5336461..004524f33fa4 100644
--- a/mlir/include/mlir/Target/LLVMIR/ModuleTranslation.h
+++ b/mlir/include/mlir/Target/LLVMIR/ModuleTranslation.h
@@ -142,18 +142,11 @@ public:
/// Looks up remapped a list of remapped values.
SmallVector<llvm::Value *, 8> lookupValues(ValueRange values);
- /// Create an LLVM IR constant of `llvmType` from the MLIR attribute `attr`.
- /// This currently supports integer, floating point, splat and dense element
- /// attributes and combinations thereof. In case of error, report it to `loc`
- /// and return nullptr.
- llvm::Constant *getLLVMConstant(llvm::Type *llvmType, Attribute attr,
- Location loc);
-
/// Returns the MLIR context of the module being translated.
MLIRContext &getContext() { return *mlirModule->getContext(); }
/// Returns the LLVM context in which the IR is being constructed.
- llvm::LLVMContext &getLLVMContext() { return llvmModule->getContext(); }
+ llvm::LLVMContext &getLLVMContext() const { return llvmModule->getContext(); }
/// Finds an LLVM IR global value that corresponds to the given MLIR operation
/// defining a global value.
@@ -184,6 +177,10 @@ public:
LogicalResult convertBlock(Block &bb, bool ignoreArguments,
llvm::IRBuilder<> &builder);
+ /// Gets the named metadata in the LLVM IR module being constructed, creating
+ /// it if it does not exist.
+ llvm::NamedMDNode *getOrInsertNamedModuleMetadata(StringRef name);
+
protected:
/// Translate the given MLIR module expressed in MLIR LLVM IR dialect into an
/// LLVM IR module. The MLIR LLVM IR dialect holds a pointer to an
@@ -208,6 +205,9 @@ private:
LogicalResult convertGlobals();
LogicalResult convertOneFunction(LLVMFuncOp func);
+ /// Translates dialect attributes attached to the given operation.
+ LogicalResult convertDialectAttributes(Operation *op);
+
/// Original and translated module.
Operation *mlirModule;
std::unique_ptr<llvm::Module> llvmModule;
@@ -228,6 +228,8 @@ private:
/// A stateful object used to translate types.
TypeToLLVMIRTranslator typeTranslator;
+ /// A dialect interface collection used for dispatching the translation to
+ /// specific dialects.
LLVMTranslationInterface iface;
/// Mappings between original and translated values, used for lookups.
@@ -249,6 +251,20 @@ void connectPHINodes(Region ®ion, const ModuleTranslation &state);
/// Get a topologically sorted list of blocks of the given region.
llvm::SetVector<Block *> getTopologicallySortedBlocks(Region ®ion);
+
+/// Create an LLVM IR constant of `llvmType` from the MLIR attribute `attr`.
+/// This currently supports integer, floating point, splat and dense element
+/// attributes and combinations thereof. In case of error, report it to `loc`
+/// and return nullptr.
+llvm::Constant *getLLVMConstant(llvm::Type *llvmType, Attribute attr,
+ Location loc,
+ const ModuleTranslation &moduleTranslation);
+
+/// Creates a call to an LLVM IR intrinsic function with the given arguments.
+llvm::Value *createIntrinsicCall(llvm::IRBuilderBase &builder,
+ llvm::Intrinsic::ID intrinsic,
+ ArrayRef<llvm::Value *> args = {},
+ ArrayRef<llvm::Type *> tys = {});
} // namespace detail
} // namespace LLVM
diff --git a/mlir/include/mlir/Target/NVVMIR.h b/mlir/include/mlir/Target/NVVMIR.h
deleted file mode 100644
index 0cd7688e275b..000000000000
--- a/mlir/include/mlir/Target/NVVMIR.h
+++ /dev/null
@@ -1,39 +0,0 @@
-//===- NVVMIR.h - MLIR to LLVM + NVVM IR conversion -------------*- C++ -*-===//
-//
-// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
-// See https://llvm.org/LICENSE.txt for license information.
-// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-//
-//===----------------------------------------------------------------------===//
-//
-// This file declares the entry point for the MLIR to LLVM + NVVM IR conversion.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef MLIR_TARGET_NVVMIR_H
-#define MLIR_TARGET_NVVMIR_H
-
-#include "llvm/ADT/StringRef.h"
-#include <memory>
-
-// Forward-declare LLVM classes.
-namespace llvm {
-class LLVMContext;
-class Module;
-} // namespace llvm
-
-namespace mlir {
-class Operation;
-
-/// Convert the given LLVM-module-like operation into NVVM IR. This conversion
-/// requires the registration of the LLVM IR dialect and will extract the LLVM
-/// context from the registered LLVM IR dialect. In case of error, report it to
-/// the error handler registered with the MLIR context, if any (obtained from
-/// the MLIR module), and return `nullptr`.
-std::unique_ptr<llvm::Module>
-translateModuleToNVVMIR(Operation *m, llvm::LLVMContext &llvmContext,
- llvm::StringRef name = "LLVMDialectModule");
-
-} // namespace mlir
-
-#endif // MLIR_TARGET_NVVMIR_H
diff --git a/mlir/include/mlir/Target/ROCDLIR.h b/mlir/include/mlir/Target/ROCDLIR.h
deleted file mode 100644
index e2cb812a173d..000000000000
--- a/mlir/include/mlir/Target/ROCDLIR.h
+++ /dev/null
@@ -1,40 +0,0 @@
-//===- ROCDLIR.h - MLIR to LLVM + ROCDL IR conversion -----------*- C++ -*-===//
-//
-// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
-// See https://llvm.org/LICENSE.txt for license information.
-// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-//
-//===----------------------------------------------------------------------===//
-//
-// This file declares the entry point for the MLIR to LLVM + ROCDL IR
-// conversion.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef MLIR_TARGET_ROCDLIR_H
-#define MLIR_TARGET_ROCDLIR_H
-
-#include "llvm/ADT/StringRef.h"
-#include <memory>
-
-// Forward-declare LLVM classes.
-namespace llvm {
-class LLVMContext;
-class Module;
-} // namespace llvm
-
-namespace mlir {
-class Operation;
-
-/// Convert the given LLVM-module-like operation into ROCDL IR. This conversion
-/// requires the registration of the LLVM IR dialect and will extract the LLVM
-/// context from the registered LLVM IR dialect. In case of error, report it to
-/// the error handler registered with the MLIR context, if any (obtained from
-/// the MLIR module), and return `nullptr`.
-std::unique_ptr<llvm::Module>
-translateModuleToROCDLIR(Operation *m, llvm::LLVMContext &llvmContext,
- llvm::StringRef name = "LLVMDialectModule");
-
-} // namespace mlir
-
-#endif // MLIR_TARGET_ROCDLIR_H
diff --git a/mlir/lib/Target/CMakeLists.txt b/mlir/lib/Target/CMakeLists.txt
index e951ffade6aa..a23222d37ede 100644
--- a/mlir/lib/Target/CMakeLists.txt
+++ b/mlir/lib/Target/CMakeLists.txt
@@ -24,26 +24,6 @@ add_mlir_translation_library(MLIRTargetLLVMIRModuleTranslation
MLIRTranslation
)
-add_mlir_translation_library(MLIRTargetAVX512
- LLVMIR/LLVMAVX512Intr.cpp
-
- ADDITIONAL_HEADER_DIRS
- ${MLIR_MAIN_INCLUDE_DIR}/mlir/Target/LLVMIR
-
- DEPENDS
- MLIRLLVMAVX512ConversionsIncGen
-
- LINK_COMPONENTS
- Core
-
- LINK_LIBS PUBLIC
- MLIRIR
- MLIRLLVMAVX512
- MLIRLLVMIR
- MLIRTargetLLVMIR
- MLIRTargetLLVMIRModuleTranslation
- )
-
add_mlir_translation_library(MLIRTargetLLVMIR
LLVMIR/ConvertFromLLVMIR.cpp
LLVMIR/ConvertToLLVMIR.cpp
@@ -56,89 +36,12 @@ add_mlir_translation_library(MLIRTargetLLVMIR
IRReader
LINK_LIBS PUBLIC
+ MLIRLLVMArmNeonToLLVMIRTranslation
+ MLIRLLVMArmSVEToLLVMIRTranslation
+ MLIRLLVMAVX512ToLLVMIRTranslation
MLIRLLVMToLLVMIRTranslation
+ MLIRNVVMToLLVMIRTranslation
MLIROpenMPToLLVMIRTranslation
- MLIRTargetLLVMIRModuleTranslation
- )
-
-add_mlir_translation_library(MLIRTargetArmNeon
- LLVMIR/LLVMArmNeonIntr.cpp
-
- ADDITIONAL_HEADER_DIRS
- ${MLIR_MAIN_INCLUDE_DIR}/mlir/Target/LLVMIR
-
- DEPENDS
- MLIRLLVMArmNeonConversionsIncGen
-
- LINK_COMPONENTS
- Core
-
- LINK_LIBS PUBLIC
- MLIRIR
- MLIRLLVMArmNeon
- MLIRLLVMIR
- MLIRTargetLLVMIR
- MLIRTargetLLVMIRModuleTranslation
- )
-
-add_mlir_translation_library(MLIRTargetArmSVE
- LLVMIR/LLVMArmSVEIntr.cpp
-
- ADDITIONAL_HEADER_DIRS
- ${MLIR_MAIN_INCLUDE_DIR}/mlir/Target/LLVMIR
-
- DEPENDS
- MLIRLLVMArmSVEConversionsIncGen
-
- LINK_COMPONENTS
- Core
-
- LINK_LIBS PUBLIC
- MLIRIR
- MLIRLLVMArmSVE
- MLIRLLVMIR
- MLIRTargetLLVMIR
- MLIRTargetLLVMIRModuleTranslation
- )
-
-add_mlir_translation_library(MLIRTargetNVVMIR
- LLVMIR/ConvertToNVVMIR.cpp
-
- ADDITIONAL_HEADER_DIRS
- ${MLIR_MAIN_INCLUDE_DIR}/mlir/Target/LLVMIR
-
- DEPENDS
- intrinsics_gen
-
- LINK_COMPONENTS
- Core
-
- LINK_LIBS PUBLIC
- MLIRGPU
- MLIRIR
- MLIRLLVMIR
- MLIRNVVMIR
- MLIRTargetLLVMIR
- MLIRTargetLLVMIRModuleTranslation
- )
-
-add_mlir_translation_library(MLIRTargetROCDLIR
- LLVMIR/ConvertToROCDLIR.cpp
-
- ADDITIONAL_HEADER_DIRS
- ${MLIR_MAIN_INCLUDE_DIR}/mlir/Target/LLVMIR
-
- DEPENDS
- intrinsics_gen
-
- LINK_COMPONENTS
- Core
-
- LINK_LIBS PUBLIC
- MLIRGPU
- MLIRIR
- MLIRLLVMIR
- MLIRROCDLIR
- MLIRTargetLLVMIR
+ MLIRROCDLToLLVMIRTranslation
MLIRTargetLLVMIRModuleTranslation
)
diff --git a/mlir/lib/Target/LLVMIR/ConvertToLLVMIR.cpp b/mlir/lib/Target/LLVMIR/ConvertToLLVMIR.cpp
index 6b30748cc79b..42391513bacf 100644
--- a/mlir/lib/Target/LLVMIR/ConvertToLLVMIR.cpp
+++ b/mlir/lib/Target/LLVMIR/ConvertToLLVMIR.cpp
@@ -12,9 +12,19 @@
#include "mlir/Target/LLVMIR.h"
+#include "mlir/Dialect/LLVMIR/LLVMAVX512Dialect.h"
+#include "mlir/Dialect/LLVMIR/LLVMArmNeonDialect.h"
+#include "mlir/Dialect/LLVMIR/LLVMArmSVEDialect.h"
+#include "mlir/Dialect/LLVMIR/NVVMDialect.h"
+#include "mlir/Dialect/LLVMIR/ROCDLDialect.h"
#include "mlir/Dialect/OpenMP/OpenMPDialect.h"
+#include "mlir/Target/LLVMIR/Dialect/LLVMAVX512/LLVMAVX512ToLLVMIRTranslation.h"
+#include "mlir/Target/LLVMIR/Dialect/LLVMArmNeon/LLVMArmNeonToLLVMIRTranslation.h"
+#include "mlir/Target/LLVMIR/Dialect/LLVMArmSVE/LLVMArmSVEToLLVMIRTranslation.h"
#include "mlir/Target/LLVMIR/Dialect/LLVMIR/LLVMToLLVMIRTranslation.h"
+#include "mlir/Target/LLVMIR/Dialect/NVVM/NVVMToLLVMIRTranslation.h"
#include "mlir/Target/LLVMIR/Dialect/OpenMP/OpenMPToLLVMIRTranslation.h"
+#include "mlir/Target/LLVMIR/Dialect/ROCDL/ROCDLToLLVMIRTranslation.h"
#include "mlir/Target/LLVMIR/ModuleTranslation.h"
#include "mlir/Translation.h"
@@ -26,14 +36,14 @@
using namespace mlir;
std::unique_ptr<llvm::Module>
-mlir::translateModuleToLLVMIR(ModuleOp m, llvm::LLVMContext &llvmContext,
+mlir::translateModuleToLLVMIR(Operation *op, llvm::LLVMContext &llvmContext,
StringRef name) {
auto llvmModule =
- LLVM::ModuleTranslation::translateModule<>(m, llvmContext, name);
+ LLVM::ModuleTranslation::translateModule<>(op, llvmContext, name);
if (!llvmModule)
- emitError(m.getLoc(), "Fail to convert MLIR to LLVM IR");
+ emitError(op->getLoc(), "Fail to convert MLIR to LLVM IR");
else if (verifyModule(*llvmModule))
- emitError(m.getLoc(), "LLVM IR fails to verify");
+ emitError(op->getLoc(), "LLVM IR fails to verify");
return llvmModule;
}
@@ -70,9 +80,24 @@ void registerToLLVMIRTranslation() {
return success();
},
[](DialectRegistry ®istry) {
- registry.insert<omp::OpenMPDialect>();
+ registry.insert<omp::OpenMPDialect, LLVM::LLVMAVX512Dialect,
+ LLVM::LLVMArmSVEDialect, LLVM::LLVMArmNeonDialect,
+ NVVM::NVVMDialect, ROCDL::ROCDLDialect>();
registry.addDialectInterface<omp::OpenMPDialect,
OpenMPDialectLLVMIRTranslationInterface>();
+ registry
+ .addDialectInterface<LLVM::LLVMAVX512Dialect,
+ LLVMAVX512DialectLLVMIRTranslationInterface>();
+ registry.addDialectInterface<
+ LLVM::LLVMArmNeonDialect,
+ LLVMArmNeonDialectLLVMIRTranslationInterface>();
+ registry
+ .addDialectInterface<LLVM::LLVMArmSVEDialect,
+ LLVMArmSVEDialectLLVMIRTranslationInterface>();
+ registry.addDialectInterface<NVVM::NVVMDialect,
+ NVVMDialectLLVMIRTranslationInterface>();
+ registry.addDialectInterface<ROCDL::ROCDLDialect,
+ ROCDLDialectLLVMIRTranslationInterface>();
registerLLVMDialectTranslation(registry);
});
}
diff --git a/mlir/lib/Target/LLVMIR/ConvertToNVVMIR.cpp b/mlir/lib/Target/LLVMIR/ConvertToNVVMIR.cpp
deleted file mode 100644
index 7aee913a27d7..000000000000
--- a/mlir/lib/Target/LLVMIR/ConvertToNVVMIR.cpp
+++ /dev/null
@@ -1,124 +0,0 @@
-//===- ConvertToNVVMIR.cpp - MLIR to LLVM IR conversion -------------------===//
-//
-// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
-// See https://llvm.org/LICENSE.txt for license information.
-// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
-//
-//===----------------------------------------------------------------------===//
-//
-// This file implements a translation between the MLIR LLVM + NVVM dialects and
-// LLVM IR with NVVM intrinsics and metadata.
-//
-//===----------------------------------------------------------------------===//
-
-#include "mlir/Target/NVVMIR.h"
-
-#include "mlir/Dialect/GPU/GPUDialect.h"
-#include "mlir/Dialect/LLVMIR/LLVMDialect.h"
-#include "mlir/Dialect/LLVMIR/NVVMDialect.h"
-#include "mlir/IR/BuiltinOps.h"
-#include "mlir/Target/LLVMIR.h"
-#include "mlir/Target/LLVMIR/ModuleTranslation.h"
-#include "mlir/Translation.h"
-
-#include "llvm/ADT/StringRef.h"
-#include "llvm/IR/IntrinsicsNVPTX.h"
-#include "llvm/IR/Module.h"
-#include "llvm/Support/ToolOutputFile.h"
-
-using namespace mlir;
-
-static llvm::Value *createIntrinsicCall(llvm::IRBuilder<> &builder,
- llvm::Intrinsic::ID intrinsic,
- ArrayRef<llvm::Value *> args = {}) {
- llvm::Module *module = builder.GetInsertBlock()->getModule();
- llvm::Function *fn = llvm::Intrinsic::getDeclaration(module, intrinsic);
- return builder.CreateCall(fn, args);
-}
-
-static llvm::Intrinsic::ID getShflBflyIntrinsicId(llvm::Type *resultType,
- bool withPredicate) {
- if (withPredicate) {
- resultType = cast<llvm::StructType>(resultType)->getElementType(0);
- return resultType->isFloatTy() ? llvm::Intrinsic::nvvm_shfl_sync_bfly_f32p
- : llvm::Intrinsic::nvvm_shfl_sync_bfly_i32p;
- }
- return resultType->isFloatTy() ? llvm::Intrinsic::nvvm_shfl_sync_bfly_f32
- : llvm::Intrinsic::nvvm_shfl_sync_bfly_i32;
-}
-
-namespace {
-class ModuleTranslation : public LLVM::ModuleTranslation {
-public:
- using LLVM::ModuleTranslation::ModuleTranslation;
-
-protected:
- LogicalResult convertOperation(Operation &opInst,
- llvm::IRBuilder<> &builder) override {
-
-#include "mlir/Dialect/LLVMIR/NVVMConversions.inc"
-
- return LLVM::ModuleTranslation::convertOperation(opInst, builder);
- }
-
- /// Allow access to the constructor.
- friend LLVM::ModuleTranslation;
-};
-} // namespace
-
-std::unique_ptr<llvm::Module>
-mlir::translateModuleToNVVMIR(Operation *m, llvm::LLVMContext &llvmContext,
- StringRef name) {
- // Register the translation to LLVM IR if nobody else did before. This may
- // happen if this translation is called inside a pass pipeline that converts
- // GPU dialects to binary blobs without translating the rest of the code.
- registerLLVMDialectTranslation(*m->getContext());
-
- auto llvmModule = LLVM::ModuleTranslation::translateModule<ModuleTranslation>(
- m, llvmContext, name);
- if (!llvmModule)
- return llvmModule;
-
- // Insert the nvvm.annotations kernel so that the NVVM backend recognizes the
- // function as a kernel.
- for (auto func :
- ModuleTranslation::getModuleBody(m).getOps<LLVM::LLVMFuncOp>()) {
- if (!func->getAttrOfType<UnitAttr>(
- NVVM::NVVMDialect::getKernelFuncAttrName()))
- continue;
-
- auto *llvmFunc = llvmModule->getFunction(func.getName());
-
- llvm::Metadata *llvmMetadata[] = {
- llvm::ValueAsMetadata::get(llvmFunc),
- llvm::MDString::get(llvmModule->getContext(), "kernel"),
- llvm::ValueAsMetadata::get(llvm::ConstantInt::get(
- llvm::Type::getInt32Ty(llvmModule->getContext()), 1))};
- llvm::MDNode *llvmMetadataNode =
- llvm::MDNode::get(llvmModule->getContext(), llvmMetadata);
- llvmModule->getOrInsertNamedMetadata("nvvm.annotations")
- ->addOperand(llvmMetadataNode);
- }
-
- return llvmModule;
-}
-
-namespace mlir {
-void registerToNVVMIRTranslation() {
- TranslateFromMLIRRegistration registration(
- "mlir-to-nvvmir",
- [](ModuleOp module, raw_ostream &output) {
- llvm::LLVMContext llvmContext;
- auto llvmModule = mlir::translateModuleToNVVMIR(module, llvmContext);
- if (!llvmModule)
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Oz - Build # 8 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz
Culprit:
<cut>
commit 844105d912a4337635001fc2077404aefb90c4c6
Author: GCC Administrator <gccadmin(a)gcc.gnu.org>
Date: Mon Aug 9 00:16:32 2021 +0000
Daily bump.
</cut>
Results regressed to (for first_bad == 844105d912a4337635001fc2077404aefb90c4c6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-844105d912a4337635001fc2077404aefb90c4c6/results_id:
1
# 482.sphinx3,[.] OUTLINED_FUNCTION_4 regressed by 117
from (for last_good == 5f564fd013327977a4d04aa520237d17f641f01a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-5f564fd013327977a4d04aa520237d17f641f01a/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/4114
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/4109
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-844105d912a4337635001fc2077404aefb90c4c6
cd investigate-gcc-844105d912a4337635001fc2077404aefb90c4c6
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 844105d912a4337635001fc2077404aefb90c4c6
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 5f564fd013327977a4d04aa520237d17f641f01a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 844105d912a4337635001fc2077404aefb90c4c6
Author: GCC Administrator <gccadmin(a)gcc.gnu.org>
Date: Mon Aug 9 00:16:32 2021 +0000
Daily bump.
---
gcc/ChangeLog | 4 ++++
gcc/DATESTAMP | 2 +-
gcc/testsuite/ChangeLog | 4 ++++
libstdc++-v3/ChangeLog | 18 ++++++++++++++++++
4 files changed, 27 insertions(+), 1 deletion(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3b0d1b06e9c..9d39f0f0064 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,7 @@
+2021-08-08 Sergei Trofimovich <siarheit(a)google.com>
+
+ * lra-constraints.c: Fix s/otput/output/ typo.
+
2021-08-06 Martin Sebor <msebor(a)redhat.com>
* builtins.c (expand_builtin_memchr): Move to gimple-ssa-warn-access.cc.
diff --git a/gcc/DATESTAMP b/gcc/DATESTAMP
index 3b0c65fa4e8..859da5af87c 100644
--- a/gcc/DATESTAMP
+++ b/gcc/DATESTAMP
@@ -1 +1 @@
-20210808
+20210809
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index fa9298d30df..034fc300a63 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,7 @@
+2021-08-08 Jeff Law <jlaw(a)localhost.localdomain>
+
+ * gcc.target/tic6x/rotdi16-scan.c: Pull rotate into its own function.
+
2021-08-07 H.J. Lu <hjl.tools(a)gmail.com>
PR tree-optimization/88531
diff --git a/libstdc++-v3/ChangeLog b/libstdc++-v3/ChangeLog
index da75afb8ebc..70fb007885a 100644
--- a/libstdc++-v3/ChangeLog
+++ b/libstdc++-v3/ChangeLog
@@ -1,3 +1,21 @@
+2021-08-08 François Dumont <fdumont(a)gcc.gnu.org>
+
+ * testsuite/25_algorithms/copy/debug/constexpr_neg.cc: Replace 'failed_assertion'
+ dg-prune-output reason with 'builtin_unreachable'.
+ * testsuite/25_algorithms/copy_backward/debug/constexpr_neg.cc: Likewise.
+ * testsuite/25_algorithms/equal/debug/constexpr_neg.cc: Likewise.
+ * testsuite/25_algorithms/lower_bound/debug/constexpr_partitioned_neg.cc: Likewise.
+ * testsuite/25_algorithms/lower_bound/debug/constexpr_partitioned_pred_neg.cc: Likewise.
+ * testsuite/25_algorithms/lower_bound/debug/constexpr_valid_range_neg.cc: Likewise.
+ * testsuite/25_algorithms/upper_bound/debug/constexpr_partitioned_neg.cc: Likewise.
+ * testsuite/25_algorithms/upper_bound/debug/constexpr_partitioned_pred_neg.cc: Likewise.
+ * testsuite/25_algorithms/upper_bound/debug/constexpr_valid_range_neg.cc: Likewise.
+
+2021-08-08 Hans-Peter Nilsson <hp(a)bitrange.com>
+
+ * testsuite/std/ranges/iota/max_size_type.cc: Set
+ dg-timeout-factor to 4.
+
2021-08-06 Jonathan Wakely <jwakely(a)redhat.com>
* libsupc++/compare (compare_three_way, strong_order)
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O2_LTO - Build # 6 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O2_LTO
Culprit:
<cut>
commit f8ed31cd991bf84372369409595707f6e3cebbce
Author: Jonny Farley <jonny.farley(a)sony.com>
Date: Tue Feb 16 16:34:35 2021 +0000
[Fuzzer][Test] Use %python substitution for trace-malloc-unbalanced.test
This test was found to fail for some of our downstream builds, on
computers where python was not on the default $PATH. Therefore
add a %python substitution to use sys.executable, based on similar
solutions for python calls in tests elsewhere in LLVM.
Differential Revision: https://reviews.llvm.org/D96799
</cut>
Results regressed to (for first_bad == f8ed31cd991bf84372369409595707f6e3cebbce)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO artifacts/build-f8ed31cd991bf84372369409595707f6e3cebbce/results_id:
1
# 400.perlbench,perlbench_base.default regressed by 103
from (for last_good == cb2876800cc827431f4143c4fc5595c6c1191269)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO artifacts/build-cb2876800cc827431f4143c4fc5595c6c1191269/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O2_LTO/4095
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O2_LTO/4070
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-f8ed31cd991bf84372369409595707f6e3cebbce
cd investigate-llvm-f8ed31cd991bf84372369409595707f6e3cebbce
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach f8ed31cd991bf84372369409595707f6e3cebbce
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach cb2876800cc827431f4143c4fc5595c6c1191269
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit f8ed31cd991bf84372369409595707f6e3cebbce
Author: Jonny Farley <jonny.farley(a)sony.com>
Date: Tue Feb 16 16:34:35 2021 +0000
[Fuzzer][Test] Use %python substitution for trace-malloc-unbalanced.test
This test was found to fail for some of our downstream builds, on
computers where python was not on the default $PATH. Therefore
add a %python substitution to use sys.executable, based on similar
solutions for python calls in tests elsewhere in LLVM.
Differential Revision: https://reviews.llvm.org/D96799
---
compiler-rt/test/fuzzer/lit.cfg.py | 2 ++
compiler-rt/test/fuzzer/trace-malloc-unbalanced.test | 4 ++--
2 files changed, 4 insertions(+), 2 deletions(-)
diff --git a/compiler-rt/test/fuzzer/lit.cfg.py b/compiler-rt/test/fuzzer/lit.cfg.py
index 00871b8a94a3..d114ae7937fa 100644
--- a/compiler-rt/test/fuzzer/lit.cfg.py
+++ b/compiler-rt/test/fuzzer/lit.cfg.py
@@ -61,6 +61,8 @@ config.substitutions.append(('%build_dir', config.cmake_binary_dir))
libfuzzer_src_root = os.path.join(config.compiler_rt_src_root, "lib", "fuzzer")
config.substitutions.append(('%libfuzzer_src', libfuzzer_src_root))
+config.substitutions.append(('%python', '"%s"' % (sys.executable)))
+
def generate_compiler_cmd(is_cpp=True, fuzzer_enabled=True, msan_enabled=False):
compiler_cmd = config.clang
extra_cmd = config.target_flags
diff --git a/compiler-rt/test/fuzzer/trace-malloc-unbalanced.test b/compiler-rt/test/fuzzer/trace-malloc-unbalanced.test
index c7b4632140cb..395386ab5cd2 100644
--- a/compiler-rt/test/fuzzer/trace-malloc-unbalanced.test
+++ b/compiler-rt/test/fuzzer/trace-malloc-unbalanced.test
@@ -8,10 +8,10 @@ RUN: %cpp_compiler %S/TraceMallocTest.cpp -o %t-TraceMallocTest
# Specify python because we can't use the shebang line on Windows.
RUN: %run %t-TraceMallocTest -seed=1 -trace_malloc=1 -runs=200 2>&1 | \
-RUN: python %libfuzzer_src/scripts/unbalanced_allocs.py --skip=5 | FileCheck %s
+RUN: %python %libfuzzer_src/scripts/unbalanced_allocs.py --skip=5 | FileCheck %s
RUN: %run %t-TraceMallocTest -seed=1 -trace_malloc=2 -runs=200 2>&1 | \
-RUN: python %libfuzzer_src/scripts/unbalanced_allocs.py --skip=5 | FileCheck %s --check-prefixes=CHECK,CHECK2
+RUN: %python %libfuzzer_src/scripts/unbalanced_allocs.py --skip=5 | FileCheck %s --check-prefixes=CHECK,CHECK2
CHECK: MallocFreeTracer: START
# Behavior of the format string "%p" is implementation defined. Account for the
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3_LTO - Build # 7 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3_LTO
Culprit:
<cut>
commit f343a730596b6b02039a91d71dc16c113d09cfe6
Author: Vitaly Buka <vitalybuka(a)google.com>
Date: Fri Apr 2 00:17:45 2021 -0700
[NFC][scudo] Convert ScudoPrimaryTest into TYPED_TEST
</cut>
Results regressed to (for first_bad == f343a730596b6b02039a91d71dc16c113d09cfe6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-f343a730596b6b02039a91d71dc16c113d09cfe6/results_id:
1
# 462.libquantum,libquantum_base.default regressed by 104
from (for last_good == 28ea218417d713bcb399e9428e4c3f8f7960feb2)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-28ea218417d713bcb399e9428e4c3f8f7960feb2/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3_LTO/4078
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3_LTO/4076
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-f343a730596b6b02039a91d71dc16c113d09cfe6
cd investigate-llvm-f343a730596b6b02039a91d71dc16c113d09cfe6
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach f343a730596b6b02039a91d71dc16c113d09cfe6
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 28ea218417d713bcb399e9428e4c3f8f7960feb2
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit f343a730596b6b02039a91d71dc16c113d09cfe6
Author: Vitaly Buka <vitalybuka(a)google.com>
Date: Fri Apr 2 00:17:45 2021 -0700
[NFC][scudo] Convert ScudoPrimaryTest into TYPED_TEST
---
.../lib/scudo/standalone/tests/primary_test.cpp | 73 +++++++++++++---------
1 file changed, 44 insertions(+), 29 deletions(-)
diff --git a/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp b/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp
index 38bf67150853..07f3d6b77c17 100644
--- a/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp
+++ b/compiler-rt/lib/scudo/standalone/tests/primary_test.cpp
@@ -52,8 +52,7 @@ template <typename Primary> static void testPrimary() {
Str.output();
}
-template <typename SizeClassMapT> struct TestConfig1 {
- using SizeClassMap = SizeClassMapT;
+struct TestConfig1 {
static const scudo::uptr PrimaryRegionSizeLog = 18U;
static const scudo::s32 PrimaryMinReleaseToOsIntervalMs = INT32_MIN;
static const scudo::s32 PrimaryMaxReleaseToOsIntervalMs = INT32_MAX;
@@ -62,8 +61,7 @@ template <typename SizeClassMapT> struct TestConfig1 {
static const scudo::uptr PrimaryCompactPtrScale = 0;
};
-template <typename SizeClassMapT> struct TestConfig2 {
- using SizeClassMap = SizeClassMapT;
+struct TestConfig2 {
static const scudo::uptr PrimaryRegionSizeLog = 24U;
static const scudo::s32 PrimaryMinReleaseToOsIntervalMs = INT32_MIN;
static const scudo::s32 PrimaryMaxReleaseToOsIntervalMs = INT32_MAX;
@@ -72,8 +70,7 @@ template <typename SizeClassMapT> struct TestConfig2 {
static const scudo::uptr PrimaryCompactPtrScale = 0;
};
-template <typename SizeClassMapT> struct TestConfig3 {
- using SizeClassMap = SizeClassMapT;
+struct TestConfig3 {
static const scudo::uptr PrimaryRegionSizeLog = 24U;
static const scudo::s32 PrimaryMinReleaseToOsIntervalMs = INT32_MIN;
static const scudo::s32 PrimaryMaxReleaseToOsIntervalMs = INT32_MAX;
@@ -82,13 +79,43 @@ template <typename SizeClassMapT> struct TestConfig3 {
static const scudo::uptr PrimaryCompactPtrScale = 0;
};
-TEST(ScudoPrimaryTest, BasicPrimary) {
- using SizeClassMap = scudo::DefaultSizeClassMap;
+template <typename BaseConfig, typename SizeClassMapT>
+struct Config : public BaseConfig {
+ using SizeClassMap = SizeClassMapT;
+};
+
+template <typename BaseConfig, typename SizeClassMapT> struct MakeAllocator {
+ using Value = scudo::SizeClassAllocator64<Config<BaseConfig, SizeClassMapT>>;
+};
+
+template <typename SizeClassMapT>
+struct MakeAllocator<TestConfig1, SizeClassMapT> {
+ using Value = scudo::SizeClassAllocator32<Config<TestConfig1, SizeClassMapT>>;
+};
+
+namespace testing {
+namespace internal {
+#define SCUDO_DEFINE_GTEST_TYPE_NAME(TYPE) \
+ template <> std::string GetTypeName<TYPE>() { return #TYPE; }
+SCUDO_DEFINE_GTEST_TYPE_NAME(TestConfig1)
+SCUDO_DEFINE_GTEST_TYPE_NAME(TestConfig2)
+SCUDO_DEFINE_GTEST_TYPE_NAME(TestConfig3)
+#undef SCUDO_DEFINE_GTEST_TYPE_NAME
+} // namespace internal
+} // namespace testing
+
+template <class BaseConfig> struct ScudoPrimaryTest : public ::testing::Test {};
+
+using ScudoPrimaryTestTypes = testing::Types<
#if !SCUDO_FUCHSIA
- testPrimary<scudo::SizeClassAllocator32<TestConfig1<SizeClassMap>>>();
+ TestConfig1,
#endif
- testPrimary<scudo::SizeClassAllocator64<TestConfig2<SizeClassMap>>>();
- testPrimary<scudo::SizeClassAllocator64<TestConfig3<SizeClassMap>>>();
+ TestConfig2, TestConfig3>;
+TYPED_TEST_CASE(ScudoPrimaryTest, ScudoPrimaryTestTypes);
+
+TYPED_TEST(ScudoPrimaryTest, BasicPrimary) {
+ using SizeClassMap = scudo::DefaultSizeClassMap;
+ testPrimary<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
}
struct SmallRegionsConfig {
@@ -178,13 +205,9 @@ template <typename Primary> static void testIteratePrimary() {
Str.output();
}
-TEST(ScudoPrimaryTest, PrimaryIterate) {
+TYPED_TEST(ScudoPrimaryTest, PrimaryIterate) {
using SizeClassMap = scudo::DefaultSizeClassMap;
-#if !SCUDO_FUCHSIA
- testIteratePrimary<scudo::SizeClassAllocator32<TestConfig1<SizeClassMap>>>();
-#endif
- testIteratePrimary<scudo::SizeClassAllocator64<TestConfig2<SizeClassMap>>>();
- testIteratePrimary<scudo::SizeClassAllocator64<TestConfig3<SizeClassMap>>>();
+ testIteratePrimary<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
}
static std::mutex Mutex;
@@ -239,13 +262,9 @@ template <typename Primary> static void testPrimaryThreaded() {
Str.output();
}
-TEST(ScudoPrimaryTest, PrimaryThreaded) {
+TYPED_TEST(ScudoPrimaryTest, PrimaryThreaded) {
using SizeClassMap = scudo::SvelteSizeClassMap;
-#if !SCUDO_FUCHSIA
- testPrimaryThreaded<scudo::SizeClassAllocator32<TestConfig1<SizeClassMap>>>();
-#endif
- testPrimaryThreaded<scudo::SizeClassAllocator64<TestConfig2<SizeClassMap>>>();
- testPrimaryThreaded<scudo::SizeClassAllocator64<TestConfig3<SizeClassMap>>>();
+ testPrimaryThreaded<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
}
// Through a simple allocation that spans two pages, verify that releaseToOS
@@ -270,11 +289,7 @@ template <typename Primary> static void testReleaseToOS() {
EXPECT_GT(Allocator->releaseToOS(), 0U);
}
-TEST(ScudoPrimaryTest, ReleaseToOS) {
+TYPED_TEST(ScudoPrimaryTest, ReleaseToOS) {
using SizeClassMap = scudo::DefaultSizeClassMap;
-#if !SCUDO_FUCHSIA
- testReleaseToOS<scudo::SizeClassAllocator32<TestConfig1<SizeClassMap>>>();
-#endif
- testReleaseToOS<scudo::SizeClassAllocator64<TestConfig2<SizeClassMap>>>();
- testReleaseToOS<scudo::SizeClassAllocator64<TestConfig3<SizeClassMap>>>();
+ testReleaseToOS<typename MakeAllocator<TypeParam, SizeClassMap>::Value>();
}
</cut>
4 years
- 1
- 0
[ACTIVITY] report week ending 20 Aug
by Peter Maydell
Progress:
* UM-2 [QEMU upstream maintainership]
+ We needed an rc4 (as usual)
+ Tried to work through some of my code review patchlog, notably
some big alignment-related series from RTH
+ Sent patchseries for some small things:
+ implement last few bits of HSTR trap-to-hypervisor functionality
+ actually take an exception if PSTATE.IL gets set
+ don't assert if user asks for both an EL3 guest CPU and KVM
* QEMU-406 [QEMU support for MVE (M-profile Vector Extension; Helium)]
+ worked through rth's code review comments for fp insn patches
these are now ready to send out once QEMU makes its 6.1 release
and the previous slice of reviewed patches can get into the tree
-- PMM
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3 - Build # 10 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3
Culprit:
<cut>
commit a838a4f69f500fc8e39fb4c9a1476f162ccf8423
Author: David Green <david.green(a)arm.com>
Date: Mon Feb 15 13:17:21 2021 +0000
[ARM] Extend search for increment in load/store optimizer
Currently the findIncDecAfter will only look at the next instruction for
post-inc candidates in the load/store optimizer. This extends that to a
search through the current BB, until an instruction that modifies or
uses the increment reg is found. This allows more post-inc load/stores
and ldm/stm's to be created, especially in cases where a schedule might
move instructions further apart.
We make sure not to look any further for an SP, as that might invalidate
stack slots that are still in use.
Differential Revision: https://reviews.llvm.org/D95881
</cut>
Results regressed to (for first_bad == a838a4f69f500fc8e39fb4c9a1476f162ccf8423)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-a838a4f69f500fc8e39fb4c9a1476f162ccf8423/results_id:
1
# 482.sphinx3,sphinx_livepretend_base.default regressed by 104
# 482.sphinx3,[.] vector_gautbl_eval_logs3 regressed by 115
from (for last_good == 20e3a6cb6270b68139f74529ab8efdfad1263533)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-20e3a6cb6270b68139f74529ab8efdfad1263533/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/4025
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/4022
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-a838a4f69f500fc8e39fb4c9a1476f162ccf8423
cd investigate-llvm-a838a4f69f500fc8e39fb4c9a1476f162ccf8423
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach a838a4f69f500fc8e39fb4c9a1476f162ccf8423
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 20e3a6cb6270b68139f74529ab8efdfad1263533
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit a838a4f69f500fc8e39fb4c9a1476f162ccf8423
Author: David Green <david.green(a)arm.com>
Date: Mon Feb 15 13:17:21 2021 +0000
[ARM] Extend search for increment in load/store optimizer
Currently the findIncDecAfter will only look at the next instruction for
post-inc candidates in the load/store optimizer. This extends that to a
search through the current BB, until an instruction that modifies or
uses the increment reg is found. This allows more post-inc load/stores
and ldm/stm's to be created, especially in cases where a schedule might
move instructions further apart.
We make sure not to look any further for an SP, as that might invalidate
stack slots that are still in use.
Differential Revision: https://reviews.llvm.org/D95881
---
llvm/lib/Target/ARM/ARMLoadStoreOptimizer.cpp | 40 +++++++++++++------
llvm/test/CodeGen/ARM/indexed-mem.ll | 6 +--
.../Thumb2/LowOverheadLoops/fast-fp-loops.ll | 9 ++---
.../Thumb2/LowOverheadLoops/mve-float-loops.ll | 45 ++++++++--------------
llvm/test/CodeGen/Thumb2/mve-float32regloops.ll | 6 +--
llvm/test/CodeGen/Thumb2/mve-postinc-distribute.ll | 9 ++---
llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll | 9 ++---
llvm/test/CodeGen/Thumb2/mve-satmul-loops.ll | 18 +++------
llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll | 6 +--
llvm/test/CodeGen/Thumb2/mve-vldshuffle.ll | 3 +-
10 files changed, 66 insertions(+), 85 deletions(-)
diff --git a/llvm/lib/Target/ARM/ARMLoadStoreOptimizer.cpp b/llvm/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
index aa1fe4e4ffda..5fe61809f31b 100644
--- a/llvm/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
+++ b/llvm/lib/Target/ARM/ARMLoadStoreOptimizer.cpp
@@ -1238,19 +1238,37 @@ findIncDecBefore(MachineBasicBlock::iterator MBBI, Register Reg,
/// Searches for a increment or decrement of \p Reg after \p MBBI.
static MachineBasicBlock::iterator
findIncDecAfter(MachineBasicBlock::iterator MBBI, Register Reg,
- ARMCC::CondCodes Pred, Register PredReg, int &Offset) {
+ ARMCC::CondCodes Pred, Register PredReg, int &Offset,
+ const TargetRegisterInfo *TRI) {
Offset = 0;
MachineBasicBlock &MBB = *MBBI->getParent();
MachineBasicBlock::iterator EndMBBI = MBB.end();
MachineBasicBlock::iterator NextMBBI = std::next(MBBI);
- // Skip debug values.
- while (NextMBBI != EndMBBI && NextMBBI->isDebugInstr())
- ++NextMBBI;
- if (NextMBBI == EndMBBI)
- return EndMBBI;
+ while (NextMBBI != EndMBBI) {
+ // Skip debug values.
+ while (NextMBBI != EndMBBI && NextMBBI->isDebugInstr())
+ ++NextMBBI;
+ if (NextMBBI == EndMBBI)
+ return EndMBBI;
+
+ unsigned Off = isIncrementOrDecrement(*NextMBBI, Reg, Pred, PredReg);
+ if (Off) {
+ Offset = Off;
+ return NextMBBI;
+ }
- Offset = isIncrementOrDecrement(*NextMBBI, Reg, Pred, PredReg);
- return Offset == 0 ? EndMBBI : NextMBBI;
+ // SP can only be combined if it is the next instruction after the original
+ // MBBI, otherwise we may be incrementing the stack pointer (invalidating
+ // anything below the new pointer) when its frame elements are still in
+ // use. Other registers can attempt to look further, until a different use
+ // or def of the register is found.
+ if (Reg == ARM::SP || NextMBBI->readsRegister(Reg, TRI) ||
+ NextMBBI->definesRegister(Reg, TRI))
+ return EndMBBI;
+
+ ++NextMBBI;
+ }
+ return EndMBBI;
}
/// Fold proceeding/trailing inc/dec of base register into the
@@ -1296,7 +1314,7 @@ bool ARMLoadStoreOpt::MergeBaseUpdateLSMultiple(MachineInstr *MI) {
} else if (Mode == ARM_AM::ib && Offset == -Bytes) {
Mode = ARM_AM::da;
} else {
- MergeInstr = findIncDecAfter(MBBI, Base, Pred, PredReg, Offset);
+ MergeInstr = findIncDecAfter(MBBI, Base, Pred, PredReg, Offset, TRI);
if (((Mode != ARM_AM::ia && Mode != ARM_AM::ib) || Offset != Bytes) &&
((Mode != ARM_AM::da && Mode != ARM_AM::db) || Offset != -Bytes)) {
@@ -1483,7 +1501,7 @@ bool ARMLoadStoreOpt::MergeBaseUpdateLoadStore(MachineInstr *MI) {
} else if (Offset == -Bytes) {
NewOpc = getPreIndexedLoadStoreOpcode(Opcode, ARM_AM::sub);
} else {
- MergeInstr = findIncDecAfter(MBBI, Base, Pred, PredReg, Offset);
+ MergeInstr = findIncDecAfter(MBBI, Base, Pred, PredReg, Offset, TRI);
if (Offset == Bytes) {
NewOpc = getPostIndexedLoadStoreOpcode(Opcode, ARM_AM::add);
} else if (!isAM5 && Offset == -Bytes) {
@@ -1614,7 +1632,7 @@ bool ARMLoadStoreOpt::MergeBaseUpdateLSDouble(MachineInstr &MI) const {
if (Offset == 8 || Offset == -8) {
NewOpc = Opcode == ARM::t2LDRDi8 ? ARM::t2LDRD_PRE : ARM::t2STRD_PRE;
} else {
- MergeInstr = findIncDecAfter(MBBI, Base, Pred, PredReg, Offset);
+ MergeInstr = findIncDecAfter(MBBI, Base, Pred, PredReg, Offset, TRI);
if (Offset == 8 || Offset == -8) {
NewOpc = Opcode == ARM::t2LDRDi8 ? ARM::t2LDRD_POST : ARM::t2STRD_POST;
} else
diff --git a/llvm/test/CodeGen/ARM/indexed-mem.ll b/llvm/test/CodeGen/ARM/indexed-mem.ll
index a5f8409a50a2..295bb377d732 100644
--- a/llvm/test/CodeGen/ARM/indexed-mem.ll
+++ b/llvm/test/CodeGen/ARM/indexed-mem.ll
@@ -220,16 +220,14 @@ define i32* @pre_dec_ldrd(i32* %base) {
define i32* @post_inc_ldrd(i32* %base, i32* %addr.3) {
; CHECK-V8M-LABEL: post_inc_ldrd:
; CHECK-V8M: @ %bb.0:
-; CHECK-V8M-NEXT: ldrd r2, r3, [r0]
-; CHECK-V8M-NEXT: adds r0, #8
+; CHECK-V8M-NEXT: ldrd r2, r3, [r0], #8
; CHECK-V8M-NEXT: add r2, r3
; CHECK-V8M-NEXT: str r2, [r1]
; CHECK-V8M-NEXT: bx lr
;
; CHECK-V8A-LABEL: post_inc_ldrd:
; CHECK-V8A: @ %bb.0:
-; CHECK-V8A-NEXT: ldm r0, {r2, r3}
-; CHECK-V8A-NEXT: add r0, r0, #8
+; CHECK-V8A-NEXT: ldm r0!, {r2, r3}
; CHECK-V8A-NEXT: add r2, r2, r3
; CHECK-V8A-NEXT: str r2, [r1]
; CHECK-V8A-NEXT: bx lr
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/fast-fp-loops.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/fast-fp-loops.ll
index f8fb8476c322..8b27a9348418 100644
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/fast-fp-loops.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/fast-fp-loops.ll
@@ -82,13 +82,10 @@ define arm_aapcs_vfpcc void @fast_float_mul(float* nocapture %a, float* nocaptur
; CHECK-NEXT: add.w r0, r0, r3, lsl #2
; CHECK-NEXT: .LBB0_10: @ %for.body.epil
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s0, [r1]
-; CHECK-NEXT: adds r1, #4
-; CHECK-NEXT: vldr s2, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vldmia r1!, {s0}
+; CHECK-NEXT: vldmia r2!, {s2}
; CHECK-NEXT: vmul.f32 s0, s2, s0
-; CHECK-NEXT: vstr s0, [r0]
-; CHECK-NEXT: adds r0, #4
+; CHECK-NEXT: vstmia r0!, {s0}
; CHECK-NEXT: le lr, .LBB0_10
; CHECK-NEXT: .LBB0_11: @ %for.cond.cleanup
; CHECK-NEXT: pop {r4, r5, r6, r7, pc}
diff --git a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
index f962458ddb11..d143976927b2 100644
--- a/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
+++ b/llvm/test/CodeGen/Thumb2/LowOverheadLoops/mve-float-loops.ll
@@ -43,14 +43,11 @@ define arm_aapcs_vfpcc void @float_float_mul(float* nocapture readonly %a, float
; CHECK-NEXT: add.w r7, r2, r12, lsl #2
; CHECK-NEXT: .LBB0_6: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s0, [r6]
-; CHECK-NEXT: adds r6, #4
-; CHECK-NEXT: vldr s2, [r5]
-; CHECK-NEXT: adds r5, #4
+; CHECK-NEXT: vldmia r6!, {s0}
; CHECK-NEXT: add.w r12, r12, #1
+; CHECK-NEXT: vldmia r5!, {s2}
; CHECK-NEXT: vmul.f32 s0, s2, s0
-; CHECK-NEXT: vstr s0, [r7]
-; CHECK-NEXT: adds r7, #4
+; CHECK-NEXT: vstmia r7!, {s0}
; CHECK-NEXT: le lr, .LBB0_6
; CHECK-NEXT: .LBB0_7: @ %for.body.prol.loopexit
; CHECK-NEXT: cmp r4, #3
@@ -261,14 +258,11 @@ define arm_aapcs_vfpcc void @float_float_add(float* nocapture readonly %a, float
; CHECK-NEXT: add.w r7, r2, r12, lsl #2
; CHECK-NEXT: .LBB1_6: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s0, [r6]
-; CHECK-NEXT: adds r6, #4
-; CHECK-NEXT: vldr s2, [r5]
-; CHECK-NEXT: adds r5, #4
+; CHECK-NEXT: vldmia r6!, {s0}
; CHECK-NEXT: add.w r12, r12, #1
+; CHECK-NEXT: vldmia r5!, {s2}
; CHECK-NEXT: vadd.f32 s0, s2, s0
-; CHECK-NEXT: vstr s0, [r7]
-; CHECK-NEXT: adds r7, #4
+; CHECK-NEXT: vstmia r7!, {s0}
; CHECK-NEXT: le lr, .LBB1_6
; CHECK-NEXT: .LBB1_7: @ %for.body.prol.loopexit
; CHECK-NEXT: cmp r4, #3
@@ -479,14 +473,11 @@ define arm_aapcs_vfpcc void @float_float_sub(float* nocapture readonly %a, float
; CHECK-NEXT: add.w r7, r2, r12, lsl #2
; CHECK-NEXT: .LBB2_6: @ %for.body.prol
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s0, [r6]
-; CHECK-NEXT: adds r6, #4
-; CHECK-NEXT: vldr s2, [r5]
-; CHECK-NEXT: adds r5, #4
+; CHECK-NEXT: vldmia r6!, {s0}
; CHECK-NEXT: add.w r12, r12, #1
+; CHECK-NEXT: vldmia r5!, {s2}
; CHECK-NEXT: vsub.f32 s0, s2, s0
-; CHECK-NEXT: vstr s0, [r7]
-; CHECK-NEXT: adds r7, #4
+; CHECK-NEXT: vstmia r7!, {s0}
; CHECK-NEXT: le lr, .LBB2_6
; CHECK-NEXT: .LBB2_7: @ %for.body.prol.loopexit
; CHECK-NEXT: cmp r4, #3
@@ -706,13 +697,11 @@ define arm_aapcs_vfpcc void @float_int_mul(float* nocapture readonly %a, i32* no
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
; CHECK-NEXT: ldr r4, [r6], #4
; CHECK-NEXT: add.w r12, r12, #1
-; CHECK-NEXT: vldr s2, [r5]
-; CHECK-NEXT: adds r5, #4
+; CHECK-NEXT: vldmia r5!, {s2}
; CHECK-NEXT: vmov s0, r4
; CHECK-NEXT: vcvt.f32.s32 s0, s0
; CHECK-NEXT: vmul.f32 s0, s2, s0
-; CHECK-NEXT: vstr s0, [r7]
-; CHECK-NEXT: adds r7, #4
+; CHECK-NEXT: vstmia r7!, {s0}
; CHECK-NEXT: le lr, .LBB3_9
; CHECK-NEXT: .LBB3_10: @ %for.body.prol.loopexit
; CHECK-NEXT: cmp.w r8, #3
@@ -1025,8 +1014,7 @@ define arm_aapcs_vfpcc void @half_half_mul(half* nocapture readonly %a, half* no
; CHECK-NEXT: adds r1, #2
; CHECK-NEXT: vmul.f16 s0, s2, s0
; CHECK-NEXT: vcvtb.f32.f16 s0, s0
-; CHECK-NEXT: vstr s0, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vstmia r2!, {s0}
; CHECK-NEXT: le lr, .LBB5_7
; CHECK-NEXT: .LBB5_8: @ %for.cond.cleanup
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
@@ -1140,8 +1128,7 @@ define arm_aapcs_vfpcc void @half_half_add(half* nocapture readonly %a, half* no
; CHECK-NEXT: adds r1, #2
; CHECK-NEXT: vadd.f16 s0, s2, s0
; CHECK-NEXT: vcvtb.f32.f16 s0, s0
-; CHECK-NEXT: vstr s0, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vstmia r2!, {s0}
; CHECK-NEXT: le lr, .LBB6_7
; CHECK-NEXT: .LBB6_8: @ %for.cond.cleanup
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
@@ -1255,8 +1242,7 @@ define arm_aapcs_vfpcc void @half_half_sub(half* nocapture readonly %a, half* no
; CHECK-NEXT: adds r1, #2
; CHECK-NEXT: vsub.f16 s0, s2, s0
; CHECK-NEXT: vcvtb.f32.f16 s0, s0
-; CHECK-NEXT: vstr s0, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vstmia r2!, {s0}
; CHECK-NEXT: le lr, .LBB7_7
; CHECK-NEXT: .LBB7_8: @ %for.cond.cleanup
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, r10, pc}
@@ -1376,8 +1362,7 @@ define arm_aapcs_vfpcc void @half_short_mul(half* nocapture readonly %a, i16* no
; CHECK-NEXT: vcvt.f16.s32 s2, s2
; CHECK-NEXT: vmul.f16 s0, s0, s2
; CHECK-NEXT: vcvtb.f32.f16 s0, s0
-; CHECK-NEXT: vstr s0, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vstmia r2!, {s0}
; CHECK-NEXT: le lr, .LBB8_7
; CHECK-NEXT: .LBB8_8: @ %for.cond.cleanup
; CHECK-NEXT: pop.w {r4, r5, r6, r7, r8, r9, pc}
diff --git a/llvm/test/CodeGen/Thumb2/mve-float32regloops.ll b/llvm/test/CodeGen/Thumb2/mve-float32regloops.ll
index 0156cfe25f8e..7e4603e4b4c6 100644
--- a/llvm/test/CodeGen/Thumb2/mve-float32regloops.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-float32regloops.ll
@@ -1442,8 +1442,7 @@ define arm_aapcs_vfpcc void @arm_biquad_cascade_stereo_df2T_f32(%struct.arm_biqu
; CHECK-NEXT: adds r1, #8
; CHECK-NEXT: vfma.f32 q5, q4, r5
; CHECK-NEXT: vfma.f32 q3, q5, q2
-; CHECK-NEXT: vstmia r7, {s20, s21}
-; CHECK-NEXT: adds r7, #8
+; CHECK-NEXT: vstmia r7!, {s20, s21}
; CHECK-NEXT: vfma.f32 q3, q4, q1
; CHECK-NEXT: vstrw.32 q3, [r4]
; CHECK-NEXT: le lr, .LBB17_3
@@ -2069,8 +2068,7 @@ define void @arm_biquad_cascade_df2T_f32(%struct.arm_biquad_cascade_df2T_instanc
; CHECK-NEXT: .LBB20_5: @ %while.body
; CHECK-NEXT: @ Parent Loop BB20_3 Depth=1
; CHECK-NEXT: @ => This Inner Loop Header: Depth=2
-; CHECK-NEXT: ldrd r7, r4, [r1]
-; CHECK-NEXT: adds r1, #8
+; CHECK-NEXT: ldrd r7, r4, [r1], #8
; CHECK-NEXT: vfma.f32 q6, q3, r7
; CHECK-NEXT: vmov r7, s24
; CHECK-NEXT: vmov q1, q6
diff --git a/llvm/test/CodeGen/Thumb2/mve-postinc-distribute.ll b/llvm/test/CodeGen/Thumb2/mve-postinc-distribute.ll
index b34896e32859..0eb1226f60db 100644
--- a/llvm/test/CodeGen/Thumb2/mve-postinc-distribute.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-postinc-distribute.ll
@@ -309,14 +309,11 @@ define void @fma8(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: .LBB2_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s0, [r0]
-; CHECK-NEXT: adds r0, #4
-; CHECK-NEXT: vldr s2, [r1]
-; CHECK-NEXT: adds r1, #4
+; CHECK-NEXT: vldmia r0!, {s0}
+; CHECK-NEXT: vldmia r1!, {s2}
; CHECK-NEXT: vldr s4, [r2]
; CHECK-NEXT: vfma.f32 s4, s2, s0
-; CHECK-NEXT: vstr s4, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vstmia r2!, {s4}
; CHECK-NEXT: le lr, .LBB2_7
; CHECK-NEXT: .LBB2_8: @ %for.cond.cleanup
; CHECK-NEXT: pop {r4, r5, r6, pc}
diff --git a/llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll b/llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll
index 070d9b744836..1b6cdfc517be 100644
--- a/llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-postinc-lsr.ll
@@ -44,14 +44,11 @@ define void @fma(float* noalias nocapture readonly %A, float* noalias nocapture
; CHECK-NEXT: add.w r2, r2, r12, lsl #2
; CHECK-NEXT: .LBB0_7: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s0, [r0]
-; CHECK-NEXT: adds r0, #4
-; CHECK-NEXT: vldr s2, [r1]
-; CHECK-NEXT: adds r1, #4
+; CHECK-NEXT: vldmia r0!, {s0}
+; CHECK-NEXT: vldmia r1!, {s2}
; CHECK-NEXT: vldr s4, [r2]
; CHECK-NEXT: vfma.f32 s4, s2, s0
-; CHECK-NEXT: vstr s4, [r2]
-; CHECK-NEXT: adds r2, #4
+; CHECK-NEXT: vstmia r2!, {s4}
; CHECK-NEXT: le lr, .LBB0_7
; CHECK-NEXT: .LBB0_8: @ %for.cond.cleanup
; CHECK-NEXT: pop {r4, r5, r6, pc}
diff --git a/llvm/test/CodeGen/Thumb2/mve-satmul-loops.ll b/llvm/test/CodeGen/Thumb2/mve-satmul-loops.ll
index 93a1535a42fe..f69eeb773a9f 100644
--- a/llvm/test/CodeGen/Thumb2/mve-satmul-loops.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-satmul-loops.ll
@@ -38,12 +38,10 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: vmvn.i32 q1, #0x80000000
; CHECK-NEXT: .LBB0_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: ldrd r5, r4, [r0]
+; CHECK-NEXT: ldrd r5, r4, [r0], #8
; CHECK-NEXT: mov.w r3, #-1
-; CHECK-NEXT: ldrd r8, r7, [r1]
-; CHECK-NEXT: adds r0, #8
+; CHECK-NEXT: ldrd r8, r7, [r1], #8
; CHECK-NEXT: smull r4, r7, r7, r4
-; CHECK-NEXT: adds r1, #8
; CHECK-NEXT: asrl r4, r7, #31
; CHECK-NEXT: smull r6, r5, r8, r5
; CHECK-NEXT: rsbs.w r9, r4, #-2147483648
@@ -95,8 +93,7 @@ define arm_aapcs_vfpcc void @ssatmul_s_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: vorr q2, q2, q4
; CHECK-NEXT: vmov r3, s10
; CHECK-NEXT: vmov r4, s8
-; CHECK-NEXT: strd r4, r3, [r2]
-; CHECK-NEXT: adds r2, #8
+; CHECK-NEXT: strd r4, r3, [r2], #8
; CHECK-NEXT: le lr, .LBB0_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: ldrd r7, r3, [sp] @ 8-byte Folded Reload
@@ -744,10 +741,8 @@ define arm_aapcs_vfpcc void @usatmul_2_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: add.w r12, r0, r5, lsl #2
; CHECK-NEXT: .LBB3_4: @ %vector.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: ldrd r4, r7, [r0]
-; CHECK-NEXT: adds r0, #8
-; CHECK-NEXT: ldrd r5, r10, [r1]
-; CHECK-NEXT: adds r1, #8
+; CHECK-NEXT: ldrd r4, r7, [r0], #8
+; CHECK-NEXT: ldrd r5, r10, [r1], #8
; CHECK-NEXT: umull r4, r5, r5, r4
; CHECK-NEXT: lsrl r4, r5, #31
; CHECK-NEXT: subs.w r6, r4, #-1
@@ -773,8 +768,7 @@ define arm_aapcs_vfpcc void @usatmul_2_q31(i32* nocapture readonly %pSrcA, i32*
; CHECK-NEXT: vorn q0, q1, q0
; CHECK-NEXT: vmov r4, s2
; CHECK-NEXT: vmov r5, s0
-; CHECK-NEXT: strd r5, r4, [r2]
-; CHECK-NEXT: adds r2, #8
+; CHECK-NEXT: strd r5, r4, [r2], #8
; CHECK-NEXT: le lr, .LBB3_4
; CHECK-NEXT: @ %bb.5: @ %middle.block
; CHECK-NEXT: ldr r7, [sp] @ 4-byte Reload
diff --git a/llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll b/llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll
index 803f20571672..4393e4646bab 100644
--- a/llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-vecreduce-loops.ll
@@ -521,8 +521,7 @@ define float @fadd_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: add.w r0, r0, r2, lsl #2
; CHECK-NEXT: .LBB5_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s2, [r0]
-; CHECK-NEXT: adds r0, #4
+; CHECK-NEXT: vldmia r0!, {s2}
; CHECK-NEXT: vadd.f32 s0, s2, s0
; CHECK-NEXT: le lr, .LBB5_8
; CHECK-NEXT: .LBB5_9: @ %for.cond.cleanup
@@ -620,8 +619,7 @@ define float @fmul_f32(float* nocapture readonly %x, i32 %n) {
; CHECK-NEXT: add.w r0, r0, r2, lsl #2
; CHECK-NEXT: .LBB6_8: @ %for.body
; CHECK-NEXT: @ =>This Inner Loop Header: Depth=1
-; CHECK-NEXT: vldr s2, [r0]
-; CHECK-NEXT: adds r0, #4
+; CHECK-NEXT: vldmia r0!, {s2}
; CHECK-NEXT: vmul.f32 s0, s2, s0
; CHECK-NEXT: le lr, .LBB6_8
; CHECK-NEXT: .LBB6_9: @ %for.cond.cleanup
diff --git a/llvm/test/CodeGen/Thumb2/mve-vldshuffle.ll b/llvm/test/CodeGen/Thumb2/mve-vldshuffle.ll
index 80e65f1ee855..d26757fc99e8 100644
--- a/llvm/test/CodeGen/Thumb2/mve-vldshuffle.ll
+++ b/llvm/test/CodeGen/Thumb2/mve-vldshuffle.ll
@@ -176,8 +176,7 @@ define void @arm_cmplx_mag_squared_f32(float* nocapture readonly %pSrc, float* n
; CHECK-NEXT: adds r3, #8
; CHECK-NEXT: vmul.f32 s0, s0, s0
; CHECK-NEXT: vfma.f32 s0, s2, s2
-; CHECK-NEXT: vstr s0, [r12]
-; CHECK-NEXT: add.w r12, r12, #4
+; CHECK-NEXT: vstmia r12!, {s0}
; CHECK-NEXT: le lr, .LBB1_7
; CHECK-NEXT: .LBB1_8: @ %while.end
; CHECK-NEXT: pop {r4, r5, r7, pc}
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gcc_bootstrap/master-arm-bootstrap_debug - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gcc_bootstrap/master-arm-bootstrap_debug. So far, this commit has regressed CI configurations:
- tcwg_gcc_bootstrap/master-arm-bootstrap_debug
Culprit:
<cut>
commit d881460deb1f0bdfc3e8fa2d391a03a9763cbff4
Author: Harald Anlauf <anlauf(a)gmx.de>
Date: Thu Aug 19 21:00:45 2021 +0200
Fortran - simplify length of substring with constant bounds
gcc/fortran/ChangeLog:
PR fortran/100950
* simplify.c (substring_has_constant_len): New.
(gfc_simplify_len): Handle case of substrings with constant
bounds.
gcc/testsuite/ChangeLog:
PR fortran/100950
* gfortran.dg/pr100950.f90: New test.
</cut>
Results regressed to (for first_bad == d881460deb1f0bdfc3e8fa2d391a03a9763cbff4)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# First few build errors in logs:
# 00:12:48 make[3]: [armv8l-unknown-linux-gnueabihf/bits/largefile-config.h] Error 1 (ignored)
# 00:21:17 /home/tcwg-buildslave/workspace/tcwg_gnu_15/abe/snapshots/gcc.git~master/gcc/fortran/simplify.c:4557:22: error: unknown conversion type character ‘l’ in format [-Werror=format=]
# 00:21:17 /home/tcwg-buildslave/workspace/tcwg_gnu_15/abe/snapshots/gcc.git~master/gcc/fortran/simplify.c:4557:22: error: format ‘%L’ expects argument of type ‘locus*’, but argument 2 has type ‘long long int’ [-Werror=format=]
# 00:21:17 /home/tcwg-buildslave/workspace/tcwg_gnu_15/abe/snapshots/gcc.git~master/gcc/fortran/simplify.c:4557:22: error: too many arguments for format [-Werror=format-extra-args]
# 00:21:17 /home/tcwg-buildslave/workspace/tcwg_gnu_15/abe/snapshots/gcc.git~master/gcc/fortran/simplify.c:4570:22: error: unknown conversion type character ‘l’ in format [-Werror=format=]
# 00:21:17 /home/tcwg-buildslave/workspace/tcwg_gnu_15/abe/snapshots/gcc.git~master/gcc/fortran/simplify.c:4570:22: error: format ‘%L’ expects argument of type ‘locus*’, but argument 2 has type ‘long long int’ [-Werror=format=]
# 00:21:17 /home/tcwg-buildslave/workspace/tcwg_gnu_15/abe/snapshots/gcc.git~master/gcc/fortran/simplify.c:4570:22: error: too many arguments for format [-Werror=format-extra-args]
# 00:21:38 make[3]: *** [fortran/simplify.o] Error 1
# 00:28:40 make[2]: *** [all-stage2-gcc] Error 2
# 00:28:40 make[1]: *** [stage2-bubble] Error 2
from (for last_good == 77bf9f83b8e388de8bedb259991f588a7b8a7f57)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe bootstrap_debug:
2
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-d881460deb1f0bdfc3e8fa2d391a03a9763cbff4
cd investigate-gcc-d881460deb1f0bdfc3e8fa2d391a03a9763cbff4
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach d881460deb1f0bdfc3e8fa2d391a03a9763cbff4
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 77bf9f83b8e388de8bedb259991f588a7b8a7f57
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de…
Build log: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap_de…
Full commit (up to 1000 lines):
<cut>
commit d881460deb1f0bdfc3e8fa2d391a03a9763cbff4
Author: Harald Anlauf <anlauf(a)gmx.de>
Date: Thu Aug 19 21:00:45 2021 +0200
Fortran - simplify length of substring with constant bounds
gcc/fortran/ChangeLog:
PR fortran/100950
* simplify.c (substring_has_constant_len): New.
(gfc_simplify_len): Handle case of substrings with constant
bounds.
gcc/testsuite/ChangeLog:
PR fortran/100950
* gfortran.dg/pr100950.f90: New test.
---
gcc/fortran/simplify.c | 75 +++++++++++++++++++++++++++++++++-
gcc/testsuite/gfortran.dg/pr100950.f90 | 53 ++++++++++++++++++++++++
2 files changed, 127 insertions(+), 1 deletion(-)
diff --git a/gcc/fortran/simplify.c b/gcc/fortran/simplify.c
index c27b47aa98f..492867e12cb 100644
--- a/gcc/fortran/simplify.c
+++ b/gcc/fortran/simplify.c
@@ -4512,6 +4512,78 @@ gfc_simplify_leadz (gfc_expr *e)
}
+/* Check for constant length of a substring. */
+
+static bool
+substring_has_constant_len (gfc_expr *e)
+{
+ gfc_ref *ref;
+ HOST_WIDE_INT istart, iend, length;
+ bool equal_length = false;
+
+ if (e->ts.type != BT_CHARACTER)
+ return false;
+
+ for (ref = e->ref; ref; ref = ref->next)
+ if (ref->type != REF_COMPONENT && ref->type != REF_ARRAY)
+ break;
+
+ if (!ref
+ || ref->type != REF_SUBSTRING
+ || !ref->u.ss.start
+ || ref->u.ss.start->expr_type != EXPR_CONSTANT
+ || !ref->u.ss.end
+ || ref->u.ss.end->expr_type != EXPR_CONSTANT
+ || !ref->u.ss.length)
+ return false;
+
+ /* For non-deferred strings the given length shall be constant. */
+ if (!e->ts.deferred
+ && (!ref->u.ss.length->length
+ || ref->u.ss.length->length->expr_type != EXPR_CONSTANT))
+ return false;
+
+ /* Basic checks on substring starting and ending indices. */
+ if (!gfc_resolve_substring (ref, &equal_length))
+ return false;
+
+ istart = gfc_mpz_get_hwi (ref->u.ss.start->value.integer);
+ iend = gfc_mpz_get_hwi (ref->u.ss.end->value.integer);
+
+ if (istart <= iend)
+ {
+ if (istart < 1)
+ {
+ gfc_error ("Substring start index (" HOST_WIDE_INT_PRINT_DEC
+ ") at %L below 1",
+ istart, &ref->u.ss.start->where);
+ return false;
+ }
+
+ /* For deferred strings use end index as proxy for length. */
+ if (e->ts.deferred)
+ length = iend;
+ else
+ length = gfc_mpz_get_hwi (ref->u.ss.length->length->value.integer);
+ if (iend > length)
+ {
+ gfc_error ("Substring end index (" HOST_WIDE_INT_PRINT_DEC
+ ") at %L exceeds string length",
+ iend, &ref->u.ss.end->where);
+ return false;
+ }
+ length = iend - istart + 1;
+ }
+ else
+ length = 0;
+
+ /* Fix substring length. */
+ e->value.character.length = length;
+
+ return true;
+}
+
+
gfc_expr *
gfc_simplify_len (gfc_expr *e, gfc_expr *kind)
{
@@ -4521,7 +4593,8 @@ gfc_simplify_len (gfc_expr *e, gfc_expr *kind)
if (k == -1)
return &gfc_bad_expr;
- if (e->expr_type == EXPR_CONSTANT)
+ if (e->expr_type == EXPR_CONSTANT
+ || substring_has_constant_len (e))
{
result = gfc_get_constant_expr (BT_INTEGER, k, &e->where);
mpz_set_si (result->value.integer, e->value.character.length);
diff --git a/gcc/testsuite/gfortran.dg/pr100950.f90 b/gcc/testsuite/gfortran.dg/pr100950.f90
new file mode 100644
index 00000000000..cb9d126bc18
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/pr100950.f90
@@ -0,0 +1,53 @@
+! { dg-do run }
+! { dg-additional-options "-fdump-tree-original" }
+! PR fortran/100950 - ICE in output_constructor_regular_field, at varasm.c:5514
+
+program p
+ character(8), parameter :: u = "123"
+ character(8) :: x = "", s
+ character(2) :: w(2) = [character(len(x(3:4))) :: 'a','b' ]
+ character(*), parameter :: y(*) = [character(len(u(3:4))) :: 'a','b' ]
+ character(*), parameter :: z(*) = [character(len(x(3:4))) :: 'a','b' ]
+ character(*), parameter :: t(*) = [character(len(x( :2))) :: 'a','b' ]
+ character(*), parameter :: v(*) = [character(len(x(7: ))) :: 'a','b' ]
+ type t_
+ character(len=5) :: s
+ character(len=8) :: t(4)
+ character(len=8), pointer :: u(:)
+ character(len=:), allocatable :: str
+ character(len=:), allocatable :: str2(:)
+ end type t_
+ type(t_) :: q, r(1)
+ integer, parameter :: lq = len (q%s(3:4)), lr = len (r%s(3:4))
+ integer, parameter :: l1 = len (q %t(1)(3:4))
+ integer, parameter :: l2 = len (q %t(:)(3:4))
+ integer, parameter :: l3 = len (q %str (3:4))
+ integer, parameter :: l4 = len (r(:)%t(1)(3:4))
+ integer, parameter :: l5 = len (r(1)%t(:)(3:4))
+ integer, parameter :: l6 = len (r(1)%str (3:4))
+ integer, parameter :: l7 = len (r(1)%str2(1)(3:4))
+ integer, parameter :: l8 = len (r(1)%str2(:)(3:4))
+
+ if (len (y) /= 2) stop 1
+ if (len (z) /= 2) stop 2
+ if (any (w /= y)) stop 3
+ if (len ([character(len(u(3:4))) :: 'a','b' ]) /= 2) stop 4
+ if (len ([character(len(x(3:4))) :: 'a','b' ]) /= 2) stop 5
+ if (any ([character(len(x(3:4))) :: 'a','b' ] /= y)) stop 6
+ write(s,*) [character(len(x(3:4))) :: 'a','b' ]
+ if (s /= " a b ") stop 7
+ if (len (t) /= 2) stop 8
+ if (len (v) /= 2) stop 9
+ if (lq /= 2 .or. lr /= 2) stop 10
+ if (l1 /= 2 .or. l2 /= 2 .or. l4 /= 2 .or. l5 /= 2) stop 11
+ if (l3 /= 2 .or. l6 /= 2 .or. l7 /= 2 .or. l8 /= 2) stop 12
+
+ block
+ integer, parameter :: l9 = len (r(1)%u(:)(3:4))
+ if (l9 /= 2) stop 13
+ end block
+end
+
+! { dg-final { scan-tree-dump-times "_gfortran_stop_numeric" 2 "original" } }
+! { dg-final { scan-tree-dump "_gfortran_stop_numeric \\(3, 0\\);" "original" } }
+! { dg-final { scan-tree-dump "_gfortran_stop_numeric \\(7, 0\\);" "original" } }
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Oz - Build # 7 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz
Culprit:
<cut>
commit 9ecccaf9771d3f3bb68ef69d34965b1aad874bd6
Merge: 1e28eed17697 12aca1ce9ee3
Author: Rob Clark <robdclark(a)chromium.org>
Date: Wed Apr 7 11:04:47 2021 -0700
Merge tag 'drm-msm-fixes-2021-04-02' into msm-next
Pull in fixes from previous cycle
</cut>
Results regressed to (for first_bad == 9ecccaf9771d3f3bb68ef69d34965b1aad874bd6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-9ecccaf9771d3f3bb68ef69d34965b1aad874bd6/results_id:
1
# 482.sphinx3,[.] OUTLINED_FUNCTION_4 regressed by 175
from (for last_good == 12aca1ce9ee33af3751aec5e55a5900747cbdd4b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-12aca1ce9ee33af3751aec5e55a5900747cbdd4b/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/3996
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/3987
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-9ecccaf9771d3f3bb68ef69d34965b1aad874bd6
cd investigate-linux-9ecccaf9771d3f3bb68ef69d34965b1aad874bd6
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 9ecccaf9771d3f3bb68ef69d34965b1aad874bd6
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 12aca1ce9ee33af3751aec5e55a5900747cbdd4b
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 9ecccaf9771d3f3bb68ef69d34965b1aad874bd6
Merge: 1e28eed17697 12aca1ce9ee3
Author: Rob Clark <robdclark(a)chromium.org>
Date: Wed Apr 7 11:04:47 2021 -0700
Merge tag 'drm-msm-fixes-2021-04-02' into msm-next
Pull in fixes from previous cycle
drivers/gpu/drm/msm/adreno/a5xx_gpu.c | 4 +-
drivers/gpu/drm/msm/adreno/a5xx_power.c | 2 +-
drivers/gpu/drm/msm/adreno/a6xx_gmu.c | 2 +-
drivers/gpu/drm/msm/adreno/a6xx_gpu.c | 108 ++++++++++++++++++++---------
drivers/gpu/drm/msm/disp/dpu1/dpu_hw_ctl.c | 4 +-
drivers/gpu/drm/msm/disp/dpu1/dpu_kms.c | 12 ++--
drivers/gpu/drm/msm/dp/dp_aux.c | 7 ++
drivers/gpu/drm/msm/dsi/pll/dsi_pll.c | 2 +-
drivers/gpu/drm/msm/dsi/pll/dsi_pll.h | 6 +-
drivers/gpu/drm/msm/dsi/pll/dsi_pll_7nm.c | 11 +--
drivers/gpu/drm/msm/msm_atomic.c | 7 +-
drivers/gpu/drm/msm/msm_drv.c | 13 ++++
drivers/gpu/drm/msm/msm_fence.c | 2 +-
drivers/gpu/drm/msm/msm_kms.h | 8 +--
14 files changed, 128 insertions(+), 60 deletions(-)
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3_LTO - Build # 6 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit cedfa38fc46d7531c44ea230b767d8286767f350
Author: Jin Lin <jinl(a)uber.com>
Date: Fri Apr 23 22:37:08 2021 -0700
Preserve the lexical order for global variables during llvm-link merge
The order of global variables is generated in the order of recursively materializing variables if the global variable has the attribute of hasLocalLinkage or hasLinkOnceLinkage during the module merging. In practice, it is often the exact reverse of source order. This new order may cause performance regression.
The change is to preserve the original lexical order for global variables.
Reviewed By: jdoerfert, dexonsmith
Differential Revision: https://reviews.llvm.org/D94202
</cut>
Results regressed to (for first_bad == cedfa38fc46d7531c44ea230b767d8286767f350)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-cedfa38fc46d7531c44ea230b767d8286767f350/results_id:
1
# 458.sjeng,sjeng_base.default regressed by 103
from (for last_good == 9579af2bd7f39b2118039b66b1a762cf05e7b102)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-9579af2bd7f39b2118039b66b1a762cf05e7b102/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/3990
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/3980
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-cedfa38fc46d7531c44ea230b767d8286767f350
cd investigate-llvm-cedfa38fc46d7531c44ea230b767d8286767f350
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach cedfa38fc46d7531c44ea230b767d8286767f350
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 9579af2bd7f39b2118039b66b1a762cf05e7b102
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit cedfa38fc46d7531c44ea230b767d8286767f350
Author: Jin Lin <jinl(a)uber.com>
Date: Fri Apr 23 22:37:08 2021 -0700
Preserve the lexical order for global variables during llvm-link merge
The order of global variables is generated in the order of recursively materializing variables if the global variable has the attribute of hasLocalLinkage or hasLinkOnceLinkage during the module merging. In practice, it is often the exact reverse of source order. This new order may cause performance regression.
The change is to preserve the original lexical order for global variables.
Reviewed By: jdoerfert, dexonsmith
Differential Revision: https://reviews.llvm.org/D94202
---
llvm/lib/Linker/IRMover.cpp | 14 ++++++++++++++
llvm/test/Linker/Inputs/globalorder-2.ll | 14 ++++++++++++++
llvm/test/Linker/comdat.ll | 2 +-
llvm/test/Linker/comdat14.ll | 2 +-
llvm/test/Linker/ctors.ll | 2 +-
llvm/test/Linker/ctors2.ll | 2 +-
llvm/test/Linker/ctors3.ll | 2 +-
llvm/test/Linker/globalorder.ll | 27 +++++++++++++++++++++++++++
llvm/test/Linker/link-flags.ll | 2 +-
llvm/test/Linker/metadata-attach.ll | 18 +++++++++---------
llvm/test/Linker/testlink.ll | 2 +-
llvm/test/ThinLTO/X86/import-constant.ll | 8 ++++----
llvm/test/ThinLTO/X86/index-const-prop.ll | 6 +++---
llvm/test/ThinLTO/X86/index-const-prop2.ll | 6 +++---
llvm/test/ThinLTO/X86/writeonly.ll | 8 ++++----
llvm/test/ThinLTO/X86/writeonly2.ll | 4 ++--
16 files changed, 87 insertions(+), 32 deletions(-)
diff --git a/llvm/lib/Linker/IRMover.cpp b/llvm/lib/Linker/IRMover.cpp
index 1433d074595b..9489f9655469 100644
--- a/llvm/lib/Linker/IRMover.cpp
+++ b/llvm/lib/Linker/IRMover.cpp
@@ -1509,6 +1509,20 @@ Error IRLinker::run() {
});
}
+ // Reorder the globals just added to the destination module to match their
+ // original order in the source module.
+ Module::GlobalListType &Globals = DstM.getGlobalList();
+ for (GlobalVariable &GV : SrcM->globals()) {
+ if (GV.hasAppendingLinkage())
+ continue;
+ Value *NewValue = Mapper.mapValue(GV);
+ if (NewValue) {
+ auto *NewGV = dyn_cast<GlobalVariable>(NewValue->stripPointerCasts());
+ if (NewGV)
+ Globals.splice(Globals.end(), Globals, NewGV->getIterator());
+ }
+ }
+
// Merge the module flags into the DstM module.
return linkModuleFlagsMetadata();
}
diff --git a/llvm/test/Linker/Inputs/globalorder-2.ll b/llvm/test/Linker/Inputs/globalorder-2.ll
new file mode 100644
index 000000000000..a984ebf78a6a
--- /dev/null
+++ b/llvm/test/Linker/Inputs/globalorder-2.ll
@@ -0,0 +1,14 @@
+@var5 = internal global i32 0, align 4
+@var6 = internal global i32 0, align 4
+@var7 = global i32* @var5, align 4
+@var8 = global i32* @var6, align 4
+
+define i32 @foo2() {
+entry:
+ %0 = load i32*, i32** @var7, align 4
+ %1 = load i32, i32* %0, align 4
+ %2 = load i32*, i32** @var8, align 4
+ %3 = load i32, i32* %2, align 4
+ %add = add nsw i32 %3, %1
+ ret i32 %add
+}
diff --git a/llvm/test/Linker/comdat.ll b/llvm/test/Linker/comdat.ll
index 2a2ec3bbb6b2..e3bb1ea39260 100644
--- a/llvm/test/Linker/comdat.ll
+++ b/llvm/test/Linker/comdat.ll
@@ -23,9 +23,9 @@ $any = comdat any
; CHECK: $foo = comdat largest
; CHECK: $any = comdat any
+; CHECK: @foo = global i64 43, comdat{{$}}
; CHECK: @qux = global i64 12, comdat{{$}}
; CHECK: @any = global i64 6, comdat{{$}}
-; CHECK: @foo = global i64 43, comdat{{$}}
; CHECK-NOT: @in_unselected_group = global i32 13, comdat $qux
; CHECK: define i32 @baz() comdat($qux)
diff --git a/llvm/test/Linker/comdat14.ll b/llvm/test/Linker/comdat14.ll
index 9c6eb7c4cc1d..1a1ba47aa017 100644
--- a/llvm/test/Linker/comdat14.ll
+++ b/llvm/test/Linker/comdat14.ll
@@ -5,5 +5,5 @@ $c = comdat any
@v = global i32 0, comdat ($c)
; CHECK: @v = global i32 0, comdat($c)
-; CHECK: @v2 = external dllexport global i32
; CHECK: @v3 = external global i32
+; CHECK: @v2 = external dllexport global i32
diff --git a/llvm/test/Linker/ctors.ll b/llvm/test/Linker/ctors.ll
index 37dba23d4c91..f68ca3e54762 100644
--- a/llvm/test/Linker/ctors.ll
+++ b/llvm/test/Linker/ctors.ll
@@ -6,12 +6,12 @@
; Test the bitcode writer too. It used to crash.
; RUN: llvm-link %s %p/Inputs/ctors.ll -o %t.bc
+; ALL: @llvm.global_ctors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 65535, void ()* @f, i8* @v }]
@v = weak global i8 0
; CHECK1: @v = weak global i8 0
; CHECK2: @v = weak global i8 1
@llvm.global_ctors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 65535, void ()* @f, i8* @v }]
-; ALL: @llvm.global_ctors = appending global [1 x { i32, void ()*, i8* }] [{ i32, void ()*, i8* } { i32 65535, void ()* @f, i8* @v }]
define weak void @f() {
ret void
diff --git a/llvm/test/Linker/ctors2.ll b/llvm/test/Linker/ctors2.ll
index 9b7a70eb7cd1..c02973faf4d0 100644
--- a/llvm/test/Linker/ctors2.ll
+++ b/llvm/test/Linker/ctors2.ll
@@ -3,5 +3,5 @@
$foo = comdat any
@foo = global i8 0, comdat
-; CHECK: @foo = global i8 0, comdat
; CHECK: @llvm.global_ctors = appending global [0 x { i32, void ()*, i8* }] zeroinitializer
+; CHECK: @foo = global i8 0, comdat
diff --git a/llvm/test/Linker/ctors3.ll b/llvm/test/Linker/ctors3.ll
index e62b92dca0b4..d522df58e891 100644
--- a/llvm/test/Linker/ctors3.ll
+++ b/llvm/test/Linker/ctors3.ll
@@ -4,5 +4,5 @@ $foo = comdat any
%t = type { i8 }
@foo = global %t zeroinitializer, comdat
-; CHECK: @foo = global %t zeroinitializer, comdat
; CHECK: @llvm.global_ctors = appending global [0 x { i32, void ()*, i8* }] zeroinitializer
+; CHECK: @foo = global %t zeroinitializer, comdat
diff --git a/llvm/test/Linker/globalorder.ll b/llvm/test/Linker/globalorder.ll
new file mode 100644
index 000000000000..caab97a6ba86
--- /dev/null
+++ b/llvm/test/Linker/globalorder.ll
@@ -0,0 +1,27 @@
+; Test the order of global variables during llvm-link
+
+; RUN: llvm-link %s %S/Inputs/globalorder-2.ll -o %t.bc
+; RUN: llvm-dis -o - %t.bc | FileCheck %s
+
+@var1 = internal global i32 0, align 4
+@var2 = internal global i32 0, align 4
+@var3 = global i32* @var1, align 4
+@var4 = global i32* @var2, align 4
+
+define i32 @foo() {
+entry:
+ %0 = load i32*, i32** @var3, align 4
+ %1 = load i32, i32* %0, align 4
+ %2 = load i32*, i32** @var4, align 4
+ %3 = load i32, i32* %2, align 4
+ %add = add nsw i32 %3, %1
+ ret i32 %add
+}
+; CHECK: @var1 =
+; CHECK-NEXT: @var2 =
+; CHECK-NEXT: @var3 =
+; CHECK-NEXT: @var4 =
+; CHECK-NEXT: @var5 =
+; CHECK-NEXT: @var6 =
+; CHECK-NEXT: @var7 =
+; CHECK-NEXT: @var8 =
diff --git a/llvm/test/Linker/link-flags.ll b/llvm/test/Linker/link-flags.ll
index 1a57e8aa4d28..4e8eaa62dd78 100644
--- a/llvm/test/Linker/link-flags.ll
+++ b/llvm/test/Linker/link-flags.ll
@@ -9,8 +9,8 @@ CI-LABEL: @X = internal global i32 5
CU-LABEL:@U = global i32 6
CI-LABEL:@U = internal global i32 6
CN-NOT:@U
-DI-LABEL: @Y = global i8 42
DI-LABEL: @llvm.used = appending global [2 x i8*] [i8* @Y, i8* bitcast (i64 ()* @foo to i8*)], section "llvm.metadata"
+DI-LABEL: @Y = global i8 42
B-LABEL: define void @bar() {
diff --git a/llvm/test/Linker/metadata-attach.ll b/llvm/test/Linker/metadata-attach.ll
index 368c72a9c5f8..6b6c8dd9ed35 100644
--- a/llvm/test/Linker/metadata-attach.ll
+++ b/llvm/test/Linker/metadata-attach.ll
@@ -6,17 +6,17 @@
; CHECK-LINKED1: @g1 = global i32 0, !attach !0{{$}}
@g1 = global i32 0, !attach !0
-; CHECK: @g3 = weak global i32 1, !attach !0{{$}}
; CHECK: @g2 = external global i32, !attach !0{{$}}
+; CHECK: @g3 = weak global i32 1, !attach !0{{$}}
; CHECK-LINKED1: @g2 = global i32 1, !attach !1{{$}}
@g2 = external global i32, !attach !0
; CHECK-LINKED1: @g3 = global i32 2, !attach !1{{$}}
@g3 = weak global i32 1, !attach !0
-; CHECK-LINKED2: @g2 = global i32 1, !attach !0{{$}}
-; CHECK-LINKED2: @g3 = global i32 2, !attach !0{{$}}
-; CHECK-LINKED2: @g1 = global i32 0, !attach !1{{$}}
+; CHECK-LINKED2: @g1 = global i32 0, !attach !0{{$}}
+; CHECK-LINKED2: @g2 = global i32 1, !attach !1{{$}}
+; CHECK-LINKED2: @g3 = global i32 2, !attach !1{{$}}
; CHECK: define void @f1() !attach !0 {
; CHECK-LINKED1: define void @f1() !attach !0 {
@@ -36,14 +36,14 @@ define weak void @f3() !attach !0 {
ret void
}
-; CHECK-LINKED2: define void @f2() !attach !0 {
-; CHECK-LINKED2: define void @f3() !attach !0 {
-; CHECK-LINKED2: define void @f1() !attach !1 {
+; CHECK-LINKED2: define void @f2() !attach !1 {
+; CHECK-LINKED2: define void @f3() !attach !1 {
+; CHECK-LINKED2: define void @f1() !attach !0 {
; CHECK-LINKED1: !0 = !{i32 0}
; CHECK-LINKED1: !1 = !{i32 1}
-; CHECK-LINKED2: !0 = !{i32 1}
-; CHECK-LINKED2: !1 = !{i32 0}
+; CHECK-LINKED2: !0 = !{i32 0}
+; CHECK-LINKED2: !1 = !{i32 1}
!0 = !{i32 0}
diff --git a/llvm/test/Linker/testlink.ll b/llvm/test/Linker/testlink.ll
index 6a316a3bf846..69870b50413c 100644
--- a/llvm/test/Linker/testlink.ll
+++ b/llvm/test/Linker/testlink.ll
@@ -1,7 +1,7 @@
; RUN: llvm-link %s %S/Inputs/testlink.ll -S | FileCheck %s
-; CHECK: %Ty2 = type { %Ty1* }
; CHECK: %Ty1 = type { %Ty2* }
+; CHECK: %Ty2 = type { %Ty1* }
%Ty1 = type opaque
%Ty2 = type { %Ty1* }
diff --git a/llvm/test/ThinLTO/X86/import-constant.ll b/llvm/test/ThinLTO/X86/import-constant.ll
index 1bc2a1c2f7a4..e5254948f591 100644
--- a/llvm/test/ThinLTO/X86/import-constant.ll
+++ b/llvm/test/ThinLTO/X86/import-constant.ll
@@ -28,9 +28,9 @@
; PROMOTE: @_ZL3Obj.llvm.{{.*}} = hidden constant %struct.S { i32 4, i32 8, i32* @val }
; @outer is a write-only variable, so it's been converted to zeroinitializer.
-; IMPORT: @outer = internal local_unnamed_addr global %struct.Q zeroinitializer
+; IMPORT: @val = available_externally global i32 42
; IMPORT-NEXT: @_ZL3Obj.llvm.{{.*}} = available_externally hidden constant %struct.S { i32 4, i32 8, i32* @val }
-; IMPORT-NEXT: @val = available_externally global i32 42
+; IMPORT-NEXT: @outer = internal local_unnamed_addr global %struct.Q zeroinitializer
; OPT: @outer = internal unnamed_addr global %struct.Q zeroinitializer
@@ -39,8 +39,8 @@
; OPT-NEXT: store %struct.S* null, %struct.S** getelementptr inbounds (%struct.Q, %struct.Q* @outer, i64 0, i32 0)
; OPT-NEXT: ret i32 12
-; NOREFS: @outer = internal local_unnamed_addr global %struct.Q zeroinitializer
-; NOREFS-NEXT: @_ZL3Obj.llvm.{{.*}} = external hidden constant %struct.S
+; NOREFS: @_ZL3Obj.llvm.{{.*}} = external hidden constant %struct.S
+; NOREFS-NEXT: @outer = internal local_unnamed_addr global %struct.Q zeroinitializer
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-unknown-linux-gnu"
diff --git a/llvm/test/ThinLTO/X86/index-const-prop.ll b/llvm/test/ThinLTO/X86/index-const-prop.ll
index 9718aec8a944..b8028d65fa58 100644
--- a/llvm/test/ThinLTO/X86/index-const-prop.ll
+++ b/llvm/test/ThinLTO/X86/index-const-prop.ll
@@ -19,14 +19,14 @@
; RUN: llvm-lto -thinlto-action=import -exported-symbol main -exported-symbol gBar %t1.bc -thinlto-index=%t3.index.bc -o %t1.imported2.bc
; RUN: llvm-dis %t1.imported2.bc -o - | FileCheck %s --check-prefix=IMPORT2
-; IMPORT: @gFoo.llvm.0 = internal unnamed_addr global i32 1, align 4, !dbg !0
-; IMPORT-NEXT: @gBar = internal local_unnamed_addr global i32 2, align 4, !dbg !5
+; IMPORT: @gBar = internal local_unnamed_addr global i32 2, align 4, !dbg !0
+; IMPORT-NEXT: @gFoo.llvm.0 = internal unnamed_addr global i32 1, align 4, !dbg !5
; IMPORT: !DICompileUnit({{.*}})
; OPTIMIZE: define i32 @main
; OPTIMIZE-NEXT: ret i32 3
-; IMPORT2: @gBar = available_externally local_unnamed_addr global i32 2, align 4, !dbg !5
+; IMPORT2: @gBar = available_externally local_unnamed_addr global i32 2, align 4, !dbg !0
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/llvm/test/ThinLTO/X86/index-const-prop2.ll b/llvm/test/ThinLTO/X86/index-const-prop2.ll
index 5bf40fc688d5..68fe058a8637 100644
--- a/llvm/test/ThinLTO/X86/index-const-prop2.ll
+++ b/llvm/test/ThinLTO/X86/index-const-prop2.ll
@@ -57,13 +57,13 @@
; with corresponsing stores
; RUN: llvm-dis %t5.2.5.precodegen.bc -o - | FileCheck %s --check-prefix=CODEGEN2-SRC
-; IMPORT: @gFoo.llvm.0 = internal unnamed_addr global i32 1, align 4
-; IMPORT-NEXT: @gBar = internal local_unnamed_addr global i32 2, align 4
+; IMPORT: @gBar = internal local_unnamed_addr global i32 2, align 4
+; IMPORT-NEXT: @gFoo.llvm.0 = internal unnamed_addr global i32 1, align 4
; IMPORT: !DICompileUnit({{.*}})
; Write only variables are imported with a zero initializer.
-; IMPORT-WRITEONLY: @gFoo.llvm.0 = internal unnamed_addr global i32 0
; IMPORT-WRITEONLY: @gBar = internal local_unnamed_addr global i32 0
+; IMPORT-WRITEONLY: @gFoo.llvm.0 = internal unnamed_addr global i32 0
; CODEGEN: i32 @main()
; CODEGEN-NEXT: ret i32 3
diff --git a/llvm/test/ThinLTO/X86/writeonly.ll b/llvm/test/ThinLTO/X86/writeonly.ll
index 7616f192fbfc..65c93a79afa9 100644
--- a/llvm/test/ThinLTO/X86/writeonly.ll
+++ b/llvm/test/ThinLTO/X86/writeonly.ll
@@ -11,8 +11,8 @@
; RUN: llvm-dis %t1.imported.bc -o - | FileCheck %s --check-prefix=IMPORT
; RUN: llvm-lto -thinlto-action=optimize %t1.imported.bc -o - | llvm-dis - -o - | FileCheck %s --check-prefix=OPTIMIZE
-; IMPORT: @gFoo.llvm.0 = internal unnamed_addr global i32 0, align 4, !dbg !0
-; IMPORT-NEXT: @gBar = internal local_unnamed_addr global i32 0, align 4, !dbg !5
+; IMPORT: @gBar = internal local_unnamed_addr global i32 0, align 4, !dbg !0
+; IMPORT-NEXT: @gFoo.llvm.0 = internal unnamed_addr global i32 0, align 4, !dbg !5
; IMPORT: !DICompileUnit({{.*}})
; STATS: 2 module-summary-index - Number of live global variables marked write only
@@ -29,8 +29,8 @@
; RUN: llvm-lto -propagate-attrs=false -thinlto-action=import -exported-symbol=main %t1.bc -thinlto-index=%t3.index.bc -o %t1.imported.bc -stats 2>&1 | FileCheck %s --check-prefix=STATS-NOPROP
; RUN: llvm-dis %t1.imported.bc -o - | FileCheck %s --check-prefix=IMPORT-NOPROP
; STATS-NOPROP-NOT: Number of live global variables marked write only
-; IMPORT-NOPROP: @gFoo.llvm.0 = available_externally
-; IMPORT-NOPROP-NEXT: @gBar = available_externally
+; IMPORT-NOPROP: @gBar = available_externally
+; IMPORT-NOPROP-NEXT: @gFoo.llvm.0 = available_externally
target datalayout = "e-m:e-p270:32:32-p271:32:32-p272:64:64-i64:64-f80:128-n8:16:32:64-S128"
target triple = "x86_64-pc-linux-gnu"
diff --git a/llvm/test/ThinLTO/X86/writeonly2.ll b/llvm/test/ThinLTO/X86/writeonly2.ll
index 2648727f0997..f31f9b35a253 100644
--- a/llvm/test/ThinLTO/X86/writeonly2.ll
+++ b/llvm/test/ThinLTO/X86/writeonly2.ll
@@ -19,8 +19,8 @@
; with corresponsing stores
; RUN: llvm-dis %t3.2.5.precodegen.bc -o - | FileCheck %s --check-prefix=CODEGEN-SRC
-; IMPORT: @gFoo.llvm.0 = internal unnamed_addr global i32 0, align 4
-; IMPORT-NEXT: @gBar = internal local_unnamed_addr global i32 0, align 4
+; IMPORT: @gBar = internal local_unnamed_addr global i32 0, align 4
+; IMPORT-NEXT: @gFoo.llvm.0 = internal unnamed_addr global i32 0, align 4
; IMPORT: !DICompileUnit({{.*}})
; CODEGEN-NOT: gFoo
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 28 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6
Author: Jan Hubicka <jh(a)suse.cz>
Date: Tue Nov 19 19:56:26 2019 +0100
Avoid redundant computations in edge_badness.
* ipa-inline.c (inlining_speedup): New function.
(edge_badness): Use it.
From-SVN: r278459
</cut>
Results regressed to (for first_bad == ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6/results_id:
1
# 447.dealII,[.] _ZNK12SparseMatrixIdE5vmultI6VectorIdES3_EEvRT regressed by 116
from (for last_good == 4aa5fd8aca1140adf0917dc53397efddc7fd4c11)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-4aa5fd8aca1140adf0917dc53397efddc7fd4c11/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3988
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3979
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6
cd investigate-gcc-ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 4aa5fd8aca1140adf0917dc53397efddc7fd4c11
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit ea8dd3b6cea2a4d4dab7e2997b88a170f8093ce6
Author: Jan Hubicka <jh(a)suse.cz>
Date: Tue Nov 19 19:56:26 2019 +0100
Avoid redundant computations in edge_badness.
* ipa-inline.c (inlining_speedup): New function.
(edge_badness): Use it.
From-SVN: r278459
---
gcc/ChangeLog | 5 +++++
gcc/ipa-inline.c | 37 ++++++++++++++++++++++++++++++-------
2 files changed, 35 insertions(+), 7 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 3516235f606..710f8dab674 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,8 @@
+2019-11-18 Jan Hubicka <jh(a)suse.cz>
+
+ * ipa-inline.c (inlining_speedup): New function.
+ (edge_badness): Use it.
+
2019-11-19 Zoran Jovanovic <zoran.jovanovic(a)mips.com>
Dragan Mladjenovic <dmladjenovic(a)wavecomp.com>
diff --git a/gcc/ipa-inline.c b/gcc/ipa-inline.c
index 1f77ba25ce0..becea8a3e8e 100644
--- a/gcc/ipa-inline.c
+++ b/gcc/ipa-inline.c
@@ -768,6 +768,33 @@ compute_inlined_call_time (struct cgraph_edge *edge,
return time;
}
+/* Determine time saved by inlininig EDGE of frequency FREQ
+ where callee's runtime w/o inlineing is UNINLINED_TYPE
+ and with inlined is INLINED_TYPE. */
+
+inline sreal
+inlining_speedup (struct cgraph_edge *edge,
+ sreal freq,
+ sreal uninlined_time,
+ sreal inlined_time)
+{
+ sreal speedup = uninlined_time - inlined_time;
+ /* Handling of call_time should match one in ipa-inline-fnsummary.c
+ (estimate_edge_size_and_time). */
+ sreal call_time = ipa_call_summaries->get (edge)->call_stmt_time;
+
+ if (freq > 0)
+ {
+ speedup = (speedup + call_time);
+ if (freq != 1)
+ speedup = speedup * freq;
+ }
+ else if (freq == 0)
+ speedup = speedup >> 11;
+ gcc_checking_assert (speedup >= 0);
+ return speedup;
+}
+
/* Return true if the speedup for inlining E is bigger than
PARAM_MAX_INLINE_MIN_SPEEDUP. */
@@ -1149,10 +1176,8 @@ edge_badness (struct cgraph_edge *edge, bool dump)
sreal numerator, denominator;
int overall_growth;
sreal freq = edge->sreal_frequency ();
- sreal inlined_time = compute_inlined_call_time (edge, edge_time, freq);
- numerator = (compute_uninlined_call_time (edge, unspec_edge_time, freq)
- - inlined_time);
+ numerator = inlining_speedup (edge, freq, unspec_edge_time, edge_time);
if (numerator <= 0)
numerator = ((sreal) 1 >> 8);
if (caller->count.ipa ().nonzero_p ())
@@ -1235,16 +1260,14 @@ edge_badness (struct cgraph_edge *edge, bool dump)
fprintf (dump_file,
" %f: guessed profile. frequency %f, count %" PRId64
" caller count %" PRId64
- " time w/o inlining %f, time with inlining %f"
+ " time saved %f"
" overall growth %i (current) %i (original)"
" %i (compensated)\n",
badness.to_double (),
freq.to_double (),
edge->count.ipa ().initialized_p () ? edge->count.ipa ().to_gcov_type () : -1,
caller->count.ipa ().initialized_p () ? caller->count.ipa ().to_gcov_type () : -1,
- compute_uninlined_call_time (edge,
- unspec_edge_time, freq).to_double (),
- inlined_time.to_double (),
+ inlining_speedup (edge, freq, unspec_edge_time, edge_time).to_double (),
estimate_growth (callee),
callee_info->growth, overall_growth);
}
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2_LTO - Build # 10 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2_LTO
Culprit:
<cut>
commit 34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e
Author: peter klausler <pklausler(a)nvidia.com>
Date: Tue Feb 2 10:51:14 2021 -0800
[flang] Add -fsyntax-only to f18; retain -fparse-only synonym
Now that semantics is working, the standard -fsyntax-only option of
GNU and Clang should be used as the name of the option that causes
f18 to just run the front-end. Support both options in f18, silently
accepting the old option as a synonym for the new one (as
preferred by the code owner), and replace all instances of the
old -fparse-only option with -fsyntax-only throughout the source base.
Differential Revision: https://reviews.llvm.org/D95887
</cut>
Results regressed to (for first_bad == 34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e/results_id:
1
# 445.gobmk,gobmk_base.default regressed by 103
from (for last_good == 81b69879c946533c71cc484bd8d9202bf1e34bfe)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-81b69879c946533c71cc484bd8d9202bf1e34bfe/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2_LTO/3985
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2_LTO/3981
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e
cd investigate-llvm-34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 81b69879c946533c71cc484bd8d9202bf1e34bfe
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 34eb0adaa9cd76f5bb0549f5a32d6ef452fe977e
Author: peter klausler <pklausler(a)nvidia.com>
Date: Tue Feb 2 10:51:14 2021 -0800
[flang] Add -fsyntax-only to f18; retain -fparse-only synonym
Now that semantics is working, the standard -fsyntax-only option of
GNU and Clang should be used as the name of the option that causes
f18 to just run the front-end. Support both options in f18, silently
accepting the old option as a synonym for the new one (as
preferred by the code owner), and replace all instances of the
old -fparse-only option with -fsyntax-only throughout the source base.
Differential Revision: https://reviews.llvm.org/D95887
---
flang/docs/ImplementingASemanticCheck.md | 2 +-
flang/docs/Overview.md | 4 ++--
flang/test/Evaluate/test_folding.sh | 2 +-
flang/test/Flang-Driver/parse-error.f95 | 2 +-
flang/test/Flang-Driver/syntax-only.f90 | 2 +-
flang/test/Frontend/prescanner-diag.f90 | 2 +-
flang/test/Lower/pre-fir-tree01.f90 | 2 +-
flang/test/Lower/pre-fir-tree02.f90 | 2 +-
flang/test/Lower/pre-fir-tree03.f90 | 2 +-
flang/test/Lower/pre-fir-tree04.f90 | 2 +-
flang/test/Lower/pre-fir-tree05.f90 | 2 +-
flang/test/Semantics/call17.f90 | 2 +-
flang/test/Semantics/data05.f90 | 2 +-
flang/test/Semantics/data08.f90 | 2 +-
flang/test/Semantics/data09.f90 | 2 +-
flang/test/Semantics/empty.f90 | 4 ++--
flang/test/Semantics/final02.f90 | 2 +-
flang/test/Semantics/getdefinition01.f90 | 8 ++++----
flang/test/Semantics/getdefinition02.f | 6 +++---
flang/test/Semantics/getdefinition03-a.f90 | 4 ++--
flang/test/Semantics/getdefinition04.f90 | 2 +-
flang/test/Semantics/getdefinition05.f90 | 4 ++--
flang/test/Semantics/getsymbols01.f90 | 2 +-
flang/test/Semantics/getsymbols02.f90 | 6 +++---
flang/test/Semantics/getsymbols03-a.f90 | 2 +-
flang/test/Semantics/getsymbols04.f90 | 2 +-
flang/test/Semantics/getsymbols05.f90 | 2 +-
flang/test/Semantics/missing_newline.f90 | 4 ++--
flang/test/Semantics/mod-file-rewriter.f90 | 8 ++++----
flang/test/Semantics/modifiable01.f90 | 2 +-
flang/test/Semantics/offsets01.f90 | 2 +-
flang/test/Semantics/offsets02.f90 | 2 +-
flang/test/Semantics/offsets03.f90 | 2 +-
flang/test/Semantics/oldparam01.f90 | 2 +-
flang/test/Semantics/oldparam02.f90 | 2 +-
flang/test/Semantics/oldparam03.f90 | 2 +-
flang/test/Semantics/resolve100.f90 | 2 +-
flang/test/Semantics/rewrite01.f90 | 2 +-
flang/test/Semantics/test_errors.sh | 2 +-
flang/test/Semantics/test_modfile.sh | 2 +-
flang/test/Semantics/typeinfo01.f90 | 2 +-
flang/tools/f18-parse-demo/f18-parse-demo.cpp | 10 +++++-----
flang/tools/f18/CMakeLists.txt | 2 +-
flang/tools/f18/f18.cpp | 10 +++++-----
44 files changed, 67 insertions(+), 67 deletions(-)
diff --git a/flang/docs/ImplementingASemanticCheck.md b/flang/docs/ImplementingASemanticCheck.md
index 35b107e4988e..4a6fe133f21f 100644
--- a/flang/docs/ImplementingASemanticCheck.md
+++ b/flang/docs/ImplementingASemanticCheck.md
@@ -67,7 +67,7 @@ of the call to `intentOutFunc()`:
I also used this program to produce a parse tree for the program using the command:
```bash
- f18 -fdebug-dump-parse-tree -fparse-only testfun.f90
+ f18 -fdebug-dump-parse-tree -fsyntax-only testfun.f90
```
Here's the relevant fragment of the parse tree produced by the compiler:
diff --git a/flang/docs/Overview.md b/flang/docs/Overview.md
index 987858943845..4ef04f865083 100644
--- a/flang/docs/Overview.md
+++ b/flang/docs/Overview.md
@@ -46,7 +46,7 @@ See: [Preprocessing.md](Preprocessing.md).
**Entry point:** `parser::Parsing::Parse`
**Command:**
- - `f18 -fdebug-dump-parse-tree -fparse-only src.f90` dumps the parse tree
+ - `f18 -fdebug-dump-parse-tree -fsyntax-only src.f90` dumps the parse tree
- `f18 -funparse src.f90` converts the parse tree to normalized Fortran
## Validate Labels and Canonicalize Do Statements
@@ -74,7 +74,7 @@ See: [Preprocessing.md](Preprocessing.md).
**Entry points:** `semantics::ResolveNames`, `semantics::RewriteParseTree`
-**Command:** `f18 -fdebug-dump-symbols -fparse-only src.f90` dumps the
+**Command:** `f18 -fdebug-dump-symbols -fsyntax-only src.f90` dumps the
tree of scopes and symbols in each scope
## Check DO CONCURRENT Constraints
diff --git a/flang/test/Evaluate/test_folding.sh b/flang/test/Evaluate/test_folding.sh
index 81ecbea55274..951ef36ecd2c 100755
--- a/flang/test/Evaluate/test_folding.sh
+++ b/flang/test/Evaluate/test_folding.sh
@@ -32,7 +32,7 @@ temp=$1
mkdir -p $temp
shift
-CMD="$* -fdebug-dump-symbols -fparse-only"
+CMD="$* -fdebug-dump-symbols -fsyntax-only"
# Check if tests should assume folding is using libpgmath
if [[ $LIBPGMATH ]]; then
diff --git a/flang/test/Flang-Driver/parse-error.f95 b/flang/test/Flang-Driver/parse-error.f95
index 84a63665659d..8266d042df02 100644
--- a/flang/test/Flang-Driver/parse-error.f95
+++ b/flang/test/Flang-Driver/parse-error.f95
@@ -1,5 +1,5 @@
! RUN: not %flang-new -fc1 -fsyntax-only %s 2>&1 | FileCheck %s --check-prefix=ERROR
-! RUN: not %f18 -parse-only %s 2>&1 | FileCheck %s --check-prefix=ERROR
+! RUN: not %f18 -syntax-only %s 2>&1 | FileCheck %s --check-prefix=ERROR
! REQUIRES: new-flang-driver
diff --git a/flang/test/Flang-Driver/syntax-only.f90 b/flang/test/Flang-Driver/syntax-only.f90
index f04dd713aeab..0eed3cca2fe9 100644
--- a/flang/test/Flang-Driver/syntax-only.f90
+++ b/flang/test/Flang-Driver/syntax-only.f90
@@ -1,5 +1,5 @@
! RUN: not %flang-new -fc1 -fsyntax-only %s 2>&1 | FileCheck %s
-! RUN: not %f18 -fparse-only %s 2>&1 | FileCheck %s
+! RUN: not %f18 -fsyntax-only %s 2>&1 | FileCheck %s
! REQUIRES: new-flang-driver
diff --git a/flang/test/Frontend/prescanner-diag.f90 b/flang/test/Frontend/prescanner-diag.f90
index 4c7e6e369beb..26536092b41b 100644
--- a/flang/test/Frontend/prescanner-diag.f90
+++ b/flang/test/Frontend/prescanner-diag.f90
@@ -6,7 +6,7 @@
! RUN: %flang-new -fc1 -E -I %S/Inputs/ %s 2>&1 | FileCheck %s
! Test with -fsyntax-only (i.e. ParseSyntaxOnlyAction, stops after semantic checks)
-! RUN: %f18 -fparse-only -I %S/Inputs/ %s 2>&1 | FileCheck %s
+! RUN: %f18 -fsyntax-only -I %S/Inputs/ %s 2>&1 | FileCheck %s
! RUN: %flang-new -fsyntax-only -I %S/Inputs/ %s 2>&1 | FileCheck %s
! RUN: %flang-new -fc1 -fsyntax-only -I %S/Inputs/ %s 2>&1 | FileCheck %s
diff --git a/flang/test/Lower/pre-fir-tree01.f90 b/flang/test/Lower/pre-fir-tree01.f90
index 6b27add4659f..5e59ff784f97 100644
--- a/flang/test/Lower/pre-fir-tree01.f90
+++ b/flang/test/Lower/pre-fir-tree01.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fdebug-pre-fir-tree -fparse-only %s | FileCheck %s
+! RUN: %f18 -fdebug-pre-fir-tree -fsyntax-only %s | FileCheck %s
! Test structure of the Pre-FIR tree
diff --git a/flang/test/Lower/pre-fir-tree02.f90 b/flang/test/Lower/pre-fir-tree02.f90
index 2d50a9394985..1db49605d98d 100644
--- a/flang/test/Lower/pre-fir-tree02.f90
+++ b/flang/test/Lower/pre-fir-tree02.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fdebug-pre-fir-tree -fparse-only %s | FileCheck %s
+! RUN: %f18 -fdebug-pre-fir-tree -fsyntax-only %s | FileCheck %s
! Test Pre-FIR Tree captures all the intended nodes from the parse-tree
! Coarray and OpenMP related nodes are tested in other files.
diff --git a/flang/test/Lower/pre-fir-tree03.f90 b/flang/test/Lower/pre-fir-tree03.f90
index 1c8651b64f83..efc923a3fe84 100644
--- a/flang/test/Lower/pre-fir-tree03.f90
+++ b/flang/test/Lower/pre-fir-tree03.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fdebug-pre-fir-tree -fparse-only -fopenmp %s | FileCheck %s
+! RUN: %f18 -fdebug-pre-fir-tree -fsyntax-only -fopenmp %s | FileCheck %s
! Test Pre-FIR Tree captures OpenMP related constructs
diff --git a/flang/test/Lower/pre-fir-tree04.f90 b/flang/test/Lower/pre-fir-tree04.f90
index 34212fbb1ff0..3f2beaf5fb47 100644
--- a/flang/test/Lower/pre-fir-tree04.f90
+++ b/flang/test/Lower/pre-fir-tree04.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fdebug-pre-fir-tree -fparse-only %s | FileCheck %s
+! RUN: %f18 -fdebug-pre-fir-tree -fsyntax-only %s | FileCheck %s
! Test Pre-FIR Tree captures all the coarray related statements
diff --git a/flang/test/Lower/pre-fir-tree05.f90 b/flang/test/Lower/pre-fir-tree05.f90
index 98af5c2de944..3acc38b20d35 100644
--- a/flang/test/Lower/pre-fir-tree05.f90
+++ b/flang/test/Lower/pre-fir-tree05.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fdebug-pre-fir-tree -fparse-only -fopenacc %s | FileCheck %s
+! RUN: %f18 -fdebug-pre-fir-tree -fsyntax-only -fopenacc %s | FileCheck %s
! Test structure of the Pre-FIR tree with OpenACC construct
diff --git a/flang/test/Semantics/call17.f90 b/flang/test/Semantics/call17.f90
index 1f4d2c4d9186..ace626037dd8 100644
--- a/flang/test/Semantics/call17.f90
+++ b/flang/test/Semantics/call17.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fparse-only $s 2>&1 | FileCheck %s
+! RUN: %f18 -fsyntax-only $s 2>&1 | FileCheck %s
! Regression test: don't emit a bogus error about an invalid specification expression
! in the declaration of a binding
diff --git a/flang/test/Semantics/data05.f90 b/flang/test/Semantics/data05.f90
index a138b067942e..f3c7aa9be6e3 100644
--- a/flang/test/Semantics/data05.f90
+++ b/flang/test/Semantics/data05.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fdebug-dump-symbols -fparse-only %s | FileCheck %s
+!RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s | FileCheck %s
module m
interface
integer function ifunc(n)
diff --git a/flang/test/Semantics/data08.f90 b/flang/test/Semantics/data08.f90
index 86a87f90163f..4040ac8e148d 100644
--- a/flang/test/Semantics/data08.f90
+++ b/flang/test/Semantics/data08.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fdebug-dump-symbols -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s 2>&1 | FileCheck %s
! CHECK: DATA statement value initializes 'jx' of type 'INTEGER(4)' with CHARACTER
! CHECK: DATA statement value initializes 'jy' of type 'INTEGER(4)' with CHARACTER
! CHECK: DATA statement value initializes 'jz' of type 'INTEGER(4)' with CHARACTER
diff --git a/flang/test/Semantics/data09.f90 b/flang/test/Semantics/data09.f90
index 1550787b0d4c..4510b830ef7f 100644
--- a/flang/test/Semantics/data09.f90
+++ b/flang/test/Semantics/data09.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fparse-only -fdebug-dump-symbols %s 2>&1 | FileCheck %s
+! RUN: %f18 -fsyntax-only -fdebug-dump-symbols %s 2>&1 | FileCheck %s
! CHECK: init:[INTEGER(4)::1065353216_4,1073741824_4,1077936128_4,1082130432_4]
! Verify that the closure of EQUIVALENCE'd symbols with any DATA
! initialization produces a combined initializer.
diff --git a/flang/test/Semantics/empty.f90 b/flang/test/Semantics/empty.f90
index e47c2e65342c..ff8f64258741 100644
--- a/flang/test/Semantics/empty.f90
+++ b/flang/test/Semantics/empty.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fparse-only %s
+! RUN: %f18 -fsyntax-only %s
! RUN: rm -rf %t && mkdir %t
! RUN: touch %t/empty.f90
-! RUN: %f18 -fparse-only %t/empty.f90
+! RUN: %f18 -fsyntax-only %t/empty.f90
diff --git a/flang/test/Semantics/final02.f90 b/flang/test/Semantics/final02.f90
index b58f91f3a228..f613a4228481 100644
--- a/flang/test/Semantics/final02.f90
+++ b/flang/test/Semantics/final02.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fparse-only %s 2>&1 | FileCheck %s
+!RUN: %f18 -fsyntax-only %s 2>&1 | FileCheck %s
module m
type :: t1
integer :: n
diff --git a/flang/test/Semantics/getdefinition01.f90 b/flang/test/Semantics/getdefinition01.f90
index 57141b671754..06f2cc0f8dda 100644
--- a/flang/test/Semantics/getdefinition01.f90
+++ b/flang/test/Semantics/getdefinition01.f90
@@ -16,12 +16,12 @@ contains
end module
! RUN and CHECK lines at the bottom as this test is sensitive to line numbers
-! RUN: %f18 -fget-definition 6 17 18 -fparse-only %s | FileCheck --check-prefix=CHECK1 %s
-! RUN: %f18 -fget-definition 7 20 23 -fparse-only %s | FileCheck --check-prefix=CHECK2 %s
-! RUN: %f18 -fget-definition 14 3 4 -fparse-only %s | FileCheck --check-prefix=CHECK3 %s
+! RUN: %f18 -fget-definition 6 17 18 -fsyntax-only %s | FileCheck --check-prefix=CHECK1 %s
+! RUN: %f18 -fget-definition 7 20 23 -fsyntax-only %s | FileCheck --check-prefix=CHECK2 %s
+! RUN: %f18 -fget-definition 14 3 4 -fsyntax-only %s | FileCheck --check-prefix=CHECK3 %s
! CHECK1: x:{{.*}}getdefinition01.f90, 5, 21-22
! CHECK2: yyy:{{.*}}getdefinition01.f90, 5, 24-27
! CHECK3: x:{{.*}}getdefinition01.f90, 13, 24-25
-! RUN: not %f18 -fget-definition -fparse-only %s 2>&1 | FileCheck --check-prefix=CHECK-ERROR %s
+! RUN: not %f18 -fget-definition -fsyntax-only %s 2>&1 | FileCheck --check-prefix=CHECK-ERROR %s
! CHECK-ERROR: Invalid argument to -fget-definitions
diff --git a/flang/test/Semantics/getdefinition02.f b/flang/test/Semantics/getdefinition02.f
index ee7a96750da5..b32536968dc0 100644
--- a/flang/test/Semantics/getdefinition02.f
+++ b/flang/test/Semantics/getdefinition02.f
@@ -17,9 +17,9 @@
end module
! RUN and CHECK lines here as test is sensitive to line numbers
-! RUN: %f18 -fget-definition 7 9 10 -fparse-only %s 2>&1 | FileCheck --check-prefix=CHECK1 %s
-! RUN: %f18 -fget-definition 8 26 29 -fparse-only %s 2>&1 | FileCheck --check-prefix=CHECK2 %s
-! RUN: %f18 -fget-definition 15 9 10 -fparse-only %s 2>&1 | FileCheck --check-prefix=CHECK3 %s
+! RUN: %f18 -fget-definition 7 9 10 -fsyntax-only %s 2>&1 | FileCheck --check-prefix=CHECK1 %s
+! RUN: %f18 -fget-definition 8 26 29 -fsyntax-only %s 2>&1 | FileCheck --check-prefix=CHECK2 %s
+! RUN: %f18 -fget-definition 15 9 10 -fsyntax-only %s 2>&1 | FileCheck --check-prefix=CHECK3 %s
! CHECK1: x:{{.*}}getdefinition02.f, 5, 27-28
! CHECK2: yyy:{{.*}}getdefinition02.f, 5, 30-33
! CHECK3: x:{{.*}}getdefinition02.f, 14, 30-31
diff --git a/flang/test/Semantics/getdefinition03-a.f90 b/flang/test/Semantics/getdefinition03-a.f90
index ecf8c9b48389..6e61637b3546 100644
--- a/flang/test/Semantics/getdefinition03-a.f90
+++ b/flang/test/Semantics/getdefinition03-a.f90
@@ -7,7 +7,7 @@ program main
x = f
end program
-! RUN: %f18 -fget-definition 7 6 7 -fparse-only %s | FileCheck --check-prefix=CHECK1 %s
-! RUN: %f18 -fget-definition 7 2 3 -fparse-only %s | FileCheck --check-prefix=CHECK2 %s
+! RUN: %f18 -fget-definition 7 6 7 -fsyntax-only %s | FileCheck --check-prefix=CHECK1 %s
+! RUN: %f18 -fget-definition 7 2 3 -fsyntax-only %s | FileCheck --check-prefix=CHECK2 %s
! CHECK1: f:{{.*}}getdefinition03-b.f90, 2, 12-13
! CHECK2: x:{{.*}}getdefinition03-a.f90, 6, 13-14
diff --git a/flang/test/Semantics/getdefinition04.f90 b/flang/test/Semantics/getdefinition04.f90
index 72429599595b..bc01f7979b42 100644
--- a/flang/test/Semantics/getdefinition04.f90
+++ b/flang/test/Semantics/getdefinition04.f90
@@ -6,5 +6,5 @@ program main
x = y
end program
-! RUN: %f18 -fget-definition 6 3 4 -fparse-only %s | FileCheck %s
+! RUN: %f18 -fget-definition 6 3 4 -fsyntax-only %s | FileCheck %s
! CHECK: x:{{.*}}getdefinition04.f90, 3, 14-15
diff --git a/flang/test/Semantics/getdefinition05.f90 b/flang/test/Semantics/getdefinition05.f90
index 315e9570d352..91952bb7fcc3 100644
--- a/flang/test/Semantics/getdefinition05.f90
+++ b/flang/test/Semantics/getdefinition05.f90
@@ -12,8 +12,8 @@ program main
end program
!! Inner x
-! RUN: %f18 -fget-definition 9 5 6 -fparse-only %s | FileCheck --check-prefix=CHECK1 %s
+! RUN: %f18 -fget-definition 9 5 6 -fsyntax-only %s | FileCheck --check-prefix=CHECK1 %s
! CHECK1: x:{{.*}}getdefinition05.f90, 7, 16-17
!! Outer y
-! RUN: %f18 -fget-definition 11 7 8 -fparse-only %s | FileCheck --check-prefix=CHECK2 %s
+! RUN: %f18 -fget-definition 11 7 8 -fsyntax-only %s | FileCheck --check-prefix=CHECK2 %s
! CHECK2: y:{{.*}}getdefinition05.f90, 5, 14-15
diff --git a/flang/test/Semantics/getsymbols01.f90 b/flang/test/Semantics/getsymbols01.f90
index bdb7bf053823..d26aa774ace4 100644
--- a/flang/test/Semantics/getsymbols01.f90
+++ b/flang/test/Semantics/getsymbols01.f90
@@ -15,7 +15,7 @@ contains
end function
end module
-! RUN: %f18 -fget-symbols-sources -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -fget-symbols-sources -fsyntax-only %s 2>&1 | FileCheck %s
! CHECK-COUNT-1:f:{{.*}}getsymbols01.f90, 12, 26-27
! CHECK-COUNT-1:mm1:{{.*}}getsymbols01.f90, 2, 8-11
! CHECK-COUNT-1:s:{{.*}}getsymbols01.f90, 5, 18-19
diff --git a/flang/test/Semantics/getsymbols02.f90 b/flang/test/Semantics/getsymbols02.f90
index 0119ab16daa8..1667548f81c3 100644
--- a/flang/test/Semantics/getsymbols02.f90
+++ b/flang/test/Semantics/getsymbols02.f90
@@ -7,8 +7,8 @@ PROGRAM helloworld
i = callget5()
ENDPROGRAM
-! RUN: %f18 -fparse-only %S/Inputs/getsymbols02-a.f90
-! RUN: %f18 -fparse-only %S/Inputs/getsymbols02-b.f90
-! RUN: %f18 -fget-symbols-sources -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -fsyntax-only %S/Inputs/getsymbols02-a.f90
+! RUN: %f18 -fsyntax-only %S/Inputs/getsymbols02-b.f90
+! RUN: %f18 -fget-symbols-sources -fsyntax-only %s 2>&1 | FileCheck %s
! CHECK: callget5: .{{[/\\]}}mm2b.mod,
! CHECK: get5: .{{[/\\]}}mm2a.mod,
diff --git a/flang/test/Semantics/getsymbols03-a.f90 b/flang/test/Semantics/getsymbols03-a.f90
index 3cbba425d875..fddf513bcc51 100644
--- a/flang/test/Semantics/getsymbols03-a.f90
+++ b/flang/test/Semantics/getsymbols03-a.f90
@@ -7,7 +7,7 @@ program main
x = f
end program
-! RUN: %f18 -fget-symbols-sources -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -fget-symbols-sources -fsyntax-only %s 2>&1 | FileCheck %s
! CHECK:f:{{.*}}getsymbols03-b.f90, 2, 12-13
! CHECK:main:{{.*}}getsymbols03-a.f90, 4, 9-13
! CHECK:mm3:{{.*}}getsymbols03-a.f90, 5, 6-9
diff --git a/flang/test/Semantics/getsymbols04.f90 b/flang/test/Semantics/getsymbols04.f90
index fc9b177abd90..ac8f2d0a7e44 100644
--- a/flang/test/Semantics/getsymbols04.f90
+++ b/flang/test/Semantics/getsymbols04.f90
@@ -6,7 +6,7 @@ program main
x = y
end program
-! RUN: %f18 -fget-symbols-sources -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -fget-symbols-sources -fsyntax-only %s 2>&1 | FileCheck %s
! CHECK:x:{{.*}}getsymbols04.f90, 3, 14-15
! CHECK:x:{{.*}}getsymbols04.f90, 5, 11-12
! CHECK:y:{{.*}}getsymbols04.f90, 4, 14-15
diff --git a/flang/test/Semantics/getsymbols05.f90 b/flang/test/Semantics/getsymbols05.f90
index 624f37a74b76..6b07678e42d0 100644
--- a/flang/test/Semantics/getsymbols05.f90
+++ b/flang/test/Semantics/getsymbols05.f90
@@ -9,7 +9,7 @@ program main
x = y
end program
-! RUN: %f18 -fget-symbols-sources -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -fget-symbols-sources -fsyntax-only %s 2>&1 | FileCheck %s
! CHECK:x:{{.*}}getsymbols05.f90, 3, 14-15
! CHECK:x:{{.*}}getsymbols05.f90, 6, 16-17
! CHECK:y:{{.*}}getsymbols05.f90, 4, 14-15
diff --git a/flang/test/Semantics/missing_newline.f90 b/flang/test/Semantics/missing_newline.f90
index 6dfafba7db86..82f9c9ceb612 100644
--- a/flang/test/Semantics/missing_newline.f90
+++ b/flang/test/Semantics/missing_newline.f90
@@ -1,4 +1,4 @@
! RUN: echo -n "end program" > %t.f90
-! RUN: %f18 -fparse-only %t.f90
+! RUN: %f18 -fsyntax-only %t.f90
! RUN: echo -ne "\rend program" > %t.f90
-! RUN: %f18 -fparse-only %t.f90
+! RUN: %f18 -fsyntax-only %t.f90
diff --git a/flang/test/Semantics/mod-file-rewriter.f90 b/flang/test/Semantics/mod-file-rewriter.f90
index 81252910e690..2856dd6dbdf3 100644
--- a/flang/test/Semantics/mod-file-rewriter.f90
+++ b/flang/test/Semantics/mod-file-rewriter.f90
@@ -1,8 +1,8 @@
! RUN: rm -fr %t && mkdir %t && cd %t
-! RUN: %f18 -fparse-only -fdebug-module-writer %s 2>&1 | FileCheck %s --check-prefix CHECK_CHANGED
-! RUN: %f18 -fparse-only -fdebug-module-writer %s 2>&1 | FileCheck %s --check-prefix CHECK_UNCHANGED
-! RUN: %f18 -fparse-only -fdebug-module-writer %p/Inputs/mod-file-unchanged.f90 2>&1 | FileCheck %s --check-prefix CHECK_UNCHANGED
-! RUN: %f18 -fparse-only -fdebug-module-writer %p/Inputs/mod-file-changed.f90 2>&1 | FileCheck %s --check-prefix CHECK_CHANGED
+! RUN: %f18 -fsyntax-only -fdebug-module-writer %s 2>&1 | FileCheck %s --check-prefix CHECK_CHANGED
+! RUN: %f18 -fsyntax-only -fdebug-module-writer %s 2>&1 | FileCheck %s --check-prefix CHECK_UNCHANGED
+! RUN: %f18 -fsyntax-only -fdebug-module-writer %p/Inputs/mod-file-unchanged.f90 2>&1 | FileCheck %s --check-prefix CHECK_UNCHANGED
+! RUN: %f18 -fsyntax-only -fdebug-module-writer %p/Inputs/mod-file-changed.f90 2>&1 | FileCheck %s --check-prefix CHECK_CHANGED
module m
real :: x(10)
diff --git a/flang/test/Semantics/modifiable01.f90 b/flang/test/Semantics/modifiable01.f90
index 391a643e3368..dfa9396565e0 100644
--- a/flang/test/Semantics/modifiable01.f90
+++ b/flang/test/Semantics/modifiable01.f90
@@ -1,4 +1,4 @@
-! RUN: not %f18 -fparse-only %s 2>&1 | FileCheck %s
+! RUN: not %f18 -fsyntax-only %s 2>&1 | FileCheck %s
! Test WhyNotModifiable() explanations
module prot
diff --git a/flang/test/Semantics/offsets01.f90 b/flang/test/Semantics/offsets01.f90
index f5491f7b9438..78183d5cc0fc 100644
--- a/flang/test/Semantics/offsets01.f90
+++ b/flang/test/Semantics/offsets01.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fdebug-dump-symbols -fparse-only %s | FileCheck %s
+!RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s | FileCheck %s
! Size and alignment of intrinsic types
subroutine s1
diff --git a/flang/test/Semantics/offsets02.f90 b/flang/test/Semantics/offsets02.f90
index f2ed1d1dbe71..b76572e1761d 100644
--- a/flang/test/Semantics/offsets02.f90
+++ b/flang/test/Semantics/offsets02.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fdebug-dump-symbols -fparse-only %s | FileCheck %s
+!RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s | FileCheck %s
! Size and alignment of derived types
diff --git a/flang/test/Semantics/offsets03.f90 b/flang/test/Semantics/offsets03.f90
index d28b3694bddd..c1c2de464a01 100644
--- a/flang/test/Semantics/offsets03.f90
+++ b/flang/test/Semantics/offsets03.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fdebug-dump-symbols -fparse-only %s | FileCheck %s
+!RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s | FileCheck %s
! Size and alignment with EQUIVALENCE and COMMON
diff --git a/flang/test/Semantics/oldparam01.f90 b/flang/test/Semantics/oldparam01.f90
index 43f33a52f364..b78869ff4d90 100644
--- a/flang/test/Semantics/oldparam01.f90
+++ b/flang/test/Semantics/oldparam01.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -falternative-parameter-statement -fdebug-dump-symbols -fparse-only %s 2>&1 | FileCheck %s
+! RUN: %f18 -falternative-parameter-statement -fdebug-dump-symbols -fsyntax-only %s 2>&1 | FileCheck %s
! Non-error tests for "old style" PARAMETER statements
diff --git a/flang/test/Semantics/oldparam02.f90 b/flang/test/Semantics/oldparam02.f90
index 72ea5c410c7a..fd58988ba0b0 100644
--- a/flang/test/Semantics/oldparam02.f90
+++ b/flang/test/Semantics/oldparam02.f90
@@ -1,4 +1,4 @@
-! RUN: not %f18 -falternative-parameter-statement -fdebug-dump-symbols -fparse-only %s 2>&1 | FileCheck %s
+! RUN: not %f18 -falternative-parameter-statement -fdebug-dump-symbols -fsyntax-only %s 2>&1 | FileCheck %s
! Error tests for "old style" PARAMETER statements
subroutine subr(x1,x2,x3,x4,x5)
diff --git a/flang/test/Semantics/oldparam03.f90 b/flang/test/Semantics/oldparam03.f90
index cbdb07057226..bc80f00a1966 100644
--- a/flang/test/Semantics/oldparam03.f90
+++ b/flang/test/Semantics/oldparam03.f90
@@ -1,4 +1,4 @@
-! RUN: not %f18 -fparse-only %s 2>&1 | FileCheck %s
+! RUN: not %f18 -fsyntax-only %s 2>&1 | FileCheck %s
! Ensure that old-style PARAMETER statements are disabled by default.
diff --git a/flang/test/Semantics/resolve100.f90 b/flang/test/Semantics/resolve100.f90
index 1e84be24c5f2..52fca54b94f7 100644
--- a/flang/test/Semantics/resolve100.f90
+++ b/flang/test/Semantics/resolve100.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fdebug-dump-symbols -fparse-only %s | FileCheck %s
+!RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s | FileCheck %s
program p
! CHECK: a size=4 offset=0: ObjectEntity type: LOGICAL(4)
diff --git a/flang/test/Semantics/rewrite01.f90 b/flang/test/Semantics/rewrite01.f90
index 221994593422..cd5453eee6be 100644
--- a/flang/test/Semantics/rewrite01.f90
+++ b/flang/test/Semantics/rewrite01.f90
@@ -1,4 +1,4 @@
-! RUN: %f18 -fparse-only -fdebug-dump-parse-tree %s 2>&1 | FileCheck %s
+! RUN: %f18 -fsyntax-only -fdebug-dump-parse-tree %s 2>&1 | FileCheck %s
! Ensure that READ(CVAR) [, item-list] is corrected when CVAR is a
! character variable so as to be a formatted read from the default
! unit, not an unformatted read from an internal unit (which is not
diff --git a/flang/test/Semantics/test_errors.sh b/flang/test/Semantics/test_errors.sh
index 5411482e4d3b..10feccb2f9f1 100755
--- a/flang/test/Semantics/test_errors.sh
+++ b/flang/test/Semantics/test_errors.sh
@@ -2,7 +2,7 @@
# Compile a source file and check errors against those listed in the file.
# Change the compiler by setting the F18 environment variable.
-F18_OPTIONS="-fparse-only"
+F18_OPTIONS="-fsyntax-only"
srcdir=$(dirname $0)
source $srcdir/common.sh
[[ ! -f $src ]] && die "File not found: $src"
diff --git a/flang/test/Semantics/test_modfile.sh b/flang/test/Semantics/test_modfile.sh
index 9205451c176d..a2aef65a101b 100755
--- a/flang/test/Semantics/test_modfile.sh
+++ b/flang/test/Semantics/test_modfile.sh
@@ -2,7 +2,7 @@
# Compile a source file and compare generated .mod files against expected.
set -e
-F18_OPTIONS="-fdebug-resolve-names -fparse-only"
+F18_OPTIONS="-fdebug-resolve-names -fsyntax-only"
srcdir=$(dirname $0)
source $srcdir/common.sh
diff --git a/flang/test/Semantics/typeinfo01.f90 b/flang/test/Semantics/typeinfo01.f90
index 834120ccb430..2274896fcd68 100644
--- a/flang/test/Semantics/typeinfo01.f90
+++ b/flang/test/Semantics/typeinfo01.f90
@@ -1,4 +1,4 @@
-!RUN: %f18 -fdebug-dump-symbols -fparse-only %s | FileCheck %s
+!RUN: %f18 -fdebug-dump-symbols -fsyntax-only %s | FileCheck %s
! Tests for derived type runtime descriptions
module m01
diff --git a/flang/tools/f18-parse-demo/f18-parse-demo.cpp b/flang/tools/f18-parse-demo/f18-parse-demo.cpp
index 4ccc65e0631d..2033ef6c3bc2 100644
--- a/flang/tools/f18-parse-demo/f18-parse-demo.cpp
+++ b/flang/tools/f18-parse-demo/f18-parse-demo.cpp
@@ -87,7 +87,7 @@ struct DriverOptions {
bool warnOnNonstandardUsage{false}; // -Mstandard
bool warningsAreErrors{false}; // -Werror
Fortran::parser::Encoding encoding{Fortran::parser::Encoding::LATIN_1};
- bool parseOnly{false};
+ bool syntaxOnly{false};
bool dumpProvenance{false};
bool dumpCookedChars{false};
bool dumpUnparse{false};
@@ -217,7 +217,7 @@ std::string CompileFortran(
Fortran::common::LanguageFeature::BackslashEscapes));
return {};
}
- if (driver.parseOnly) {
+ if (driver.syntaxOnly) {
return {};
}
@@ -369,8 +369,8 @@ int main(int argc, char *const argv[]) {
driver.dumpUnparse = true;
} else if (arg == "-ftime-parse") {
driver.timeParse = true;
- } else if (arg == "-fparse-only") {
- driver.parseOnly = true;
+ } else if (arg == "-fparse-only" || arg == "-fsyntax-only") {
+ driver.syntaxOnly = true;
} else if (arg == "-c") {
driver.compileOnly = true;
} else if (arg == "-o") {
@@ -405,7 +405,7 @@ int main(int argc, char *const argv[]) {
<< " -ed enable fixed form D lines\n"
<< " -E prescan & preprocess only\n"
<< " -ftime-parse measure parsing time\n"
- << " -fparse-only parse only, no output except messages\n"
+ << " -fsyntax-only parse only, no output except messages\n"
<< " -funparse parse & reformat only, no code "
"generation\n"
<< " -fdump-provenance dump the provenance table (no code)\n"
diff --git a/flang/tools/f18/CMakeLists.txt b/flang/tools/f18/CMakeLists.txt
index 2e5350aecdc6..41237fe06003 100644
--- a/flang/tools/f18/CMakeLists.txt
+++ b/flang/tools/f18/CMakeLists.txt
@@ -46,7 +46,7 @@ foreach(filename ${MODULES})
set(depends ${include}/__fortran_builtins.mod)
endif()
add_custom_command(OUTPUT ${include}/${filename}.mod
- COMMAND f18 -fparse-only -I${include}
+ COMMAND f18 -fsyntax-only -I${include}
${FLANG_SOURCE_DIR}/module/${filename}.f90
WORKING_DIRECTORY ${include}
DEPENDS f18 ${FLANG_SOURCE_DIR}/module/${filename}.f90 ${depends}
diff --git a/flang/tools/f18/f18.cpp b/flang/tools/f18/f18.cpp
index fecd37d49936..4546353fe010 100644
--- a/flang/tools/f18/f18.cpp
+++ b/flang/tools/f18/f18.cpp
@@ -92,7 +92,7 @@ struct DriverOptions {
bool warningsAreErrors{false}; // -Werror
bool byteswapio{false}; // -byteswapio
Fortran::parser::Encoding encoding{Fortran::parser::Encoding::UTF_8};
- bool parseOnly{false};
+ bool syntaxOnly{false};
bool dumpProvenance{false};
bool dumpCookedChars{false};
bool dumpUnparse{false};
@@ -327,7 +327,7 @@ std::string CompileFortran(std::string path, Fortran::parser::Options options,
exitStatus = EXIT_FAILURE;
}
}
- if (driver.parseOnly) {
+ if (driver.syntaxOnly) {
return {};
}
@@ -544,8 +544,8 @@ int main(int argc, char *const argv[]) {
driver.dumpUnparseWithSymbols = true;
} else if (arg == "-funparse-typed-exprs-to-f18-fc") {
driver.unparseTypedExprsToF18_FC = true;
- } else if (arg == "-fparse-only") {
- driver.parseOnly = true;
+ } else if (arg == "-fparse-only" || arg == "-fsyntax-only") {
+ driver.syntaxOnly = true;
} else if (arg == "-c") {
driver.compileOnly = true;
} else if (arg == "-o") {
@@ -649,7 +649,7 @@ int main(int argc, char *const argv[]) {
<< " -module dir module output directory (default .)\n"
<< " -flatin interpret source as Latin-1 (ISO 8859-1) "
"rather than UTF-8\n"
- << " -fparse-only parse only, no output except messages\n"
+ << " -fsyntax-only parsing and semantics only, no output except messages\n"
<< " -funparse parse & reformat only, no code "
"generation\n"
<< " -funparse-with-symbols parse, resolve symbols, and unparse\n"
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gcc_bootstrap/master-arm-bootstrap - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gcc_bootstrap/master-arm-bootstrap. So far, this commit has regressed CI configurations:
- tcwg_gcc_bootstrap/master-arm-bootstrap
Culprit:
<cut>
commit e4f16e9f357a38ec702fb69a0ffab9d292a6af9b
Author: Thomas Schwinge <thomas(a)codesourcery.com>
Date: Fri Aug 13 17:53:12 2021 +0200
Add more self-tests for 'hash_map' with Value type with non-trivial constructor/destructor
... to document the current behavior.
gcc/
* hash-map-tests.c (test_map_of_type_with_ctor_and_dtor): Extend.
(test_map_of_type_with_ctor_and_dtor_expand): Add function.
(hash_map_tests_c_tests): Call it.
</cut>
Results regressed to (for first_bad == e4f16e9f357a38ec702fb69a0ffab9d292a6af9b)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# First few build errors in logs:
# 00:02:51 cc1: internal compiler error: in fail, at selftest.c:47
# 00:02:51 cc1plus: internal compiler error: in fail, at selftest.c:47
# 00:02:51 make[3]: *** [s-selftest-c] Error 1
# 00:02:51 make[3]: *** [s-selftest-c++] Error 1
# 00:02:51 make[2]: *** [all-stage1-gcc] Error 2
# 00:02:51 make[1]: *** [stage1-bubble] Error 2
# 00:02:51 make: *** [all] Error 2
from (for last_good == 602fca427df6c5f7452677cfcdd16a5b9a3ca86a)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe bootstrap:
2
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-e4f16e9f357a38ec702fb69a0ffab9d292a6af9b
cd investigate-gcc-e4f16e9f357a38ec702fb69a0ffab9d292a6af9b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach e4f16e9f357a38ec702fb69a0ffab9d292a6af9b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 602fca427df6c5f7452677cfcdd16a5b9a3ca86a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/…
Build log: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-arm-bootstrap/1/…
Full commit (up to 1000 lines):
<cut>
commit e4f16e9f357a38ec702fb69a0ffab9d292a6af9b
Author: Thomas Schwinge <thomas(a)codesourcery.com>
Date: Fri Aug 13 17:53:12 2021 +0200
Add more self-tests for 'hash_map' with Value type with non-trivial constructor/destructor
... to document the current behavior.
gcc/
* hash-map-tests.c (test_map_of_type_with_ctor_and_dtor): Extend.
(test_map_of_type_with_ctor_and_dtor_expand): Add function.
(hash_map_tests_c_tests): Call it.
---
gcc/hash-map-tests.c | 152 +++++++++++++++++++++++++++++++++++++++++++++++++++
1 file changed, 152 insertions(+)
diff --git a/gcc/hash-map-tests.c b/gcc/hash-map-tests.c
index 5b6b192cd28..257f2be0c26 100644
--- a/gcc/hash-map-tests.c
+++ b/gcc/hash-map-tests.c
@@ -278,6 +278,156 @@ test_map_of_type_with_ctor_and_dtor ()
ASSERT_TRUE (val_t::ndefault + val_t::ncopy == val_t::ndtor);
}
+
+
+ /* Verify basic construction and destruction of Value objects. */
+ {
+ /* Configure, arbitrary. */
+ const size_t N_init = 0;
+ const int N_elem = 28;
+
+ void *a[N_elem];
+ for (size_t i = 0; i < N_elem; ++i)
+ a[i] = &a[i];
+
+ val_t::ndefault = 0;
+ val_t::ncopy = 0;
+ val_t::nassign = 0;
+ val_t::ndtor = 0;
+ Map m (N_init);
+ ASSERT_EQ (val_t::ndefault
+ + val_t::ncopy
+ + val_t::nassign
+ + val_t::ndtor, 0);
+
+ for (int i = 0; i < N_elem; ++i)
+ {
+ m.get_or_insert (a[i]);
+ ASSERT_EQ (val_t::ndefault, 1 + i);
+ ASSERT_EQ (val_t::ncopy, 0);
+ ASSERT_EQ (val_t::nassign, 0);
+ ASSERT_EQ (val_t::ndtor, i);
+
+ m.remove (a[i]);
+ ASSERT_EQ (val_t::ndefault, 1 + i);
+ ASSERT_EQ (val_t::ncopy, 0);
+ ASSERT_EQ (val_t::nassign, 0);
+ ASSERT_EQ (val_t::ndtor, 1 + i);
+ }
+ }
+}
+
+/* Verify aspects of 'hash_table::expand'. */
+
+static void
+test_map_of_type_with_ctor_and_dtor_expand (bool remove_some_inline)
+{
+ /* Configure, so that hash table expansion triggers a few times. */
+ const size_t N_init = 0;
+ const int N_elem = 70;
+ size_t expand_c_expected = 4;
+ size_t expand_c = 0;
+
+ void *a[N_elem];
+ for (size_t i = 0; i < N_elem; ++i)
+ a[i] = &a[i];
+
+ typedef hash_map <void *, val_t> Map;
+
+ /* Note that we are starting with a fresh 'Map'. Even if an existing one has
+ been cleared out completely, there remain 'deleted' elements, and these
+ would disturb the following logic, where we don't have access to the
+ actual 'm_n_deleted' value. */
+ size_t m_n_deleted = 0;
+
+ val_t::ndefault = 0;
+ val_t::ncopy = 0;
+ val_t::nassign = 0;
+ val_t::ndtor = 0;
+ Map m (N_init);
+
+ /* In the following, in particular related to 'expand', we're adapting from
+ the internal logic of 'hash_table', glossing over "some details" not
+ relevant for this testing here. */
+
+ /* Per 'hash_table::hash_table'. */
+ size_t m_size;
+ {
+ unsigned int size_prime_index_ = hash_table_higher_prime_index (N_init);
+ m_size = prime_tab[size_prime_index_].prime;
+ }
+
+ int n_expand_moved = 0;
+
+ for (int i = 0; i < N_elem; ++i)
+ {
+ size_t elts = m.elements ();
+
+ /* Per 'hash_table::find_slot_with_hash'. */
+ size_t m_n_elements = elts + m_n_deleted;
+ bool expand = m_size * 3 <= m_n_elements * 4;
+
+ m.get_or_insert (a[i]);
+ if (expand)
+ {
+ ++expand_c;
+
+ /* Per 'hash_table::expand'. */
+ {
+ unsigned int nindex = hash_table_higher_prime_index (elts * 2);
+ m_size = prime_tab[nindex].prime;
+ }
+ m_n_deleted = 0;
+
+ /* All non-deleted elements have been moved. */
+ n_expand_moved += i;
+ if (remove_some_inline)
+ n_expand_moved -= (i + 2) / 3;
+ }
+
+ ASSERT_EQ (val_t::ndefault, 1 + i);
+ ASSERT_EQ (val_t::ncopy, n_expand_moved);
+ ASSERT_EQ (val_t::nassign, 0);
+ if (remove_some_inline)
+ ASSERT_EQ (val_t::ndtor, (i + 2) / 3);
+ else
+ ASSERT_EQ (val_t::ndtor, 0);
+
+ /* Remove some inline. This never triggers an 'expand' here, but via
+ 'm_n_deleted' does influence any following one. */
+ if (remove_some_inline
+ && !(i % 3))
+ {
+ m.remove (a[i]);
+ /* Per 'hash_table::remove_elt_with_hash'. */
+ m_n_deleted++;
+
+ ASSERT_EQ (val_t::ndefault, 1 + i);
+ ASSERT_EQ (val_t::ncopy, n_expand_moved);
+ ASSERT_EQ (val_t::nassign, 0);
+ ASSERT_EQ (val_t::ndtor, 1 + (i + 2) / 3);
+ }
+ }
+ ASSERT_EQ (expand_c, expand_c_expected);
+
+ int ndefault = val_t::ndefault;
+ int ncopy = val_t::ncopy;
+ int nassign = val_t::nassign;
+ int ndtor = val_t::ndtor;
+
+ for (int i = 0; i < N_elem; ++i)
+ {
+ if (remove_some_inline
+ && !(i % 3))
+ continue;
+
+ m.remove (a[i]);
+ ++ndtor;
+ ASSERT_EQ (val_t::ndefault, ndefault);
+ ASSERT_EQ (val_t::ncopy, ncopy);
+ ASSERT_EQ (val_t::nassign, nassign);
+ ASSERT_EQ (val_t::ndtor, ndtor);
+ }
}
/* Test calling empty on a hash_map that has a key type with non-zero
@@ -309,6 +459,8 @@ hash_map_tests_c_tests ()
test_map_of_strings_to_int ();
test_map_of_int_to_strings ();
test_map_of_type_with_ctor_and_dtor ();
+ test_map_of_type_with_ctor_and_dtor_expand (false);
+ test_map_of_type_with_ctor_and_dtor_expand (true);
test_nonzero_empty_key ();
}
</cut>
4 years
- 3
- 2
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3_LTO - Build # 6 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3_LTO
Culprit:
<cut>
commit 310b35304cdf5a230c042904655583c5532d3e91
Author: Rong Xu <xur(a)google.com>
Date: Tue Feb 16 10:53:38 2021 -0800
[SampleFDO][NFC] Refactor SampleProfile.cpp
Refactor SampleProfile.cpp to use the core code in CodeGen.
The main changes are:
(1) Move SampleProfileLoaderBaseImpl class to a header file.
(2) Split SampleCoverageTracker to a head file and a cpp file.
(3) Move the common codes (common options and callsiteIsHot())
to the common cpp file.
Differential Revision: https://reviews.llvm.org/D96455
</cut>
Results regressed to (for first_bad == 310b35304cdf5a230c042904655583c5532d3e91)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-310b35304cdf5a230c042904655583c5532d3e91/results_id:
1
# 482.sphinx3,sphinx_livepretend_base.default regressed by 106
from (for last_good == cddc53ef088b68586094c9841a76b41bee3994a4)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-cddc53ef088b68586094c9841a76b41bee3994a4/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3_LTO/3917
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3_LTO/3930
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-310b35304cdf5a230c042904655583c5532d3e91
cd investigate-llvm-310b35304cdf5a230c042904655583c5532d3e91
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 310b35304cdf5a230c042904655583c5532d3e91
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach cddc53ef088b68586094c9841a76b41bee3994a4
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 310b35304cdf5a230c042904655583c5532d3e91
Author: Rong Xu <xur(a)google.com>
Date: Tue Feb 16 10:53:38 2021 -0800
[SampleFDO][NFC] Refactor SampleProfile.cpp
Refactor SampleProfile.cpp to use the core code in CodeGen.
The main changes are:
(1) Move SampleProfileLoaderBaseImpl class to a header file.
(2) Split SampleCoverageTracker to a head file and a cpp file.
(3) Move the common codes (common options and callsiteIsHot())
to the common cpp file.
Differential Revision: https://reviews.llvm.org/D96455
---
.../llvm/ProfileData/SampleProfileLoaderBaseImpl.h | 862 +++++++++++++++++
.../llvm/ProfileData/SampleProfileLoaderBaseUtil.h | 97 ++
llvm/lib/ProfileData/CMakeLists.txt | 1 +
.../ProfileData/SampleProfileLoaderBaseUtil.cpp | 192 ++++
llvm/lib/Transforms/IPO/SampleProfile.cpp | 1001 +-------------------
5 files changed, 1161 insertions(+), 992 deletions(-)
diff --git a/llvm/include/llvm/ProfileData/SampleProfileLoaderBaseImpl.h b/llvm/include/llvm/ProfileData/SampleProfileLoaderBaseImpl.h
new file mode 100644
index 000000000000..f02bacb6edc3
--- /dev/null
+++ b/llvm/include/llvm/ProfileData/SampleProfileLoaderBaseImpl.h
@@ -0,0 +1,862 @@
+////===- SampleProfileLoadBaseImpl.h - Profile loader base impl --*- C++-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file
+/// This file provides the interface for the sampled PGO profile loader base
+/// implementation.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_IPO_SAMPLEPROFILELOADERIMPL_H
+#define LLVM_TRANSFORMS_IPO_SAMPLEPROFILELOADERIMPL_H
+
+#include "llvm/ADT/ArrayRef.h"
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/ADT/DenseSet.h"
+#include "llvm/ADT/SmallPtrSet.h"
+#include "llvm/ADT/SmallSet.h"
+#include "llvm/ADT/SmallVector.h"
+#include "llvm/Analysis/LoopInfo.h"
+#include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/PostDominators.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/CFG.h"
+#include "llvm/IR/DebugInfoMetadata.h"
+#include "llvm/IR/DebugLoc.h"
+#include "llvm/IR/Dominators.h"
+#include "llvm/IR/Function.h"
+#include "llvm/IR/Instruction.h"
+#include "llvm/IR/Instructions.h"
+#include "llvm/IR/Module.h"
+#include "llvm/ProfileData/SampleProf.h"
+#include "llvm/ProfileData/SampleProfReader.h"
+#include "llvm/ProfileData/SampleProfileLoaderBaseUtil.h"
+#include "llvm/Support/CommandLine.h"
+#include "llvm/Support/GenericDomTree.h"
+#include "llvm/Support/raw_ostream.h"
+
+namespace llvm {
+using namespace llvm;
+using namespace sampleprof;
+using ProfileCount = Function::ProfileCount;
+namespace sampleprofutil {
+bool callsiteIsHot(const SampleCoverageTracker *CT,
+ const FunctionSamples *CallsiteFS, ProfileSummaryInfo *PSI,
+ bool ProfAccForSymsInList);
+} // namespace sampleprofutil
+using namespace sampleprofutil;
+
+#define DEBUG_TYPE "sample-profile-impl"
+
+using BlockWeightMap = DenseMap<const BasicBlock *, uint64_t>;
+using EquivalenceClassMap = DenseMap<const BasicBlock *, const BasicBlock *>;
+using Edge = std::pair<const BasicBlock *, const BasicBlock *>;
+using EdgeWeightMap = DenseMap<Edge, uint64_t>;
+using BlockEdgeMap =
+ DenseMap<const BasicBlock *, SmallVector<const BasicBlock *, 8>>;
+
+extern cl::opt<unsigned> SampleProfileMaxPropagateIterations;
+extern cl::opt<unsigned> SampleProfileRecordCoverage;
+extern cl::opt<unsigned> SampleProfileSampleCoverage;
+extern cl::opt<bool> NoWarnSampleUnused;
+
+class SampleProfileLoaderBaseImpl {
+public:
+ SampleProfileLoaderBaseImpl(std::string Name) : Filename(Name) {}
+ void dump() { Reader->dump(); }
+
+protected:
+ friend class SampleCoverageTracker;
+
+ unsigned getFunctionLoc(Function &F);
+ virtual ErrorOr<uint64_t> getInstWeight(const Instruction &Inst);
+ ErrorOr<uint64_t> getInstWeightImpl(const Instruction &Inst);
+ ErrorOr<uint64_t> getBlockWeight(const BasicBlock *BB);
+ mutable DenseMap<const DILocation *, const FunctionSamples *>
+ DILocation2SampleMap;
+ virtual const FunctionSamples *
+ findFunctionSamples(const Instruction &I) const;
+ void printEdgeWeight(raw_ostream &OS, Edge E);
+ void printBlockWeight(raw_ostream &OS, const BasicBlock *BB) const;
+ void printBlockEquivalence(raw_ostream &OS, const BasicBlock *BB);
+ bool computeBlockWeights(Function &F);
+ void findEquivalenceClasses(Function &F);
+ template <bool IsPostDom>
+ void findEquivalencesFor(BasicBlock *BB1, ArrayRef<BasicBlock *> Descendants,
+ DominatorTreeBase<BasicBlock, IsPostDom> *DomTree);
+
+ void propagateWeights(Function &F);
+ uint64_t visitEdge(Edge E, unsigned *NumUnknownEdges, Edge *UnknownEdge);
+ void buildEdges(Function &F);
+ bool propagateThroughEdges(Function &F, bool UpdateBlockCount);
+ void clearFunctionData();
+ void computeDominanceAndLoopInfo(Function &F);
+ bool
+ computeAndPropagateWeights(Function &F,
+ const DenseSet<GlobalValue::GUID> &InlinedGUIDs);
+ void emitCoverageRemarks(Function &F);
+
+ /// Map basic blocks to their computed weights.
+ ///
+ /// The weight of a basic block is defined to be the maximum
+ /// of all the instruction weights in that block.
+ BlockWeightMap BlockWeights;
+
+ /// Map edges to their computed weights.
+ ///
+ /// Edge weights are computed by propagating basic block weights in
+ /// SampleProfile::propagateWeights.
+ EdgeWeightMap EdgeWeights;
+
+ /// Set of visited blocks during propagation.
+ SmallPtrSet<const BasicBlock *, 32> VisitedBlocks;
+
+ /// Set of visited edges during propagation.
+ SmallSet<Edge, 32> VisitedEdges;
+
+ /// Equivalence classes for block weights.
+ ///
+ /// Two blocks BB1 and BB2 are in the same equivalence class if they
+ /// dominate and post-dominate each other, and they are in the same loop
+ /// nest. When this happens, the two blocks are guaranteed to execute
+ /// the same number of times.
+ EquivalenceClassMap EquivalenceClass;
+
+ /// Dominance, post-dominance and loop information.
+ std::unique_ptr<DominatorTree> DT;
+ std::unique_ptr<PostDominatorTree> PDT;
+ std::unique_ptr<LoopInfo> LI;
+
+ /// Predecessors for each basic block in the CFG.
+ BlockEdgeMap Predecessors;
+
+ /// Successors for each basic block in the CFG.
+ BlockEdgeMap Successors;
+
+ /// Profile coverage tracker.
+ SampleCoverageTracker CoverageTracker;
+
+ /// Profile reader object.
+ std::unique_ptr<SampleProfileReader> Reader;
+
+ /// Samples collected for the body of this function.
+ FunctionSamples *Samples = nullptr;
+
+ /// Name of the profile file to load.
+ std::string Filename;
+
+ /// Profile Summary Info computed from sample profile.
+ ProfileSummaryInfo *PSI = nullptr;
+
+ /// Optimization Remark Emitter used to emit diagnostic remarks.
+ OptimizationRemarkEmitter *ORE = nullptr;
+};
+
+/// Clear all the per-function data used to load samples and propagate weights.
+void SampleProfileLoaderBaseImpl::clearFunctionData() {
+ BlockWeights.clear();
+ EdgeWeights.clear();
+ VisitedBlocks.clear();
+ VisitedEdges.clear();
+ EquivalenceClass.clear();
+ DT = nullptr;
+ PDT = nullptr;
+ LI = nullptr;
+ Predecessors.clear();
+ Successors.clear();
+ CoverageTracker.clear();
+}
+
+#ifndef NDEBUG
+/// Print the weight of edge \p E on stream \p OS.
+///
+/// \param OS Stream to emit the output to.
+/// \param E Edge to print.
+void SampleProfileLoaderBaseImpl::printEdgeWeight(raw_ostream &OS, Edge E) {
+ OS << "weight[" << E.first->getName() << "->" << E.second->getName()
+ << "]: " << EdgeWeights[E] << "\n";
+}
+
+/// Print the equivalence class of block \p BB on stream \p OS.
+///
+/// \param OS Stream to emit the output to.
+/// \param BB Block to print.
+void SampleProfileLoaderBaseImpl::printBlockEquivalence(raw_ostream &OS,
+ const BasicBlock *BB) {
+ const BasicBlock *Equiv = EquivalenceClass[BB];
+ OS << "equivalence[" << BB->getName()
+ << "]: " << ((Equiv) ? EquivalenceClass[BB]->getName() : "NONE") << "\n";
+}
+
+/// Print the weight of block \p BB on stream \p OS.
+///
+/// \param OS Stream to emit the output to.
+/// \param BB Block to print.
+void SampleProfileLoaderBaseImpl::printBlockWeight(raw_ostream &OS,
+ const BasicBlock *BB) const {
+ const auto &I = BlockWeights.find(BB);
+ uint64_t W = (I == BlockWeights.end() ? 0 : I->second);
+ OS << "weight[" << BB->getName() << "]: " << W << "\n";
+}
+#endif
+
+/// Get the weight for an instruction.
+///
+/// The "weight" of an instruction \p Inst is the number of samples
+/// collected on that instruction at runtime. To retrieve it, we
+/// need to compute the line number of \p Inst relative to the start of its
+/// function. We use HeaderLineno to compute the offset. We then
+/// look up the samples collected for \p Inst using BodySamples.
+///
+/// \param Inst Instruction to query.
+///
+/// \returns the weight of \p Inst.
+ErrorOr<uint64_t>
+SampleProfileLoaderBaseImpl::getInstWeight(const Instruction &Inst) {
+ return getInstWeightImpl(Inst);
+}
+
+ErrorOr<uint64_t>
+SampleProfileLoaderBaseImpl::getInstWeightImpl(const Instruction &Inst) {
+ const FunctionSamples *FS = findFunctionSamples(Inst);
+ if (!FS)
+ return std::error_code();
+
+ const DebugLoc &DLoc = Inst.getDebugLoc();
+ if (!DLoc)
+ return std::error_code();
+
+ const DILocation *DIL = DLoc;
+ uint32_t LineOffset = FunctionSamples::getOffset(DIL);
+ uint32_t Discriminator = DIL->getBaseDiscriminator();
+ ErrorOr<uint64_t> R = FS->findSamplesAt(LineOffset, Discriminator);
+ if (R) {
+ bool FirstMark =
+ CoverageTracker.markSamplesUsed(FS, LineOffset, Discriminator, R.get());
+ if (FirstMark) {
+ ORE->emit([&]() {
+ OptimizationRemarkAnalysis Remark(DEBUG_TYPE, "AppliedSamples", &Inst);
+ Remark << "Applied " << ore::NV("NumSamples", *R);
+ Remark << " samples from profile (offset: ";
+ Remark << ore::NV("LineOffset", LineOffset);
+ if (Discriminator) {
+ Remark << ".";
+ Remark << ore::NV("Discriminator", Discriminator);
+ }
+ Remark << ")";
+ return Remark;
+ });
+ }
+ LLVM_DEBUG(dbgs() << " " << DLoc.getLine() << "."
+ << DIL->getBaseDiscriminator() << ":" << Inst
+ << " (line offset: " << LineOffset << "."
+ << DIL->getBaseDiscriminator() << " - weight: " << R.get()
+ << ")\n");
+ }
+ return R;
+}
+
+/// Compute the weight of a basic block.
+///
+/// The weight of basic block \p BB is the maximum weight of all the
+/// instructions in BB.
+///
+/// \param BB The basic block to query.
+///
+/// \returns the weight for \p BB.
+ErrorOr<uint64_t>
+SampleProfileLoaderBaseImpl::getBlockWeight(const BasicBlock *BB) {
+ uint64_t Max = 0;
+ bool HasWeight = false;
+ for (auto &I : BB->getInstList()) {
+ const ErrorOr<uint64_t> &R = getInstWeight(I);
+ if (R) {
+ Max = std::max(Max, R.get());
+ HasWeight = true;
+ }
+ }
+ return HasWeight ? ErrorOr<uint64_t>(Max) : std::error_code();
+}
+
+/// Compute and store the weights of every basic block.
+///
+/// This populates the BlockWeights map by computing
+/// the weights of every basic block in the CFG.
+///
+/// \param F The function to query.
+bool SampleProfileLoaderBaseImpl::computeBlockWeights(Function &F) {
+ bool Changed = false;
+ LLVM_DEBUG(dbgs() << "Block weights\n");
+ for (const auto &BB : F) {
+ ErrorOr<uint64_t> Weight = getBlockWeight(&BB);
+ if (Weight) {
+ BlockWeights[&BB] = Weight.get();
+ VisitedBlocks.insert(&BB);
+ Changed = true;
+ }
+ LLVM_DEBUG(printBlockWeight(dbgs(), &BB));
+ }
+
+ return Changed;
+}
+
+/// Get the FunctionSamples for an instruction.
+///
+/// The FunctionSamples of an instruction \p Inst is the inlined instance
+/// in which that instruction is coming from. We traverse the inline stack
+/// of that instruction, and match it with the tree nodes in the profile.
+///
+/// \param Inst Instruction to query.
+///
+/// \returns the FunctionSamples pointer to the inlined instance.
+const FunctionSamples *SampleProfileLoaderBaseImpl::findFunctionSamples(
+ const Instruction &Inst) const {
+ const DILocation *DIL = Inst.getDebugLoc();
+ if (!DIL)
+ return Samples;
+
+ auto it = DILocation2SampleMap.try_emplace(DIL, nullptr);
+ if (it.second) {
+ it.first->second = Samples->findFunctionSamples(DIL, Reader->getRemapper());
+ }
+ return it.first->second;
+}
+
+/// Find equivalence classes for the given block.
+///
+/// This finds all the blocks that are guaranteed to execute the same
+/// number of times as \p BB1. To do this, it traverses all the
+/// descendants of \p BB1 in the dominator or post-dominator tree.
+///
+/// A block BB2 will be in the same equivalence class as \p BB1 if
+/// the following holds:
+///
+/// 1- \p BB1 is a descendant of BB2 in the opposite tree. So, if BB2
+/// is a descendant of \p BB1 in the dominator tree, then BB2 should
+/// dominate BB1 in the post-dominator tree.
+///
+/// 2- Both BB2 and \p BB1 must be in the same loop.
+///
+/// For every block BB2 that meets those two requirements, we set BB2's
+/// equivalence class to \p BB1.
+///
+/// \param BB1 Block to check.
+/// \param Descendants Descendants of \p BB1 in either the dom or pdom tree.
+/// \param DomTree Opposite dominator tree. If \p Descendants is filled
+/// with blocks from \p BB1's dominator tree, then
+/// this is the post-dominator tree, and vice versa.
+template <bool IsPostDom>
+void SampleProfileLoaderBaseImpl::findEquivalencesFor(
+ BasicBlock *BB1, ArrayRef<BasicBlock *> Descendants,
+ DominatorTreeBase<BasicBlock, IsPostDom> *DomTree) {
+ const BasicBlock *EC = EquivalenceClass[BB1];
+ uint64_t Weight = BlockWeights[EC];
+ for (const auto *BB2 : Descendants) {
+ bool IsDomParent = DomTree->dominates(BB2, BB1);
+ bool IsInSameLoop = LI->getLoopFor(BB1) == LI->getLoopFor(BB2);
+ if (BB1 != BB2 && IsDomParent && IsInSameLoop) {
+ EquivalenceClass[BB2] = EC;
+ // If BB2 is visited, then the entire EC should be marked as visited.
+ if (VisitedBlocks.count(BB2)) {
+ VisitedBlocks.insert(EC);
+ }
+
+ // If BB2 is heavier than BB1, make BB2 have the same weight
+ // as BB1.
+ //
+ // Note that we don't worry about the opposite situation here
+ // (when BB2 is lighter than BB1). We will deal with this
+ // during the propagation phase. Right now, we just want to
+ // make sure that BB1 has the largest weight of all the
+ // members of its equivalence set.
+ Weight = std::max(Weight, BlockWeights[BB2]);
+ }
+ }
+ if (EC == &EC->getParent()->getEntryBlock()) {
+ BlockWeights[EC] = Samples->getHeadSamples() + 1;
+ } else {
+ BlockWeights[EC] = Weight;
+ }
+}
+
+/// Find equivalence classes.
+///
+/// Since samples may be missing from blocks, we can fill in the gaps by setting
+/// the weights of all the blocks in the same equivalence class to the same
+/// weight. To compute the concept of equivalence, we use dominance and loop
+/// information. Two blocks B1 and B2 are in the same equivalence class if B1
+/// dominates B2, B2 post-dominates B1 and both are in the same loop.
+///
+/// \param F The function to query.
+void SampleProfileLoaderBaseImpl::findEquivalenceClasses(Function &F) {
+ SmallVector<BasicBlock *, 8> DominatedBBs;
+ LLVM_DEBUG(dbgs() << "\nBlock equivalence classes\n");
+ // Find equivalence sets based on dominance and post-dominance information.
+ for (auto &BB : F) {
+ BasicBlock *BB1 = &BB;
+
+ // Compute BB1's equivalence class once.
+ if (EquivalenceClass.count(BB1)) {
+ LLVM_DEBUG(printBlockEquivalence(dbgs(), BB1));
+ continue;
+ }
+
+ // By default, blocks are in their own equivalence class.
+ EquivalenceClass[BB1] = BB1;
+
+ // Traverse all the blocks dominated by BB1. We are looking for
+ // every basic block BB2 such that:
+ //
+ // 1- BB1 dominates BB2.
+ // 2- BB2 post-dominates BB1.
+ // 3- BB1 and BB2 are in the same loop nest.
+ //
+ // If all those conditions hold, it means that BB2 is executed
+ // as many times as BB1, so they are placed in the same equivalence
+ // class by making BB2's equivalence class be BB1.
+ DominatedBBs.clear();
+ DT->getDescendants(BB1, DominatedBBs);
+ findEquivalencesFor(BB1, DominatedBBs, PDT.get());
+
+ LLVM_DEBUG(printBlockEquivalence(dbgs(), BB1));
+ }
+
+ // Assign weights to equivalence classes.
+ //
+ // All the basic blocks in the same equivalence class will execute
+ // the same number of times. Since we know that the head block in
+ // each equivalence class has the largest weight, assign that weight
+ // to all the blocks in that equivalence class.
+ LLVM_DEBUG(
+ dbgs() << "\nAssign the same weight to all blocks in the same class\n");
+ for (auto &BI : F) {
+ const BasicBlock *BB = &BI;
+ const BasicBlock *EquivBB = EquivalenceClass[BB];
+ if (BB != EquivBB)
+ BlockWeights[BB] = BlockWeights[EquivBB];
+ LLVM_DEBUG(printBlockWeight(dbgs(), BB));
+ }
+}
+
+/// Visit the given edge to decide if it has a valid weight.
+///
+/// If \p E has not been visited before, we copy to \p UnknownEdge
+/// and increment the count of unknown edges.
+///
+/// \param E Edge to visit.
+/// \param NumUnknownEdges Current number of unknown edges.
+/// \param UnknownEdge Set if E has not been visited before.
+///
+/// \returns E's weight, if known. Otherwise, return 0.
+uint64_t SampleProfileLoaderBaseImpl::visitEdge(Edge E,
+ unsigned *NumUnknownEdges,
+ Edge *UnknownEdge) {
+ if (!VisitedEdges.count(E)) {
+ (*NumUnknownEdges)++;
+ *UnknownEdge = E;
+ return 0;
+ }
+
+ return EdgeWeights[E];
+}
+
+/// Propagate weights through incoming/outgoing edges.
+///
+/// If the weight of a basic block is known, and there is only one edge
+/// with an unknown weight, we can calculate the weight of that edge.
+///
+/// Similarly, if all the edges have a known count, we can calculate the
+/// count of the basic block, if needed.
+///
+/// \param F Function to process.
+/// \param UpdateBlockCount Whether we should update basic block counts that
+/// has already been annotated.
+///
+/// \returns True if new weights were assigned to edges or blocks.
+bool SampleProfileLoaderBaseImpl::propagateThroughEdges(Function &F,
+ bool UpdateBlockCount) {
+ bool Changed = false;
+ LLVM_DEBUG(dbgs() << "\nPropagation through edges\n");
+ for (const auto &BI : F) {
+ const BasicBlock *BB = &BI;
+ const BasicBlock *EC = EquivalenceClass[BB];
+
+ // Visit all the predecessor and successor edges to determine
+ // which ones have a weight assigned already. Note that it doesn't
+ // matter that we only keep track of a single unknown edge. The
+ // only case we are interested in handling is when only a single
+ // edge is unknown (see setEdgeOrBlockWeight).
+ for (unsigned i = 0; i < 2; i++) {
+ uint64_t TotalWeight = 0;
+ unsigned NumUnknownEdges = 0, NumTotalEdges = 0;
+ Edge UnknownEdge, SelfReferentialEdge, SingleEdge;
+
+ if (i == 0) {
+ // First, visit all predecessor edges.
+ NumTotalEdges = Predecessors[BB].size();
+ for (auto *Pred : Predecessors[BB]) {
+ Edge E = std::make_pair(Pred, BB);
+ TotalWeight += visitEdge(E, &NumUnknownEdges, &UnknownEdge);
+ if (E.first == E.second)
+ SelfReferentialEdge = E;
+ }
+ if (NumTotalEdges == 1) {
+ SingleEdge = std::make_pair(Predecessors[BB][0], BB);
+ }
+ } else {
+ // On the second round, visit all successor edges.
+ NumTotalEdges = Successors[BB].size();
+ for (auto *Succ : Successors[BB]) {
+ Edge E = std::make_pair(BB, Succ);
+ TotalWeight += visitEdge(E, &NumUnknownEdges, &UnknownEdge);
+ }
+ if (NumTotalEdges == 1) {
+ SingleEdge = std::make_pair(BB, Successors[BB][0]);
+ }
+ }
+
+ // After visiting all the edges, there are three cases that we
+ // can handle immediately:
+ //
+ // - All the edge weights are known (i.e., NumUnknownEdges == 0).
+ // In this case, we simply check that the sum of all the edges
+ // is the same as BB's weight. If not, we change BB's weight
+ // to match. Additionally, if BB had not been visited before,
+ // we mark it visited.
+ //
+ // - Only one edge is unknown and BB has already been visited.
+ // In this case, we can compute the weight of the edge by
+ // subtracting the total block weight from all the known
+ // edge weights. If the edges weight more than BB, then the
+ // edge of the last remaining edge is set to zero.
+ //
+ // - There exists a self-referential edge and the weight of BB is
+ // known. In this case, this edge can be based on BB's weight.
+ // We add up all the other known edges and set the weight on
+ // the self-referential edge as we did in the previous case.
+ //
+ // In any other case, we must continue iterating. Eventually,
+ // all edges will get a weight, or iteration will stop when
+ // it reaches SampleProfileMaxPropagateIterations.
+ if (NumUnknownEdges <= 1) {
+ uint64_t &BBWeight = BlockWeights[EC];
+ if (NumUnknownEdges == 0) {
+ if (!VisitedBlocks.count(EC)) {
+ // If we already know the weight of all edges, the weight of the
+ // basic block can be computed. It should be no larger than the sum
+ // of all edge weights.
+ if (TotalWeight > BBWeight) {
+ BBWeight = TotalWeight;
+ Changed = true;
+ LLVM_DEBUG(dbgs() << "All edge weights for " << BB->getName()
+ << " known. Set weight for block: ";
+ printBlockWeight(dbgs(), BB););
+ }
+ } else if (NumTotalEdges == 1 &&
+ EdgeWeights[SingleEdge] < BlockWeights[EC]) {
+ // If there is only one edge for the visited basic block, use the
+ // block weight to adjust edge weight if edge weight is smaller.
+ EdgeWeights[SingleEdge] = BlockWeights[EC];
+ Changed = true;
+ }
+ } else if (NumUnknownEdges == 1 && VisitedBlocks.count(EC)) {
+ // If there is a single unknown edge and the block has been
+ // visited, then we can compute E's weight.
+ if (BBWeight >= TotalWeight)
+ EdgeWeights[UnknownEdge] = BBWeight - TotalWeight;
+ else
+ EdgeWeights[UnknownEdge] = 0;
+ const BasicBlock *OtherEC;
+ if (i == 0)
+ OtherEC = EquivalenceClass[UnknownEdge.first];
+ else
+ OtherEC = EquivalenceClass[UnknownEdge.second];
+ // Edge weights should never exceed the BB weights it connects.
+ if (VisitedBlocks.count(OtherEC) &&
+ EdgeWeights[UnknownEdge] > BlockWeights[OtherEC])
+ EdgeWeights[UnknownEdge] = BlockWeights[OtherEC];
+ VisitedEdges.insert(UnknownEdge);
+ Changed = true;
+ LLVM_DEBUG(dbgs() << "Set weight for edge: ";
+ printEdgeWeight(dbgs(), UnknownEdge));
+ }
+ } else if (VisitedBlocks.count(EC) && BlockWeights[EC] == 0) {
+ // If a block Weights 0, all its in/out edges should weight 0.
+ if (i == 0) {
+ for (auto *Pred : Predecessors[BB]) {
+ Edge E = std::make_pair(Pred, BB);
+ EdgeWeights[E] = 0;
+ VisitedEdges.insert(E);
+ }
+ } else {
+ for (auto *Succ : Successors[BB]) {
+ Edge E = std::make_pair(BB, Succ);
+ EdgeWeights[E] = 0;
+ VisitedEdges.insert(E);
+ }
+ }
+ } else if (SelfReferentialEdge.first && VisitedBlocks.count(EC)) {
+ uint64_t &BBWeight = BlockWeights[BB];
+ // We have a self-referential edge and the weight of BB is known.
+ if (BBWeight >= TotalWeight)
+ EdgeWeights[SelfReferentialEdge] = BBWeight - TotalWeight;
+ else
+ EdgeWeights[SelfReferentialEdge] = 0;
+ VisitedEdges.insert(SelfReferentialEdge);
+ Changed = true;
+ LLVM_DEBUG(dbgs() << "Set self-referential edge weight to: ";
+ printEdgeWeight(dbgs(), SelfReferentialEdge));
+ }
+ if (UpdateBlockCount && !VisitedBlocks.count(EC) && TotalWeight > 0) {
+ BlockWeights[EC] = TotalWeight;
+ VisitedBlocks.insert(EC);
+ Changed = true;
+ }
+ }
+ }
+
+ return Changed;
+}
+
+/// Build in/out edge lists for each basic block in the CFG.
+///
+/// We are interested in unique edges. If a block B1 has multiple
+/// edges to another block B2, we only add a single B1->B2 edge.
+void SampleProfileLoaderBaseImpl::buildEdges(Function &F) {
+ for (auto &BI : F) {
+ BasicBlock *B1 = &BI;
+
+ // Add predecessors for B1.
+ SmallPtrSet<BasicBlock *, 16> Visited;
+ if (!Predecessors[B1].empty())
+ llvm_unreachable("Found a stale predecessors list in a basic block.");
+ for (BasicBlock *B2 : predecessors(B1))
+ if (Visited.insert(B2).second)
+ Predecessors[B1].push_back(B2);
+
+ // Add successors for B1.
+ Visited.clear();
+ if (!Successors[B1].empty())
+ llvm_unreachable("Found a stale successors list in a basic block.");
+ for (BasicBlock *B2 : successors(B1))
+ if (Visited.insert(B2).second)
+ Successors[B1].push_back(B2);
+ }
+}
+
+/// Propagate weights into edges
+///
+/// The following rules are applied to every block BB in the CFG:
+///
+/// - If BB has a single predecessor/successor, then the weight
+/// of that edge is the weight of the block.
+///
+/// - If all incoming or outgoing edges are known except one, and the
+/// weight of the block is already known, the weight of the unknown
+/// edge will be the weight of the block minus the sum of all the known
+/// edges. If the sum of all the known edges is larger than BB's weight,
+/// we set the unknown edge weight to zero.
+///
+/// - If there is a self-referential edge, and the weight of the block is
+/// known, the weight for that edge is set to the weight of the block
+/// minus the weight of the other incoming edges to that block (if
+/// known).
+void SampleProfileLoaderBaseImpl::propagateWeights(Function &F) {
+ bool Changed = true;
+ unsigned I = 0;
+
+ // If BB weight is larger than its corresponding loop's header BB weight,
+ // use the BB weight to replace the loop header BB weight.
+ for (auto &BI : F) {
+ BasicBlock *BB = &BI;
+ Loop *L = LI->getLoopFor(BB);
+ if (!L) {
+ continue;
+ }
+ BasicBlock *Header = L->getHeader();
+ if (Header && BlockWeights[BB] > BlockWeights[Header]) {
+ BlockWeights[Header] = BlockWeights[BB];
+ }
+ }
+
+ // Before propagation starts, build, for each block, a list of
+ // unique predecessors and successors. This is necessary to handle
+ // identical edges in multiway branches. Since we visit all blocks and all
+ // edges of the CFG, it is cleaner to build these lists once at the start
+ // of the pass.
+ buildEdges(F);
+
+ // Propagate until we converge or we go past the iteration limit.
+ while (Changed && I++ < SampleProfileMaxPropagateIterations) {
+ Changed = propagateThroughEdges(F, false);
+ }
+
+ // The first propagation propagates BB counts from annotated BBs to unknown
+ // BBs. The 2nd propagation pass resets edges weights, and use all BB weights
+ // to propagate edge weights.
+ VisitedEdges.clear();
+ Changed = true;
+ while (Changed && I++ < SampleProfileMaxPropagateIterations) {
+ Changed = propagateThroughEdges(F, false);
+ }
+
+ // The 3rd propagation pass allows adjust annotated BB weights that are
+ // obviously wrong.
+ Changed = true;
+ while (Changed && I++ < SampleProfileMaxPropagateIterations) {
+ Changed = propagateThroughEdges(F, true);
+ }
+}
+
+/// Generate branch weight metadata for all branches in \p F.
+///
+/// Branch weights are computed out of instruction samples using a
+/// propagation heuristic. Propagation proceeds in 3 phases:
+///
+/// 1- Assignment of block weights. All the basic blocks in the function
+/// are initial assigned the same weight as their most frequently
+/// executed instruction.
+///
+/// 2- Creation of equivalence classes. Since samples may be missing from
+/// blocks, we can fill in the gaps by setting the weights of all the
+/// blocks in the same equivalence class to the same weight. To compute
+/// the concept of equivalence, we use dominance and loop information.
+/// Two blocks B1 and B2 are in the same equivalence class if B1
+/// dominates B2, B2 post-dominates B1 and both are in the same loop.
+///
+/// 3- Propagation of block weights into edges. This uses a simple
+/// propagation heuristic. The following rules are applied to every
+/// block BB in the CFG:
+///
+/// - If BB has a single predecessor/successor, then the weight
+/// of that edge is the weight of the block.
+///
+/// - If all the edges are known except one, and the weight of the
+/// block is already known, the weight of the unknown edge will
+/// be the weight of the block minus the sum of all the known
+/// edges. If the sum of all the known edges is larger than BB's weight,
+/// we set the unknown edge weight to zero.
+///
+/// - If there is a self-referential edge, and the weight of the block is
+/// known, the weight for that edge is set to the weight of the block
+/// minus the weight of the other incoming edges to that block (if
+/// known).
+///
+/// Since this propagation is not guaranteed to finalize for every CFG, we
+/// only allow it to proceed for a limited number of iterations (controlled
+/// by -sample-profile-max-propagate-iterations).
+///
+/// FIXME: Try to replace this propagation heuristic with a scheme
+/// that is guaranteed to finalize. A work-list approach similar to
+/// the standard value propagation algorithm used by SSA-CCP might
+/// work here.
+///
+/// \param F The function to query.
+///
+/// \returns true if \p F was modified. Returns false, otherwise.
+bool SampleProfileLoaderBaseImpl::computeAndPropagateWeights(
+ Function &F, const DenseSet<GlobalValue::GUID> &InlinedGUIDs) {
+ bool Changed = (InlinedGUIDs.size() != 0);
+
+ // Compute basic block weights.
+ Changed |= computeBlockWeights(F);
+
+ if (Changed) {
+ // Add an entry count to the function using the samples gathered at the
+ // function entry.
+ // Sets the GUIDs that are inlined in the profiled binary. This is used
+ // for ThinLink to make correct liveness analysis, and also make the IR
+ // match the profiled binary before annotation.
+ F.setEntryCount(
+ ProfileCount(Samples->getHeadSamples() + 1, Function::PCT_Real),
+ &InlinedGUIDs);
+
+ // Compute dominance and loop info needed for propagation.
+ computeDominanceAndLoopInfo(F);
+
+ // Find equivalence classes.
+ findEquivalenceClasses(F);
+
+ // Propagate weights to all edges.
+ propagateWeights(F);
+ }
+
+ return Changed;
+}
+
+void SampleProfileLoaderBaseImpl::emitCoverageRemarks(Function &F) {
+ // If coverage checking was requested, compute it now.
+ if (SampleProfileRecordCoverage) {
+ unsigned Used = CoverageTracker.countUsedRecords(Samples, PSI);
+ unsigned Total = CoverageTracker.countBodyRecords(Samples, PSI);
+ unsigned Coverage = CoverageTracker.computeCoverage(Used, Total);
+ if (Coverage < SampleProfileRecordCoverage) {
+ F.getContext().diagnose(DiagnosticInfoSampleProfile(
+ F.getSubprogram()->getFilename(), getFunctionLoc(F),
+ Twine(Used) + " of " + Twine(Total) + " available profile records (" +
+ Twine(Coverage) + "%) were applied",
+ DS_Warning));
+ }
+ }
+
+ if (SampleProfileSampleCoverage) {
+ uint64_t Used = CoverageTracker.getTotalUsedSamples();
+ uint64_t Total = CoverageTracker.countBodySamples(Samples, PSI);
+ unsigned Coverage = CoverageTracker.computeCoverage(Used, Total);
+ if (Coverage < SampleProfileSampleCoverage) {
+ F.getContext().diagnose(DiagnosticInfoSampleProfile(
+ F.getSubprogram()->getFilename(), getFunctionLoc(F),
+ Twine(Used) + " of " + Twine(Total) + " available profile samples (" +
+ Twine(Coverage) + "%) were applied",
+ DS_Warning));
+ }
+ }
+}
+
+/// Get the line number for the function header.
+///
+/// This looks up function \p F in the current compilation unit and
+/// retrieves the line number where the function is defined. This is
+/// line 0 for all the samples read from the profile file. Every line
+/// number is relative to this line.
+///
+/// \param F Function object to query.
+///
+/// \returns the line number where \p F is defined. If it returns 0,
+/// it means that there is no debug information available for \p F.
+unsigned SampleProfileLoaderBaseImpl::getFunctionLoc(Function &F) {
+ if (DISubprogram *S = F.getSubprogram())
+ return S->getLine();
+
+ if (NoWarnSampleUnused)
+ return 0;
+
+ // If the start of \p F is missing, emit a diagnostic to inform the user
+ // about the missed opportunity.
+ F.getContext().diagnose(DiagnosticInfoSampleProfile(
+ "No debug information found in function " + F.getName() +
+ ": Function profile not used",
+ DS_Warning));
+ return 0;
+}
+
+void SampleProfileLoaderBaseImpl::computeDominanceAndLoopInfo(Function &F) {
+ DT.reset(new DominatorTree);
+ DT->recalculate(F);
+
+ PDT.reset(new PostDominatorTree(F));
+
+ LI.reset(new LoopInfo);
+ LI->analyze(*DT);
+}
+
+#undef DEBUG_TYPE
+
+} // namespace llvm
+#endif // LLVM_TRANSFORMS_IPO_SAMPLEPROFILELOADERIMPL_H
diff --git a/llvm/include/llvm/ProfileData/SampleProfileLoaderBaseUtil.h b/llvm/include/llvm/ProfileData/SampleProfileLoaderBaseUtil.h
new file mode 100644
index 000000000000..37dc8d8187d9
--- /dev/null
+++ b/llvm/include/llvm/ProfileData/SampleProfileLoaderBaseUtil.h
@@ -0,0 +1,97 @@
+////===- SampleProfileLoadBaseUtil.h - Profile loader util func --*- C++-*-===//
+//
+// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
+// See https://llvm.org/LICENSE.txt for license information.
+// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
+//
+//===----------------------------------------------------------------------===//
+//
+/// \file
+/// This file provides the utility functions for the sampled PGO loader base
+/// implementation.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_TRANSFORMS_IPO_SAMPLEPROFILELOADERUTIL_H
+#define LLVM_TRANSFORMS_IPO_SAMPLEPROFILELOADERUTIL_H
+
+#include "llvm/ADT/DenseMap.h"
+#include "llvm/Analysis/ProfileSummaryInfo.h"
+#include "llvm/IR/BasicBlock.h"
+#include "llvm/IR/CFG.h"
+#include "llvm/IR/DebugLoc.h"
+#include "llvm/IR/Function.h"
+#include "llvm/ProfileData/SampleProf.h"
+#include "llvm/Support/CommandLine.h"
+
+namespace llvm {
+using namespace sampleprof;
+
+extern cl::opt<unsigned> SampleProfileMaxPropagateIterations;
+extern cl::opt<unsigned> SampleProfileRecordCoverage;
+extern cl::opt<unsigned> SampleProfileSampleCoverage;
+extern cl::opt<bool> NoWarnSampleUnused;
+
+namespace sampleprofutil {
+
+class SampleCoverageTracker {
+public:
+ bool markSamplesUsed(const FunctionSamples *FS, uint32_t LineOffset,
+ uint32_t Discriminator, uint64_t Samples);
+ unsigned computeCoverage(unsigned Used, unsigned Total) const;
+ unsigned countUsedRecords(const FunctionSamples *FS,
+ ProfileSummaryInfo *PSI) const;
+ unsigned countBodyRecords(const FunctionSamples *FS,
+ ProfileSummaryInfo *PSI) const;
+ uint64_t getTotalUsedSamples() const { return TotalUsedSamples; }
+ uint64_t countBodySamples(const FunctionSamples *FS,
+ ProfileSummaryInfo *PSI) const;
+
+ void clear() {
+ SampleCoverage.clear();
+ TotalUsedSamples = 0;
+ }
+ void setProfAccForSymsInList(bool V) { ProfAccForSymsInList = V; }
+
+private:
+ using BodySampleCoverageMap = std::map<LineLocation, unsigned>;
+ using FunctionSamplesCoverageMap =
+ DenseMap<const FunctionSamples *, BodySampleCoverageMap>;
+
+ /// Coverage map for sampling records.
+ ///
+ /// This map keeps a record of sampling records that have been matched to
+ /// an IR instruction. This is used to detect some form of staleness in
+ /// profiles (see flag -sample-profile-check-coverage).
+ ///
+ /// Each entry in the map corresponds to a FunctionSamples instance. This is
+ /// another map that counts how many times the sample record at the
+ /// given location has been used.
+ FunctionSamplesCoverageMap SampleCoverage;
+
+ /// Number of samples used from the profile.
+ ///
+ /// When a sampling record is used for the first time, the samples from
+ /// that record are added to this accumulator. Coverage is later computed
+ /// based on the total number of samples available in this function and
+ /// its callsites.
+ ///
+ /// Note that this accumulator tracks samples used from a single function
+ /// and all the inlined callsites. Strictly, we should have a map of counters
+ /// keyed by FunctionSamples pointers, but these stats are cleared after
+ /// every function, so we just need to keep a single counter.
+ uint64_t TotalUsedSamples = 0;
+
+ // For symbol in profile symbol list, whether to regard their profiles
+ // to be accurate. This is passed from the SampleLoader instance.
+ bool ProfAccForSymsInList = false;
+};
+
+/// Return true if the given callsite is hot wrt to hot cutoff threshold.
+bool callsiteIsHot(const FunctionSamples *CallsiteFS, ProfileSummaryInfo *PSI,
+ bool ProfAccForSymsInList);
+
+} // end of namespace sampleprofutil
+} // end of namespace llvm
+
+#endif // LLVM_TRANSFORMS_IPO_SAMPLEPROFILELOADERUTIL_H
diff --git a/llvm/lib/ProfileData/CMakeLists.txt b/llvm/lib/ProfileData/CMakeLists.txt
index 2a377e4d74d3..4125fac918ab 100644
--- a/llvm/lib/ProfileData/CMakeLists.txt
+++ b/llvm/lib/ProfileData/CMakeLists.txt
@@ -5,6 +5,7 @@ add_llvm_component_library(LLVMProfileData
InstrProfWriter.cpp
ProfileSummaryBuilder.cpp
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O2 - Build # 15 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2
Culprit:
<cut>
commit a0a9c9e188f5b97ff8b74287d1536f57ec5dda54
Author: Sanjay Patel <spatel(a)rotateright.com>
Date: Wed Aug 11 12:41:47 2021 -0400
[InstCombine] avoid breaking up min/max (cmp+sel) idioms
This is a quick fix for a motivating case that looks like this:
https://godbolt.org/z/GeMqzMc38
As noted, we might be able to restore the min/max patterns
with select folds, or we just wait for this to become easier
with canonicalization to min/max intrinsics.
</cut>
Results regressed to (for first_bad == a0a9c9e188f5b97ff8b74287d1536f57ec5dda54)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2 artifacts/build-a0a9c9e188f5b97ff8b74287d1536f57ec5dda54/results_id:
1
# 464.h264ref,h264ref_base.default regressed by 106
# 464.h264ref,[.] FastFullPelBlockMotionSearch regressed by 146
from (for last_good == 5bf4ab0e79e1a8552019918a662bdf7af8b3825a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2 artifacts/build-5bf4ab0e79e1a8552019918a662bdf7af8b3825a/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/3875
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/3877
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-a0a9c9e188f5b97ff8b74287d1536f57ec5dda54
cd investigate-llvm-a0a9c9e188f5b97ff8b74287d1536f57ec5dda54
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach a0a9c9e188f5b97ff8b74287d1536f57ec5dda54
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 5bf4ab0e79e1a8552019918a662bdf7af8b3825a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit a0a9c9e188f5b97ff8b74287d1536f57ec5dda54
Author: Sanjay Patel <spatel(a)rotateright.com>
Date: Wed Aug 11 12:41:47 2021 -0400
[InstCombine] avoid breaking up min/max (cmp+sel) idioms
This is a quick fix for a motivating case that looks like this:
https://godbolt.org/z/GeMqzMc38
As noted, we might be able to restore the min/max patterns
with select folds, or we just wait for this to become easier
with canonicalization to min/max intrinsics.
---
llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp | 12 +++++++++---
llvm/test/Transforms/InstCombine/icmp-add.ll | 13 ++++++-------
2 files changed, 15 insertions(+), 10 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
index 2e20bca300d3..71037616585c 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCompares.cpp
@@ -5755,9 +5755,6 @@ Instruction *InstCombinerImpl::visitICmpInst(ICmpInst &I) {
if (Instruction *Res = foldICmpWithDominatingICmp(I))
return Res;
- if (Instruction *Res = foldICmpBinOp(I, Q))
- return Res;
-
if (Instruction *Res = foldICmpUsingKnownBits(I))
return Res;
@@ -5803,6 +5800,15 @@ Instruction *InstCombinerImpl::visitICmpInst(ICmpInst &I) {
}
}
+ // The folds in here may rely on wrapping flags and special constants, so
+ // they can break up min/max idioms in some cases but not seemingly similar
+ // patterns.
+ // FIXME: It may be possible to enhance select folding to make this
+ // unnecessary. It may also be moot if we canonicalize to min/max
+ // intrinsics.
+ if (Instruction *Res = foldICmpBinOp(I, Q))
+ return Res;
+
if (Instruction *Res = foldICmpInstWithConstant(I))
return Res;
diff --git a/llvm/test/Transforms/InstCombine/icmp-add.ll b/llvm/test/Transforms/InstCombine/icmp-add.ll
index 187e0ad1a31b..1750b5685c50 100644
--- a/llvm/test/Transforms/InstCombine/icmp-add.ll
+++ b/llvm/test/Transforms/InstCombine/icmp-add.ll
@@ -972,7 +972,6 @@ define i1 @slt_offset_nsw(i8 %a, i8 %c) {
ret i1 %ov
}
-; FIXME:
; In the following 4 tests, we could push the inc/dec
; through the min/max, but we should not break up the
; min/max idiom by using different icmp and select
@@ -980,9 +979,9 @@ define i1 @slt_offset_nsw(i8 %a, i8 %c) {
define i32 @increment_max(i32 %x) {
; CHECK-LABEL: @increment_max(
-; CHECK-NEXT: [[A:%.*]] = add nsw i32 [[X:%.*]], 1
-; CHECK-NEXT: [[C_INV:%.*]] = icmp slt i32 [[X]], 0
-; CHECK-NEXT: [[S:%.*]] = select i1 [[C_INV]], i32 0, i32 [[A]]
+; CHECK-NEXT: [[TMP1:%.*]] = icmp sgt i32 [[X:%.*]], -1
+; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 -1
+; CHECK-NEXT: [[S:%.*]] = add nsw i32 [[TMP2]], 1
; CHECK-NEXT: ret i32 [[S]]
;
%a = add nsw i32 %x, 1
@@ -1019,9 +1018,9 @@ define i32 @increment_min(i32 %x) {
define i32 @decrement_min(i32 %x) {
; CHECK-LABEL: @decrement_min(
-; CHECK-NEXT: [[A:%.*]] = add nsw i32 [[X:%.*]], -1
-; CHECK-NEXT: [[C_INV:%.*]] = icmp sgt i32 [[X]], 0
-; CHECK-NEXT: [[S:%.*]] = select i1 [[C_INV]], i32 0, i32 [[A]]
+; CHECK-NEXT: [[TMP1:%.*]] = icmp slt i32 [[X:%.*]], 1
+; CHECK-NEXT: [[TMP2:%.*]] = select i1 [[TMP1]], i32 [[X]], i32 1
+; CHECK-NEXT: [[S:%.*]] = add nsw i32 [[TMP2]], -1
; CHECK-NEXT: ret i32 [[S]]
;
%a = add nsw i32 %x, -1
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Os - Build # 4 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Os. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Os
Culprit:
<cut>
commit dae7adda949993bd96aa50c551dc64ddebba7923
Author: Matt Jacobson <mhjacobson(a)me.com>
Date: Fri Aug 6 10:12:00 2021 +0800
[AVR][clang] Pass '-fno-use-init-array' to cc1 as default
On AVR, '.ctors' is used, not '.init_array'. Make this the default
unless specifically overridden by driver argument.
This matches gcc, and it matches the behavior in (e.g.) the NetBSD
driver (for certain OS variants).
Reviewed by: MaskRay
Differential Revision: https://reviews.llvm.org/D107610
</cut>
Results regressed to (for first_bad == dae7adda949993bd96aa50c551dc64ddebba7923)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os artifacts/build-dae7adda949993bd96aa50c551dc64ddebba7923/results_id:
1
# 400.perlbench,perlbench_base.default regressed by 94393
# 453.povray,povray_base.default regressed by 102
# 470.lbm,lbm_base.default regressed by 103
# 470.lbm,[.] LBM_performStreamCollide regressed by 118
from (for last_good == 66b1e629d89543cb7542c184f7dfb32deee732e1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os artifacts/build-66b1e629d89543cb7542c184f7dfb32deee732e1/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Os/3855
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Os/3852
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-dae7adda949993bd96aa50c551dc64ddebba7923
cd investigate-llvm-dae7adda949993bd96aa50c551dc64ddebba7923
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach dae7adda949993bd96aa50c551dc64ddebba7923
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 66b1e629d89543cb7542c184f7dfb32deee732e1
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit dae7adda949993bd96aa50c551dc64ddebba7923
Author: Matt Jacobson <mhjacobson(a)me.com>
Date: Fri Aug 6 10:12:00 2021 +0800
[AVR][clang] Pass '-fno-use-init-array' to cc1 as default
On AVR, '.ctors' is used, not '.init_array'. Make this the default
unless specifically overridden by driver argument.
This matches gcc, and it matches the behavior in (e.g.) the NetBSD
driver (for certain OS variants).
Reviewed by: MaskRay
Differential Revision: https://reviews.llvm.org/D107610
---
clang/lib/Driver/ToolChains/AVR.cpp | 10 ++++++++++
clang/lib/Driver/ToolChains/AVR.h | 7 ++++++-
clang/test/Driver/avr-toolchain.c | 2 +-
3 files changed, 17 insertions(+), 2 deletions(-)
diff --git a/clang/lib/Driver/ToolChains/AVR.cpp b/clang/lib/Driver/ToolChains/AVR.cpp
index 5b097f9b2ed9..18c6f41e22b1 100644
--- a/clang/lib/Driver/ToolChains/AVR.cpp
+++ b/clang/lib/Driver/ToolChains/AVR.cpp
@@ -370,6 +370,16 @@ void AVRToolChain::AddClangSystemIncludeArgs(const ArgList &DriverArgs,
addSystemInclude(DriverArgs, CC1Args, AVRInc);
}
+void AVRToolChain::addClangTargetOptions(
+ const llvm::opt::ArgList &DriverArgs, llvm::opt::ArgStringList &CC1Args,
+ Action::OffloadKind DeviceOffloadKind) const {
+ // By default, use `.ctors` (not `.init_array`), as required by libgcc, which
+ // runs constructors/destructors on AVR.
+ if (!DriverArgs.hasFlag(options::OPT_fuse_init_array,
+ options::OPT_fno_use_init_array, false))
+ CC1Args.push_back("-fno-use-init-array");
+}
+
Tool *AVRToolChain::buildLinker() const {
return new tools::AVR::Linker(getTriple(), *this, LinkStdlib);
}
diff --git a/clang/lib/Driver/ToolChains/AVR.h b/clang/lib/Driver/ToolChains/AVR.h
index f612aa691182..2d027957ed76 100644
--- a/clang/lib/Driver/ToolChains/AVR.h
+++ b/clang/lib/Driver/ToolChains/AVR.h
@@ -11,8 +11,8 @@
#include "Gnu.h"
#include "clang/Driver/InputInfo.h"
-#include "clang/Driver/ToolChain.h"
#include "clang/Driver/Tool.h"
+#include "clang/Driver/ToolChain.h"
namespace clang {
namespace driver {
@@ -26,6 +26,11 @@ public:
AddClangSystemIncludeArgs(const llvm::opt::ArgList &DriverArgs,
llvm::opt::ArgStringList &CC1Args) const override;
+ void
+ addClangTargetOptions(const llvm::opt::ArgList &DriverArgs,
+ llvm::opt::ArgStringList &CC1Args,
+ Action::OffloadKind DeviceOffloadKind) const override;
+
protected:
Tool *buildLinker() const override;
diff --git a/clang/test/Driver/avr-toolchain.c b/clang/test/Driver/avr-toolchain.c
index 692063dc2c34..877f650a3d02 100644
--- a/clang/test/Driver/avr-toolchain.c
+++ b/clang/test/Driver/avr-toolchain.c
@@ -1,7 +1,7 @@
// A basic clang -cc1 command-line.
// RUN: %clang %s -### -no-canonical-prefixes -target avr 2>&1 | FileCheck -check-prefix=CC1 %s
-// CC1: clang{{.*}} "-cc1" "-triple" "avr"
+// CC1: clang{{.*}} "-cc1" "-triple" "avr" {{.*}} "-fno-use-init-array"
// RUN: %clang %s -### -no-canonical-prefixes -target avr --sysroot %S/Inputs/basic_avr_tree 2>&1 | FileCheck -check-prefix CC1A %s
// CC1A: clang{{.*}} "-cc1" "-triple" "avr" {{.*}} "-internal-isystem" {{".*avr/include"}}
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3 - Build # 9 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3
Culprit:
<cut>
commit cd6de0e8de4a5fd558580be4b1a07116914fc8ed
Author: Sjoerd Meijer <sjoerd.meijer(a)arm.com>
Date: Fri Feb 12 15:15:05 2021 +0000
[TTI] Unify FavorPostInc and FavorBackedgeIndex into getPreferredAddressingMode
This refactors shouldFavorPostInc() and shouldFavorBackedgeIndex() into
getPreferredAddressingMode() so that we have one interface to steer LSR in
generating the preferred addressing mode.
Differential Revision: https://reviews.llvm.org/D96600
</cut>
Results regressed to (for first_bad == cd6de0e8de4a5fd558580be4b1a07116914fc8ed)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-cd6de0e8de4a5fd558580be4b1a07116914fc8ed/results_id:
1
# 482.sphinx3,sphinx_livepretend_base.default regressed by 103
# 482.sphinx3,[.] vector_gautbl_eval_logs3 regressed by 111
from (for last_good == 4bd5bd40094c7b8b691cf394d813efc48d82acfd)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-4bd5bd40094c7b8b691cf394d813efc48d82acfd/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/3835
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/3840
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-cd6de0e8de4a5fd558580be4b1a07116914fc8ed
cd investigate-llvm-cd6de0e8de4a5fd558580be4b1a07116914fc8ed
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach cd6de0e8de4a5fd558580be4b1a07116914fc8ed
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 4bd5bd40094c7b8b691cf394d813efc48d82acfd
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit cd6de0e8de4a5fd558580be4b1a07116914fc8ed
Author: Sjoerd Meijer <sjoerd.meijer(a)arm.com>
Date: Fri Feb 12 15:15:05 2021 +0000
[TTI] Unify FavorPostInc and FavorBackedgeIndex into getPreferredAddressingMode
This refactors shouldFavorPostInc() and shouldFavorBackedgeIndex() into
getPreferredAddressingMode() so that we have one interface to steer LSR in
generating the preferred addressing mode.
Differential Revision: https://reviews.llvm.org/D96600
---
llvm/include/llvm/Analysis/TargetTransformInfo.h | 25 ++++++++++++----------
.../llvm/Analysis/TargetTransformInfoImpl.h | 7 +++---
llvm/lib/Analysis/TargetTransformInfo.cpp | 10 ++++-----
llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp | 22 ++++++++++---------
llvm/lib/Target/ARM/ARMTargetTransformInfo.h | 4 ++--
.../Target/Hexagon/HexagonTargetTransformInfo.cpp | 5 +++--
.../Target/Hexagon/HexagonTargetTransformInfo.h | 3 ++-
llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp | 24 ++++++++++++---------
8 files changed, 55 insertions(+), 45 deletions(-)
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfo.h b/llvm/include/llvm/Analysis/TargetTransformInfo.h
index c3d7d2cc80a4..79303dab92a2 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfo.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfo.h
@@ -638,13 +638,15 @@ public:
DominatorTree *DT, AssumptionCache *AC,
TargetLibraryInfo *LibInfo) const;
- /// \return True is LSR should make efforts to create/preserve post-inc
- /// addressing mode expressions.
- bool shouldFavorPostInc() const;
+ enum AddressingModeKind {
+ AMK_PreIndexed,
+ AMK_PostIndexed,
+ AMK_None
+ };
- /// Return true if LSR should make efforts to generate indexed addressing
- /// modes that operate across loop iterations.
- bool shouldFavorBackedgeIndex(const Loop *L) const;
+ /// Return the preferred addressing mode LSR should make efforts to generate.
+ AddressingModeKind getPreferredAddressingMode(const Loop *L,
+ ScalarEvolution *SE) const;
/// Return true if the target supports masked store.
bool isLegalMaskedStore(Type *DataType, Align Alignment) const;
@@ -1454,8 +1456,8 @@ public:
virtual bool canSaveCmp(Loop *L, BranchInst **BI, ScalarEvolution *SE,
LoopInfo *LI, DominatorTree *DT, AssumptionCache *AC,
TargetLibraryInfo *LibInfo) = 0;
- virtual bool shouldFavorPostInc() const = 0;
- virtual bool shouldFavorBackedgeIndex(const Loop *L) const = 0;
+ virtual AddressingModeKind
+ getPreferredAddressingMode(const Loop *L, ScalarEvolution *SE) const = 0;
virtual bool isLegalMaskedStore(Type *DataType, Align Alignment) = 0;
virtual bool isLegalMaskedLoad(Type *DataType, Align Alignment) = 0;
virtual bool isLegalNTStore(Type *DataType, Align Alignment) = 0;
@@ -1796,9 +1798,10 @@ public:
TargetLibraryInfo *LibInfo) override {
return Impl.canSaveCmp(L, BI, SE, LI, DT, AC, LibInfo);
}
- bool shouldFavorPostInc() const override { return Impl.shouldFavorPostInc(); }
- bool shouldFavorBackedgeIndex(const Loop *L) const override {
- return Impl.shouldFavorBackedgeIndex(L);
+ AddressingModeKind
+ getPreferredAddressingMode(const Loop *L,
+ ScalarEvolution *SE) const override {
+ return Impl.getPreferredAddressingMode(L, SE);
}
bool isLegalMaskedStore(Type *DataType, Align Alignment) override {
return Impl.isLegalMaskedStore(DataType, Alignment);
diff --git a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
index 84de5038df42..a9c9d3cb9f4f 100644
--- a/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
+++ b/llvm/include/llvm/Analysis/TargetTransformInfoImpl.h
@@ -209,9 +209,10 @@ public:
return false;
}
- bool shouldFavorPostInc() const { return false; }
-
- bool shouldFavorBackedgeIndex(const Loop *L) const { return false; }
+ TTI::AddressingModeKind
+ getPreferredAddressingMode(const Loop *L, ScalarEvolution *SE) const {
+ return TTI::AMK_None;
+ }
bool isLegalMaskedStore(Type *DataType, Align Alignment) const {
return false;
diff --git a/llvm/lib/Analysis/TargetTransformInfo.cpp b/llvm/lib/Analysis/TargetTransformInfo.cpp
index 16992d099e0a..3db4b0b0d553 100644
--- a/llvm/lib/Analysis/TargetTransformInfo.cpp
+++ b/llvm/lib/Analysis/TargetTransformInfo.cpp
@@ -409,12 +409,10 @@ bool TargetTransformInfo::canSaveCmp(Loop *L, BranchInst **BI,
return TTIImpl->canSaveCmp(L, BI, SE, LI, DT, AC, LibInfo);
}
-bool TargetTransformInfo::shouldFavorPostInc() const {
- return TTIImpl->shouldFavorPostInc();
-}
-
-bool TargetTransformInfo::shouldFavorBackedgeIndex(const Loop *L) const {
- return TTIImpl->shouldFavorBackedgeIndex(L);
+TTI::AddressingModeKind
+TargetTransformInfo::getPreferredAddressingMode(const Loop *L,
+ ScalarEvolution *SE) const {
+ return TTIImpl->getPreferredAddressingMode(L, SE);
}
bool TargetTransformInfo::isLegalMaskedStore(Type *DataType,
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index 80f1f2a2a8f7..8c2a79efc674 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -100,18 +100,20 @@ bool ARMTTIImpl::areInlineCompatible(const Function *Caller,
return MatchExact && MatchSubset;
}
-bool ARMTTIImpl::shouldFavorBackedgeIndex(const Loop *L) const {
- if (L->getHeader()->getParent()->hasOptSize())
- return false;
+TTI::AddressingModeKind
+ARMTTIImpl::getPreferredAddressingMode(const Loop *L,
+ ScalarEvolution *SE) const {
if (ST->hasMVEIntegerOps())
- return false;
- return ST->isMClass() && ST->isThumb2() && L->getNumBlocks() == 1;
-}
+ return TTI::AMK_PostIndexed;
-bool ARMTTIImpl::shouldFavorPostInc() const {
- if (ST->hasMVEIntegerOps())
- return true;
- return false;
+ if (L->getHeader()->getParent()->hasOptSize())
+ return TTI::AMK_None;
+
+ if (ST->isMClass() && ST->isThumb2() &&
+ L->getNumBlocks() == 1)
+ return TTI::AMK_PreIndexed;
+
+ return TTI::AMK_None;
}
Optional<Instruction *>
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
index b8de27101a61..808128929000 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.h
@@ -103,8 +103,8 @@ public:
bool enableInterleavedAccessVectorization() { return true; }
- bool shouldFavorBackedgeIndex(const Loop *L) const;
- bool shouldFavorPostInc() const;
+ TTI::AddressingModeKind
+ getPreferredAddressingMode(const Loop *L, ScalarEvolution *SE) const;
/// Floating-point computation using ARMv8 AArch32 Advanced
/// SIMD instructions remains unchanged from ARMv7. Only AArch64 SIMD
diff --git a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp
index af7bc4682249..89e7df0aa27e 100644
--- a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp
+++ b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.cpp
@@ -80,8 +80,9 @@ void HexagonTTIImpl::getPeelingPreferences(Loop *L, ScalarEvolution &SE,
}
}
-bool HexagonTTIImpl::shouldFavorPostInc() const {
- return true;
+AddressingModeKind::getPreferredAddressingMode(const Loop *L,
+ ScalarEvolution *SE) const {
+ return AMK_PostIndexed;
}
/// --- Vector TTI begin ---
diff --git a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h
index dc075d6147b6..ebaa619837f0 100644
--- a/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h
+++ b/llvm/lib/Target/Hexagon/HexagonTargetTransformInfo.h
@@ -67,7 +67,8 @@ public:
TTI::PeelingPreferences &PP);
/// Bias LSR towards creating post-increment opportunities.
- bool shouldFavorPostInc() const;
+ AddressingModeKind getPreferredAddressingMode(const Loop *L,
+ ScalarEvolution *SE) const;
// L1 cache prefetch.
unsigned getPrefetchDistance() const override;
diff --git a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
index 5dec9b542076..2f90df70a3c3 100644
--- a/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
+++ b/llvm/lib/Transforms/Scalar/LoopStrengthReduce.cpp
@@ -1227,13 +1227,15 @@ static unsigned getSetupCost(const SCEV *Reg, unsigned Depth) {
/// Tally up interesting quantities from the given register.
void Cost::RateRegister(const Formula &F, const SCEV *Reg,
SmallPtrSetImpl<const SCEV *> &Regs) {
+ TTI::AddressingModeKind AMK = TTI->getPreferredAddressingMode(L, SE);
+
if (const SCEVAddRecExpr *AR = dyn_cast<SCEVAddRecExpr>(Reg)) {
// If this is an addrec for another loop, it should be an invariant
// with respect to L since L is the innermost loop (at least
// for now LSR only handles innermost loops).
if (AR->getLoop() != L) {
// If the AddRec exists, consider it's register free and leave it alone.
- if (isExistingPhi(AR, *SE) && !TTI->shouldFavorPostInc())
+ if (isExistingPhi(AR, *SE) && AMK != TTI::AMK_PostIndexed)
return;
// It is bad to allow LSR for current loop to add induction variables
@@ -1254,13 +1256,11 @@ void Cost::RateRegister(const Formula &F, const SCEV *Reg,
// If the step size matches the base offset, we could use pre-indexed
// addressing.
- if (TTI->shouldFavorBackedgeIndex(L)) {
+ if (AMK == TTI::AMK_PreIndexed) {
if (auto *Step = dyn_cast<SCEVConstant>(AR->getStepRecurrence(*SE)))
if (Step->getAPInt() == F.BaseOffset)
LoopCost = 0;
- }
-
- if (TTI->shouldFavorPostInc()) {
+ } else if (AMK == TTI::AMK_PostIndexed) {
const SCEV *LoopStep = AR->getStepRecurrence(*SE);
if (isa<SCEVConstant>(LoopStep)) {
const SCEV *LoopStart = AR->getStart();
@@ -3575,7 +3575,8 @@ void LSRInstance::GenerateReassociationsImpl(LSRUse &LU, unsigned LUIdx,
// may generate a post-increment operator. The reason is that the
// reassociations cause extra base+register formula to be created,
// and possibly chosen, but the post-increment is more efficient.
- if (TTI.shouldFavorPostInc() && mayUsePostIncMode(TTI, LU, BaseReg, L, SE))
+ TTI::AddressingModeKind AMK = TTI.getPreferredAddressingMode(L, &SE);
+ if (AMK == TTI::AMK_PostIndexed && mayUsePostIncMode(TTI, LU, BaseReg, L, SE))
return;
SmallVector<const SCEV *, 8> AddOps;
const SCEV *Remainder = CollectSubexprs(BaseReg, nullptr, AddOps, L, SE);
@@ -4239,7 +4240,8 @@ void LSRInstance::GenerateCrossUseConstantOffsets() {
NewF.BaseOffset = (uint64_t)NewF.BaseOffset + Imm;
if (!isLegalUse(TTI, LU.MinOffset, LU.MaxOffset,
LU.Kind, LU.AccessTy, NewF)) {
- if (TTI.shouldFavorPostInc() &&
+ if (TTI.getPreferredAddressingMode(this->L, &SE) ==
+ TTI::AMK_PostIndexed &&
mayUsePostIncMode(TTI, LU, OrigReg, this->L, SE))
continue;
if (!TTI.isLegalAddImmediate((uint64_t)NewF.UnfoldedOffset + Imm))
@@ -4679,7 +4681,7 @@ void LSRInstance::NarrowSearchSpaceByFilterFormulaWithSameScaledReg() {
/// If we are over the complexity limit, filter out any post-inc prefering
/// variables to only post-inc values.
void LSRInstance::NarrowSearchSpaceByFilterPostInc() {
- if (!TTI.shouldFavorPostInc())
+ if (TTI.getPreferredAddressingMode(L, &SE) != TTI::AMK_PostIndexed)
return;
if (EstimateSearchSpaceComplexity() < ComplexityLimit)
return;
@@ -4978,7 +4980,8 @@ void LSRInstance::SolveRecurse(SmallVectorImpl<const Formula *> &Solution,
// This can sometimes (notably when trying to favour postinc) lead to
// sub-optimial decisions. There it is best left to the cost modelling to
// get correct.
- if (!TTI.shouldFavorPostInc() || LU.Kind != LSRUse::Address) {
+ if (TTI.getPreferredAddressingMode(L, &SE) != TTI::AMK_PostIndexed ||
+ LU.Kind != LSRUse::Address) {
int NumReqRegsToFind = std::min(F.getNumRegs(), ReqRegs.size());
for (const SCEV *Reg : ReqRegs) {
if ((F.ScaledReg && F.ScaledReg == Reg) ||
@@ -5560,7 +5563,8 @@ LSRInstance::LSRInstance(Loop *L, IVUsers &IU, ScalarEvolution &SE,
TargetLibraryInfo &TLI, MemorySSAUpdater *MSSAU)
: IU(IU), SE(SE), DT(DT), LI(LI), AC(AC), TLI(TLI), TTI(TTI), L(L),
MSSAU(MSSAU), FavorBackedgeIndex(EnableBackedgeIndexing &&
- TTI.shouldFavorBackedgeIndex(L)) {
+ TTI.getPreferredAddressingMode(L, &SE) ==
+ TTI::AMK_PreIndexed) {
// If LoopSimplify form is not available, stay out of trouble.
if (!L->isLoopSimplifyForm())
return;
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-master-aarch64-lts-allmodconfig - Build # 6 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-master-aarch64-lts-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-master-aarch64-lts-allmodconfig
Culprit:
<cut>
commit 132a8267adabd645476b542b3b132c1b91988fe8
Author: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Date: Thu Aug 12 13:22:21 2021 +0200
Linux 5.10.58
Link: https://lore.kernel.org/r/20210810172955.660225700@linuxfoundation.org
Tested-by: Fox Chen <foxhlchen(a)gmail.com>
Tested-by: Hulk Robot <hulkrobot(a)huawei.com>
Tested-by: Sudip Mukherjee <sudip.mukherjee(a)codethink.co.uk>
Tested-by: Linux Kernel Functional Testing <lkft(a)linaro.org>
Tested-by: Guenter Roeck <linux(a)roeck-us.net>
Tested-by: Shuah Khan <skhan(a)linuxfoundation.org>
Tested-by: Aakash Hemadri <aakashhemadri123(a)gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
</cut>
Results regressed to (for first_bad == 132a8267adabd645476b542b3b132c1b91988fe8)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
28702
# linux build successful:
all
# First few build errors in logs:
from (for last_good == 3d7d1b0f5f41d66a2d177f9fdcdb32e23a4b2513)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
28702
# linux build successful:
all
# linux boot successful:
boot
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-132a8267adabd645476b542b3b132c1b91988fe8
cd investigate-linux-132a8267adabd645476b542b3b132c1b91988fe8
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 132a8267adabd645476b542b3b132c1b91988fe8
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 3d7d1b0f5f41d66a2d177f9fdcdb32e23a4b2513
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-aarch64-lts-a…
Full commit (up to 1000 lines):
<cut>
commit 132a8267adabd645476b542b3b132c1b91988fe8
Author: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
Date: Thu Aug 12 13:22:21 2021 +0200
Linux 5.10.58
Link: https://lore.kernel.org/r/20210810172955.660225700@linuxfoundation.org
Tested-by: Fox Chen <foxhlchen(a)gmail.com>
Tested-by: Hulk Robot <hulkrobot(a)huawei.com>
Tested-by: Sudip Mukherjee <sudip.mukherjee(a)codethink.co.uk>
Tested-by: Linux Kernel Functional Testing <lkft(a)linaro.org>
Tested-by: Guenter Roeck <linux(a)roeck-us.net>
Tested-by: Shuah Khan <skhan(a)linuxfoundation.org>
Tested-by: Aakash Hemadri <aakashhemadri123(a)gmail.com>
Signed-off-by: Greg Kroah-Hartman <gregkh(a)linuxfoundation.org>
---
Makefile | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/Makefile b/Makefile
index e9621a90e752..232dee1140c1 100644
--- a/Makefile
+++ b/Makefile
@@ -1,7 +1,7 @@
# SPDX-License-Identifier: GPL-2.0
VERSION = 5
PATCHLEVEL = 10
-SUBLEVEL = 57
+SUBLEVEL = 58
EXTRAVERSION =
NAME = Dare mighty things
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O2_LTO - Build # 22 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2_LTO
Culprit:
<cut>
commit 4389a413e2129d7d55ee779638b649aa852b6f8a
Author: Zahira Ammarguellat <zahira.ammarguellat(a)intel.com>
Date: Fri Aug 6 12:01:47 2021 -0700
Revert "[clang][fpenv][patch] Change clang option -ffp-model=precise to select ffp-contract=on"
This reverts commit 48ad446a0fb2c9b98cb7047e4daf8a84c29cef8f.
</cut>
Results regressed to (for first_bad == 4389a413e2129d7d55ee779638b649aa852b6f8a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO artifacts/build-4389a413e2129d7d55ee779638b649aa852b6f8a/results_id:
1
# 444.namd,namd_base.default regressed by 104
# 447.dealII,dealII_base.default regressed by 105
from (for last_good == dfce2909ee1ea1523ec27b834a0e56429e9c2beb)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO artifacts/build-dfce2909ee1ea1523ec27b834a0e56429e9c2beb/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2_LTO/3823
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2_LTO/3819
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a
cd investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 4389a413e2129d7d55ee779638b649aa852b6f8a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dfce2909ee1ea1523ec27b834a0e56429e9c2beb
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 4389a413e2129d7d55ee779638b649aa852b6f8a
Author: Zahira Ammarguellat <zahira.ammarguellat(a)intel.com>
Date: Fri Aug 6 12:01:47 2021 -0700
Revert "[clang][fpenv][patch] Change clang option -ffp-model=precise to select ffp-contract=on"
This reverts commit 48ad446a0fb2c9b98cb7047e4daf8a84c29cef8f.
---
clang/docs/UsersManual.rst | 48 ++-----------------------
clang/lib/Driver/ToolChains/Clang.cpp | 33 ++++++++---------
clang/test/CodeGen/ffp-contract-option.c | 47 +++---------------------
clang/test/CodeGen/ppc-emmintrin.c | 4 +--
clang/test/CodeGen/ppc-xmmintrin.c | 4 +--
clang/test/Driver/fp-model.c | 61 +++++++++++++++-----------------
6 files changed, 58 insertions(+), 139 deletions(-)
diff --git a/clang/docs/UsersManual.rst b/clang/docs/UsersManual.rst
index 838669794ea8..980d0ab45975 100644
--- a/clang/docs/UsersManual.rst
+++ b/clang/docs/UsersManual.rst
@@ -1260,50 +1260,8 @@ installed.
Controlling Floating Point Behavior
-----------------------------------
-Clang provides a number of ways to control floating point behavior, including
-with command line options and source pragmas. This section
-describes the various floating point semantic modes and the corresponding options.
-
-.. csv-table:: Floating Point Semantic Modes
- :header: "Mode", "Values"
- :widths: 15, 30, 30
-
- "except_behavior", "{ignore, strict, may_trap}", "ffp-exception-behavior"
- "fenv_access", "{off, on}", "(none)"
- "rounding_mode", "{dynamic, tonearest, downward, upward, towardzero}", "frounding-math"
- "contract", "{on, off, fast}", "ffp-contract"
- "denormal_fp_math", "{IEEE, PreserveSign, PositiveZero}", "fdenormal-fp-math"
- "denormal_fp32_math", "{IEEE, PreserveSign, PositiveZero}", "fdenormal-fp-math-fp32"
- "support_math_errno", "{on, off}", "fmath-errno"
- "no_honor_nans", "{on, off}", "fhonor-nans"
- "no_honor_infinities", "{on, off}", "fhonor-infinities"
- "no_signed_zeros", "{on, off}", "fsigned-zeros"
- "allow_reciprocal", "{on, off}", "freciprocal-math"
- "allow_approximate_fns", "{on, off}", "(none)"
- "allow_reassociation", "{on, off}", "fassociative-math"
-
-
-This table describes the option settings that correspond to the three
-floating point semantic models: precise (the default), strict, and fast.
-
-
-.. csv-table:: Floating Point Models
- :header: "Mode", "Precise", "Strict", "Fast"
- :widths: 25, 15, 15, 15
-
- "except_behavior", "ignore", "strict", "ignore"
- "fenv_access", "off", "on", "off"
- "rounding_mode", "tonearest", "dynamic", "tonearest"
- "contract", "on", "off", "fast"
- "denormal_fp_math", "IEEE", "IEEE", "PreserveSign"
- "denormal_fp32_math", "IEEE","IEEE", "PreserveSign"
- "support_math_errno", "on", "on", "off"
- "no_honor_nans", "off", "off", "on"
- "no_honor_infinities", "off", "off", "on"
- "no_signed_zeros", "off", "off", "on"
- "allow_reciprocal", "off", "off", "on"
- "allow_approximate_fns", "off", "off", "on"
- "allow_reassociation", "off", "off", "on"
+Clang provides a number of ways to control floating point behavior. The options
+are listed below.
.. option:: -ffast-math
@@ -1498,7 +1456,7 @@ Note that floating-point operations performed as part of constant initialization
and ``fast``.
Details:
- * ``precise`` Disables optimizations that are not value-safe on floating-point data, although FP contraction (FMA) is enabled (``-ffp-contract=on``). This is the default behavior.
+ * ``precise`` Disables optimizations that are not value-safe on floating-point data, although FP contraction (FMA) is enabled (``-ffp-contract=fast``). This is the default behavior.
* ``strict`` Enables ``-frounding-math`` and ``-ffp-exception-behavior=strict``, and disables contractions (FMA). All of the ``-ffast-math`` enablements are disabled. Enables ``STDC FENV_ACCESS``: by default ``FENV_ACCESS`` is disabled. This option setting behaves as though ``#pragma STDC FENV_ACESS ON`` appeared at the top of the source file.
* ``fast`` Behaves identically to specifying both ``-ffast-math`` and ``ffp-contract=fast``
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 1c79640be80f..96bbc0250126 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -2641,7 +2641,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
llvm::DenormalMode DenormalFPMath = DefaultDenormalFPMath;
llvm::DenormalMode DenormalFP32Math = DefaultDenormalFP32Math;
- StringRef FPContract = "on";
+ StringRef FPContract = "";
bool StrictFPModel = false;
@@ -2666,7 +2666,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
ReciprocalMath = false;
SignedZeros = true;
// -fno_fast_math restores default denormal and fpcontract handling
- FPContract = "on";
+ FPContract = "";
DenormalFPMath = llvm::DenormalMode::getIEEE();
// FIXME: The target may have picked a non-IEEE default mode here based on
@@ -2686,18 +2686,20 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
// ffp-model= is a Driver option, it is entirely rewritten into more
// granular options before being passed into cc1.
// Use the gcc option in the switch below.
- if (!FPModel.empty() && !FPModel.equals(Val))
+ if (!FPModel.empty() && !FPModel.equals(Val)) {
D.Diag(clang::diag::warn_drv_overriding_flag_option)
<< Args.MakeArgString("-ffp-model=" + FPModel)
<< Args.MakeArgString("-ffp-model=" + Val);
+ FPContract = "";
+ }
if (Val.equals("fast")) {
optID = options::OPT_ffast_math;
FPModel = Val;
- FPContract = Val;
+ FPContract = "fast";
} else if (Val.equals("precise")) {
optID = options::OPT_ffp_contract;
FPModel = Val;
- FPContract = "on";
+ FPContract = "fast";
PreciseFPModel = true;
} else if (Val.equals("strict")) {
StrictFPModel = true;
@@ -2783,11 +2785,9 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
case options::OPT_ffp_contract: {
StringRef Val = A->getValue();
if (PreciseFPModel) {
- // When -ffp-model=precise is seen on the command line,
- // the boolean PreciseFPModel is set to true which indicates
- // "the current option is actually PreciseFPModel". The optID
- // is changed to OPT_ffp_contract and FPContract is set to "on".
- // the argument Val string is "precise": it shouldn't be checked.
+ // -ffp-model=precise enables ffp-contract=fast as a side effect
+ // the FPContract value has already been set to a string literal
+ // and the Val string isn't a pertinent value.
;
} else if (Val.equals("fast") || Val.equals("on") || Val.equals("off"))
FPContract = Val;
@@ -2897,17 +2897,18 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
// -fno_fast_math restores default denormal and fpcontract handling
DenormalFPMath = DefaultDenormalFPMath;
DenormalFP32Math = llvm::DenormalMode::getIEEE();
- FPContract = "on";
+ FPContract = "";
break;
}
if (StrictFPModel) {
// If -ffp-model=strict has been specified on command line but
// subsequent options conflict then emit warning diagnostic.
- if (HonorINFs && HonorNaNs && !AssociativeMath && !ReciprocalMath &&
- SignedZeros && TrappingMath && RoundingFPMath &&
- DenormalFPMath == llvm::DenormalMode::getIEEE() &&
- DenormalFP32Math == llvm::DenormalMode::getIEEE() &&
- FPContract.equals("off"))
+ if (HonorINFs && HonorNaNs &&
+ !AssociativeMath && !ReciprocalMath &&
+ SignedZeros && TrappingMath && RoundingFPMath &&
+ (FPContract.equals("off") || FPContract.empty()) &&
+ DenormalFPMath == llvm::DenormalMode::getIEEE() &&
+ DenormalFP32Math == llvm::DenormalMode::getIEEE())
// OK: Current Arg doesn't conflict with -ffp-model=strict
;
else {
diff --git a/clang/test/CodeGen/ffp-contract-option.c b/clang/test/CodeGen/ffp-contract-option.c
index efc72c2b5461..52b750795940 100644
--- a/clang/test/CodeGen/ffp-contract-option.c
+++ b/clang/test/CodeGen/ffp-contract-option.c
@@ -1,46 +1,9 @@
-// RUN: %clang_cc1 -O3 -ffp-contract=fast -triple=aarch64-apple-darwin -S -o - %s | FileCheck --check-prefix=CHECK-FMADD %s
+// RUN: %clang_cc1 -O3 -ffp-contract=fast -triple=aarch64-apple-darwin -S -o - %s | FileCheck %s
// REQUIRES: aarch64-registered-target
float fma_test1(float a, float b, float c) {
-// CHECK-FMADD: fmadd
- float x = a * b;
- float y = x + c;
- return y;
-}
-
-// RUN: %clang_cc1 -triple=x86_64 %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULT %s
-//
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=off %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULT %s
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=on %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-ON %s
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=fast %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-CONTRACTFAST %s
-//
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULTFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=off %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULTFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=on %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-ONFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=fast %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-FASTFAST %s
-float mymuladd( float x, float y, float z ) {
- return x * y + z;
- // CHECK-DEFAULT: = fmul float
- // CHECK-DEFAULT: = fadd float
-
- // CHECK-ON: = call float @llvm.fmuladd.f32
-
- // CHECK-CONTRACTFAST: = fmul contract float
- // CHECK-CONTRACTFAST: = fadd contract float
-
- // CHECK-DEFAULTFAST: = fmul reassoc nnan ninf nsz arcp afn float
- // CHECK-DEFAULTFAST: = fadd reassoc nnan ninf nsz arcp afn float
-
- // CHECK-ONFAST: = call reassoc nnan ninf nsz arcp afn float @llvm.fmuladd.f32
-
- // CHECK-FASTFAST: = fmul fast float
- // CHECK-FASTFAST: = fadd fast float
+// CHECK: fmadd
+ float x = a * b;
+ float y = x + c;
+ return y;
}
diff --git a/clang/test/CodeGen/ppc-emmintrin.c b/clang/test/CodeGen/ppc-emmintrin.c
index 4a246ff92d76..fa3801f50a01 100644
--- a/clang/test/CodeGen/ppc-emmintrin.c
+++ b/clang/test/CodeGen/ppc-emmintrin.c
@@ -2,9 +2,9 @@
// REQUIRES: powerpc-registered-target
// RUN: %clang -S -emit-llvm -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
// RUN: %clang -S -emit-llvm -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
// CHECK-BE-DAG: @_mm_movemask_pd.perm_mask = internal constant <4 x i32> <i32 -2139062144, i32 -2139062144, i32 -2139062144, i32 -2139078656>, align 16
// CHECK-BE-DAG: @_mm_shuffle_epi32.permute_selectors = internal constant [4 x i32] [i32 66051, i32 67438087, i32 134810123, i32 202182159], align 4
diff --git a/clang/test/CodeGen/ppc-xmmintrin.c b/clang/test/CodeGen/ppc-xmmintrin.c
index a7f6ed6e0e67..d3f18bfbb1e5 100644
--- a/clang/test/CodeGen/ppc-xmmintrin.c
+++ b/clang/test/CodeGen/ppc-xmmintrin.c
@@ -2,11 +2,11 @@
// REQUIRES: powerpc-registered-target
// RUN: %clang -S -emit-llvm -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
// RUN: %clang -x c++ -fsyntax-only -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns
// RUN: %clang -S -emit-llvm -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
// RUN: %clang -x c++ -fsyntax-only -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns
diff --git a/clang/test/Driver/fp-model.c b/clang/test/Driver/fp-model.c
index c6d683e25c0b..5fa9d110dd83 100644
--- a/clang/test/Driver/fp-model.c
+++ b/clang/test/Driver/fp-model.c
@@ -1,90 +1,88 @@
// Test that incompatible combinations of -ffp-model= options
// and other floating point options get a warning diagnostic.
+//
+// REQUIRES: clang-driver
-// RUN: %clang -target x86_64 -### -ffp-model=fast -ffp-contract=off -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=fast -ffp-contract=off -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN %s
// WARN: warning: overriding '-ffp-model=fast' option with '-ffp-contract=off' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=fast -ffp-contract=on -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=fast -ffp-contract=on -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN1 %s
// WARN1: warning: overriding '-ffp-model=fast' option with '-ffp-contract=on' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fassociative-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fassociative-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN2 %s
// WARN2: warning: overriding '-ffp-model=strict' option with '-fassociative-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffast-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffast-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN3 %s
// WARN3: warning: overriding '-ffp-model=strict' option with '-ffast-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffinite-math-only -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffinite-math-only -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN4 %s
// WARN4: warning: overriding '-ffp-model=strict' option with '-ffinite-math-only' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN5 %s
// WARN5: warning: overriding '-ffp-model=strict' option with '-ffp-contract=fast' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
-// RUN: | FileCheck --check-prefix=WARN6 %s
-// WARN6: warning: overriding '-ffp-model=strict' option with '-ffp-contract=fast' [-Woverriding-t-option]
-
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=on -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffp-contract=on -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN7 %s
// WARN7: warning: overriding '-ffp-model=strict' option with '-ffp-contract=on' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-honor-infinities -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-honor-infinities -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN8 %s
// WARN8: warning: overriding '-ffp-model=strict' option with '-fno-honor-infinities' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-honor-nans -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-honor-nans -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN9 %s
// WARN9: warning: overriding '-ffp-model=strict' option with '-fno-honor-nans' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-rounding-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-rounding-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNa %s
// WARNa: warning: overriding '-ffp-model=strict' option with '-fno-rounding-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-signed-zeros -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-signed-zeros -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNb %s
// WARNb: warning: overriding '-ffp-model=strict' option with '-fno-signed-zeros' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-trapping-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-trapping-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNc %s
// WARNc: warning: overriding '-ffp-model=strict' option with '-fno-trapping-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -freciprocal-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -freciprocal-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNd %s
// WARNd: warning: overriding '-ffp-model=strict' option with '-freciprocal-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -funsafe-math-optimizations -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -funsafe-math-optimizations -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNe %s
// WARNe: warning: overriding '-ffp-model=strict' option with '-funsafe-math-optimizations' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -Ofast -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -Ofast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNf %s
// WARNf: warning: overriding '-ffp-model=strict' option with '-Ofast' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fdenormal-fp-math=preserve-sign,preserve-sign -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fdenormal-fp-math=preserve-sign,preserve-sign -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN10 %s
// WARN10: warning: overriding '-ffp-model=strict' option with '-fdenormal-fp-math=preserve-sign,preserve-sign' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -c %s 2>&1 \
+// RUN: %clang -### -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-NOROUND %s
// CHECK-NOROUND: "-cc1"
// CHECK-NOROUND: "-fno-rounding-math"
-// RUN: %clang -target x86_64 -### -frounding-math -c %s 2>&1 \
+// RUN: %clang -### -frounding-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-ROUND --implicit-check-not ffp-exception-behavior=strict %s
// CHECK-ROUND: "-cc1"
// CHECK-ROUND: "-frounding-math"
-// RUN: %clang -target x86_64 -### -ftrapping-math -c %s 2>&1 \
+// RUN: %clang -### -ftrapping-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-TRAP %s
// CHECK-TRAP: "-cc1"
// CHECK-TRAP: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=fast -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=fast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-FAST %s
// CHECK-FPM-FAST: "-cc1"
// CHECK-FPM-FAST: "-menable-no-infs"
@@ -98,35 +96,34 @@
// CHECK-FPM-FAST: "-ffast-math"
// CHECK-FPM-FAST: "-ffinite-math-only"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=precise -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=precise -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-PRECISE %s
// CHECK-FPM-PRECISE: "-cc1"
-// CHECK-FPM-PRECISE: "-ffp-contract=on"
+// CHECK-FPM-PRECISE: "-ffp-contract=fast"
// CHECK-FPM-PRECISE: "-fno-rounding-math"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=strict -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=strict -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-STRICT %s
// CHECK-FPM-STRICT: "-cc1"
-// CHECK-FPM-STRICT: "-fmath-errno"
-// CHECK-FPM-STRICT: "-ffp-contract=off"
// CHECK-FPM-STRICT: "-frounding-math"
// CHECK-FPM-STRICT: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=strict -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=strict -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-STRICT %s
// CHECK-FEB-STRICT: "-cc1"
// CHECK-FEB-STRICT: "-fno-rounding-math"
// CHECK-FEB-STRICT: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=maytrap -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=maytrap -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-MAYTRAP %s
// CHECK-FEB-MAYTRAP: "-cc1"
// CHECK-FEB-MAYTRAP: "-fno-rounding-math"
// CHECK-FEB-MAYTRAP: "-ffp-exception-behavior=maytrap"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=ignore -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=ignore -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-IGNORE %s
// CHECK-FEB-IGNORE: "-cc1"
// CHECK-FEB-IGNORE: "-fno-rounding-math"
// CHECK-FEB-IGNORE: "-ffp-exception-behavior=ignore"
+
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gcc_bootstrap/master-aarch64-bootstrap_ubsan - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gcc_bootstrap/master-aarch64-bootstrap_ubsan. So far, this commit has regressed CI configurations:
- tcwg_gcc_bootstrap/master-aarch64-bootstrap_ubsan
Culprit:
<cut>
commit d1819df86fbe42125cccb2fc2959a0bf51e524d6
Author: Jonathan Wright <jonathan.wright(a)arm.com>
Date: Mon Aug 16 14:37:18 2021 +0100
aarch64: Remove macros for vld4[q]_lane Neon intrinsics
Remove macros for vld4[q]_lane Neon intrinsics. This is a preparatory
step before adding new modes for structures of Advanced SIMD vectors.
gcc/ChangeLog:
2021-08-16 Jonathan Wright <jonathan.wright(a)arm.com>
* config/aarch64/arm_neon.h (__LD4_LANE_FUNC): Delete.
(__LD4Q_LANE_FUNC): Likewise.
(vld4_lane_u8): Define without macro.
(vld4_lane_u16): Likewise.
(vld4_lane_u32): Likewise.
(vld4_lane_u64): Likewise.
(vld4_lane_s8): Likewise.
(vld4_lane_s16): Likewise.
(vld4_lane_s32): Likewise.
(vld4_lane_s64): Likewise.
(vld4_lane_f16): Likewise.
(vld4_lane_f32): Likewise.
(vld4_lane_f64): Likewise.
(vld4_lane_p8): Likewise.
(vld4_lane_p16): Likewise.
(vld4_lane_p64): Likewise.
(vld4q_lane_u8): Likewise.
(vld4q_lane_u16): Likewise.
(vld4q_lane_u32): Likewise.
(vld4q_lane_u64): Likewise.
(vld4q_lane_s8): Likewise.
(vld4q_lane_s16): Likewise.
(vld4q_lane_s32): Likewise.
(vld4q_lane_s64): Likewise.
(vld4q_lane_f16): Likewise.
(vld4q_lane_f32): Likewise.
(vld4q_lane_f64): Likewise.
(vld4q_lane_p8): Likewise.
(vld4q_lane_p16): Likewise.
(vld4q_lane_p64): Likewise.
(vld4_lane_bf16): Likewise.
(vld4q_lane_bf16): Likewise.
</cut>
Results regressed to (for first_bad == d1819df86fbe42125cccb2fc2959a0bf51e524d6)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# First few build errors in logs:
# 00:10:53 make[3]: [Makefile:1769: aarch64-unknown-linux-gnu/bits/largefile-config.h] Error 1 (ignored)
# 00:10:53 make[3]: [Makefile:1770: aarch64-unknown-linux-gnu/bits/largefile-config.h] Error 1 (ignored)
# 00:26:15 /home/tcwg-buildslave/workspace/tcwg_gnu_2/abe/builds/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/gcc-gcc.git~master-stage2/prev-gcc/include/arm_neon.h:21081:11: error: cannot convert ‘float*’ to ‘const int*’
# 00:26:15 /home/tcwg-buildslave/workspace/tcwg_gnu_2/abe/builds/aarch64-unknown-linux-gnu/aarch64-unknown-linux-gnu/gcc-gcc.git~master-stage2/prev-gcc/include/arm_neon.h:21384:9: error: cannot convert ‘long int*’ to ‘const double*’
# 00:26:16 make[3]: *** [Makefile:226: lex.o] Error 1
# 00:26:30 make[2]: *** [Makefile:9758: all-stage2-libcpp] Error 2
# 00:28:15 make[1]: *** [Makefile:25899: stage2-bubble] Error 2
# 00:28:15 make: *** [Makefile:1010: all] Error 2
from (for last_good == 08f83812e5c5fdd9a7a4a1b9e46bb33725185c5a)
# reset_artifacts:
-10
# true:
0
# build_abe binutils:
1
# build_abe bootstrap_ubsan:
2
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-d1819df86fbe42125cccb2fc2959a0bf51e524d6
cd investigate-gcc-d1819df86fbe42125cccb2fc2959a0bf51e524d6
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach d1819df86fbe42125cccb2fc2959a0bf51e524d6
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 08f83812e5c5fdd9a7a4a1b9e46bb33725185c5a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Build log: https://ci.linaro.org/job/tcwg_gcc_bootstrap-bisect-master-aarch64-bootstra…
Full commit (up to 1000 lines):
<cut>
commit d1819df86fbe42125cccb2fc2959a0bf51e524d6
Author: Jonathan Wright <jonathan.wright(a)arm.com>
Date: Mon Aug 16 14:37:18 2021 +0100
aarch64: Remove macros for vld4[q]_lane Neon intrinsics
Remove macros for vld4[q]_lane Neon intrinsics. This is a preparatory
step before adding new modes for structures of Advanced SIMD vectors.
gcc/ChangeLog:
2021-08-16 Jonathan Wright <jonathan.wright(a)arm.com>
* config/aarch64/arm_neon.h (__LD4_LANE_FUNC): Delete.
(__LD4Q_LANE_FUNC): Likewise.
(vld4_lane_u8): Define without macro.
(vld4_lane_u16): Likewise.
(vld4_lane_u32): Likewise.
(vld4_lane_u64): Likewise.
(vld4_lane_s8): Likewise.
(vld4_lane_s16): Likewise.
(vld4_lane_s32): Likewise.
(vld4_lane_s64): Likewise.
(vld4_lane_f16): Likewise.
(vld4_lane_f32): Likewise.
(vld4_lane_f64): Likewise.
(vld4_lane_p8): Likewise.
(vld4_lane_p16): Likewise.
(vld4_lane_p64): Likewise.
(vld4q_lane_u8): Likewise.
(vld4q_lane_u16): Likewise.
(vld4q_lane_u32): Likewise.
(vld4q_lane_u64): Likewise.
(vld4q_lane_s8): Likewise.
(vld4q_lane_s16): Likewise.
(vld4q_lane_s32): Likewise.
(vld4q_lane_s64): Likewise.
(vld4q_lane_f16): Likewise.
(vld4q_lane_f32): Likewise.
(vld4q_lane_f64): Likewise.
(vld4q_lane_p8): Likewise.
(vld4q_lane_p16): Likewise.
(vld4q_lane_p64): Likewise.
(vld4_lane_bf16): Likewise.
(vld4q_lane_bf16): Likewise.
---
gcc/config/aarch64/arm_neon.h | 728 ++++++++++++++++++++++++++++++++++++------
1 file changed, 624 insertions(+), 104 deletions(-)
diff --git a/gcc/config/aarch64/arm_neon.h b/gcc/config/aarch64/arm_neon.h
index 29b62988a91..d8b29706a20 100644
--- a/gcc/config/aarch64/arm_neon.h
+++ b/gcc/config/aarch64/arm_neon.h
@@ -20856,110 +20856,595 @@ vld3q_lane_p64 (const poly64_t * __ptr, poly64x2x3_t __b, const int __c)
/* vld4_lane */
-#define __LD4_LANE_FUNC(intype, vectype, largetype, ptrtype, mode, \
- qmode, ptrmode, funcsuffix, signedtype) \
-__extension__ extern __inline intype \
-__attribute__ ((__always_inline__, __gnu_inline__,__artificial__)) \
-vld4_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c) \
-{ \
- __builtin_aarch64_simd_xi __o; \
- largetype __temp; \
- __temp.val[0] = \
- vcombine_##funcsuffix (__b.val[0], vcreate_##funcsuffix (0)); \
- __temp.val[1] = \
- vcombine_##funcsuffix (__b.val[1], vcreate_##funcsuffix (0)); \
- __temp.val[2] = \
- vcombine_##funcsuffix (__b.val[2], vcreate_##funcsuffix (0)); \
- __temp.val[3] = \
- vcombine_##funcsuffix (__b.val[3], vcreate_##funcsuffix (0)); \
- __o = __builtin_aarch64_set_qregxi##qmode (__o, \
- (signedtype) __temp.val[0], \
- 0); \
- __o = __builtin_aarch64_set_qregxi##qmode (__o, \
- (signedtype) __temp.val[1], \
- 1); \
- __o = __builtin_aarch64_set_qregxi##qmode (__o, \
- (signedtype) __temp.val[2], \
- 2); \
- __o = __builtin_aarch64_set_qregxi##qmode (__o, \
- (signedtype) __temp.val[3], \
- 3); \
- __o = __builtin_aarch64_ld4_lane##mode ( \
- (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c); \
- __b.val[0] = (vectype) __builtin_aarch64_get_dregxidi (__o, 0); \
- __b.val[1] = (vectype) __builtin_aarch64_get_dregxidi (__o, 1); \
- __b.val[2] = (vectype) __builtin_aarch64_get_dregxidi (__o, 2); \
- __b.val[3] = (vectype) __builtin_aarch64_get_dregxidi (__o, 3); \
- return __b; \
+__extension__ extern __inline uint8x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_u8 (const uint8_t * __ptr, uint8x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint8x16x4_t __temp;
+ __temp.val[0] = vcombine_u8 (__b.val[0], vcreate_u8 (0));
+ __temp.val[1] = vcombine_u8 (__b.val[1], vcreate_u8 (0));
+ __temp.val[2] = vcombine_u8 (__b.val[2], vcreate_u8 (0));
+ __temp.val[3] = vcombine_u8 (__b.val[3], vcreate_u8 (0));
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8qi (
+ (__builtin_aarch64_simd_qi *) __ptr, __o, __c);
+ __b.val[0] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (uint8x8_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
}
-/* vld4q_lane */
+__extension__ extern __inline uint16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_u16 (const uint16_t * __ptr, uint16x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint16x8x4_t __temp;
+ __temp.val[0] = vcombine_u16 (__b.val[0], vcreate_u16 (0));
+ __temp.val[1] = vcombine_u16 (__b.val[1], vcreate_u16 (0));
+ __temp.val[2] = vcombine_u16 (__b.val[2], vcreate_u16 (0));
+ __temp.val[3] = vcombine_u16 (__b.val[3], vcreate_u16 (0));
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4hi (
+ (__builtin_aarch64_simd_hi *) __ptr, __o, __c);
+ __b.val[0] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (uint16x4_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline uint32x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_u32 (const uint32_t * __ptr, uint32x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint32x4x4_t __temp;
+ __temp.val[0] = vcombine_u32 (__b.val[0], vcreate_u32 (0));
+ __temp.val[1] = vcombine_u32 (__b.val[1], vcreate_u32 (0));
+ __temp.val[2] = vcombine_u32 (__b.val[2], vcreate_u32 (0));
+ __temp.val[3] = vcombine_u32 (__b.val[3], vcreate_u32 (0));
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2si (
+ (__builtin_aarch64_simd_si *) __ptr, __o, __c);
+ __b.val[0] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (uint32x2_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline uint64x1x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_u64 (const uint64_t * __ptr, uint64x1x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint64x2x4_t __temp;
+ __temp.val[0] = vcombine_u64 (__b.val[0], vcreate_u64 (0));
+ __temp.val[1] = vcombine_u64 (__b.val[1], vcreate_u64 (0));
+ __temp.val[2] = vcombine_u64 (__b.val[2], vcreate_u64 (0));
+ __temp.val[3] = vcombine_u64 (__b.val[3], vcreate_u64 (0));
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanedi (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ __b.val[0] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (uint64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline int8x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_s8 (const int8_t * __ptr, int8x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int8x16x4_t __temp;
+ __temp.val[0] = vcombine_s8 (__b.val[0], vcreate_s8 (0));
+ __temp.val[1] = vcombine_s8 (__b.val[1], vcreate_s8 (0));
+ __temp.val[2] = vcombine_s8 (__b.val[2], vcreate_s8 (0));
+ __temp.val[3] = vcombine_s8 (__b.val[3], vcreate_s8 (0));
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8qi (
+ (__builtin_aarch64_simd_qi *) __ptr, __o, __c);
+ __b.val[0] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (int8x8_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline int16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_s16 (const int16_t * __ptr, int16x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int16x8x4_t __temp;
+ __temp.val[0] = vcombine_s16 (__b.val[0], vcreate_s16 (0));
+ __temp.val[1] = vcombine_s16 (__b.val[1], vcreate_s16 (0));
+ __temp.val[2] = vcombine_s16 (__b.val[2], vcreate_s16 (0));
+ __temp.val[3] = vcombine_s16 (__b.val[3], vcreate_s16 (0));
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4hi (
+ (__builtin_aarch64_simd_hi *) __ptr, __o, __c);
+ __b.val[0] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (int16x4_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline int32x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_s32 (const int32_t * __ptr, int32x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int32x4x4_t __temp;
+ __temp.val[0] = vcombine_s32 (__b.val[0], vcreate_s32 (0));
+ __temp.val[1] = vcombine_s32 (__b.val[1], vcreate_s32 (0));
+ __temp.val[2] = vcombine_s32 (__b.val[2], vcreate_s32 (0));
+ __temp.val[3] = vcombine_s32 (__b.val[3], vcreate_s32 (0));
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2si (
+ (__builtin_aarch64_simd_si *) __ptr, __o, __c);
+ __b.val[0] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (int32x2_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline int64x1x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_s64 (const int64_t * __ptr, int64x1x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int64x2x4_t __temp;
+ __temp.val[0] = vcombine_s64 (__b.val[0], vcreate_s64 (0));
+ __temp.val[1] = vcombine_s64 (__b.val[1], vcreate_s64 (0));
+ __temp.val[2] = vcombine_s64 (__b.val[2], vcreate_s64 (0));
+ __temp.val[3] = vcombine_s64 (__b.val[3], vcreate_s64 (0));
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanedi (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ __b.val[0] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (int64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline float16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_f16 (const float16_t * __ptr, float16x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ float16x8x4_t __temp;
+ __temp.val[0] = vcombine_f16 (__b.val[0], vcreate_f16 (0));
+ __temp.val[1] = vcombine_f16 (__b.val[1], vcreate_f16 (0));
+ __temp.val[2] = vcombine_f16 (__b.val[2], vcreate_f16 (0));
+ __temp.val[3] = vcombine_f16 (__b.val[3], vcreate_f16 (0));
+ __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv8hf (__o, (float16x8_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4hf (
+ (__builtin_aarch64_simd_hf *) __ptr, __o, __c);
+ __b.val[0] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (float16x4_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline float32x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_f32 (const float32_t * __ptr, float32x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ float32x4x4_t __temp;
+ __temp.val[0] = vcombine_f32 (__b.val[0], vcreate_f32 (0));
+ __temp.val[1] = vcombine_f32 (__b.val[1], vcreate_f32 (0));
+ __temp.val[2] = vcombine_f32 (__b.val[2], vcreate_f32 (0));
+ __temp.val[3] = vcombine_f32 (__b.val[3], vcreate_f32 (0));
+ __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4sf (__o, (float32x4_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2si (
+ (__builtin_aarch64_simd_sf *) __ptr, __o, __c);
+ __b.val[0] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (float32x2_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline float64x1x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_f64 (const float64_t * __ptr, float64x1x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ float64x2x4_t __temp;
+ __temp.val[0] = vcombine_f64 (__b.val[0], vcreate_f64 (0));
+ __temp.val[1] = vcombine_f64 (__b.val[1], vcreate_f64 (0));
+ __temp.val[2] = vcombine_f64 (__b.val[2], vcreate_f64 (0));
+ __temp.val[3] = vcombine_f64 (__b.val[3], vcreate_f64 (0));
+ __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv2df (__o, (float64x2_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanedf (
+ (__builtin_aarch64_simd_df *) __ptr, __o, __c);
+ __b.val[0] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (float64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline poly8x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_p8 (const poly8_t * __ptr, poly8x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ poly8x16x4_t __temp;
+ __temp.val[0] = vcombine_p8 (__b.val[0], vcreate_p8 (0));
+ __temp.val[1] = vcombine_p8 (__b.val[1], vcreate_p8 (0));
+ __temp.val[2] = vcombine_p8 (__b.val[2], vcreate_p8 (0));
+ __temp.val[3] = vcombine_p8 (__b.val[3], vcreate_p8 (0));
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv16qi (__o, (int8x16_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8qi (
+ (__builtin_aarch64_simd_qi *) __ptr, __o, __c);
+ __b.val[0] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (poly8x8_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
-__LD4_LANE_FUNC (float16x4x4_t, float16x4_t, float16x8x4_t, float16_t, v4hf,
- v8hf, hf, f16, float16x8_t)
-__LD4_LANE_FUNC (float32x2x4_t, float32x2_t, float32x4x4_t, float32_t, v2sf, v4sf,
- sf, f32, float32x4_t)
-__LD4_LANE_FUNC (float64x1x4_t, float64x1_t, float64x2x4_t, float64_t, df, v2df,
- df, f64, float64x2_t)
-__LD4_LANE_FUNC (poly8x8x4_t, poly8x8_t, poly8x16x4_t, poly8_t, v8qi, v16qi, qi, p8,
- int8x16_t)
-__LD4_LANE_FUNC (poly16x4x4_t, poly16x4_t, poly16x8x4_t, poly16_t, v4hi, v8hi, hi,
- p16, int16x8_t)
-__LD4_LANE_FUNC (poly64x1x4_t, poly64x1_t, poly64x2x4_t, poly64_t, di,
- v2di_ssps, di, p64, poly64x2_t)
-__LD4_LANE_FUNC (int8x8x4_t, int8x8_t, int8x16x4_t, int8_t, v8qi, v16qi, qi, s8,
- int8x16_t)
-__LD4_LANE_FUNC (int16x4x4_t, int16x4_t, int16x8x4_t, int16_t, v4hi, v8hi, hi, s16,
- int16x8_t)
-__LD4_LANE_FUNC (int32x2x4_t, int32x2_t, int32x4x4_t, int32_t, v2si, v4si, si, s32,
- int32x4_t)
-__LD4_LANE_FUNC (int64x1x4_t, int64x1_t, int64x2x4_t, int64_t, di, v2di, di, s64,
- int64x2_t)
-__LD4_LANE_FUNC (uint8x8x4_t, uint8x8_t, uint8x16x4_t, uint8_t, v8qi, v16qi, qi, u8,
- int8x16_t)
-__LD4_LANE_FUNC (uint16x4x4_t, uint16x4_t, uint16x8x4_t, uint16_t, v4hi, v8hi, hi,
- u16, int16x8_t)
-__LD4_LANE_FUNC (uint32x2x4_t, uint32x2_t, uint32x4x4_t, uint32_t, v2si, v4si, si,
- u32, int32x4_t)
-__LD4_LANE_FUNC (uint64x1x4_t, uint64x1_t, uint64x2x4_t, uint64_t, di, v2di, di,
- u64, int64x2_t)
+__extension__ extern __inline poly16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_p16 (const poly16_t * __ptr, poly16x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ poly16x8x4_t __temp;
+ __temp.val[0] = vcombine_p16 (__b.val[0], vcreate_p16 (0));
+ __temp.val[1] = vcombine_p16 (__b.val[1], vcreate_p16 (0));
+ __temp.val[2] = vcombine_p16 (__b.val[2], vcreate_p16 (0));
+ __temp.val[3] = vcombine_p16 (__b.val[3], vcreate_p16 (0));
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv8hi (__o, (int16x8_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4hi (
+ (__builtin_aarch64_simd_hi *) __ptr, __o, __c);
+ __b.val[0] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (poly16x4_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline poly64x1x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_p64 (const poly64_t * __ptr, poly64x1x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ poly64x2x4_t __temp;
+ __temp.val[0] = vcombine_p64 (__b.val[0], vcreate_p64 (0));
+ __temp.val[1] = vcombine_p64 (__b.val[1], vcreate_p64 (0));
+ __temp.val[2] = vcombine_p64 (__b.val[2], vcreate_p64 (0));
+ __temp.val[3] = vcombine_p64 (__b.val[3], vcreate_p64 (0));
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv2di (__o, (int64x2_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanedi (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ __b.val[0] = (poly64x1_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (poly64x1_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (poly64x1_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (poly64x1_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
/* vld4q_lane */
-#define __LD4Q_LANE_FUNC(intype, vtype, ptrtype, mode, ptrmode, funcsuffix) \
-__extension__ extern __inline intype \
-__attribute__ ((__always_inline__, __gnu_inline__,__artificial__)) \
-vld4q_lane_##funcsuffix (const ptrtype * __ptr, intype __b, const int __c) \
-{ \
- __builtin_aarch64_simd_xi __o; \
- intype ret; \
- __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0); \
- __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1); \
- __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2); \
- __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3); \
- __o = __builtin_aarch64_ld4_lane##mode ( \
- (__builtin_aarch64_simd_##ptrmode *) __ptr, __o, __c); \
- ret.val[0] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 0); \
- ret.val[1] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 1); \
- ret.val[2] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 2); \
- ret.val[3] = (vtype) __builtin_aarch64_get_qregxiv4si (__o, 3); \
- return ret; \
-}
-
-__LD4Q_LANE_FUNC (float16x8x4_t, float16x8_t, float16_t, v8hf, hf, f16)
-__LD4Q_LANE_FUNC (float32x4x4_t, float32x4_t, float32_t, v4sf, sf, f32)
-__LD4Q_LANE_FUNC (float64x2x4_t, float64x2_t, float64_t, v2df, df, f64)
-__LD4Q_LANE_FUNC (poly8x16x4_t, poly8x16_t, poly8_t, v16qi, qi, p8)
-__LD4Q_LANE_FUNC (poly16x8x4_t, poly16x8_t, poly16_t, v8hi, hi, p16)
-__LD4Q_LANE_FUNC (poly64x2x4_t, poly64x2_t, poly64_t, v2di, di, p64)
-__LD4Q_LANE_FUNC (int8x16x4_t, int8x16_t, int8_t, v16qi, qi, s8)
-__LD4Q_LANE_FUNC (int16x8x4_t, int16x8_t, int16_t, v8hi, hi, s16)
-__LD4Q_LANE_FUNC (int32x4x4_t, int32x4_t, int32_t, v4si, si, s32)
-__LD4Q_LANE_FUNC (int64x2x4_t, int64x2_t, int64_t, v2di, di, s64)
-__LD4Q_LANE_FUNC (uint8x16x4_t, uint8x16_t, uint8_t, v16qi, qi, u8)
-__LD4Q_LANE_FUNC (uint16x8x4_t, uint16x8_t, uint16_t, v8hi, hi, u16)
-__LD4Q_LANE_FUNC (uint32x4x4_t, uint32x4_t, uint32_t, v4si, si, u32)
-__LD4Q_LANE_FUNC (uint64x2x4_t, uint64x2_t, uint64_t, v2di, di, u64)
+__extension__ extern __inline uint8x16x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_u8 (const uint8_t * __ptr, uint8x16x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint8x16x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev16qi (
+ (__builtin_aarch64_simd_qi *) __ptr, __o, __c);
+ ret.val[0] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (uint8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline uint16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_u16 (const uint16_t * __ptr, uint16x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint16x8x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8hi (
+ (__builtin_aarch64_simd_hi *) __ptr, __o, __c);
+ ret.val[0] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (uint16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline uint32x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_u32 (const uint32_t * __ptr, uint32x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint32x4x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4si (
+ (__builtin_aarch64_simd_si *) __ptr, __o, __c);
+ ret.val[0] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (uint32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline uint64x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_u64 (const uint64_t * __ptr, uint64x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ uint64x2x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2di (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ ret.val[0] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (uint64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline int8x16x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_s8 (const int8_t * __ptr, int8x16x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int8x16x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev16qi (
+ (__builtin_aarch64_simd_qi *) __ptr, __o, __c);
+ ret.val[0] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (int8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline int16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_s16 (const int16_t * __ptr, int16x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int16x8x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8hi (
+ (__builtin_aarch64_simd_hi *) __ptr, __o, __c);
+ ret.val[0] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (int16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline int32x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_s32 (const int32_t * __ptr, int32x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int32x4x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4si (
+ (__builtin_aarch64_simd_si *) __ptr, __o, __c);
+ ret.val[0] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (int32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline int64x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_s64 (const int64_t * __ptr, int64x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ int64x2x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2di (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ ret.val[0] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (int64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline float16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_f16 (const float16_t * __ptr, float16x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ float16x8x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8hf (
+ (__builtin_aarch64_simd_hf *) __ptr, __o, __c);
+ ret.val[0] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (float16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline float32x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_f32 (const float32_t * __ptr, float32x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ float32x4x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4sf (
+ (__builtin_aarch64_simd_sf *) __ptr, __o, __c);
+ ret.val[0] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (float32x4_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline float64x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_f64 (const float64_t * __ptr, float64x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ float64x2x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2df (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ ret.val[0] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (float64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline poly8x16x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_p8 (const poly8_t * __ptr, poly8x16x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ poly8x16x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev16qi (
+ (__builtin_aarch64_simd_qi *) __ptr, __o, __c);
+ ret.val[0] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (poly8x16_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline poly16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_p16 (const poly16_t * __ptr, poly16x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ poly16x8x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8hi (
+ (__builtin_aarch64_simd_hi *) __ptr, __o, __c);
+ ret.val[0] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (poly16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
+
+__extension__ extern __inline poly64x2x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_p64 (const poly64_t * __ptr, poly64x2x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ poly64x2x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev2di (
+ (__builtin_aarch64_simd_di *) __ptr, __o, __c);
+ ret.val[0] = (poly64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (poly64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (poly64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (poly64x2_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
/* vmax */
@@ -35441,9 +35926,47 @@ vld3q_lane_bf16 (const bfloat16_t * __ptr, bfloat16x8x3_t __b, const int __c)
return ret;
}
-__LD4_LANE_FUNC (bfloat16x4x4_t, bfloat16x4_t, bfloat16x8x4_t, bfloat16_t, v4bf,
- v8bf, bf, bf16, bfloat16x8_t)
-__LD4Q_LANE_FUNC (bfloat16x8x4_t, bfloat16x8_t, bfloat16_t, v8bf, bf, bf16)
+__extension__ extern __inline bfloat16x4x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4_lane_bf16 (const bfloat16_t * __ptr, bfloat16x4x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ bfloat16x8x4_t __temp;
+ __temp.val[0] = vcombine_bf16 (__b.val[0], vcreate_bf16 (0));
+ __temp.val[1] = vcombine_bf16 (__b.val[1], vcreate_bf16 (0));
+ __temp.val[2] = vcombine_bf16 (__b.val[2], vcreate_bf16 (0));
+ __temp.val[3] = vcombine_bf16 (__b.val[3], vcreate_bf16 (0));
+ __o = __builtin_aarch64_set_qregxiv8bf (__o, (bfloat16x8_t) __temp.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv8bf (__o, (bfloat16x8_t) __temp.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv8bf (__o, (bfloat16x8_t) __temp.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv8bf (__o, (bfloat16x8_t) __temp.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev4bf (
+ (__builtin_aarch64_simd_bf *) __ptr, __o, __c);
+ __b.val[0] = (bfloat16x4_t) __builtin_aarch64_get_dregxidi (__o, 0);
+ __b.val[1] = (bfloat16x4_t) __builtin_aarch64_get_dregxidi (__o, 1);
+ __b.val[2] = (bfloat16x4_t) __builtin_aarch64_get_dregxidi (__o, 2);
+ __b.val[3] = (bfloat16x4_t) __builtin_aarch64_get_dregxidi (__o, 3);
+ return __b;
+}
+
+__extension__ extern __inline bfloat16x8x4_t
+__attribute__ ((__always_inline__, __gnu_inline__,__artificial__))
+vld4q_lane_bf16 (const bfloat16_t * __ptr, bfloat16x8x4_t __b, const int __c)
+{
+ __builtin_aarch64_simd_xi __o;
+ bfloat16x8x4_t ret;
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[0], 0);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[1], 1);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[2], 2);
+ __o = __builtin_aarch64_set_qregxiv4si (__o, (int32x4_t) __b.val[3], 3);
+ __o = __builtin_aarch64_ld4_lanev8bf (
+ (__builtin_aarch64_simd_bf *) __ptr, __o, __c);
+ ret.val[0] = (bfloat16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 0);
+ ret.val[1] = (bfloat16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 1);
+ ret.val[2] = (bfloat16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 2);
+ ret.val[3] = (bfloat16x8_t) __builtin_aarch64_get_qregxiv4si (__o, 3);
+ return ret;
+}
__extension__ extern __inline void
__attribute__ ((__always_inline__, __gnu_inline__, __artificial__))
@@ -35739,7 +36262,4 @@ vaddq_p128 (poly128_t __a, poly128_t __b)
#undef __aarch64_vdupq_laneq_u32
#undef __aarch64_vdupq_laneq_u64
-#undef __LD4_LANE_FUNC
-#undef __LD4Q_LANE_FUNC
-
#endif
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-arm-next-allmodconfig - Build # 31 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-arm-next-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-release-arm-next-allmodconfig
Culprit:
<cut>
commit fad7cd3310db3099f95dd34312c77740fbc455e5
Author: Baokun Li <libaokun1(a)huawei.com>
Date: Wed Aug 4 10:12:12 2021 +0800
nbd: add the check to prevent overflow in __nbd_ioctl()
If user specify a large enough value of NBD blocks option, it may trigger
signed integer overflow which may lead to nbd->config->bytesize becomes a
large or small value, zero in particular.
UBSAN: Undefined behaviour in drivers/block/nbd.c:325:31
signed integer overflow:
1024 * 4611686155866341414 cannot be represented in type 'long long int'
[...]
Call trace:
[...]
handle_overflow+0x188/0x1dc lib/ubsan.c:192
__ubsan_handle_mul_overflow+0x34/0x44 lib/ubsan.c:213
nbd_size_set drivers/block/nbd.c:325 [inline]
__nbd_ioctl drivers/block/nbd.c:1342 [inline]
nbd_ioctl+0x998/0xa10 drivers/block/nbd.c:1395
__blkdev_driver_ioctl block/ioctl.c:311 [inline]
[...]
Although it is not a big deal, still silence the UBSAN by limit
the input value.
Reported-by: Hulk Robot <hulkci(a)huawei.com>
Signed-off-by: Baokun Li <libaokun1(a)huawei.com>
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Link: https://lore.kernel.org/r/20210804021212.990223-1-libaokun1@huawei.com
[axboe: dropped unlikely()]
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
</cut>
Results regressed to (for first_bad == fad7cd3310db3099f95dd34312c77740fbc455e5)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
21709
# First few build errors in logs:
# 00:07:12 make[1]: *** [modules-only.symvers] Error 1
# 00:07:12 make: *** [modules] Error 2
from (for last_good == da20b58d5bbbb0d23ae9530992a37d0f0d1787a4)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29751
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Configuration details:
rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#ecf9343…"
Reproduce builds:
<cut>
mkdir investigate-linux-fad7cd3310db3099f95dd34312c77740fbc455e5
cd investigate-linux-fad7cd3310db3099f95dd34312c77740fbc455e5
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach fad7cd3310db3099f95dd34312c77740fbc455e5
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach da20b58d5bbbb0d23ae9530992a37d0f0d1787a4
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Full commit (up to 1000 lines):
<cut>
commit fad7cd3310db3099f95dd34312c77740fbc455e5
Author: Baokun Li <libaokun1(a)huawei.com>
Date: Wed Aug 4 10:12:12 2021 +0800
nbd: add the check to prevent overflow in __nbd_ioctl()
If user specify a large enough value of NBD blocks option, it may trigger
signed integer overflow which may lead to nbd->config->bytesize becomes a
large or small value, zero in particular.
UBSAN: Undefined behaviour in drivers/block/nbd.c:325:31
signed integer overflow:
1024 * 4611686155866341414 cannot be represented in type 'long long int'
[...]
Call trace:
[...]
handle_overflow+0x188/0x1dc lib/ubsan.c:192
__ubsan_handle_mul_overflow+0x34/0x44 lib/ubsan.c:213
nbd_size_set drivers/block/nbd.c:325 [inline]
__nbd_ioctl drivers/block/nbd.c:1342 [inline]
nbd_ioctl+0x998/0xa10 drivers/block/nbd.c:1395
__blkdev_driver_ioctl block/ioctl.c:311 [inline]
[...]
Although it is not a big deal, still silence the UBSAN by limit
the input value.
Reported-by: Hulk Robot <hulkci(a)huawei.com>
Signed-off-by: Baokun Li <libaokun1(a)huawei.com>
Reviewed-by: Josef Bacik <josef(a)toxicpanda.com>
Link: https://lore.kernel.org/r/20210804021212.990223-1-libaokun1@huawei.com
[axboe: dropped unlikely()]
Signed-off-by: Jens Axboe <axboe(a)kernel.dk>
---
drivers/block/nbd.c | 6 ++++--
1 file changed, 4 insertions(+), 2 deletions(-)
diff --git a/drivers/block/nbd.c b/drivers/block/nbd.c
index c38317979f74..f82264835794 100644
--- a/drivers/block/nbd.c
+++ b/drivers/block/nbd.c
@@ -1384,6 +1384,7 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
unsigned int cmd, unsigned long arg)
{
struct nbd_config *config = nbd->config;
+ loff_t bytesize;
switch (cmd) {
case NBD_DISCONNECT:
@@ -1398,8 +1399,9 @@ static int __nbd_ioctl(struct block_device *bdev, struct nbd_device *nbd,
case NBD_SET_SIZE:
return nbd_set_size(nbd, arg, config->blksize);
case NBD_SET_SIZE_BLOCKS:
- return nbd_set_size(nbd, arg * config->blksize,
- config->blksize);
+ if (check_mul_overflow((loff_t)arg, config->blksize, &bytesize))
+ return -EINVAL;
+ return nbd_set_size(nbd, bytesize, config->blksize);
case NBD_SET_TIMEOUT:
nbd_set_cmd_timeout(nbd, arg);
return 0;
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3 - Build # 7 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3
Culprit:
<cut>
commit 6998f8ae2d14e096aff33968f226587b5c1a193a
Author: David Sherwood <david.sherwood(a)arm.com>
Date: Wed Mar 10 08:34:19 2021 +0000
[LoopVectorize] Simplify scalar cost calculation in getInstructionCost
This patch simplifies the calculation of certain costs in
getInstructionCost when isScalarAfterVectorization() returns a true value.
There are a few places where we multiply a cost by a number N, i.e.
unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
return N * TTI.getArithmeticInstrCost(...
After some investigation it seems that there are only these cases that occur
in practice:
1. VF is a scalar, in which case N = 1.
2. VF is a vector. We can only get here if: a) the instruction is a
GEP/bitcast/PHI with scalar uses, or b) this is an update to an induction
variable that remains scalar.
I have changed the code so that N is assumed to always be 1. For GEPs
the cost is always 0, since this is calculated later on as part of the
load/store cost. PHI nodes are costed separately and were never previously
multiplied by VF. For all other cases I have added an assert that none of
the users needs scalarising, which didn't fire in any unit tests.
Only one test required fixing and I believe the original cost for the scalar
add instruction to have been wrong, since only one copy remains after
vectorisation.
I have also added a new test for the case when a pointer PHI feeds directly
into a store that will be scalarised as we were previously never testing it.
Differential Revision: https://reviews.llvm.org/D99718
</cut>
Results regressed to (for first_bad == 6998f8ae2d14e096aff33968f226587b5c1a193a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-6998f8ae2d14e096aff33968f226587b5c1a193a/results_id:
1
# 462.libquantum,libquantum_base.default regressed by 114
# 462.libquantum,[.] quantum_toffoli regressed by 123
# 462.libquantum,[.] quantum_cnot regressed by 115
from (for last_good == c835630c25a4f9925517949579f66a43b113fbc9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-c835630c25a4f9925517949579f66a43b113fbc9/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3/3744
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3/3755
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-6998f8ae2d14e096aff33968f226587b5c1a193a
cd investigate-llvm-6998f8ae2d14e096aff33968f226587b5c1a193a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 6998f8ae2d14e096aff33968f226587b5c1a193a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c835630c25a4f9925517949579f66a43b113fbc9
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 6998f8ae2d14e096aff33968f226587b5c1a193a
Author: David Sherwood <david.sherwood(a)arm.com>
Date: Wed Mar 10 08:34:19 2021 +0000
[LoopVectorize] Simplify scalar cost calculation in getInstructionCost
This patch simplifies the calculation of certain costs in
getInstructionCost when isScalarAfterVectorization() returns a true value.
There are a few places where we multiply a cost by a number N, i.e.
unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
return N * TTI.getArithmeticInstrCost(...
After some investigation it seems that there are only these cases that occur
in practice:
1. VF is a scalar, in which case N = 1.
2. VF is a vector. We can only get here if: a) the instruction is a
GEP/bitcast/PHI with scalar uses, or b) this is an update to an induction
variable that remains scalar.
I have changed the code so that N is assumed to always be 1. For GEPs
the cost is always 0, since this is calculated later on as part of the
load/store cost. PHI nodes are costed separately and were never previously
multiplied by VF. For all other cases I have added an assert that none of
the users needs scalarising, which didn't fire in any unit tests.
Only one test required fixing and I believe the original cost for the scalar
add instruction to have been wrong, since only one copy remains after
vectorisation.
I have also added a new test for the case when a pointer PHI feeds directly
into a store that will be scalarised as we were previously never testing it.
Differential Revision: https://reviews.llvm.org/D99718
---
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 73 +++++++++++++---------
.../AArch64/no_vector_instructions.ll | 2 +-
.../LoopVectorize/AArch64/predication_costs.ll | 35 +++++++++++
.../Transforms/LoopVectorize/scalarized-bitcast.ll | 40 ++++++++++++
4 files changed, 121 insertions(+), 29 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index 2b413fc49505..f25af23c86c2 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -7383,10 +7383,39 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
Type *RetTy = I->getType();
if (canTruncateToMinimalBitwidth(I, VF))
RetTy = IntegerType::get(RetTy->getContext(), MinBWs[I]);
- VectorTy = isScalarAfterVectorization(I, VF) ? RetTy : ToVectorTy(RetTy, VF);
auto SE = PSE.getSE();
TTI::TargetCostKind CostKind = TTI::TCK_RecipThroughput;
+ auto hasSingleCopyAfterVectorization = [this](Instruction *I,
+ ElementCount VF) -> bool {
+ if (VF.isScalar())
+ return true;
+
+ auto Scalarized = InstsToScalarize.find(VF);
+ assert(Scalarized != InstsToScalarize.end() &&
+ "VF not yet analyzed for scalarization profitability");
+ return !Scalarized->second.count(I) &&
+ llvm::all_of(I->users(), [&](User *U) {
+ auto *UI = cast<Instruction>(U);
+ return !Scalarized->second.count(UI);
+ });
+ };
+
+ if (isScalarAfterVectorization(I, VF)) {
+ // With the exception of GEPs and PHIs, after scalarization there should
+ // only be one copy of the instruction generated in the loop. This is
+ // because the VF is either 1, or any instructions that need scalarizing
+ // have already been dealt with by the the time we get here. As a result,
+ // it means we don't have to multiply the instruction cost by VF.
+ assert(I->getOpcode() == Instruction::GetElementPtr ||
+ I->getOpcode() == Instruction::PHI ||
+ (I->getOpcode() == Instruction::BitCast &&
+ I->getType()->isPointerTy()) ||
+ hasSingleCopyAfterVectorization(I, VF));
+ VectorTy = RetTy;
+ } else
+ VectorTy = ToVectorTy(RetTy, VF);
+
// TODO: We need to estimate the cost of intrinsic calls.
switch (I->getOpcode()) {
case Instruction::GetElementPtr:
@@ -7514,21 +7543,16 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
Op2VK = TargetTransformInfo::OK_UniformValue;
SmallVector<const Value *, 4> Operands(I->operand_values());
- unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
- return N * TTI.getArithmeticInstrCost(
- I->getOpcode(), VectorTy, CostKind,
- TargetTransformInfo::OK_AnyValue,
- Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
+ return TTI.getArithmeticInstrCost(
+ I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
+ Op2VK, TargetTransformInfo::OP_None, Op2VP, Operands, I);
}
case Instruction::FNeg: {
assert(!VF.isScalable() && "VF is assumed to be non scalable.");
- unsigned N = isScalarAfterVectorization(I, VF) ? VF.getKnownMinValue() : 1;
- return N * TTI.getArithmeticInstrCost(
- I->getOpcode(), VectorTy, CostKind,
- TargetTransformInfo::OK_AnyValue,
- TargetTransformInfo::OK_AnyValue,
- TargetTransformInfo::OP_None, TargetTransformInfo::OP_None,
- I->getOperand(0), I);
+ return TTI.getArithmeticInstrCost(
+ I->getOpcode(), VectorTy, CostKind, TargetTransformInfo::OK_AnyValue,
+ TargetTransformInfo::OK_AnyValue, TargetTransformInfo::OP_None,
+ TargetTransformInfo::OP_None, I->getOperand(0), I);
}
case Instruction::Select: {
SelectInst *SI = cast<SelectInst>(I);
@@ -7583,6 +7607,10 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
VectorTy = ToVectorTy(getMemInstValueType(I), Width);
return getMemoryInstructionCost(I, VF);
}
+ case Instruction::BitCast:
+ if (I->getType()->isPointerTy())
+ return 0;
+ LLVM_FALLTHROUGH;
case Instruction::ZExt:
case Instruction::SExt:
case Instruction::FPToUI:
@@ -7593,8 +7621,7 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
case Instruction::SIToFP:
case Instruction::UIToFP:
case Instruction::Trunc:
- case Instruction::FPTrunc:
- case Instruction::BitCast: {
+ case Instruction::FPTrunc: {
// Computes the CastContextHint from a Load/Store instruction.
auto ComputeCCH = [&](Instruction *I) -> TTI::CastContextHint {
assert((isa<LoadInst>(I) || isa<StoreInst>(I)) &&
@@ -7672,14 +7699,7 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
}
}
- unsigned N;
- if (isScalarAfterVectorization(I, VF)) {
- assert(!VF.isScalable() && "VF is assumed to be non scalable");
- N = VF.getKnownMinValue();
- } else
- N = 1;
- return N *
- TTI.getCastInstrCost(Opcode, VectorTy, SrcVecTy, CCH, CostKind, I);
+ return TTI.getCastInstrCost(Opcode, VectorTy, SrcVecTy, CCH, CostKind, I);
}
case Instruction::Call: {
bool NeedToScalarize;
@@ -7694,11 +7714,8 @@ LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF,
case Instruction::ExtractValue:
return TTI.getInstructionCost(I, TTI::TCK_RecipThroughput);
default:
- // The cost of executing VF copies of the scalar instruction. This opcode
- // is unknown. Assume that it is the same as 'mul'.
- return VF.getKnownMinValue() * TTI.getArithmeticInstrCost(
- Instruction::Mul, VectorTy, CostKind) +
- getScalarizationOverhead(I, VF);
+ // This opcode is unknown. Assume that it is the same as 'mul'.
+ return TTI.getArithmeticInstrCost(Instruction::Mul, VectorTy, CostKind);
} // end of switch.
}
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll b/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
index 247ea35ff5d0..3061998518ad 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/no_vector_instructions.ll
@@ -6,7 +6,7 @@ target triple = "aarch64--linux-gnu"
; CHECK-LABEL: all_scalar
; CHECK: LV: Found scalar instruction: %i.next = add nuw nsw i64 %i, 2
-; CHECK: LV: Found an estimated cost of 2 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
+; CHECK: LV: Found an estimated cost of 1 for VF 2 For instruction: %i.next = add nuw nsw i64 %i, 2
; CHECK: LV: Not considering vector loop of width 2 because it will not generate any vector instructions
;
define void @all_scalar(i64* %a, i64 %n) {
diff --git a/llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll b/llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll
index b0ebb4edf2ad..858b28ddd321 100644
--- a/llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll
+++ b/llvm/test/Transforms/LoopVectorize/AArch64/predication_costs.ll
@@ -86,6 +86,41 @@ for.end:
ret void
}
+; CHECK-LABEL: predicated_store_phi
+;
+; Same as predicate_store except we use a pointer PHI to maintain the address
+;
+; CHECK: Found new scalar instruction: %addr = phi i32* [ %a, %entry ], [ %addr.next, %for.inc ]
+; CHECK: Found new scalar instruction: %addr.next = getelementptr inbounds i32, i32* %addr, i64 1
+; CHECK: Scalarizing and predicating: store i32 %tmp2, i32* %addr, align 4
+; CHECK: Found an estimated cost of 0 for VF 2 For instruction: %addr = phi i32* [ %a, %entry ], [ %addr.next, %for.inc ]
+; CHECK: Found an estimated cost of 3 for VF 2 For instruction: store i32 %tmp2, i32* %addr, align 4
+;
+define void @predicated_store_phi(i32* %a, i1 %c, i32 %x, i64 %n) {
+entry:
+ br label %for.body
+
+for.body:
+ %i = phi i64 [ 0, %entry ], [ %i.next, %for.inc ]
+ %addr = phi i32 * [ %a, %entry ], [ %addr.next, %for.inc ]
+ %tmp1 = load i32, i32* %addr, align 4
+ %tmp2 = add nsw i32 %tmp1, %x
+ br i1 %c, label %if.then, label %for.inc
+
+if.then:
+ store i32 %tmp2, i32* %addr, align 4
+ br label %for.inc
+
+for.inc:
+ %i.next = add nuw nsw i64 %i, 1
+ %cond = icmp slt i64 %i.next, %n
+ %addr.next = getelementptr inbounds i32, i32* %addr, i64 1
+ br i1 %cond, label %for.body, label %for.end
+
+for.end:
+ ret void
+}
+
; CHECK-LABEL: predicated_udiv_scalarized_operand
;
; This test checks that we correctly compute the cost of the predicated udiv
diff --git a/llvm/test/Transforms/LoopVectorize/scalarized-bitcast.ll b/llvm/test/Transforms/LoopVectorize/scalarized-bitcast.ll
new file mode 100644
index 000000000000..0c97e6ac475e
--- /dev/null
+++ b/llvm/test/Transforms/LoopVectorize/scalarized-bitcast.ll
@@ -0,0 +1,40 @@
+; REQUIRES: asserts
+; RUN: opt -loop-vectorize -force-vector-width=2 -debug-only=loop-vectorize -S -o - < %s 2>&1 | FileCheck %s
+
+%struct.foo = type { i32, i64 }
+
+; CHECK: LV: Found an estimated cost of 0 for VF 2 For instruction: %0 = bitcast i64* %b to i32*
+
+; The bitcast below will be scalarized due to the predication in the loop. Bitcasts
+; between pointer types should be treated as free, despite the scalarization.
+define void @foo(%struct.foo* noalias nocapture %in, i32* noalias nocapture readnone %out, i64 %n) {
+entry:
+ br label %for.body
+
+for.body: ; preds = %entry, %if.end
+ %i.012 = phi i64 [ %inc, %if.end ], [ 0, %entry ]
+ %b = getelementptr inbounds %struct.foo, %struct.foo* %in, i64 %i.012, i32 1
+ %0 = bitcast i64* %b to i32*
+ %a = getelementptr inbounds %struct.foo, %struct.foo* %in, i64 %i.012, i32 0
+ %1 = load i32, i32* %a, align 8
+ %tobool.not = icmp eq i32 %1, 0
+ br i1 %tobool.not, label %if.end, label %land.lhs.true
+
+land.lhs.true: ; preds = %for.body
+ %2 = load i32, i32* %0, align 4
+ %cmp2 = icmp sgt i32 %2, 0
+ br i1 %cmp2, label %if.then, label %if.end
+
+if.then: ; preds = %land.lhs.true
+ %sub = add nsw i32 %2, -1
+ store i32 %sub, i32* %0, align 4
+ br label %if.end
+
+if.end: ; preds = %if.then, %land.lhs.true, %for.body
+ %inc = add nuw nsw i64 %i.012, 1
+ %exitcond.not = icmp eq i64 %inc, %n
+ br i1 %exitcond.not, label %for.end, label %for.body
+
+for.end: ; preds = %if.end
+ ret void
+}
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Oz_LTO - Build # 3 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz_LTO
Culprit:
<cut>
commit 4aafd5f00c2a772337ec065d4542ef158453a343
Author: Jan Svoboda <jan_svoboda(a)apple.com>
Date: Fri Aug 6 14:46:41 2021 +0200
[clang] Remove misleading assertion in FullSourceLoc
D31709 added an assertion was added to `FullSourceLoc::hasManager()` that ensured a valid `SourceLocation` is always paired with a `SourceManager`, and missing `SourceManager` is always paired with an invalid `SourceLocation`.
This appears to be incorrect, since clients never cared about constructing `FullSourceLoc` to uphold that invariant, or always checking `isValid()` before calling `hasManager()`.
The assertion started failing when serializing diagnostics pointing into an explicit module. Explicit modules don't have valid `SourceLocation` for the `import` statement, since they are "imported" from the command-line argument `-fmodule-name=x.pcm`.
This patch removes the assertion, since `FullSourceLoc` was never intended to uphold any kind of invariants between the validity of `SourceLocation` and presence of `SourceManager`.
Reviewed By: arphaman
Differential Revision: https://reviews.llvm.org/D106862
</cut>
Results regressed to (for first_bad == 4aafd5f00c2a772337ec065d4542ef158453a343)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz_LTO artifacts/build-4aafd5f00c2a772337ec065d4542ef158453a343/results_id:
1
# 470.lbm,lbm_base.default regressed by 104
from (for last_good == 3709822d2602b8b7db2d9bcc0e856f676582f25d)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz_LTO artifacts/build-3709822d2602b8b7db2d9bcc0e856f676582f25d/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz_LTO/3746
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz_LTO/3725
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-4aafd5f00c2a772337ec065d4542ef158453a343
cd investigate-llvm-4aafd5f00c2a772337ec065d4542ef158453a343
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 4aafd5f00c2a772337ec065d4542ef158453a343
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 3709822d2602b8b7db2d9bcc0e856f676582f25d
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 4aafd5f00c2a772337ec065d4542ef158453a343
Author: Jan Svoboda <jan_svoboda(a)apple.com>
Date: Fri Aug 6 14:46:41 2021 +0200
[clang] Remove misleading assertion in FullSourceLoc
D31709 added an assertion was added to `FullSourceLoc::hasManager()` that ensured a valid `SourceLocation` is always paired with a `SourceManager`, and missing `SourceManager` is always paired with an invalid `SourceLocation`.
This appears to be incorrect, since clients never cared about constructing `FullSourceLoc` to uphold that invariant, or always checking `isValid()` before calling `hasManager()`.
The assertion started failing when serializing diagnostics pointing into an explicit module. Explicit modules don't have valid `SourceLocation` for the `import` statement, since they are "imported" from the command-line argument `-fmodule-name=x.pcm`.
This patch removes the assertion, since `FullSourceLoc` was never intended to uphold any kind of invariants between the validity of `SourceLocation` and presence of `SourceManager`.
Reviewed By: arphaman
Differential Revision: https://reviews.llvm.org/D106862
---
clang/include/clang/Basic/SourceLocation.h | 13 +++++++------
clang/test/Modules/Inputs/explicit-build-diags/a.h | 1 +
.../Modules/Inputs/explicit-build-diags/module.modulemap | 1 +
clang/test/Modules/explicit-build-diags.cpp | 8 ++++++++
4 files changed, 17 insertions(+), 6 deletions(-)
diff --git a/clang/include/clang/Basic/SourceLocation.h b/clang/include/clang/Basic/SourceLocation.h
index 540de23b9f55..ba2e9156a2b1 100644
--- a/clang/include/clang/Basic/SourceLocation.h
+++ b/clang/include/clang/Basic/SourceLocation.h
@@ -363,6 +363,10 @@ class FileEntry;
/// A SourceLocation and its associated SourceManager.
///
/// This is useful for argument passing to functions that expect both objects.
+///
+/// This class does not guarantee the presence of either the SourceManager or
+/// a valid SourceLocation. Clients should use `isValid()` and `hasManager()`
+/// before calling the member functions.
class FullSourceLoc : public SourceLocation {
const SourceManager *SrcMgr = nullptr;
@@ -373,13 +377,10 @@ public:
explicit FullSourceLoc(SourceLocation Loc, const SourceManager &SM)
: SourceLocation(Loc), SrcMgr(&SM) {}
- bool hasManager() const {
- bool hasSrcMgr = SrcMgr != nullptr;
- assert(hasSrcMgr == isValid() && "FullSourceLoc has location but no manager");
- return hasSrcMgr;
- }
+ /// Checks whether the SourceManager is present.
+ bool hasManager() const { return SrcMgr != nullptr; }
- /// \pre This FullSourceLoc has an associated SourceManager.
+ /// \pre hasManager()
const SourceManager &getManager() const {
assert(SrcMgr && "SourceManager is NULL.");
return *SrcMgr;
diff --git a/clang/test/Modules/Inputs/explicit-build-diags/a.h b/clang/test/Modules/Inputs/explicit-build-diags/a.h
new file mode 100644
index 000000000000..486941dde83b
--- /dev/null
+++ b/clang/test/Modules/Inputs/explicit-build-diags/a.h
@@ -0,0 +1 @@
+void a() __attribute__((deprecated));
diff --git a/clang/test/Modules/Inputs/explicit-build-diags/module.modulemap b/clang/test/Modules/Inputs/explicit-build-diags/module.modulemap
new file mode 100644
index 000000000000..bb00c840ce39
--- /dev/null
+++ b/clang/test/Modules/Inputs/explicit-build-diags/module.modulemap
@@ -0,0 +1 @@
+module a { header "a.h" }
diff --git a/clang/test/Modules/explicit-build-diags.cpp b/clang/test/Modules/explicit-build-diags.cpp
new file mode 100644
index 000000000000..4a37dc108a68
--- /dev/null
+++ b/clang/test/Modules/explicit-build-diags.cpp
@@ -0,0 +1,8 @@
+// RUN: rm -rf %t && mkdir %t
+// RUN: %clang_cc1 -fmodules -x c++ %S/Inputs/explicit-build-diags/module.modulemap -fmodule-name=a -emit-module -o %t/a.pcm
+// RUN: %clang_cc1 -fmodules -Wdeprecated-declarations -fdiagnostics-show-note-include-stack -serialize-diagnostic-file %t/tu.dia \
+// RUN: -I %S/Inputs/explicit-build-diags -fmodule-file=%t/a.pcm -fsyntax-only %s
+
+#include "a.h"
+
+void foo() { a(); }
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2_LTO - Build # 9 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2_LTO
Culprit:
<cut>
commit d8c373815d35df1b8544784ce172ade68fb01f8f
Author: Vladislav Vinogradov <vlad.vinogradov(a)intel.com>
Date: Tue Feb 2 18:26:05 2021 +0000
[mlir][NFC] Add missing include guards to MlirOptMain.h
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D95533
</cut>
Results regressed to (for first_bad == d8c373815d35df1b8544784ce172ade68fb01f8f)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-d8c373815d35df1b8544784ce172ade68fb01f8f/results_id:
1
# 464.h264ref,libc.so.6 regressed by 120
from (for last_good == f1bdf9fa9bc5edc616842b6cb9028b7d207e012c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-f1bdf9fa9bc5edc616842b6cb9028b7d207e012c/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2_LTO/3730
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2_LTO/3737
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-d8c373815d35df1b8544784ce172ade68fb01f8f
cd investigate-llvm-d8c373815d35df1b8544784ce172ade68fb01f8f
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach d8c373815d35df1b8544784ce172ade68fb01f8f
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach f1bdf9fa9bc5edc616842b6cb9028b7d207e012c
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit d8c373815d35df1b8544784ce172ade68fb01f8f
Author: Vladislav Vinogradov <vlad.vinogradov(a)intel.com>
Date: Tue Feb 2 18:26:05 2021 +0000
[mlir][NFC] Add missing include guards to MlirOptMain.h
Reviewed By: mehdi_amini
Differential Revision: https://reviews.llvm.org/D95533
---
mlir/include/mlir/Support/MlirOptMain.h | 5 +++++
1 file changed, 5 insertions(+)
diff --git a/mlir/include/mlir/Support/MlirOptMain.h b/mlir/include/mlir/Support/MlirOptMain.h
index da03baed2ae7..71d47317571e 100644
--- a/mlir/include/mlir/Support/MlirOptMain.h
+++ b/mlir/include/mlir/Support/MlirOptMain.h
@@ -10,6 +10,9 @@
//
//===----------------------------------------------------------------------===//
+#ifndef MLIR_SUPPORT_MLIROPTMAIN_H
+#define MLIR_SUPPORT_MLIROPTMAIN_H
+
#include "mlir/Support/LogicalResult.h"
#include "llvm/ADT/StringRef.h"
@@ -59,3 +62,5 @@ LogicalResult MlirOptMain(int argc, char **argv, llvm::StringRef toolName,
bool preloadDialectsInContext = true);
} // end namespace mlir
+
+#endif // MLIR_SUPPORT_MLIROPTMAIN_H
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Oz - Build # 5 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz
Culprit:
<cut>
commit fd26ce83981c6b50519805500272ab26b4e4c4b0
Author: Jeff Law <jlaw(a)localhost.localdomain>
Date: Sun Aug 8 11:20:41 2021 -0400
Fix c6x test compromised by recent improvements to bswap & rotates
gcc/testsuite
* gcc.target/tic6x/rotdi16-scan.c: Pull rotate into its own function.
</cut>
Results regressed to (for first_bad == fd26ce83981c6b50519805500272ab26b4e4c4b0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-fd26ce83981c6b50519805500272ab26b4e4c4b0/results_id:
1
# 482.sphinx3,[.] OUTLINED_FUNCTION_4 regressed by 117
from (for last_good == e9b639c4b532212ca92b2261f820768993770daa)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-e9b639c4b532212ca92b2261f820768993770daa/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/3651
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/3643
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-fd26ce83981c6b50519805500272ab26b4e4c4b0
cd investigate-gcc-fd26ce83981c6b50519805500272ab26b4e4c4b0
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach fd26ce83981c6b50519805500272ab26b4e4c4b0
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach e9b639c4b532212ca92b2261f820768993770daa
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit fd26ce83981c6b50519805500272ab26b4e4c4b0
Author: Jeff Law <jlaw(a)localhost.localdomain>
Date: Sun Aug 8 11:20:41 2021 -0400
Fix c6x test compromised by recent improvements to bswap & rotates
gcc/testsuite
* gcc.target/tic6x/rotdi16-scan.c: Pull rotate into its own function.
---
gcc/testsuite/gcc.target/tic6x/rotdi16-scan.c | 8 ++++++--
1 file changed, 6 insertions(+), 2 deletions(-)
diff --git a/gcc/testsuite/gcc.target/tic6x/rotdi16-scan.c b/gcc/testsuite/gcc.target/tic6x/rotdi16-scan.c
index 4d7816c1537..550418324e6 100644
--- a/gcc/testsuite/gcc.target/tic6x/rotdi16-scan.c
+++ b/gcc/testsuite/gcc.target/tic6x/rotdi16-scan.c
@@ -7,10 +7,14 @@
unsigned long long z = 0x012389ab4567cdefull;
+unsigned long long __attribute__ ((noinline,noclone,noipa)) bar ()
+{
+ return (z << 48) | (z >> 16);
+}
+
int main ()
{
- unsigned long long z2 = (z << 48) | (z >> 16);
- if (z2 != 0xcdef012389ab4567ull)
+ if (bar() != 0xcdef012389ab4567ull)
abort ();
exit (0);
}
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O3 - Build # 8 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O3
Culprit:
<cut>
commit e771614bae0a05585f720812d5936a0b81dcddf0
Author: David Green <david.green(a)arm.com>
Date: Thu Feb 11 11:58:55 2021 +0000
[ARM] Change getScalarizationOverhead overload used in gather costs. NFC
This changes which of the getScalarizationOverhead overloads is used in
the gather/scatter cost to use the base variant directly, not relying on
the version using heuristics on the number of args with no args
provided. It should still produce the same costs for scalarized
gathers/scatters.
</cut>
Results regressed to (for first_bad == e771614bae0a05585f720812d5936a0b81dcddf0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-e771614bae0a05585f720812d5936a0b81dcddf0/results_id:
1
# 445.gobmk,[.] fastlib regressed by 115
from (for last_good == a31eae840525e9292a3a42c1fdac3fc594f42949)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_marm artifacts/build-a31eae840525e9292a3a42c1fdac3fc594f42949/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/3644
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O3/3642
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-e771614bae0a05585f720812d5936a0b81dcddf0
cd investigate-llvm-e771614bae0a05585f720812d5936a0b81dcddf0
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach e771614bae0a05585f720812d5936a0b81dcddf0
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach a31eae840525e9292a3a42c1fdac3fc594f42949
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit e771614bae0a05585f720812d5936a0b81dcddf0
Author: David Green <david.green(a)arm.com>
Date: Thu Feb 11 11:58:55 2021 +0000
[ARM] Change getScalarizationOverhead overload used in gather costs. NFC
This changes which of the getScalarizationOverhead overloads is used in
the gather/scatter cost to use the base variant directly, not relying on
the version using heuristics on the number of args with no args
provided. It should still produce the same costs for scalarized
gathers/scatters.
---
llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp | 5 +++--
1 file changed, 3 insertions(+), 2 deletions(-)
diff --git a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
index af67839c2d75..de2c0607d2ed 100644
--- a/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
+++ b/llvm/lib/Target/ARM/ARMTargetTransformInfo.cpp
@@ -1416,8 +1416,9 @@ unsigned ARMTTIImpl::getGatherScatterOpCost(unsigned Opcode, Type *DataTy,
unsigned VectorCost = NumElems * LT.first * ST->getMVEVectorCostFactor();
// The scalarization cost should be a lot higher. We use the number of vector
// elements plus the scalarization overhead.
- unsigned ScalarCost =
- NumElems * LT.first + BaseT::getScalarizationOverhead(VTy, {});
+ unsigned ScalarCost = NumElems * LT.first +
+ BaseT::getScalarizationOverhead(VTy, true, false) +
+ BaseT::getScalarizationOverhead(VTy, false, true);
if (EltSize < 8 || Alignment < EltSize / 8)
return ScalarCost;
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3 - Build # 19 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3
Culprit:
<cut>
commit 4389a413e2129d7d55ee779638b649aa852b6f8a
Author: Zahira Ammarguellat <zahira.ammarguellat(a)intel.com>
Date: Fri Aug 6 12:01:47 2021 -0700
Revert "[clang][fpenv][patch] Change clang option -ffp-model=precise to select ffp-contract=on"
This reverts commit 48ad446a0fb2c9b98cb7047e4daf8a84c29cef8f.
</cut>
Results regressed to (for first_bad == 4389a413e2129d7d55ee779638b649aa852b6f8a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-4389a413e2129d7d55ee779638b649aa852b6f8a/results_id:
1
# 470.lbm,lbm_base.default regressed by 108
# 447.dealII,dealII_base.default regressed by 104
# 447.dealII,[.] _ZNK12SparseMatrixIdE5vmultI6VectorIdES3_EEvRT regressed by 120
# 444.namd,namd_base.default regressed by 104
# 400.perlbench,perlbench_base.default regressed by 103
from (for last_good == dfce2909ee1ea1523ec27b834a0e56429e9c2beb)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-dfce2909ee1ea1523ec27b834a0e56429e9c2beb/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3640
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3621
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a
cd investigate-llvm-4389a413e2129d7d55ee779638b649aa852b6f8a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 4389a413e2129d7d55ee779638b649aa852b6f8a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dfce2909ee1ea1523ec27b834a0e56429e9c2beb
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 4389a413e2129d7d55ee779638b649aa852b6f8a
Author: Zahira Ammarguellat <zahira.ammarguellat(a)intel.com>
Date: Fri Aug 6 12:01:47 2021 -0700
Revert "[clang][fpenv][patch] Change clang option -ffp-model=precise to select ffp-contract=on"
This reverts commit 48ad446a0fb2c9b98cb7047e4daf8a84c29cef8f.
---
clang/docs/UsersManual.rst | 48 ++-----------------------
clang/lib/Driver/ToolChains/Clang.cpp | 33 ++++++++---------
clang/test/CodeGen/ffp-contract-option.c | 47 +++---------------------
clang/test/CodeGen/ppc-emmintrin.c | 4 +--
clang/test/CodeGen/ppc-xmmintrin.c | 4 +--
clang/test/Driver/fp-model.c | 61 +++++++++++++++-----------------
6 files changed, 58 insertions(+), 139 deletions(-)
diff --git a/clang/docs/UsersManual.rst b/clang/docs/UsersManual.rst
index 838669794ea8..980d0ab45975 100644
--- a/clang/docs/UsersManual.rst
+++ b/clang/docs/UsersManual.rst
@@ -1260,50 +1260,8 @@ installed.
Controlling Floating Point Behavior
-----------------------------------
-Clang provides a number of ways to control floating point behavior, including
-with command line options and source pragmas. This section
-describes the various floating point semantic modes and the corresponding options.
-
-.. csv-table:: Floating Point Semantic Modes
- :header: "Mode", "Values"
- :widths: 15, 30, 30
-
- "except_behavior", "{ignore, strict, may_trap}", "ffp-exception-behavior"
- "fenv_access", "{off, on}", "(none)"
- "rounding_mode", "{dynamic, tonearest, downward, upward, towardzero}", "frounding-math"
- "contract", "{on, off, fast}", "ffp-contract"
- "denormal_fp_math", "{IEEE, PreserveSign, PositiveZero}", "fdenormal-fp-math"
- "denormal_fp32_math", "{IEEE, PreserveSign, PositiveZero}", "fdenormal-fp-math-fp32"
- "support_math_errno", "{on, off}", "fmath-errno"
- "no_honor_nans", "{on, off}", "fhonor-nans"
- "no_honor_infinities", "{on, off}", "fhonor-infinities"
- "no_signed_zeros", "{on, off}", "fsigned-zeros"
- "allow_reciprocal", "{on, off}", "freciprocal-math"
- "allow_approximate_fns", "{on, off}", "(none)"
- "allow_reassociation", "{on, off}", "fassociative-math"
-
-
-This table describes the option settings that correspond to the three
-floating point semantic models: precise (the default), strict, and fast.
-
-
-.. csv-table:: Floating Point Models
- :header: "Mode", "Precise", "Strict", "Fast"
- :widths: 25, 15, 15, 15
-
- "except_behavior", "ignore", "strict", "ignore"
- "fenv_access", "off", "on", "off"
- "rounding_mode", "tonearest", "dynamic", "tonearest"
- "contract", "on", "off", "fast"
- "denormal_fp_math", "IEEE", "IEEE", "PreserveSign"
- "denormal_fp32_math", "IEEE","IEEE", "PreserveSign"
- "support_math_errno", "on", "on", "off"
- "no_honor_nans", "off", "off", "on"
- "no_honor_infinities", "off", "off", "on"
- "no_signed_zeros", "off", "off", "on"
- "allow_reciprocal", "off", "off", "on"
- "allow_approximate_fns", "off", "off", "on"
- "allow_reassociation", "off", "off", "on"
+Clang provides a number of ways to control floating point behavior. The options
+are listed below.
.. option:: -ffast-math
@@ -1498,7 +1456,7 @@ Note that floating-point operations performed as part of constant initialization
and ``fast``.
Details:
- * ``precise`` Disables optimizations that are not value-safe on floating-point data, although FP contraction (FMA) is enabled (``-ffp-contract=on``). This is the default behavior.
+ * ``precise`` Disables optimizations that are not value-safe on floating-point data, although FP contraction (FMA) is enabled (``-ffp-contract=fast``). This is the default behavior.
* ``strict`` Enables ``-frounding-math`` and ``-ffp-exception-behavior=strict``, and disables contractions (FMA). All of the ``-ffast-math`` enablements are disabled. Enables ``STDC FENV_ACCESS``: by default ``FENV_ACCESS`` is disabled. This option setting behaves as though ``#pragma STDC FENV_ACESS ON`` appeared at the top of the source file.
* ``fast`` Behaves identically to specifying both ``-ffast-math`` and ``ffp-contract=fast``
diff --git a/clang/lib/Driver/ToolChains/Clang.cpp b/clang/lib/Driver/ToolChains/Clang.cpp
index 1c79640be80f..96bbc0250126 100644
--- a/clang/lib/Driver/ToolChains/Clang.cpp
+++ b/clang/lib/Driver/ToolChains/Clang.cpp
@@ -2641,7 +2641,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
llvm::DenormalMode DenormalFPMath = DefaultDenormalFPMath;
llvm::DenormalMode DenormalFP32Math = DefaultDenormalFP32Math;
- StringRef FPContract = "on";
+ StringRef FPContract = "";
bool StrictFPModel = false;
@@ -2666,7 +2666,7 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
ReciprocalMath = false;
SignedZeros = true;
// -fno_fast_math restores default denormal and fpcontract handling
- FPContract = "on";
+ FPContract = "";
DenormalFPMath = llvm::DenormalMode::getIEEE();
// FIXME: The target may have picked a non-IEEE default mode here based on
@@ -2686,18 +2686,20 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
// ffp-model= is a Driver option, it is entirely rewritten into more
// granular options before being passed into cc1.
// Use the gcc option in the switch below.
- if (!FPModel.empty() && !FPModel.equals(Val))
+ if (!FPModel.empty() && !FPModel.equals(Val)) {
D.Diag(clang::diag::warn_drv_overriding_flag_option)
<< Args.MakeArgString("-ffp-model=" + FPModel)
<< Args.MakeArgString("-ffp-model=" + Val);
+ FPContract = "";
+ }
if (Val.equals("fast")) {
optID = options::OPT_ffast_math;
FPModel = Val;
- FPContract = Val;
+ FPContract = "fast";
} else if (Val.equals("precise")) {
optID = options::OPT_ffp_contract;
FPModel = Val;
- FPContract = "on";
+ FPContract = "fast";
PreciseFPModel = true;
} else if (Val.equals("strict")) {
StrictFPModel = true;
@@ -2783,11 +2785,9 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
case options::OPT_ffp_contract: {
StringRef Val = A->getValue();
if (PreciseFPModel) {
- // When -ffp-model=precise is seen on the command line,
- // the boolean PreciseFPModel is set to true which indicates
- // "the current option is actually PreciseFPModel". The optID
- // is changed to OPT_ffp_contract and FPContract is set to "on".
- // the argument Val string is "precise": it shouldn't be checked.
+ // -ffp-model=precise enables ffp-contract=fast as a side effect
+ // the FPContract value has already been set to a string literal
+ // and the Val string isn't a pertinent value.
;
} else if (Val.equals("fast") || Val.equals("on") || Val.equals("off"))
FPContract = Val;
@@ -2897,17 +2897,18 @@ static void RenderFloatingPointOptions(const ToolChain &TC, const Driver &D,
// -fno_fast_math restores default denormal and fpcontract handling
DenormalFPMath = DefaultDenormalFPMath;
DenormalFP32Math = llvm::DenormalMode::getIEEE();
- FPContract = "on";
+ FPContract = "";
break;
}
if (StrictFPModel) {
// If -ffp-model=strict has been specified on command line but
// subsequent options conflict then emit warning diagnostic.
- if (HonorINFs && HonorNaNs && !AssociativeMath && !ReciprocalMath &&
- SignedZeros && TrappingMath && RoundingFPMath &&
- DenormalFPMath == llvm::DenormalMode::getIEEE() &&
- DenormalFP32Math == llvm::DenormalMode::getIEEE() &&
- FPContract.equals("off"))
+ if (HonorINFs && HonorNaNs &&
+ !AssociativeMath && !ReciprocalMath &&
+ SignedZeros && TrappingMath && RoundingFPMath &&
+ (FPContract.equals("off") || FPContract.empty()) &&
+ DenormalFPMath == llvm::DenormalMode::getIEEE() &&
+ DenormalFP32Math == llvm::DenormalMode::getIEEE())
// OK: Current Arg doesn't conflict with -ffp-model=strict
;
else {
diff --git a/clang/test/CodeGen/ffp-contract-option.c b/clang/test/CodeGen/ffp-contract-option.c
index efc72c2b5461..52b750795940 100644
--- a/clang/test/CodeGen/ffp-contract-option.c
+++ b/clang/test/CodeGen/ffp-contract-option.c
@@ -1,46 +1,9 @@
-// RUN: %clang_cc1 -O3 -ffp-contract=fast -triple=aarch64-apple-darwin -S -o - %s | FileCheck --check-prefix=CHECK-FMADD %s
+// RUN: %clang_cc1 -O3 -ffp-contract=fast -triple=aarch64-apple-darwin -S -o - %s | FileCheck %s
// REQUIRES: aarch64-registered-target
float fma_test1(float a, float b, float c) {
-// CHECK-FMADD: fmadd
- float x = a * b;
- float y = x + c;
- return y;
-}
-
-// RUN: %clang_cc1 -triple=x86_64 %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULT %s
-//
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=off %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULT %s
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=on %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-ON %s
-// RUN: %clang_cc1 -triple=x86_64 -ffp-contract=fast %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-CONTRACTFAST %s
-//
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULTFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=off %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-DEFAULTFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=on %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-ONFAST %s
-// RUN: %clang_cc1 -triple=x86_64 -ffast-math -ffp-contract=fast %s -emit-llvm -o - \
-// RUN:| FileCheck --check-prefix=CHECK-FASTFAST %s
-float mymuladd( float x, float y, float z ) {
- return x * y + z;
- // CHECK-DEFAULT: = fmul float
- // CHECK-DEFAULT: = fadd float
-
- // CHECK-ON: = call float @llvm.fmuladd.f32
-
- // CHECK-CONTRACTFAST: = fmul contract float
- // CHECK-CONTRACTFAST: = fadd contract float
-
- // CHECK-DEFAULTFAST: = fmul reassoc nnan ninf nsz arcp afn float
- // CHECK-DEFAULTFAST: = fadd reassoc nnan ninf nsz arcp afn float
-
- // CHECK-ONFAST: = call reassoc nnan ninf nsz arcp afn float @llvm.fmuladd.f32
-
- // CHECK-FASTFAST: = fmul fast float
- // CHECK-FASTFAST: = fadd fast float
+// CHECK: fmadd
+ float x = a * b;
+ float y = x + c;
+ return y;
}
diff --git a/clang/test/CodeGen/ppc-emmintrin.c b/clang/test/CodeGen/ppc-emmintrin.c
index 4a246ff92d76..fa3801f50a01 100644
--- a/clang/test/CodeGen/ppc-emmintrin.c
+++ b/clang/test/CodeGen/ppc-emmintrin.c
@@ -2,9 +2,9 @@
// REQUIRES: powerpc-registered-target
// RUN: %clang -S -emit-llvm -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
// RUN: %clang -S -emit-llvm -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
// CHECK-BE-DAG: @_mm_movemask_pd.perm_mask = internal constant <4 x i32> <i32 -2139062144, i32 -2139062144, i32 -2139062144, i32 -2139078656>, align 16
// CHECK-BE-DAG: @_mm_shuffle_epi32.permute_selectors = internal constant [4 x i32] [i32 66051, i32 67438087, i32 134810123, i32 202182159], align 4
diff --git a/clang/test/CodeGen/ppc-xmmintrin.c b/clang/test/CodeGen/ppc-xmmintrin.c
index a7f6ed6e0e67..d3f18bfbb1e5 100644
--- a/clang/test/CodeGen/ppc-xmmintrin.c
+++ b/clang/test/CodeGen/ppc-xmmintrin.c
@@ -2,11 +2,11 @@
// REQUIRES: powerpc-registered-target
// RUN: %clang -S -emit-llvm -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-BE
// RUN: %clang -x c++ -fsyntax-only -target powerpc64-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns
// RUN: %clang -S -emit-llvm -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
-// RUN: -ffp-contract=off -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
+// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns -o - | llvm-cxxfilt -n | FileCheck %s --check-prefixes=CHECK,CHECK-LE
// RUN: %clang -x c++ -fsyntax-only -target powerpc64le-unknown-linux-gnu -mcpu=pwr8 -ffreestanding -DNO_WARN_X86_INTRINSICS %s \
// RUN: -fno-discard-value-names -mllvm -disable-llvm-optzns
diff --git a/clang/test/Driver/fp-model.c b/clang/test/Driver/fp-model.c
index c6d683e25c0b..5fa9d110dd83 100644
--- a/clang/test/Driver/fp-model.c
+++ b/clang/test/Driver/fp-model.c
@@ -1,90 +1,88 @@
// Test that incompatible combinations of -ffp-model= options
// and other floating point options get a warning diagnostic.
+//
+// REQUIRES: clang-driver
-// RUN: %clang -target x86_64 -### -ffp-model=fast -ffp-contract=off -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=fast -ffp-contract=off -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN %s
// WARN: warning: overriding '-ffp-model=fast' option with '-ffp-contract=off' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=fast -ffp-contract=on -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=fast -ffp-contract=on -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN1 %s
// WARN1: warning: overriding '-ffp-model=fast' option with '-ffp-contract=on' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fassociative-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fassociative-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN2 %s
// WARN2: warning: overriding '-ffp-model=strict' option with '-fassociative-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffast-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffast-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN3 %s
// WARN3: warning: overriding '-ffp-model=strict' option with '-ffast-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffinite-math-only -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffinite-math-only -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN4 %s
// WARN4: warning: overriding '-ffp-model=strict' option with '-ffinite-math-only' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN5 %s
// WARN5: warning: overriding '-ffp-model=strict' option with '-ffp-contract=fast' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=fast -c %s 2>&1 \
-// RUN: | FileCheck --check-prefix=WARN6 %s
-// WARN6: warning: overriding '-ffp-model=strict' option with '-ffp-contract=fast' [-Woverriding-t-option]
-
-// RUN: %clang -target x86_64 -### -ffp-model=strict -ffp-contract=on -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -ffp-contract=on -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN7 %s
// WARN7: warning: overriding '-ffp-model=strict' option with '-ffp-contract=on' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-honor-infinities -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-honor-infinities -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN8 %s
// WARN8: warning: overriding '-ffp-model=strict' option with '-fno-honor-infinities' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-honor-nans -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-honor-nans -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN9 %s
// WARN9: warning: overriding '-ffp-model=strict' option with '-fno-honor-nans' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-rounding-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-rounding-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNa %s
// WARNa: warning: overriding '-ffp-model=strict' option with '-fno-rounding-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-signed-zeros -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-signed-zeros -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNb %s
// WARNb: warning: overriding '-ffp-model=strict' option with '-fno-signed-zeros' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fno-trapping-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fno-trapping-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNc %s
// WARNc: warning: overriding '-ffp-model=strict' option with '-fno-trapping-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -freciprocal-math -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -freciprocal-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNd %s
// WARNd: warning: overriding '-ffp-model=strict' option with '-freciprocal-math' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -funsafe-math-optimizations -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -funsafe-math-optimizations -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNe %s
// WARNe: warning: overriding '-ffp-model=strict' option with '-funsafe-math-optimizations' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -Ofast -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -Ofast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARNf %s
// WARNf: warning: overriding '-ffp-model=strict' option with '-Ofast' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -ffp-model=strict -fdenormal-fp-math=preserve-sign,preserve-sign -c %s 2>&1 \
+// RUN: %clang -### -ffp-model=strict -fdenormal-fp-math=preserve-sign,preserve-sign -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=WARN10 %s
// WARN10: warning: overriding '-ffp-model=strict' option with '-fdenormal-fp-math=preserve-sign,preserve-sign' [-Woverriding-t-option]
-// RUN: %clang -target x86_64 -### -c %s 2>&1 \
+// RUN: %clang -### -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-NOROUND %s
// CHECK-NOROUND: "-cc1"
// CHECK-NOROUND: "-fno-rounding-math"
-// RUN: %clang -target x86_64 -### -frounding-math -c %s 2>&1 \
+// RUN: %clang -### -frounding-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-ROUND --implicit-check-not ffp-exception-behavior=strict %s
// CHECK-ROUND: "-cc1"
// CHECK-ROUND: "-frounding-math"
-// RUN: %clang -target x86_64 -### -ftrapping-math -c %s 2>&1 \
+// RUN: %clang -### -ftrapping-math -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-TRAP %s
// CHECK-TRAP: "-cc1"
// CHECK-TRAP: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=fast -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=fast -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-FAST %s
// CHECK-FPM-FAST: "-cc1"
// CHECK-FPM-FAST: "-menable-no-infs"
@@ -98,35 +96,34 @@
// CHECK-FPM-FAST: "-ffast-math"
// CHECK-FPM-FAST: "-ffinite-math-only"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=precise -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=precise -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-PRECISE %s
// CHECK-FPM-PRECISE: "-cc1"
-// CHECK-FPM-PRECISE: "-ffp-contract=on"
+// CHECK-FPM-PRECISE: "-ffp-contract=fast"
// CHECK-FPM-PRECISE: "-fno-rounding-math"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-model=strict -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-model=strict -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FPM-STRICT %s
// CHECK-FPM-STRICT: "-cc1"
-// CHECK-FPM-STRICT: "-fmath-errno"
-// CHECK-FPM-STRICT: "-ffp-contract=off"
// CHECK-FPM-STRICT: "-frounding-math"
// CHECK-FPM-STRICT: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=strict -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=strict -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-STRICT %s
// CHECK-FEB-STRICT: "-cc1"
// CHECK-FEB-STRICT: "-fno-rounding-math"
// CHECK-FEB-STRICT: "-ffp-exception-behavior=strict"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=maytrap -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=maytrap -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-MAYTRAP %s
// CHECK-FEB-MAYTRAP: "-cc1"
// CHECK-FEB-MAYTRAP: "-fno-rounding-math"
// CHECK-FEB-MAYTRAP: "-ffp-exception-behavior=maytrap"
-// RUN: %clang -target x86_64 -### -nostdinc -ffp-exception-behavior=ignore -c %s 2>&1 \
+// RUN: %clang -### -nostdinc -ffp-exception-behavior=ignore -c %s 2>&1 \
// RUN: | FileCheck --check-prefix=CHECK-FEB-IGNORE %s
// CHECK-FEB-IGNORE: "-cc1"
// CHECK-FEB-IGNORE: "-fno-rounding-math"
// CHECK-FEB-IGNORE: "-ffp-exception-behavior=ignore"
+
</cut>
4 years
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3_LTO - Build # 5 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit 669ddd1e9b1226432b003dbba05b99f8e992285b
Author: Arthur Eubanks <aeubanks(a)google.com>
Date: Mon Jan 25 11:00:56 2021 -0800
Turn on the new pass manager by default
This turns on the new pass manager by default for the optimization pipeline in
Clang and ThinLTO in various LLD backends. This also makes uses of `opt
-instcombine` use the new pass manager (unless specifically opted out).
This does not affect the backend target-dependent codegen pipeline.
If this causes regressions, you can opt out of the new pass manager
either via the -DENABLE_EXPERIMENTAL_NEW_PASS_MANAGER=OFF CMake flag
while building LLVM, or via various compiler flags, e.g.
-flegacy-pass-manager for Clang or -Wl,--lto-legacy-pass-manager for
ELF LLD. Please file bugs for any regressions.
Major differences:
* The inliner works slightly differently
* -O1 does some amount of inlining
* LCSSA and LoopSimplify are run before all loop passes
* Loop unswitching is implemented slightly differently
* A new SpeculateAroundPHIs pass is added to the pipeline
https://lists.llvm.org/pipermail/llvm-dev/2021-January/148098.html
Reviewed By: asbirlea, ychen, MaskRay, echristo
Differential Revision: https://reviews.llvm.org/D95380
</cut>
Results regressed to (for first_bad == 669ddd1e9b1226432b003dbba05b99f8e992285b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-669ddd1e9b1226432b003dbba05b99f8e992285b/results_id:
1
# 473.astar,astar_base.default regressed by 106
from (for last_good == b15cbaf5a03d0b32dbc32c37766e32ccf66e6c87)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3_LTO artifacts/build-b15cbaf5a03d0b32dbc32c37766e32ccf66e6c87/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/3543
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3_LTO/3539
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-669ddd1e9b1226432b003dbba05b99f8e992285b
cd investigate-llvm-669ddd1e9b1226432b003dbba05b99f8e992285b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 669ddd1e9b1226432b003dbba05b99f8e992285b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach b15cbaf5a03d0b32dbc32c37766e32ccf66e6c87
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 669ddd1e9b1226432b003dbba05b99f8e992285b
Author: Arthur Eubanks <aeubanks(a)google.com>
Date: Mon Jan 25 11:00:56 2021 -0800
Turn on the new pass manager by default
This turns on the new pass manager by default for the optimization pipeline in
Clang and ThinLTO in various LLD backends. This also makes uses of `opt
-instcombine` use the new pass manager (unless specifically opted out).
This does not affect the backend target-dependent codegen pipeline.
If this causes regressions, you can opt out of the new pass manager
either via the -DENABLE_EXPERIMENTAL_NEW_PASS_MANAGER=OFF CMake flag
while building LLVM, or via various compiler flags, e.g.
-flegacy-pass-manager for Clang or -Wl,--lto-legacy-pass-manager for
ELF LLD. Please file bugs for any regressions.
Major differences:
* The inliner works slightly differently
* -O1 does some amount of inlining
* LCSSA and LoopSimplify are run before all loop passes
* Loop unswitching is implemented slightly differently
* A new SpeculateAroundPHIs pass is added to the pipeline
https://lists.llvm.org/pipermail/llvm-dev/2021-January/148098.html
Reviewed By: asbirlea, ychen, MaskRay, echristo
Differential Revision: https://reviews.llvm.org/D95380
---
llvm/CMakeLists.txt | 4 ++--
1 file changed, 2 insertions(+), 2 deletions(-)
diff --git a/llvm/CMakeLists.txt b/llvm/CMakeLists.txt
index 1affc289e64b..f5298de9f7ca 100644
--- a/llvm/CMakeLists.txt
+++ b/llvm/CMakeLists.txt
@@ -688,8 +688,8 @@ else()
endif()
option(LLVM_ENABLE_PLUGINS "Enable plugin support" ${LLVM_ENABLE_PLUGINS_default})
-set(ENABLE_EXPERIMENTAL_NEW_PASS_MANAGER FALSE CACHE BOOL
- "Enable the experimental new pass manager by default.")
+set(ENABLE_EXPERIMENTAL_NEW_PASS_MANAGER TRUE CACHE BOOL
+ "Enable the new pass manager by default.")
include(HandleLLVMOptions)
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Os_LTO - Build # 5 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Os_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Os_LTO
Culprit:
<cut>
commit 0a241e90d4931a764109da70c2322a0a9386b1a7
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Sat Aug 7 15:59:21 2021 +0300
[NFC][InstCombine] `vector_reduce_xor(?ext(<n x i1>))` --> `?ext(vector_reduce_add(<n x i1>))`
Instead of expanding it ourselves,
we can just forward to `?ext(vector_reduce_add(<n x i1>))`, as per alive2:
https://alive2.llvm.org/ce/z/ymz7zE (self)
https://alive2.llvm.org/ce/z/eKu2v2 (skipped zext)
https://alive2.llvm.org/ce/z/c3BXgc (skipped sext)
</cut>
Results regressed to (for first_bad == 0a241e90d4931a764109da70c2322a0a9386b1a7)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os_LTO artifacts/build-0a241e90d4931a764109da70c2322a0a9386b1a7/results_id:
1
# 433.milc,milc_base.default regressed by 102
# 453.povray,povray_base.default regressed by 102
# 470.lbm,lbm_base.default regressed by 103
from (for last_good == c6ff867f92f67c6451ed1709f2af66211cb7b901)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os_LTO artifacts/build-c6ff867f92f67c6451ed1709f2af66211cb7b901/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Os_LTO/3523
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Os_LTO/3530
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-0a241e90d4931a764109da70c2322a0a9386b1a7
cd investigate-llvm-0a241e90d4931a764109da70c2322a0a9386b1a7
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 0a241e90d4931a764109da70c2322a0a9386b1a7
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c6ff867f92f67c6451ed1709f2af66211cb7b901
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 0a241e90d4931a764109da70c2322a0a9386b1a7
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Sat Aug 7 15:59:21 2021 +0300
[NFC][InstCombine] `vector_reduce_xor(?ext(<n x i1>))` --> `?ext(vector_reduce_add(<n x i1>))`
Instead of expanding it ourselves,
we can just forward to `?ext(vector_reduce_add(<n x i1>))`, as per alive2:
https://alive2.llvm.org/ce/z/ymz7zE (self)
https://alive2.llvm.org/ce/z/eKu2v2 (skipped zext)
https://alive2.llvm.org/ce/z/c3BXgc (skipped sext)
---
llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp | 11 ++++-------
1 file changed, 4 insertions(+), 7 deletions(-)
diff --git a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
index 2ba326d791c2..210652e23377 100644
--- a/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
+++ b/llvm/lib/Transforms/InstCombine/InstCombineCalls.cpp
@@ -2038,20 +2038,17 @@ Instruction *InstCombinerImpl::visitCallInst(CallInst &CI) {
if (IID == Intrinsic::vector_reduce_xor) {
// Exclusive disjunction reduction over the vector with
// (potentially-extended) i1 element type is actually a
- // (potentially-extended) parity check:
+ // (potentially-extended) arithmetic `add` reduction over the original
+ // non-extended value:
// vector_reduce_xor(?ext(<n x i1>))
// -->
- // ?ext(trunc(vector_reduce_and(<n x i1>) to i1))
+ // ?ext(vector_reduce_add(<n x i1>))
Value *Arg = II->getArgOperand(0);
Value *Vect;
if (match(Arg, m_ZExtOrSExtOrSelf(m_Value(Vect)))) {
if (auto *FTy = dyn_cast<FixedVectorType>(Vect->getType()))
if (FTy->getElementType() == Builder.getInt1Ty()) {
- Value *V = Builder.CreateBitCast(
- Vect, Builder.getIntNTy(FTy->getNumElements()));
- Value *Res = Builder.CreateUnaryIntrinsic(Intrinsic::ctpop, V);
- Res = Builder.CreateTrunc(Res,
- IntegerType::get(Res->getContext(), 1));
+ Value *Res = Builder.CreateAddReduce(Vect);
if (Arg != Vect)
Res = Builder.CreateCast(cast<CastInst>(Arg)->getOpcode(), Res,
II->getType());
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2 - Build # 16 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2
Culprit:
<cut>
commit 7d15c4941499b1454432d63604dc6bbe56e32ce7
Author: Sanjay Patel <spatel(a)rotateright.com>
Date: Tue May 18 14:02:11 2021 -0400
[x86] trim zeros from constants for readability; NFC
</cut>
Results regressed to (for first_bad == 7d15c4941499b1454432d63604dc6bbe56e32ce7)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_marm artifacts/build-7d15c4941499b1454432d63604dc6bbe56e32ce7/results_id:
1
# 482.sphinx3,sphinx_livepretend_base.default regressed by 104
from (for last_good == 2257e4a70e4aabe7255161f3a54922d7dcf1c059)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_marm artifacts/build-2257e4a70e4aabe7255161f3a54922d7dcf1c059/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/3446
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/3510
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-7d15c4941499b1454432d63604dc6bbe56e32ce7
cd investigate-llvm-7d15c4941499b1454432d63604dc6bbe56e32ce7
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 7d15c4941499b1454432d63604dc6bbe56e32ce7
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 2257e4a70e4aabe7255161f3a54922d7dcf1c059
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 7d15c4941499b1454432d63604dc6bbe56e32ce7
Author: Sanjay Patel <spatel(a)rotateright.com>
Date: Tue May 18 14:02:11 2021 -0400
[x86] trim zeros from constants for readability; NFC
---
llvm/test/CodeGen/X86/fma-fneg-combine.ll | 58 +++++++++++++++----------------
1 file changed, 29 insertions(+), 29 deletions(-)
diff --git a/llvm/test/CodeGen/X86/fma-fneg-combine.ll b/llvm/test/CodeGen/X86/fma-fneg-combine.ll
index a67595c1e95a..9e47548f27f1 100644
--- a/llvm/test/CodeGen/X86/fma-fneg-combine.ll
+++ b/llvm/test/CodeGen/X86/fma-fneg-combine.ll
@@ -11,7 +11,7 @@ define <16 x float> @test1(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: vfmsub213ps {{.*#+}} zmm0 = (zmm1 * zmm0) - zmm2
; CHECK-NEXT: retq
entry:
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 4) #2
ret <16 x float> %0
}
@@ -28,7 +28,7 @@ define <16 x float> @test2(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i32 4) #2
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0
ret <16 x float> %sub.i
}
@@ -39,7 +39,7 @@ define <16 x float> @test3(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 4) #2
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0
ret <16 x float> %sub.i
}
@@ -50,7 +50,7 @@ define <16 x float> @test4(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 4) #2
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0
ret <16 x float> %sub.i
}
@@ -60,7 +60,7 @@ define <16 x float> @test5(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: vfmsub213ps {ru-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
entry:
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 10) #2
ret <16 x float> %0
}
@@ -72,7 +72,7 @@ define <16 x float> @test6(<16 x float> %a, <16 x float> %b, <16 x float> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 -1, i32 10) #2
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0
ret <16 x float> %sub.i
}
@@ -84,7 +84,7 @@ define <8 x float> @test7(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %c) #2
- %sub.i = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
+ %sub.i = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0
ret <8 x float> %sub.i
}
@@ -94,7 +94,7 @@ define <8 x float> @test8(<8 x float> %a, <8 x float> %b, <8 x float> %c) {
; CHECK-NEXT: vfmadd213ps {{.*#+}} ymm0 = (ymm1 * ymm0) + ymm2
; CHECK-NEXT: retq
entry:
- %sub.c = fsub <8 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.c = fsub <8 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <8 x float> @llvm.x86.fma.vfmsub.ps.256(<8 x float> %a, <8 x float> %b, <8 x float> %sub.c) #2
ret <8 x float> %0
}
@@ -109,7 +109,7 @@ define <8 x double> @test9(<8 x double> %a, <8 x double> %b, <8 x double> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %c, i32 4) #2
- %sub.i = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %0
+ %sub.i = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %0
ret <8 x double> %sub.i
}
@@ -123,7 +123,7 @@ define <2 x double> @test10(<2 x double> %a, <2 x double> %b, <2 x double> %c) {
; CHECK-NEXT: retq
entry:
%0 = tail call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %a, <2 x double> %b, <2 x double> %c, i8 -1, i32 4) #2
- %sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %0
+ %sub.i = fsub <2 x double> <double -0.0, double -0.0>, %0
ret <2 x double> %sub.i
}
@@ -149,7 +149,7 @@ define <4 x float> @test11(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vmovaps %xmm3, %xmm0
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i, i8 %mask, i32 4) #10
ret <4 x float> %0
}
@@ -169,7 +169,7 @@ define <4 x float> @test11b(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 z
; KNL-NEXT: vfmsub213ss {{.*#+}} xmm0 {%k1} = (xmm1 * xmm0) - xmm2
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i, i8 %mask, i32 4) #10
ret <4 x float> %0
}
@@ -194,7 +194,7 @@ entry:
%0 = tail call <8 x double> @llvm.x86.avx512.vfmadd.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %c, i32 4) #2
%bc = bitcast i8 %mask to <8 x i1>
%sel = select <8 x i1> %bc, <8 x double> %0, <8 x double> %a
- %sub.i = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %sel
+ %sub.i = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %sel
ret <8 x double> %sub.i
}
@@ -218,7 +218,7 @@ define <2 x double> @test13(<2 x double> %a, <2 x double> %b, <2 x double> %c, i
; KNL-NEXT: retq
entry:
- %sub.i = fsub <2 x double> <double -0.000000e+00, double -0.000000e+00>, %a
+ %sub.i = fsub <2 x double> <double -0.0, double -0.0>, %a
%0 = tail call <2 x double> @llvm.x86.avx512.mask.vfmadd.sd(<2 x double> %sub.i, <2 x double> %b, <2 x double> %c, i8 %mask, i32 4)
ret <2 x double> %0
}
@@ -239,7 +239,7 @@ define <16 x float> @test14(<16 x float> %a, <16 x float> %b, <16 x float> %c, i
; KNL-NEXT: retq
entry:
%0 = tail call <16 x float> @llvm.x86.avx512.mask.vfnmsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %c, i16 %mask, i32 10) #2
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %0
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %0
ret <16 x float> %sub.i
}
@@ -265,7 +265,7 @@ define <16 x float> @test15(<16 x float> %a, <16 x float> %b, <16 x float> %c, i
; KNL-NEXT: retq
entry:
%bc = bitcast i16 %mask to <16 x i1>
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %a
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %a
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sub.i, <16 x float> %b, <16 x float> %c, i32 10)
%sel = select <16 x i1> %bc, <16 x float> %0, <16 x float> %sub.i
%1 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %sel, <16 x float> %sub.i, <16 x float> %c, i32 9)
@@ -285,7 +285,7 @@ define <16 x float> @test16(<16 x float> %a, <16 x float> %b, <16 x float> %c, i
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vfmsubadd132ps {rd-sae}, %zmm1, %zmm2, %zmm0 {%k1}
; KNL-NEXT: retq
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%res = call <16 x float> @llvm.x86.avx512.vfmaddsub.ps.512(<16 x float> %a, <16 x float> %b, <16 x float> %sub.i, i32 9)
%bc = bitcast i16 %mask to <16 x i1>
%sel = select <16 x i1> %bc, <16 x float> %res, <16 x float> %a
@@ -305,7 +305,7 @@ define <8 x double> @test17(<8 x double> %a, <8 x double> %b, <8 x double> %c, i
; KNL-NEXT: kmovw %edi, %k1
; KNL-NEXT: vfmsubadd132pd {{.*#+}} zmm0 {%k1} = (zmm0 * zmm1) -/+ zmm2
; KNL-NEXT: retq
- %sub.i = fsub <8 x double> <double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00, double -0.000000e+00>, %c
+ %sub.i = fsub <8 x double> <double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0, double -0.0>, %c
%res = call <8 x double> @llvm.x86.avx512.vfmaddsub.pd.512(<8 x double> %a, <8 x double> %b, <8 x double> %sub.i, i32 4)
%bc = bitcast i8 %mask to <8 x i1>
%sel = select <8 x i1> %bc, <8 x double> %res, <8 x double> %a
@@ -326,7 +326,7 @@ define <4 x float> @test18(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vfnmadd213ss {{.*#+}} xmm0 {%k1} = -(xmm1 * xmm0) + xmm2
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b
%0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 4) #10
ret <4 x float> %0
}
@@ -344,8 +344,8 @@ define <4 x float> @test19(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vfnmsub213ss {{.*#+}} xmm0 {%k1} = -(xmm1 * xmm0) - xmm2
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
- %sub.i.2 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b
+ %sub.i.2 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %sub.i.2, i8 %mask, i32 4) #10
ret <4 x float> %0
}
@@ -365,7 +365,7 @@ define <4 x float> @test20(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vmovaps %xmm2, %xmm0
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b
%0 = tail call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 4) #10
ret <4 x float> %0
}
@@ -383,7 +383,7 @@ define <4 x float> @test21(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vfnmadd213ss {rn-sae}, %xmm2, %xmm1, %xmm0 {%k1}
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b
%0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 8) #10
ret <4 x float> %0
}
@@ -401,8 +401,8 @@ define <4 x float> @test22(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vfnmsub213ss {rn-sae}, %xmm2, %xmm1, %xmm0 {%k1}
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
- %sub.i.2 = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b
+ %sub.i.2 = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %sub.i.2, i8 %mask, i32 8) #10
ret <4 x float> %0
}
@@ -422,7 +422,7 @@ define <4 x float> @test23(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vmovaps %xmm2, %xmm0
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %b
%0 = tail call <4 x float> @llvm.x86.avx512.mask3.vfmadd.ss(<4 x float> %a, <4 x float> %sub.i, <4 x float> %c, i8 %mask, i32 8) #10
ret <4 x float> %0
}
@@ -440,7 +440,7 @@ define <4 x float> @test24(<4 x float> %a, <4 x float> %b, <4 x float> %c, i8 ze
; KNL-NEXT: vfmsub213ss {rn-sae}, %xmm2, %xmm1, %xmm0 {%k1}
; KNL-NEXT: retq
entry:
- %sub.i = fsub <4 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <4 x float> <float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <4 x float> @llvm.x86.avx512.mask.vfmadd.ss(<4 x float> %a, <4 x float> %b, <4 x float> %sub.i, i8 %mask, i32 8) #10
ret <4 x float> %0
}
@@ -451,8 +451,8 @@ define <16 x float> @test25(<16 x float> %a, <16 x float> %b, <16 x float> %c)
; CHECK-NEXT: vfnmsub213ps {rn-sae}, %zmm2, %zmm1, %zmm0
; CHECK-NEXT: retq
entry:
- %sub.i = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %b
- %sub.i.2 = fsub <16 x float> <float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00, float -0.000000e+00>, %c
+ %sub.i = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %b
+ %sub.i.2 = fsub <16 x float> <float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0, float -0.0>, %c
%0 = tail call <16 x float> @llvm.x86.avx512.vfmadd.ps.512(<16 x float> %a, <16 x float> %sub.i, <16 x float> %sub.i.2, i32 8) #2
ret <16 x float> %0
}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 25 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit df7c22831f1e48dba49479c5960c1c180d8eab2c
Author: Richard Sandiford <richard.sandiford(a)arm.com>
Date: Thu Nov 14 15:12:58 2019 +0000
Support vectorisation with mixed vector sizes
After previous patches, it's now possible to make the vectoriser
support multiple vector sizes in the same vector region, using
related_vector_mode to pick the right vector mode for a given
element mode. No port yet takes advantage of this, but I have
a follow-on patch for AArch64.
This patch also seemed like a good opportunity to add some more dump
messages: one to make it clear which vector size/mode was being used
when analysis passed or failed, and another to say when we've decided
to skip a redundant vector size/mode.
2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com>
gcc/
* machmode.h (opt_machine_mode::operator==): New function.
(opt_machine_mode::operator!=): Likewise.
* tree-vectorizer.h (vec_info::vector_mode): Update comment.
(get_related_vectype_for_scalar_type): Delete.
(get_vectype_for_scalar_type_and_size): Declare.
* tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say
whether analysis passed or failed, and with what vector modes.
Use related_vector_mode to check whether trying a particular
vector mode would be redundant with the autodetected mode,
and print a dump message if we decide to skip it.
* tree-vect-loop.c (vect_analyze_loop): Likewise.
(vect_create_epilog_for_reduction): Use
get_related_vectype_for_scalar_type instead of
get_vectype_for_scalar_type_and_size.
* tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace
with...
(get_related_vectype_for_scalar_type): ...this new function.
Take a starting/"prevailing" vector mode rather than a vector size.
Take an optional nunits argument, with the same meaning as for
related_vector_mode. Use related_vector_mode when not
auto-detecting a mode, falling back to mode_for_vector if no
target mode exists.
(get_vectype_for_scalar_type): Update accordingly.
(get_same_sized_vectype): Likewise.
* tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise.
From-SVN: r278240
</cut>
Results regressed to (for first_bad == df7c22831f1e48dba49479c5960c1c180d8eab2c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-df7c22831f1e48dba49479c5960c1c180d8eab2c/results_id:
1
# 453.povray,[.] _ZN3povL24All_Sphere_IntersectionsEPNS_13Objec regressed by 114
# 482.sphinx3,[.] subvq_mgau_shortlist regressed by 112
from (for last_good == 7f52eb891b738337d5cf82c7c440a5eea8c7b0c9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-7f52eb891b738337d5cf82c7c440a5eea8c7b0c9/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3483
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3492
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-df7c22831f1e48dba49479c5960c1c180d8eab2c
cd investigate-gcc-df7c22831f1e48dba49479c5960c1c180d8eab2c
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach df7c22831f1e48dba49479c5960c1c180d8eab2c
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 7f52eb891b738337d5cf82c7c440a5eea8c7b0c9
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit df7c22831f1e48dba49479c5960c1c180d8eab2c
Author: Richard Sandiford <richard.sandiford(a)arm.com>
Date: Thu Nov 14 15:12:58 2019 +0000
Support vectorisation with mixed vector sizes
After previous patches, it's now possible to make the vectoriser
support multiple vector sizes in the same vector region, using
related_vector_mode to pick the right vector mode for a given
element mode. No port yet takes advantage of this, but I have
a follow-on patch for AArch64.
This patch also seemed like a good opportunity to add some more dump
messages: one to make it clear which vector size/mode was being used
when analysis passed or failed, and another to say when we've decided
to skip a redundant vector size/mode.
2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com>
gcc/
* machmode.h (opt_machine_mode::operator==): New function.
(opt_machine_mode::operator!=): Likewise.
* tree-vectorizer.h (vec_info::vector_mode): Update comment.
(get_related_vectype_for_scalar_type): Delete.
(get_vectype_for_scalar_type_and_size): Declare.
* tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say
whether analysis passed or failed, and with what vector modes.
Use related_vector_mode to check whether trying a particular
vector mode would be redundant with the autodetected mode,
and print a dump message if we decide to skip it.
* tree-vect-loop.c (vect_analyze_loop): Likewise.
(vect_create_epilog_for_reduction): Use
get_related_vectype_for_scalar_type instead of
get_vectype_for_scalar_type_and_size.
* tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace
with...
(get_related_vectype_for_scalar_type): ...this new function.
Take a starting/"prevailing" vector mode rather than a vector size.
Take an optional nunits argument, with the same meaning as for
related_vector_mode. Use related_vector_mode when not
auto-detecting a mode, falling back to mode_for_vector if no
target mode exists.
(get_vectype_for_scalar_type): Update accordingly.
(get_same_sized_vectype): Likewise.
* tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise.
From-SVN: r278240
---
gcc/ChangeLog | 28 +++++++++++++++++++++++++
gcc/machmode.h | 3 +++
gcc/tree-vect-loop.c | 54 +++++++++++++++++++++++++++++++++++-------------
gcc/tree-vect-slp.c | 33 +++++++++++++++++++++++++----
gcc/tree-vect-stmts.c | 57 ++++++++++++++++++++++++++++++++++++---------------
gcc/tree-vectorizer.c | 2 +-
gcc/tree-vectorizer.h | 8 +++++---
7 files changed, 147 insertions(+), 38 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 41c94140b1a..680aa85121a 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,31 @@
+2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com>
+
+ * machmode.h (opt_machine_mode::operator==): New function.
+ (opt_machine_mode::operator!=): Likewise.
+ * tree-vectorizer.h (vec_info::vector_mode): Update comment.
+ (get_related_vectype_for_scalar_type): Delete.
+ (get_vectype_for_scalar_type_and_size): Declare.
+ * tree-vect-slp.c (vect_slp_bb_region): Print dump messages to say
+ whether analysis passed or failed, and with what vector modes.
+ Use related_vector_mode to check whether trying a particular
+ vector mode would be redundant with the autodetected mode,
+ and print a dump message if we decide to skip it.
+ * tree-vect-loop.c (vect_analyze_loop): Likewise.
+ (vect_create_epilog_for_reduction): Use
+ get_related_vectype_for_scalar_type instead of
+ get_vectype_for_scalar_type_and_size.
+ * tree-vect-stmts.c (get_vectype_for_scalar_type_and_size): Replace
+ with...
+ (get_related_vectype_for_scalar_type): ...this new function.
+ Take a starting/"prevailing" vector mode rather than a vector size.
+ Take an optional nunits argument, with the same meaning as for
+ related_vector_mode. Use related_vector_mode when not
+ auto-detecting a mode, falling back to mode_for_vector if no
+ target mode exists.
+ (get_vectype_for_scalar_type): Update accordingly.
+ (get_same_sized_vectype): Likewise.
+ * tree-vectorizer.c (get_vec_alignment_for_array_type): Likewise.
+
2019-11-14 Richard Sandiford <richard.sandiford(a)arm.com>
* tree-vect-stmts.c (vectorizable_call): Require the types
diff --git a/gcc/machmode.h b/gcc/machmode.h
index 6750833c2fe..a507ed66c3f 100644
--- a/gcc/machmode.h
+++ b/gcc/machmode.h
@@ -258,6 +258,9 @@ public:
bool exists () const;
template<typename U> bool exists (U *) const;
+ bool operator== (const T &m) const { return m_mode == m; }
+ bool operator!= (const T &m) const { return m_mode != m; }
+
private:
machine_mode m_mode;
};
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 213d620ed2c..e60c159d11a 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -2435,6 +2435,17 @@ vect_analyze_loop (class loop *loop, vec_info_shared *shared)
res = vect_analyze_loop_2 (loop_vinfo, fatal, &n_stmts);
if (mode_i == 0)
autodetected_vector_mode = loop_vinfo->vector_mode;
+ if (dump_enabled_p ())
+ {
+ if (res)
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "***** Analysis succeeded with vector mode %s\n",
+ GET_MODE_NAME (loop_vinfo->vector_mode));
+ else
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "***** Analysis failed with vector mode %s\n",
+ GET_MODE_NAME (loop_vinfo->vector_mode));
+ }
loop->aux = NULL;
if (res)
@@ -2501,9 +2512,22 @@ vect_analyze_loop (class loop *loop, vec_info_shared *shared)
}
if (mode_i < vector_modes.length ()
- && known_eq (GET_MODE_SIZE (vector_modes[mode_i]),
- GET_MODE_SIZE (autodetected_vector_mode)))
- mode_i += 1;
+ && VECTOR_MODE_P (autodetected_vector_mode)
+ && (related_vector_mode (vector_modes[mode_i],
+ GET_MODE_INNER (autodetected_vector_mode))
+ == autodetected_vector_mode)
+ && (related_vector_mode (autodetected_vector_mode,
+ GET_MODE_INNER (vector_modes[mode_i]))
+ == vector_modes[mode_i]))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "***** Skipping vector mode %s, which would"
+ " repeat the analysis for %s\n",
+ GET_MODE_NAME (vector_modes[mode_i]),
+ GET_MODE_NAME (autodetected_vector_mode));
+ mode_i += 1;
+ }
if (mode_i == vector_modes.length ()
|| autodetected_vector_mode == VOIDmode)
@@ -4898,13 +4922,14 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info,
halves against each other. */
enum machine_mode mode1 = mode;
tree stype = TREE_TYPE (vectype);
- unsigned sz = tree_to_uhwi (TYPE_SIZE_UNIT (vectype));
- unsigned sz1 = sz;
+ unsigned nunits = TYPE_VECTOR_SUBPARTS (vectype).to_constant ();
+ unsigned nunits1 = nunits;
if (!slp_reduc
&& (mode1 = targetm.vectorize.split_reduction (mode)) != mode)
- sz1 = GET_MODE_SIZE (mode1).to_constant ();
+ nunits1 = GET_MODE_NUNITS (mode1).to_constant ();
- tree vectype1 = get_vectype_for_scalar_type_and_size (stype, sz1);
+ tree vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype),
+ stype, nunits1);
reduce_with_shift = have_whole_vector_shift (mode1);
if (!VECTOR_MODE_P (mode1))
reduce_with_shift = false;
@@ -4918,11 +4943,13 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info,
/* First reduce the vector to the desired vector size we should
do shift reduction on by combining upper and lower halves. */
new_temp = new_phi_result;
- while (sz > sz1)
+ while (nunits > nunits1)
{
gcc_assert (!slp_reduc);
- sz /= 2;
- vectype1 = get_vectype_for_scalar_type_and_size (stype, sz);
+ nunits /= 2;
+ vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype),
+ stype, nunits);
+ unsigned int bitsize = tree_to_uhwi (TYPE_SIZE (vectype1));
/* The target has to make sure we support lowpart/highpart
extraction, either via direct vector extract or through
@@ -4947,15 +4974,14 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info,
= gimple_build_assign (dst2, BIT_FIELD_REF,
build3 (BIT_FIELD_REF, vectype1,
new_temp, TYPE_SIZE (vectype1),
- bitsize_int (sz * BITS_PER_UNIT)));
+ bitsize_int (bitsize)));
gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
}
else
{
/* Extract via punning to appropriately sized integer mode
vector. */
- tree eltype = build_nonstandard_integer_type (sz * BITS_PER_UNIT,
- 1);
+ tree eltype = build_nonstandard_integer_type (bitsize, 1);
tree etype = build_vector_type (eltype, 2);
gcc_assert (convert_optab_handler (vec_extract_optab,
TYPE_MODE (etype),
@@ -4984,7 +5010,7 @@ vect_create_epilog_for_reduction (stmt_vec_info stmt_info,
= gimple_build_assign (tem, BIT_FIELD_REF,
build3 (BIT_FIELD_REF, eltype,
new_temp, TYPE_SIZE (eltype),
- bitsize_int (sz * BITS_PER_UNIT)));
+ bitsize_int (bitsize)));
gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
dst2 = make_ssa_name (vectype1);
epilog_stmt = gimple_build_assign (dst2, VIEW_CONVERT_EXPR,
diff --git a/gcc/tree-vect-slp.c b/gcc/tree-vect-slp.c
index 3885d9cbe4a..1e00db5a326 100644
--- a/gcc/tree-vect-slp.c
+++ b/gcc/tree-vect-slp.c
@@ -3203,7 +3203,12 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin,
&& dbg_cnt (vect_slp))
{
if (dump_enabled_p ())
- dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n");
+ {
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "***** Analysis succeeded with vector mode"
+ " %s\n", GET_MODE_NAME (bb_vinfo->vector_mode));
+ dump_printf_loc (MSG_NOTE, vect_location, "SLPing BB part\n");
+ }
bb_vinfo->shared->check_datarefs ();
vect_schedule_slp (bb_vinfo);
@@ -3223,6 +3228,13 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin,
vectorized = true;
}
+ else
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "***** Analysis failed with vector mode %s\n",
+ GET_MODE_NAME (bb_vinfo->vector_mode));
+ }
if (mode_i == 0)
autodetected_vector_mode = bb_vinfo->vector_mode;
@@ -3230,9 +3242,22 @@ vect_slp_bb_region (gimple_stmt_iterator region_begin,
delete bb_vinfo;
if (mode_i < vector_modes.length ()
- && known_eq (GET_MODE_SIZE (vector_modes[mode_i]),
- GET_MODE_SIZE (autodetected_vector_mode)))
- mode_i += 1;
+ && VECTOR_MODE_P (autodetected_vector_mode)
+ && (related_vector_mode (vector_modes[mode_i],
+ GET_MODE_INNER (autodetected_vector_mode))
+ == autodetected_vector_mode)
+ && (related_vector_mode (autodetected_vector_mode,
+ GET_MODE_INNER (vector_modes[mode_i]))
+ == vector_modes[mode_i]))
+ {
+ if (dump_enabled_p ())
+ dump_printf_loc (MSG_NOTE, vect_location,
+ "***** Skipping vector mode %s, which would"
+ " repeat the analysis for %s\n",
+ GET_MODE_NAME (vector_modes[mode_i]),
+ GET_MODE_NAME (autodetected_vector_mode));
+ mode_i += 1;
+ }
if (vectorized
|| mode_i == vector_modes.length ()
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 80f59accad7..36f832bb522 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -11138,18 +11138,28 @@ vect_remove_stores (stmt_vec_info first_stmt_info)
}
}
-/* Function get_vectype_for_scalar_type_and_size.
+/* If NUNITS is nonzero, return a vector type that contains NUNITS
+ elements of type SCALAR_TYPE, or null if the target doesn't support
+ such a type.
- Returns the vector type corresponding to SCALAR_TYPE and SIZE as supported
- by the target. */
+ If NUNITS is zero, return a vector type that contains elements of
+ type SCALAR_TYPE, choosing whichever vector size the target prefers.
+
+ If PREVAILING_MODE is VOIDmode, we have not yet chosen a vector mode
+ for this vectorization region and want to "autodetect" the best choice.
+ Otherwise, PREVAILING_MODE is a previously-chosen vector TYPE_MODE
+ and we want the new type to be interoperable with it. PREVAILING_MODE
+ in this case can be a scalar integer mode or a vector mode; when it
+ is a vector mode, the function acts like a tree-level version of
+ related_vector_mode. */
tree
-get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size)
+get_related_vectype_for_scalar_type (machine_mode prevailing_mode,
+ tree scalar_type, poly_uint64 nunits)
{
tree orig_scalar_type = scalar_type;
scalar_mode inner_mode;
machine_mode simd_mode;
- poly_uint64 nunits;
tree vectype;
if (!is_int_mode (TYPE_MODE (scalar_type), &inner_mode)
@@ -11189,10 +11199,11 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size)
if (scalar_type == NULL_TREE)
return NULL_TREE;
- /* If no size was supplied use the mode the target prefers. Otherwise
- lookup a vector mode of the specified size. */
- if (known_eq (size, 0U))
+ /* If no prevailing mode was supplied, use the mode the target prefers.
+ Otherwise lookup a vector mode based on the prevailing mode. */
+ if (prevailing_mode == VOIDmode)
{
+ gcc_assert (known_eq (nunits, 0U));
simd_mode = targetm.vectorize.preferred_simd_mode (inner_mode);
if (SCALAR_INT_MODE_P (simd_mode))
{
@@ -11208,9 +11219,19 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size)
return NULL_TREE;
}
}
- else if (!multiple_p (size, nbytes, &nunits)
- || !mode_for_vector (inner_mode, nunits).exists (&simd_mode))
- return NULL_TREE;
+ else if (SCALAR_INT_MODE_P (prevailing_mode)
+ || !related_vector_mode (prevailing_mode,
+ inner_mode, nunits).exists (&simd_mode))
+ {
+ /* Fall back to using mode_for_vector, mostly in the hope of being
+ able to use an integer mode. */
+ if (known_eq (nunits, 0U)
+ && !multiple_p (GET_MODE_SIZE (prevailing_mode), nbytes, &nunits))
+ return NULL_TREE;
+
+ if (!mode_for_vector (inner_mode, nunits).exists (&simd_mode))
+ return NULL_TREE;
+ }
vectype = build_vector_type_for_mode (scalar_type, simd_mode);
@@ -11238,9 +11259,8 @@ get_vectype_for_scalar_type_and_size (tree scalar_type, poly_uint64 size)
tree
get_vectype_for_scalar_type (vec_info *vinfo, tree scalar_type)
{
- tree vectype;
- poly_uint64 vector_size = GET_MODE_SIZE (vinfo->vector_mode);
- vectype = get_vectype_for_scalar_type_and_size (scalar_type, vector_size);
+ tree vectype = get_related_vectype_for_scalar_type (vinfo->vector_mode,
+ scalar_type);
if (vectype && vinfo->vector_mode == VOIDmode)
vinfo->vector_mode = TYPE_MODE (vectype);
return vectype;
@@ -11273,8 +11293,13 @@ get_same_sized_vectype (tree scalar_type, tree vector_type)
if (VECT_SCALAR_BOOLEAN_TYPE_P (scalar_type))
return truth_type_for (vector_type);
- return get_vectype_for_scalar_type_and_size
- (scalar_type, GET_MODE_SIZE (TYPE_MODE (vector_type)));
+ poly_uint64 nunits;
+ if (!multiple_p (GET_MODE_SIZE (TYPE_MODE (vector_type)),
+ GET_MODE_SIZE (TYPE_MODE (scalar_type)), &nunits))
+ return NULL_TREE;
+
+ return get_related_vectype_for_scalar_type (TYPE_MODE (vector_type),
+ scalar_type, nunits);
}
/* Function vect_is_simple_use.
diff --git a/gcc/tree-vectorizer.c b/gcc/tree-vectorizer.c
index d6de78350e6..7be81a0b27f 100644
--- a/gcc/tree-vectorizer.c
+++ b/gcc/tree-vectorizer.c
@@ -1359,7 +1359,7 @@ get_vec_alignment_for_array_type (tree type)
poly_uint64 array_size, vector_size;
tree scalar_type = strip_array_types (type);
- tree vectype = get_vectype_for_scalar_type_and_size (scalar_type, 0);
+ tree vectype = get_related_vectype_for_scalar_type (VOIDmode, scalar_type);
if (!vectype
|| !poly_int_tree_p (TYPE_SIZE (type), &array_size)
|| !poly_int_tree_p (TYPE_SIZE (vectype), &vector_size)
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index f6efed1f863..fadc4d89d16 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -335,8 +335,9 @@ public:
/* Cost data used by the target cost model. */
void *target_cost_data;
- /* If we've chosen a vector size for this vectorization region,
- this is one mode that has such a size, otherwise it is VOIDmode. */
+ /* The argument we should pass to related_vector_mode when looking up
+ the vector mode for a scalar mode, or VOIDmode if we haven't yet
+ made any decisions about which vector modes to use. */
machine_mode vector_mode;
private:
@@ -1624,8 +1625,9 @@ extern bool vect_can_advance_ivs_p (loop_vec_info);
extern void vect_update_inits_of_drs (loop_vec_info, tree, tree_code);
/* In tree-vect-stmts.c. */
+extern tree get_related_vectype_for_scalar_type (machine_mode, tree,
+ poly_uint64 = 0);
extern tree get_vectype_for_scalar_type (vec_info *, tree);
-extern tree get_vectype_for_scalar_type_and_size (tree, poly_uint64);
extern tree get_mask_type_for_scalar_type (vec_info *, tree);
extern tree get_same_sized_vectype (tree, tree);
extern bool vect_get_loop_mask_type (loop_vec_info);
</cut>
4 years, 1 month
- 1
- 0
[ACTIVITY] week ending Aug. 15 2021
by Alex Bennée
VirtIO Initiative ([STR-9])
===========================
- posted Enabling hypervisor agnosticism for VirtIO backends
Message-Id: <87v94ldrqq.fsf(a)linaro.org>
VirtIO RPMB ([STR-5])
- made more progress and now have PROGRAM_KEY/WRITE_COUNTER done -
feels like it's getting faster
[hacking branch] <https://github.com/stsquad/virtio-rpmb/tree/hacking>
Fix VirtIO spec as per Rucha's email
------------------------------------
QEMU Upstream Work ([UM-2])
===========================
- posted [PATCH for 6.1-rc3 v1 0/4] gitlab and plugins pre-PR
Message-Id: <20210806141015.2487502-1-alex.bennee(a)linaro.org>
- prepared a potential [pull request for testing issues] but looks
like it will wait for 6.2
[pull request for testing issues]
<https://github.com/stsquad/qemu/tree/pr/120821-for-6.1-rc4-1>
Write a generic overview of vhost user usage for the manual
Enable plugins by default on TCG builds
- [X] clean-up testing matrix
Completed Reviews [10/10]
=========================
[PATCH 00/13] new plugin argument passing scheme
Message-Id: <20210717100920.240793-1-ma.mandourr(a)gmail.com>
[PATCH 0/9] new plugin argument passing scheme
Message-Id: <20210716080345.136784-1-ma.mandourr(a)gmail.com>
[RFC PATCH] Subject: [RFC PATCH] plugins: Passed the parsed arguments directly to plugins
Message-Id: <20210623155553.481099-1-ma.mandourr(a)gmail.com>
[PATCH 3/6] plugins/cache: Fixed a use-after-free bug with multithreaded usermode
Message-Id: <20210714172151.8494-4-ma.mandourr(a)gmail.com>
[PATCH v8] tests/tcg/s390x: Test SIGILL and SIGSEGV handling
Message-Id: <20210804225146.154513-1-iii(a)linux.ibm.com>
[RFC PATCH v2] Add a post for the new TCG cache modelling plugin
Message-Id: <20210617121707.764126-1-ma.mandourr(a)gmail.com>
[PATCH for 6.1] plugins: do not limit exported symbols if modules are active
Message-Id: <20210811100550.54714-1-pbonzini(a)redhat.com>
[PATCH v4 00/13] new plugin argument passing scheme
Message-Id: <20210730135817.17816-1-ma.mandourr(a)gmail.com>
[PATCH 0/6] docs/devel: Organize devel manual into further subsections
Message-Id: <20210804005621.1577302-1-jsnow(a)redhat.com>
[PATCH] Makefile: Fix cscope issues on MacOS and soft links
Message-Id: <20210801171144.60412-1-peterx(a)redhat.com>
Absences
========
- Another partial week
- On holiday for rest of August
Current Review Queue
====================
TODO [PATCH v3] accel/tcg: Clear PAGE_WRITE before translation
Message-Id: <20210805204835.158918-1-iii(a)linux.ibm.com>
=====================================================================================================================
TODO [PATCH 0/7] tcg: some small towards more modular tcg
Message-Id: <20210804143826.3402872-1-kraxel(a)redhat.com>
=================================================================================================================
TODO [PATCH 0/2] Acceptance Tests: clean up of temporary dirs and MAINTAINERS entry
Message-Id: <20210803193447.3946219-1-crosa(a)redhat.com>
==========================================================================================================================================
TODO [PATCH v2 00/11] Atomic cleanup + clang-12 build fix
Message-Id: <20210717014121.1784956-1-richard.henderson(a)linaro.org>
============================================================================================================================
--
Alex Bennée
4 years, 1 month
- 1
- 0
[ACTIVITY] report week ending 13 Aug
by Peter Maydell
Progress:
* UM-2 [QEMU upstream maintainership]
+ Getting rc3 out of the door
+ Finished the systick timer refactoring series and sent it out for
review (it ended up weighing in at 25 patches...)
+ Worked through some Coverity issue reports to analyze them and
either close as false-positive or send out patches fixing them
-- PMM
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O2 - Build # 14 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2
Culprit:
<cut>
commit 2db8461a9492cb64046a085f35048b9c4e45bfc2
Author: Raphael Isemann <teemperor(a)gmail.com>
Date: Tue Aug 10 16:15:57 2021 +0200
[lldb][NFC] Fix inversed documentation of Process::GetID/SetID
</cut>
Results regressed to (for first_bad == 2db8461a9492cb64046a085f35048b9c4e45bfc2)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2 artifacts/build-2db8461a9492cb64046a085f35048b9c4e45bfc2/results_id:
1
# 453.povray,[.] _ZN3povL24All_Sphere_IntersectionsEPNS_13Objec regressed by 116
from (for last_good == 9900af52f6b186a260d83321791177728fb369c5)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2 artifacts/build-9900af52f6b186a260d83321791177728fb369c5/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/3417
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2/3391
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-2db8461a9492cb64046a085f35048b9c4e45bfc2
cd investigate-llvm-2db8461a9492cb64046a085f35048b9c4e45bfc2
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 2db8461a9492cb64046a085f35048b9c4e45bfc2
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 9900af52f6b186a260d83321791177728fb369c5
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 2db8461a9492cb64046a085f35048b9c4e45bfc2
Author: Raphael Isemann <teemperor(a)gmail.com>
Date: Tue Aug 10 16:15:57 2021 +0200
[lldb][NFC] Fix inversed documentation of Process::GetID/SetID
---
lldb/include/lldb/Target/Process.h | 8 ++++----
1 file changed, 4 insertions(+), 4 deletions(-)
diff --git a/lldb/include/lldb/Target/Process.h b/lldb/include/lldb/Target/Process.h
index aaa2470d2931..8dcc15b1667b 100644
--- a/lldb/include/lldb/Target/Process.h
+++ b/lldb/include/lldb/Target/Process.h
@@ -536,13 +536,13 @@ public:
uint32_t GetAddressByteSize() const;
+ /// Returns the pid of the process or LLDB_INVALID_PROCESS_ID if there is
+ /// no known pid.
+ lldb::pid_t GetID() const { return m_pid; }
+
/// Sets the stored pid.
///
/// This does not change the pid of underlying process.
- lldb::pid_t GetID() const { return m_pid; }
-
- /// Returns the pid of the process or LLDB_INVALID_PROCESS_ID if there is
- /// no known pid.
void SetID(lldb::pid_t new_pid) { m_pid = new_pid; }
uint32_t GetUniqueID() const { return m_process_unique_id; }
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-master-arm-next-allmodconfig - Build # 20 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-master-arm-next-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-master-arm-next-allmodconfig
Culprit:
<cut>
commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
Author: Eric Dumazet <edumazet(a)google.com>
Date: Tue Aug 10 02:45:47 2021 -0700
net: igmp: fix data-race in igmp_ifc_timer_expire()
Fix the data-race reported by syzbot [1]
Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count
while another change just occured from another context.
in_dev->mr_ifc_count is only 8bit wide, so the race had little
consequences.
[1]
BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire
write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0:
igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821
igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356
____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461
__ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199
ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218
do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline]
ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423
tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362
__sys_setsockopt+0x18f/0x200 net/socket.c:2159
__do_sys_setsockopt net/socket.c:2170 [inline]
__se_sys_setsockopt net/socket.c:2167 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2167
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1:
igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808
call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419
expire_timers+0x135/0x250 kernel/time/timer.c:1464
__run_timers+0x358/0x420 kernel/time/timer.c:1732
run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745
__do_softirq+0x12c/0x26e kernel/softirq.c:558
invoke_softirq kernel/softirq.c:432 [inline]
__irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636
sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646
vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174
vprintk_default+0x22/0x30 kernel/printk/printk.c:2185
vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392
printk+0x62/0x87 kernel/printk/printk.c:2216
selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041
security_netlink_send+0x42/0x90 security/security.c:2070
netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:703 [inline]
sock_sendmsg net/socket.c:723 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2392
___sys_sendmsg net/socket.c:2446 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2475
__do_sys_sendmsg net/socket.c:2484 [inline]
__se_sys_sendmsg net/socket.c:2482 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2482
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x01 -> 0x02
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet(a)google.com>
Reported-by: syzbot <syzkaller(a)googlegroups.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
</cut>
Results regressed to (for first_bad == 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
21692
# First few build errors in logs:
# 00:03:56 ld.lld: error: undefined symbol: __bad_cmpxchg
# 00:03:56 make: *** [Makefile:1176: vmlinux] Error 1
from (for last_good == 37c86c4a0bfc2faaf0ed959db9de814c85797f09)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29753
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm…
Configuration details:
rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#761c6d7…"
Reproduce builds:
<cut>
mkdir investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
cd investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 37c86c4a0bfc2faaf0ed959db9de814c85797f09
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-next-allm…
Full commit (up to 1000 lines):
<cut>
commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
Author: Eric Dumazet <edumazet(a)google.com>
Date: Tue Aug 10 02:45:47 2021 -0700
net: igmp: fix data-race in igmp_ifc_timer_expire()
Fix the data-race reported by syzbot [1]
Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count
while another change just occured from another context.
in_dev->mr_ifc_count is only 8bit wide, so the race had little
consequences.
[1]
BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire
write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0:
igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821
igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356
____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461
__ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199
ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218
do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline]
ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423
tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362
__sys_setsockopt+0x18f/0x200 net/socket.c:2159
__do_sys_setsockopt net/socket.c:2170 [inline]
__se_sys_setsockopt net/socket.c:2167 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2167
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1:
igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808
call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419
expire_timers+0x135/0x250 kernel/time/timer.c:1464
__run_timers+0x358/0x420 kernel/time/timer.c:1732
run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745
__do_softirq+0x12c/0x26e kernel/softirq.c:558
invoke_softirq kernel/softirq.c:432 [inline]
__irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636
sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646
vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174
vprintk_default+0x22/0x30 kernel/printk/printk.c:2185
vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392
printk+0x62/0x87 kernel/printk/printk.c:2216
selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041
security_netlink_send+0x42/0x90 security/security.c:2070
netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:703 [inline]
sock_sendmsg net/socket.c:723 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2392
___sys_sendmsg net/socket.c:2446 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2475
__do_sys_sendmsg net/socket.c:2484 [inline]
__se_sys_sendmsg net/socket.c:2482 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2482
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x01 -> 0x02
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet(a)google.com>
Reported-by: syzbot <syzkaller(a)googlegroups.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
---
net/ipv4/igmp.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6b3c558a4f23..a51360087b19 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t)
static void igmp_ifc_timer_expire(struct timer_list *t)
{
struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer);
+ u8 mr_ifc_count;
igmpv3_send_cr(in_dev);
- if (in_dev->mr_ifc_count) {
- in_dev->mr_ifc_count--;
+restart:
+ mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count);
+
+ if (mr_ifc_count) {
+ if (cmpxchg(&in_dev->mr_ifc_count,
+ mr_ifc_count,
+ mr_ifc_count - 1) != mr_ifc_count)
+ goto restart;
igmp_ifc_start_timer(in_dev,
unsolicited_report_interval(in_dev));
}
@@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
igmp_ifc_start_timer(in_dev, 1);
}
@@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
in_dev->mr_qri;
}
/* cancel the interface change timer */
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
/* clear deleted report items */
@@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev)
igmp_group_dropped(pmc);
#ifdef CONFIG_IP_MULTICAST
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
in_dev->mr_gq_running = 0;
@@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(pmc->interface);
@@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* else no filters; keep old mode for reports */
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(in_dev);
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/gnu-master-arm-next-allyesconfig - Build # 34 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/gnu-master-arm-next-allyesconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/gnu-master-arm-next-allyesconfig
Culprit:
<cut>
commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
Author: Eric Dumazet <edumazet(a)google.com>
Date: Tue Aug 10 02:45:47 2021 -0700
net: igmp: fix data-race in igmp_ifc_timer_expire()
Fix the data-race reported by syzbot [1]
Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count
while another change just occured from another context.
in_dev->mr_ifc_count is only 8bit wide, so the race had little
consequences.
[1]
BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire
write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0:
igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821
igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356
____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461
__ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199
ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218
do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline]
ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423
tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362
__sys_setsockopt+0x18f/0x200 net/socket.c:2159
__do_sys_setsockopt net/socket.c:2170 [inline]
__se_sys_setsockopt net/socket.c:2167 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2167
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1:
igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808
call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419
expire_timers+0x135/0x250 kernel/time/timer.c:1464
__run_timers+0x358/0x420 kernel/time/timer.c:1732
run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745
__do_softirq+0x12c/0x26e kernel/softirq.c:558
invoke_softirq kernel/softirq.c:432 [inline]
__irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636
sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646
vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174
vprintk_default+0x22/0x30 kernel/printk/printk.c:2185
vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392
printk+0x62/0x87 kernel/printk/printk.c:2216
selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041
security_netlink_send+0x42/0x90 security/security.c:2070
netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:703 [inline]
sock_sendmsg net/socket.c:723 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2392
___sys_sendmsg net/socket.c:2446 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2475
__do_sys_sendmsg net/socket.c:2484 [inline]
__se_sys_sendmsg net/socket.c:2482 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2482
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x01 -> 0x02
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet(a)google.com>
Reported-by: syzbot <syzkaller(a)googlegroups.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
</cut>
Results regressed to (for first_bad == 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
19624
# First few build errors in logs:
# 00:49:46 igmp.c:(.text+0xa6f4): undefined reference to `__bad_cmpxchg'
# 00:49:48 make: *** [Makefile:1176: vmlinux] Error 1
from (for last_good == 37c86c4a0bfc2faaf0ed959db9de814c85797f09)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
19709
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes…
Configuration details:
rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#9e723c5…"
Reproduce builds:
<cut>
mkdir investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
cd investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 37c86c4a0bfc2faaf0ed959db9de814c85797f09
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes…
Build log: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allyes…
Full commit (up to 1000 lines):
<cut>
commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
Author: Eric Dumazet <edumazet(a)google.com>
Date: Tue Aug 10 02:45:47 2021 -0700
net: igmp: fix data-race in igmp_ifc_timer_expire()
Fix the data-race reported by syzbot [1]
Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count
while another change just occured from another context.
in_dev->mr_ifc_count is only 8bit wide, so the race had little
consequences.
[1]
BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire
write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0:
igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821
igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356
____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461
__ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199
ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218
do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline]
ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423
tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362
__sys_setsockopt+0x18f/0x200 net/socket.c:2159
__do_sys_setsockopt net/socket.c:2170 [inline]
__se_sys_setsockopt net/socket.c:2167 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2167
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1:
igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808
call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419
expire_timers+0x135/0x250 kernel/time/timer.c:1464
__run_timers+0x358/0x420 kernel/time/timer.c:1732
run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745
__do_softirq+0x12c/0x26e kernel/softirq.c:558
invoke_softirq kernel/softirq.c:432 [inline]
__irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636
sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646
vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174
vprintk_default+0x22/0x30 kernel/printk/printk.c:2185
vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392
printk+0x62/0x87 kernel/printk/printk.c:2216
selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041
security_netlink_send+0x42/0x90 security/security.c:2070
netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:703 [inline]
sock_sendmsg net/socket.c:723 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2392
___sys_sendmsg net/socket.c:2446 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2475
__do_sys_sendmsg net/socket.c:2484 [inline]
__se_sys_sendmsg net/socket.c:2482 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2482
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x01 -> 0x02
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet(a)google.com>
Reported-by: syzbot <syzkaller(a)googlegroups.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
---
net/ipv4/igmp.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6b3c558a4f23..a51360087b19 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t)
static void igmp_ifc_timer_expire(struct timer_list *t)
{
struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer);
+ u8 mr_ifc_count;
igmpv3_send_cr(in_dev);
- if (in_dev->mr_ifc_count) {
- in_dev->mr_ifc_count--;
+restart:
+ mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count);
+
+ if (mr_ifc_count) {
+ if (cmpxchg(&in_dev->mr_ifc_count,
+ mr_ifc_count,
+ mr_ifc_count - 1) != mr_ifc_count)
+ goto restart;
igmp_ifc_start_timer(in_dev,
unsolicited_report_interval(in_dev));
}
@@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
igmp_ifc_start_timer(in_dev, 1);
}
@@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
in_dev->mr_qri;
}
/* cancel the interface change timer */
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
/* clear deleted report items */
@@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev)
igmp_group_dropped(pmc);
#ifdef CONFIG_IP_MULTICAST
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
in_dev->mr_gq_running = 0;
@@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(pmc->interface);
@@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* else no filters; keep old mode for reports */
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(in_dev);
</cut>
4 years, 1 month
- 1
- 0
GDB aarch64 malfunctions w/Linaro / ARM gcc 10.3 compiler
by Dietmar May
I'm compiling and running a bare metal AArch64 bootloader using 3
different compilers: the Linaro / ARM GCC 10.3.1 compiler, the Linaro /
ARM GCC 10.2.1 compiler, and an in-house built GCC 10.2.0 compiler.
GDB will single step using the either of the GCC 10.2 compilers; but
runs without halting when step is requested - or perhaps steps multiple
instructions - when built using the Linaro / ARM-supplied GCC 10.3.1.
Eclipse CDT (v4.20 aka 2021-06) is able to correlate debugging
information from binaries built with either of the gcc 10.2 toolchains,
and to single step correctly through the program. Breakpoints work as
expected. Registers display fine.
Eclipse CDT is not able to correlate current PC location to source code
using the binary built with Linaro / ARM 10.3, instead bringing up a
disassembly window. Breakpoints placed at assembly instructions in the
editor do not work.
I've tried three different GDB versions - ARM's supplied 10.2 and 10.3
GDB, and the in-house built GDB. Results are the same.
The same makefile is used to create the binaries, with just a few macro
definitions to switch. The only compiler flag of interest is
-march=armv8.2-a (and of course -g -O0). -mtune=cortex-a53 doesn't help.
The board is connected via JTAG using OpenOCD 0.11.0+ and an Olimex
ARM-USB-OCD-H adapter.
I'm building in a cygwin shell on Windows 10 version 21H1 using the
compilers:
gcc-arm-10.3-2021.07-mingw-w64-i686-aarch64-none-elf.tar.xz
gcc-arm-10.2-2020.11-mingw-w64-i686-aarch64-none-elf.tar.xz
downloaded from:
https://developer.arm.com/tools-and-software/open-source-software/developer…
Differences in compiler configuration (gcc -v) are:
Failing - Linaro / ARM GCC 10.3(.1):
--enable-checking=release
--target=aarch64-none-elf
--with-libiconv-prefix=/data/jenkins/workspace/GNU-toolchain/arm-10-4/build-mingw-aarch64-none-elf/host-tools
Working - in house GCC 10.2.1:
--build=x86_64-w64-mingw32
--disable-libffi
--disable-libgomp
--disable-libmudflap
--disable-libssp
--disable-libstdcxx-pch
--disable-lto
--disable-win32-registry
--enable-multilib
--target=aarch64-elf
--with-gcc
--with-gnu-as
--with-gnu-ld
--with-host-libstdcxx='-static-libgcc -Wl,-Bstatic,-lstdc++,-Bdynamic -lm'
--with-multilib-list=lp64,ilp32
--with-stabs
--with-sysroot=/build/aarch64-elf_10.2.0/cross-gcc/aarch64-elf
--with-zstd=/build/aarch64-elf_10.2.0/host
Has anyone been able to perform hardware debugging of binaries built
with the latest 10.3 builds using GDB (and maybe even Eclipse CDT)?
Any suggestions as to other steps to try?
Thanks.
4 years, 1 month
- 2
- 1
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3 - Build # 18 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3
Culprit:
<cut>
commit b4c0307d598004cfd96c770d2a4a84a37c838ba9
Author: Jon Roelofs <jonathan_roelofs(a)apple.com>
Date: Thu Aug 5 09:35:02 2021 -0700
Fix clang-interpreter build after 2487db1f286222e2501c2fa8e8244eda13f6afc3
</cut>
Results regressed to (for first_bad == b4c0307d598004cfd96c770d2a4a84a37c838ba9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-b4c0307d598004cfd96c770d2a4a84a37c838ba9/results_id:
1
# 470.lbm,lbm_base.default regressed by 109
from (for last_good == bd17ced1db9a674fc8aa6632899e245672c7aa35)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-bd17ced1db9a674fc8aa6632899e245672c7aa35/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3351
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3314
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-b4c0307d598004cfd96c770d2a4a84a37c838ba9
cd investigate-llvm-b4c0307d598004cfd96c770d2a4a84a37c838ba9
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach b4c0307d598004cfd96c770d2a4a84a37c838ba9
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach bd17ced1db9a674fc8aa6632899e245672c7aa35
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit b4c0307d598004cfd96c770d2a4a84a37c838ba9
Author: Jon Roelofs <jonathan_roelofs(a)apple.com>
Date: Thu Aug 5 09:35:02 2021 -0700
Fix clang-interpreter build after 2487db1f286222e2501c2fa8e8244eda13f6afc3
---
clang/examples/clang-interpreter/main.cpp | 3 ++-
1 file changed, 2 insertions(+), 1 deletion(-)
diff --git a/clang/examples/clang-interpreter/main.cpp b/clang/examples/clang-interpreter/main.cpp
index 342d42089472..a2c50167f6b1 100644
--- a/clang/examples/clang-interpreter/main.cpp
+++ b/clang/examples/clang-interpreter/main.cpp
@@ -66,7 +66,8 @@ private:
SimpleJIT(
std::unique_ptr<TargetMachine> TM, DataLayout DL,
std::unique_ptr<DynamicLibrarySearchGenerator> ProcessSymbolsGenerator)
- : TM(std::move(TM)), DL(std::move(DL)) {
+ : ES(cantFail(SelfExecutorProcessControl::Create())), TM(std::move(TM)),
+ DL(std::move(DL)) {
llvm::sys::DynamicLibrary::LoadLibraryPermanently(nullptr);
MainJD.addGenerator(std::move(ProcessSymbolsGenerator));
}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/gnu-master-arm-next-allmodconfig - Build # 36 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/gnu-master-arm-next-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/gnu-master-arm-next-allmodconfig
Culprit:
<cut>
commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
Author: Eric Dumazet <edumazet(a)google.com>
Date: Tue Aug 10 02:45:47 2021 -0700
net: igmp: fix data-race in igmp_ifc_timer_expire()
Fix the data-race reported by syzbot [1]
Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count
while another change just occured from another context.
in_dev->mr_ifc_count is only 8bit wide, so the race had little
consequences.
[1]
BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire
write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0:
igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821
igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356
____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461
__ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199
ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218
do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline]
ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423
tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362
__sys_setsockopt+0x18f/0x200 net/socket.c:2159
__do_sys_setsockopt net/socket.c:2170 [inline]
__se_sys_setsockopt net/socket.c:2167 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2167
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1:
igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808
call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419
expire_timers+0x135/0x250 kernel/time/timer.c:1464
__run_timers+0x358/0x420 kernel/time/timer.c:1732
run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745
__do_softirq+0x12c/0x26e kernel/softirq.c:558
invoke_softirq kernel/softirq.c:432 [inline]
__irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636
sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646
vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174
vprintk_default+0x22/0x30 kernel/printk/printk.c:2185
vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392
printk+0x62/0x87 kernel/printk/printk.c:2216
selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041
security_netlink_send+0x42/0x90 security/security.c:2070
netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:703 [inline]
sock_sendmsg net/socket.c:723 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2392
___sys_sendmsg net/socket.c:2446 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2475
__do_sys_sendmsg net/socket.c:2484 [inline]
__se_sys_sendmsg net/socket.c:2482 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2482
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x01 -> 0x02
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet(a)google.com>
Reported-by: syzbot <syzkaller(a)googlegroups.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
</cut>
Results regressed to (for first_bad == 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
21598
# First few build errors in logs:
# 00:32:42 igmp.c:(.text+0xa734): undefined reference to `__bad_cmpxchg'
# 00:32:42 make: *** [Makefile:1176: vmlinux] Error 1
from (for last_good == 37c86c4a0bfc2faaf0ed959db9de814c85797f09)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
29650
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod…
Configuration details:
rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#9e723c5…"
Reproduce builds:
<cut>
mkdir investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
cd investigate-linux-4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 37c86c4a0bfc2faaf0ed959db9de814c85797f09
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod…
Build log: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-next-allmod…
Full commit (up to 1000 lines):
<cut>
commit 4a2b285e7e103d4d6c6ed3e5052a0ff74a5d7f15
Author: Eric Dumazet <edumazet(a)google.com>
Date: Tue Aug 10 02:45:47 2021 -0700
net: igmp: fix data-race in igmp_ifc_timer_expire()
Fix the data-race reported by syzbot [1]
Issue here is that igmp_ifc_timer_expire() can update in_dev->mr_ifc_count
while another change just occured from another context.
in_dev->mr_ifc_count is only 8bit wide, so the race had little
consequences.
[1]
BUG: KCSAN: data-race in igmp_ifc_event / igmp_ifc_timer_expire
write to 0xffff8881051e3062 of 1 bytes by task 12547 on cpu 0:
igmp_ifc_event+0x1d5/0x290 net/ipv4/igmp.c:821
igmp_group_added+0x462/0x490 net/ipv4/igmp.c:1356
____ip_mc_inc_group+0x3ff/0x500 net/ipv4/igmp.c:1461
__ip_mc_join_group+0x24d/0x2c0 net/ipv4/igmp.c:2199
ip_mc_join_group_ssm+0x20/0x30 net/ipv4/igmp.c:2218
do_ip_setsockopt net/ipv4/ip_sockglue.c:1285 [inline]
ip_setsockopt+0x1827/0x2a80 net/ipv4/ip_sockglue.c:1423
tcp_setsockopt+0x8c/0xa0 net/ipv4/tcp.c:3657
sock_common_setsockopt+0x5d/0x70 net/core/sock.c:3362
__sys_setsockopt+0x18f/0x200 net/socket.c:2159
__do_sys_setsockopt net/socket.c:2170 [inline]
__se_sys_setsockopt net/socket.c:2167 [inline]
__x64_sys_setsockopt+0x62/0x70 net/socket.c:2167
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
read to 0xffff8881051e3062 of 1 bytes by interrupt on cpu 1:
igmp_ifc_timer_expire+0x706/0xa30 net/ipv4/igmp.c:808
call_timer_fn+0x2e/0x1d0 kernel/time/timer.c:1419
expire_timers+0x135/0x250 kernel/time/timer.c:1464
__run_timers+0x358/0x420 kernel/time/timer.c:1732
run_timer_softirq+0x19/0x30 kernel/time/timer.c:1745
__do_softirq+0x12c/0x26e kernel/softirq.c:558
invoke_softirq kernel/softirq.c:432 [inline]
__irq_exit_rcu+0x9a/0xb0 kernel/softirq.c:636
sysvec_apic_timer_interrupt+0x69/0x80 arch/x86/kernel/apic/apic.c:1100
asm_sysvec_apic_timer_interrupt+0x12/0x20 arch/x86/include/asm/idtentry.h:638
console_unlock+0x8e8/0xb30 kernel/printk/printk.c:2646
vprintk_emit+0x125/0x3d0 kernel/printk/printk.c:2174
vprintk_default+0x22/0x30 kernel/printk/printk.c:2185
vprintk+0x15a/0x170 kernel/printk/printk_safe.c:392
printk+0x62/0x87 kernel/printk/printk.c:2216
selinux_netlink_send+0x399/0x400 security/selinux/hooks.c:6041
security_netlink_send+0x42/0x90 security/security.c:2070
netlink_sendmsg+0x59e/0x7c0 net/netlink/af_netlink.c:1919
sock_sendmsg_nosec net/socket.c:703 [inline]
sock_sendmsg net/socket.c:723 [inline]
____sys_sendmsg+0x360/0x4d0 net/socket.c:2392
___sys_sendmsg net/socket.c:2446 [inline]
__sys_sendmsg+0x1ed/0x270 net/socket.c:2475
__do_sys_sendmsg net/socket.c:2484 [inline]
__se_sys_sendmsg net/socket.c:2482 [inline]
__x64_sys_sendmsg+0x42/0x50 net/socket.c:2482
do_syscall_x64 arch/x86/entry/common.c:50 [inline]
do_syscall_64+0x3d/0x90 arch/x86/entry/common.c:80
entry_SYSCALL_64_after_hwframe+0x44/0xae
value changed: 0x01 -> 0x02
Reported by Kernel Concurrency Sanitizer on:
CPU: 1 PID: 12539 Comm: syz-executor.1 Not tainted 5.14.0-rc4-syzkaller #0
Hardware name: Google Google Compute Engine/Google Compute Engine, BIOS Google 01/01/2011
Fixes: 1da177e4c3f4 ("Linux-2.6.12-rc2")
Signed-off-by: Eric Dumazet <edumazet(a)google.com>
Reported-by: syzbot <syzkaller(a)googlegroups.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
---
net/ipv4/igmp.c | 21 ++++++++++++++-------
1 file changed, 14 insertions(+), 7 deletions(-)
diff --git a/net/ipv4/igmp.c b/net/ipv4/igmp.c
index 6b3c558a4f23..a51360087b19 100644
--- a/net/ipv4/igmp.c
+++ b/net/ipv4/igmp.c
@@ -803,10 +803,17 @@ static void igmp_gq_timer_expire(struct timer_list *t)
static void igmp_ifc_timer_expire(struct timer_list *t)
{
struct in_device *in_dev = from_timer(in_dev, t, mr_ifc_timer);
+ u8 mr_ifc_count;
igmpv3_send_cr(in_dev);
- if (in_dev->mr_ifc_count) {
- in_dev->mr_ifc_count--;
+restart:
+ mr_ifc_count = READ_ONCE(in_dev->mr_ifc_count);
+
+ if (mr_ifc_count) {
+ if (cmpxchg(&in_dev->mr_ifc_count,
+ mr_ifc_count,
+ mr_ifc_count - 1) != mr_ifc_count)
+ goto restart;
igmp_ifc_start_timer(in_dev,
unsolicited_report_interval(in_dev));
}
@@ -818,7 +825,7 @@ static void igmp_ifc_event(struct in_device *in_dev)
struct net *net = dev_net(in_dev->dev);
if (IGMP_V1_SEEN(in_dev) || IGMP_V2_SEEN(in_dev))
return;
- in_dev->mr_ifc_count = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
+ WRITE_ONCE(in_dev->mr_ifc_count, in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv);
igmp_ifc_start_timer(in_dev, 1);
}
@@ -957,7 +964,7 @@ static bool igmp_heard_query(struct in_device *in_dev, struct sk_buff *skb,
in_dev->mr_qri;
}
/* cancel the interface change timer */
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
/* clear deleted report items */
@@ -1724,7 +1731,7 @@ void ip_mc_down(struct in_device *in_dev)
igmp_group_dropped(pmc);
#ifdef CONFIG_IP_MULTICAST
- in_dev->mr_ifc_count = 0;
+ WRITE_ONCE(in_dev->mr_ifc_count, 0);
if (del_timer(&in_dev->mr_ifc_timer))
__in_dev_put(in_dev);
in_dev->mr_gq_running = 0;
@@ -1941,7 +1948,7 @@ static int ip_mc_del_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
pmc->sfmode = MCAST_INCLUDE;
#ifdef CONFIG_IP_MULTICAST
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(pmc->interface);
@@ -2120,7 +2127,7 @@ static int ip_mc_add_src(struct in_device *in_dev, __be32 *pmca, int sfmode,
/* else no filters; keep old mode for reports */
pmc->crcount = in_dev->mr_qrv ?: net->ipv4.sysctl_igmp_qrv;
- in_dev->mr_ifc_count = pmc->crcount;
+ WRITE_ONCE(in_dev->mr_ifc_count, pmc->crcount);
for (psf = pmc->sources; psf; psf = psf->sf_next)
psf->sf_crcount = 0;
igmp_ifc_event(in_dev);
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/gnu-master-arm-spec2k6-O2 - Build # 18 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *binutils* in CI configuration tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O2
Culprit:
<cut>
commit 3ee0cd9e55368d162aea19a42369f3ee2a1356f3
Author: Nick Clifton <nickc(a)redhat.com>
Date: Tue Aug 10 16:40:37 2021 +0100
Updated Serbian and Russian translations for various sub-directories
</cut>
Results regressed to (for first_bad == 3ee0cd9e55368d162aea19a42369f3ee2a1356f3)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2_marm artifacts/build-3ee0cd9e55368d162aea19a42369f3ee2a1356f3/results_id:
1
# 453.povray,[.] _ZN3pov16Intersect_SphereEPNS_10Ray_StructEPdd regressed by 121
from (for last_good == c173cc8a666792a6e864b5beb1c4d6903169b5cd)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2_marm artifacts/build-c173cc8a666792a6e864b5beb1c4d6903169b5cd/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of last_good: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O2/3301
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of first_bad: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O2/3306
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-binutils-3ee0cd9e55368d162aea19a42369f3ee2a1356f3
cd investigate-binutils-3ee0cd9e55368d162aea19a42369f3ee2a1356f3
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /binutils/ ./ ./bisect/baseline/
cd binutils
# Reproduce first_bad build
git checkout --detach 3ee0cd9e55368d162aea19a42369f3ee2a1356f3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c173cc8a666792a6e864b5beb1c4d6903169b5cd
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Full commit (up to 1000 lines):
<cut>
commit 3ee0cd9e55368d162aea19a42369f3ee2a1356f3
Author: Nick Clifton <nickc(a)redhat.com>
Date: Tue Aug 10 16:40:37 2021 +0100
Updated Serbian and Russian translations for various sub-directories
---
bfd/ChangeLog | 4 +
bfd/po/sr.po | 3134 ++++++++++---------
binutils/ChangeLog | 4 +
binutils/po/sr.po | 6126 ++++++++++++++++++++++---------------
gas/ChangeLog | 4 +
gas/po/ru.po | 8567 ++++++++++++++++++++++++++--------------------------
gold/ChangeLog | 4 +
gold/po/sr.po | 856 +++---
opcodes/ChangeLog | 4 +
opcodes/po/sr.po | 525 ++--
10 files changed, 10262 insertions(+), 8966 deletions(-)
diff --git a/bfd/ChangeLog b/bfd/ChangeLog
index d22d38dc2d1..6d551303637 100644
--- a/bfd/ChangeLog
+++ b/bfd/ChangeLog
@@ -1,3 +1,7 @@
+2021-08-10 Nick Clifton <nickc(a)redhat.com>
+
+ * po/sr.po: Updated Serbian translation.
+
2021-07-18 Nick Clifton <nickc(a)redhat.com>
* config.bfd: Move pending obsoletion targets to obsolete list.
diff --git a/bfd/po/sr.po b/bfd/po/sr.po
index 7e09d4dc52c..eb80c2c5430 100644
--- a/bfd/po/sr.po
+++ b/bfd/po/sr.po
@@ -4,10 +4,10 @@
# Мирослав Николић <miroslavnikolic(a)rocketmail.com>, 2016–2021.
msgid ""
msgstr ""
-"Project-Id-Version: bfd-2.35.90\n"
+"Project-Id-Version: bfd-2.36.90\n"
"Report-Msgid-Bugs-To: bug-binutils(a)gnu.org\n"
-"POT-Creation-Date: 2021-01-09 10:55+0000\n"
-"PO-Revision-Date: 2021-01-11 11:45+0200\n"
+"POT-Creation-Date: 2021-07-03 15:02+0100\n"
+"PO-Revision-Date: 2021-07-24 06:30+0200\n"
"Last-Translator: Мирослав Николић <miroslavnikolic(a)rocketmail.com>\n"
"Language-Team: Serbian <(nothing)>\n"
"Language: sr\n"
@@ -32,21 +32,21 @@ msgstr "%pB: неподржана врста премештања је увез
msgid "%pB: bad relocation record imported: %d"
msgstr "%pB: увезен је лош снимак премештања: %d"
-#: aoutx.h:1265 aoutx.h:1613 pdp11.c:1236 pdp11.c:1510
+#: aoutx.h:1265 aoutx.h:1613 pdp11.c:1238 pdp11.c:1512
#, c-format
msgid "%pB: can not represent section `%pA' in a.out object file format"
msgstr "%pB: не могу да представим одељак „%pA“ у „a.out“ запису датотеке објекта"
-#: aoutx.h:1577 pdp11.c:1482
+#: aoutx.h:1577 pdp11.c:1484
#, c-format
msgid "%pB: can not represent section for symbol `%s' in a.out object file format"
msgstr "%pB: не могу да представим одељак за симбол „%s“ у „a.out“ запису датотеке објекта"
-#: aoutx.h:1580 vms-alpha.c:8040
+#: aoutx.h:1580 vms-alpha.c:8038
msgid "*unknown*"
msgstr "*непознато*"
-#: aoutx.h:1716 pdp11.c:1578
+#: aoutx.h:1716 pdp11.c:1580
#, c-format
msgid "%pB: invalid string offset %<PRIu64> >= %<PRIu64>"
msgstr "%pB: неисправан померај ниске „%<PRIu64> >= %<PRIu64>“"
@@ -56,53 +56,53 @@ msgstr "%pB: неисправан померај ниске „%<PRIu64> >= %<PR
msgid "%pB: unsupported AOUT relocation size: %d"
msgstr "%pB: неподржана величина „AOUT“ премештања: %d"
-#: aoutx.h:2412 aoutx.h:2430 pdp11.c:2058
+#: aoutx.h:2412 aoutx.h:2430 pdp11.c:2060
#, c-format
msgid "%pB: attempt to write out unknown reloc type"
msgstr "%pB: покушавам да запишем непознату врсту премештања"
-#: aoutx.h:4087 pdp11.c:3441
+#: aoutx.h:4085 pdp11.c:3441
#, c-format
msgid "%pB: unsupported relocation type"
msgstr "%pB: врста премештања није подржана"
#. Unknown relocation.
-#: aoutx.h:4408 coff-alpha.c:601 coff-alpha.c:1512 coff-rs6000.c:2791
+#: aoutx.h:4405 coff-alpha.c:601 coff-alpha.c:1518 coff-rs6000.c:2916
#: coff-sh.c:504 coff-tic4x.c:184 coff-tic54x.c:279 elf-hppa.h:798
#: elf-hppa.h:826 elf-m10200.c:226 elf-m10300.c:813 elf32-arc.c:532
-#: elf32-arm.c:1985 elf32-avr.c:962 elf32-bfin.c:1062 elf32-bfin.c:4686
+#: elf32-arm.c:1985 elf32-avr.c:962 elf32-bfin.c:1062 elf32-bfin.c:4687
#: elf32-cr16.c:654 elf32-cr16.c:684 elf32-cris.c:467 elf32-crx.c:429
#: elf32-csky.c:991 elf32-d10v.c:234 elf32-d30v.c:522 elf32-d30v.c:544
#: elf32-dlx.c:546 elf32-epiphany.c:372 elf32-fr30.c:381 elf32-frv.c:2559
-#: elf32-frv.c:6241 elf32-ft32.c:306 elf32-h8300.c:302 elf32-i386.c:400
+#: elf32-frv.c:6240 elf32-ft32.c:305 elf32-h8300.c:302 elf32-i386.c:400
#: elf32-ip2k.c:1240 elf32-iq2000.c:442 elf32-lm32.c:496 elf32-m32c.c:305
#: elf32-m32r.c:1286 elf32-m32r.c:1311 elf32-m32r.c:2209 elf32-m68hc11.c:390
#: elf32-m68hc12.c:510 elf32-m68k.c:354 elf32-mcore.c:354 elf32-mcore.c:440
#: elf32-mep.c:385 elf32-metag.c:871 elf32-microblaze.c:690
#: elf32-microblaze.c:961 elf32-mips.c:2231 elf32-moxie.c:137
#: elf32-msp430.c:737 elf32-msp430.c:747 elf32-mt.c:241 elf32-nds32.c:3237
-#: elf32-nds32.c:3263 elf32-nds32.c:5029 elf32-nios2.c:3019 elf32-or1k.c:1038
-#: elf32-pj.c:326 elf32-ppc.c:901 elf32-ppc.c:914 elf32-pru.c:423
+#: elf32-nds32.c:3263 elf32-nds32.c:5029 elf32-nios2.c:3019 elf32-or1k.c:1070
+#: elf32-pj.c:326 elf32-ppc.c:898 elf32-ppc.c:911 elf32-pru.c:423
#: elf32-rl78.c:291 elf32-rx.c:313 elf32-rx.c:322 elf32-s12z.c:296
-#: elf32-s390.c:347 elf32-score.c:2392 elf32-score7.c:2231 elf32-sh.c:438
+#: elf32-s390.c:347 elf32-score.c:2392 elf32-score7.c:2231 elf32-sh.c:437
#: elf32-spu.c:163 elf32-tic6x.c:1498 elf32-tic6x.c:1508 elf32-tic6x.c:1527
#: elf32-tic6x.c:1537 elf32-tic6x.c:2583 elf32-tilepro.c:792 elf32-v850.c:1902
-#: elf32-v850.c:1924 elf32-v850.c:4249 elf32-vax.c:290 elf32-visium.c:481
+#: elf32-v850.c:1924 elf32-v850.c:4249 elf32-vax.c:289 elf32-visium.c:481
#: elf32-wasm32.c:105 elf32-xc16x.c:250 elf32-xgate.c:418
#: elf32-xstormy16.c:395 elf32-xtensa.c:522 elf32-xtensa.c:556 elf32-z80.c:331
-#: elf64-alpha.c:1114 elf64-alpha.c:4071 elf64-alpha.c:4219 elf64-bpf.c:325
+#: elf64-alpha.c:1114 elf64-alpha.c:4072 elf64-alpha.c:4220 elf64-bpf.c:325
#: elf64-ia64-vms.c:255 elf64-ia64-vms.c:3431 elf64-mips.c:3958
-#: elf64-mips.c:3974 elf64-mmix.c:1264 elf64-nfp.c:238 elf64-ppc.c:1018
-#: elf64-ppc.c:1370 elf64-ppc.c:1379 elf64-s390.c:328 elf64-s390.c:378
-#: elf64-x86-64.c:281 elfn32-mips.c:3788 elfxx-ia64.c:324 elfxx-riscv.c:969
+#: elf64-mips.c:3974 elf64-mmix.c:1264 elf64-nfp.c:238 elf64-ppc.c:1021
+#: elf64-ppc.c:1373 elf64-ppc.c:1382 elf64-s390.c:328 elf64-s390.c:378
+#: elf64-x86-64.c:279 elfn32-mips.c:3788 elfxx-ia64.c:324 elfxx-riscv.c:970
#: elfxx-sparc.c:589 elfxx-sparc.c:639 elfxx-tilegx.c:907 elfxx-tilegx.c:947
#: elfnn-aarch64.c:2215 elfnn-aarch64.c:2313 elfnn-ia64.c:214
-#: elfnn-ia64.c:3828
+#: elfnn-ia64.c:3820
#, c-format
msgid "%pB: unsupported relocation type %#x"
msgstr "%pB: врста премештања није подржана „%#x“"
-#: aoutx.h:5435 pdp11.c:3864
+#: aoutx.h:5432 pdp11.c:3864
#, c-format
msgid "%pB: relocatable link from %s to %s not supported"
msgstr "%pB: преместива веза са „%s“ на „%s“ није подржана"
@@ -110,13 +110,13 @@ msgstr "%pB: преместива веза са „%s“ на „%s“ није
#: arc-got.h:69
#, c-format
msgid "%pB: cannot allocate memory for local GOT entries"
-msgstr "%pB: не могу да доделим меморију за локалне „GOT“ уноси"
+msgstr "%pB: не могу да доделим меморију за локалне „GOT“ уносе"
#: archive.c:2241
msgid "warning: writing archive was slow: rewriting timestamp"
msgstr "упозорење: упис у архиву је спор: поново уписујем време"
-#: archive.c:2308 archive.c:2368 elflink.c:4609 linker.c:1428
+#: archive.c:2308 archive.c:2368 elflink.c:4611 linker.c:1427
#, c-format
msgid "%pB: plugin needed to handle lto object"
msgstr "%pB: потребан је прикључак за руковање „lto“ објектом"
@@ -222,22 +222,22 @@ msgstr "грешка читања „%s“: %s"
msgid "#<invalid error code>"
msgstr "#<неисправан код грешке>"
-#: bfd.c:1662
+#: bfd.c:1640
#, c-format
msgid "BFD %s assertion fail %s:%d"
msgstr "„BFD“ „%s“ тврдња није успела „%s“:%d"
-#: bfd.c:1675
+#: bfd.c:1653
#, c-format
msgid "BFD %s internal error, aborting at %s:%d in %s\n"
msgstr "Унутрашња грешка „BFD“ %s, прекидам на „%s“ %d. реду у „%s“\n"
-#: bfd.c:1680
+#: bfd.c:1658
#, c-format
msgid "BFD %s internal error, aborting at %s:%d\n"
msgstr "Унутрашња грешка „BFD“ %s, прекидам при „%s“ %d. реду\n"
-#: bfd.c:1682
+#: bfd.c:1660
msgid "Please report this bug.\n"
msgstr "Пријавите ову грешку.\n"
@@ -266,21 +266,21 @@ msgstr "поново отварам „%pB“: %s\n"
msgid "%pB: cannot handle compressed Alpha binaries; use compiler flags, or objZ, to generate uncompressed binaries"
msgstr "%pB: не могу да радим са сажетим бинарним Алфа датотекама; користите заставице преводиоца, или „objZ“, да створите несажете бинарне датотеке"
-#: coff-alpha.c:850 coff-alpha.c:887 coff-alpha.c:1954 coff-mips.c:953
+#: coff-alpha.c:856 coff-alpha.c:893 coff-alpha.c:1960 coff-mips.c:953
msgid "GP relative relocation used when GP not defined"
msgstr "употребљено је релативно премештање општег показивача када није дефинисан"
-#: coff-alpha.c:1441
+#: coff-alpha.c:1447
msgid "using multiple gp values"
msgstr "користим неколико вредности општег показивача"
-#: coff-alpha.c:1499 coff-alpha.c:1505 elf.c:9442 elf32-mcore.c:100
-#: elf32-mcore.c:455 elf32-ppc.c:7597 elf32-ppc.c:8748 elf64-ppc.c:16199
+#: coff-alpha.c:1505 coff-alpha.c:1511 elf.c:9463 elf32-mcore.c:100
+#: elf32-mcore.c:455 elf32-ppc.c:7614 elf32-ppc.c:8763 elf64-ppc.c:16242
#, c-format
msgid "%pB: %s unsupported"
msgstr "%pB: „%s“ није подржано"
-#: coff-go32.c:156 coffswap.h:785
+#: coff-go32.c:156 coffswap.h:792
#, c-format
msgid "%pB: warning: %s: line number overflow: 0x%lx > 0xffff"
msgstr "%pB: упозорење: %s: прекорачење броја редова: 0x%lx > 0xffff"
@@ -290,17 +290,39 @@ msgstr "%pB: упозорење: %s: прекорачење броја редо
msgid "GP relative relocation when _gp not defined"
msgstr "Релативно премештање општег показивача када „_gp“ није дефинисано"
-#: coff-rs6000.c:2877
+#: coff-rs6000.c:484 coff64-rs6000.c:377
+#, c-format
+msgid "%pB: unsupported swap_aux_in for storage class %#x"
+msgstr "%pB: неподржано „swap_aux_in“ за смештајну класу „%#x“"
+
+#: coff-rs6000.c:570 coff64-rs6000.c:499
+#, c-format
+msgid "%pB: unsupported swap_aux_out for storage class %#x"
+msgstr "%pB: неподржано „swap_aux_out“ за смештајну класу „%#x“"
+
+#: coff-rs6000.c:3002
#, c-format
msgid "%pB: TOC reloc at %#<PRIx64> to symbol `%s' with no TOC entry"
msgstr "%pB: премештање табеле садржаја са „%#<PRIx64>“ на симбол „%s“ без уноса табеле садржаја"
-#: coff-rs6000.c:3640 coff64-rs6000.c:2152
+#: coff-rs6000.c:3209 coff-rs6000.c:3220
+msgid "%pB: TLS relocation at (0x%"
+msgstr "%pB: ТЛС премештање на (0x%"
+
+#: coff-rs6000.c:3234
+msgid "%pB: TLS local relocation at (0x%"
+msgstr "%pB: ТЛС локално премештање на (0x%"
+
+#: coff-rs6000.c:3642 coff64-rs6000.c:1573
+msgid "%pB: relocatation (%d) at (0x%"
+msgstr "%pB: премештање (%d) на (0x%"
+
+#: coff-rs6000.c:3905 coff64-rs6000.c:2023
#, c-format
msgid "%pB: symbol `%s' has unrecognized smclas %d"
msgstr "%pB: симбол „%s“ има непознату класу симбола „%d“"
-#: coff-sh.c:778 elf32-sh.c:521
+#: coff-sh.c:778 elf32-sh.c:520
#, c-format
msgid "%pB: %#<PRIx64>: warning: bad R_SH_USES offset"
msgstr "%pB: %#<PRIx64>: упозорење: лош „R_SH_USES“ померај"
@@ -310,32 +332,32 @@ msgstr "%pB: %#<PRIx64>: упозорење: лош „R_SH_USES“ помера
msgid "%pB: %#<PRIx64>: warning: R_SH_USES points to unrecognized insn %#x"
msgstr "%pB: %#<PRIx64>: упозорење: „R_SH_USES“ показује на непознат „insn“ %#x"
-#: coff-sh.c:807 elf32-sh.c:552
+#: coff-sh.c:807 elf32-sh.c:551
#, c-format
msgid "%pB: %#<PRIx64>: warning: bad R_SH_USES load offset"
msgstr "%pB: %#<PRIx64>: упозорење: лош померај учитавања „R_SH_USES“"
-#: coff-sh.c:832 elf32-sh.c:568
+#: coff-sh.c:832 elf32-sh.c:567
#, c-format
msgid "%pB: %#<PRIx64>: warning: could not find expected reloc"
msgstr "%pB: %#<PRIx64>: упозорење: не могу да нађем очекивано премештање"
-#: coff-sh.c:849 elf32-sh.c:597
+#: coff-sh.c:849 elf32-sh.c:596
#, c-format
msgid "%pB: %#<PRIx64>: warning: symbol in unexpected section"
msgstr "%pB: %#<PRIx64>: упозорење: симбол је у неочекиваном одељку"
-#: coff-sh.c:975 elf32-sh.c:727
+#: coff-sh.c:975 elf32-sh.c:726
#, c-format
msgid "%pB: %#<PRIx64>: warning: could not find expected COUNT reloc"
msgstr "%pB: %#<PRIx64>: упозорење: не могу да нађем очекивано премештање „COUNT“"
-#: coff-sh.c:985 elf32-sh.c:738
+#: coff-sh.c:985 elf32-sh.c:737
#, c-format
msgid "%pB: %#<PRIx64>: warning: bad count"
msgstr "%pB: %#<PRIx64>: упозорење: лош број"
-#: coff-sh.c:1356 coff-sh.c:2644 elf32-sh.c:1138 elf32-sh.c:1505
+#: coff-sh.c:1356 coff-sh.c:2644 elf32-sh.c:1137 elf32-sh.c:1504
#, c-format
msgid "%pB: %#<PRIx64>: fatal: reloc overflow while relaxing"
msgstr "%pB: %#<PRIx64>: кобна грешка: прекорачење премештања приликом опуштања"
@@ -345,34 +367,44 @@ msgstr "%pB: %#<PRIx64>: кобна грешка: прекорачење пре
msgid "%pB: fatal: generic symbols retrieved before relaxing"
msgstr "%pB: кобно: општи симболи су пронађени пре опуштања"
-#: coff-sh.c:2781 cofflink.c:2948
+#: coff-sh.c:2781 cofflink.c:2959
#, c-format
msgid "%pB: illegal symbol index %ld in relocs"
msgstr "%pB: неисправан индекс симбола %ld у премештањима"
-#: coff-tic4x.c:228 coff-tic54x.c:366 coffcode.h:5050
+#: coff-tic4x.c:228 coff-tic54x.c:366 coffcode.h:5124
#, c-format
msgid "%pB: warning: illegal symbol index %ld in relocs"
msgstr "%pB: упозорење: неисправан индекс симбола %ld у премештањима"
-#: coffcode.h:953
+#: coff64-rs6000.c:449 coff64-rs6000.c:555
+#, c-format
+msgid "%pB: C_STAT isn't supported by XCOFF64"
+msgstr "%pB: „C_STAT“ није подржано „XCOFF64“-ом"
+
+#: coff64-rs6000.c:479
+#, c-format
+msgid "%pB: wrong auxtype %#x for storage class %#x"
+msgstr "%pB: погрешна „aux“ врста %#x за смештајну класу %#x"
+
+#: coffcode.h:986
#, c-format
msgid "%pB: unable to load COMDAT section name"
msgstr "%pB: не могу да учитам „COMDAT“ назив одељка"
#. Malformed input files can trigger this test.
#. cf PR 21781.
-#: coffcode.h:988
+#: coffcode.h:1021
#, c-format
msgid "%pB: error: unexpected symbol '%s' in COMDAT section"
msgstr "%pB: грешка: неочекивани симбол „%s“ у „COMDAT“ одељку"
-#: coffcode.h:1000
+#: coffcode.h:1033
#, c-format
msgid "%pB: warning: COMDAT symbol '%s' does not match section name '%s'"
msgstr "%pB: упозорење: „COMDAT“ симбол „%s“ се не подудара са називом одељка „%s“"
-#: coffcode.h:1010
+#: coffcode.h:1043
#, c-format
msgid "%pB: warning: no symbol for section '%s' found"
msgstr "%pB: упозорење: нисам нашао никакав симбол за одељак „%s“"
@@ -380,126 +412,126 @@ msgstr "%pB: упозорење: нисам нашао никакав симбо
#. Generate a warning message rather using the 'unhandled'
#. variable as this will allow some .sys files generate by
#. other toolchains to be processed. See bugzilla issue 196.
-#: coffcode.h:1241
+#: coffcode.h:1274
#, c-format
msgid "%pB: warning: ignoring section flag %s in section %s"
msgstr "%pB: упозорење: занемарујем заставицу одељка „%s“ у одељку „%s“"
-#: coffcode.h:1310
+#: coffcode.h:1343
#, c-format
msgid "%pB (%s): section flag %s (%#lx) ignored"
msgstr "%pB (%s): заставица одељка „%s“ (%#lx) је занемарена"
-#: coffcode.h:1926 coffcode.h:1991
+#: coffcode.h:1959 coffcode.h:2024
#, c-format
msgid "%pB: warning: claims to have 0xffff relocs, without overflow"
msgstr "%pB: упозорење: потврђујем 0xffff премештања, без прекорачења"
-#: coffcode.h:2352
+#: coffcode.h:2385
#, c-format
msgid "unrecognized TI COFF target id '0x%x'"
msgstr "непознат ид „TI COFF“ циља „0x%x“"
-#: coffcode.h:2630
+#: coffcode.h:2663
#, c-format
msgid "%pB: reloc against a non-existent symbol index: %ld"
msgstr "%pB: премештање наспрам непостојећег индекса симбола: %ld"
-#: coffcode.h:2930
+#: coffcode.h:2961
#, c-format
msgid "%pB: page size is too large (0x%x)"
msgstr "%pB: величина странице је превелика (0x%x)"
-#: coffcode.h:3090
+#: coffcode.h:3121
#, c-format
msgid "%pB: too many sections (%d)"
msgstr "%pB: превише одељака (%d)"
-#: coffcode.h:3508
+#: coffcode.h:3548
#, c-format
msgid "%pB: section %pA: string table overflow at offset %ld"
msgstr "%pB: одељак „%pA“: прекорачење табеле ниски на померају %ld"
-#: coffcode.h:3608
+#: coffcode.h:3655
#, c-format
msgid "%pB:%s section %s: alignment 2**%u not representable"
msgstr "%pB:%s одељак %s: поравнање 2**%u се не може представити"
-#: coffcode.h:4284
+#: coffcode.h:4358
#, c-format
msgid "%pB: warning: line number count (%#lx) exceeds section size (%#lx)"
msgstr "%pB: упозорење: број редова (%#lx) превазилази величину одељка (%#lx)"
-#: coffcode.h:4304
+#: coffcode.h:4378
#, c-format
msgid "%pB: warning: line number table read failed"
msgstr "%pB: упозорење: није успело читање броја реда табеле"
-#: coffcode.h:4338 coffcode.h:4352
+#: coffcode.h:4412 coffcode.h:4426
#, c-format
msgid "%pB: warning: illegal symbol index 0x%lx in line number entry %d"
msgstr "%pB: упозорење: неисправан индекс симбола 0x%lx у уносу броја реда %d"
-#: coffcode.h:4366
+#: coffcode.h:4440
#, c-format
msgid "%pB: warning: illegal symbol in line number entry %d"
msgstr "%pB: упозорење: неисправан индекс симбола у уносу броја реда %d"
-#: coffcode.h:4379
+#: coffcode.h:4453
#, c-format
msgid "%pB: warning: duplicate line number information for `%s'"
msgstr "%pB: упозорење: удвостручени податак о броју реда за „%s“"
-#: coffcode.h:4800
+#: coffcode.h:4874
#, c-format
msgid "%pB: unrecognized storage class %d for %s symbol `%s'"
msgstr "%pB: непозната класа смештаја „%d“ за „%s“ симбол „%s“"
-#: coffcode.h:4940
+#: coffcode.h:5014
#, c-format
msgid "warning: %pB: local symbol `%s' has no section"
msgstr "упозорење: %pB: локални симбол „%s“ нема одељак"
-#: coffcode.h:5090
+#: coffcode.h:5164
#, c-format
msgid "%pB: illegal relocation type %d at address %#<PRIx64>"
msgstr "%pB: неисправна врста премештања %d на адреси %#<PRIx64>"
-#: coffgen.c:179 elf.c:1238
+#: coffgen.c:179 elf.c:1239
#, c-format
msgid "%pB: unable to initialize compress status for section %s"
msgstr "%pB: не могу да започнем стање сажимања за одељак „%s“"
-#: coffgen.c:203 elf.c:1249
+#: coffgen.c:203 elf.c:1250
#, c-format
msgid "%pB: unable to initialize decompress status for section %s"
msgstr "%pB: не могу да започнем стање распакивања за одељак „%s“"
-#: coffgen.c:1704
+#: coffgen.c:1706
#, c-format
msgid "%pB: bad string table size %<PRIu64>"
msgstr "%pB: лоша величина табеле низа %<PRIu64>"
-#: coffgen.c:1876 coffgen.c:1936 coffgen.c:1954 cofflink.c:2024 elf.c:1923
-#: xcofflink.c:4512
+#: coffgen.c:1878 coffgen.c:1938 coffgen.c:1956 cofflink.c:2024 elf.c:1936
+#: xcofflink.c:4540
msgid "<corrupt>"
msgstr "<оштећење>"
-#: coffgen.c:2085
+#: coffgen.c:2087
#, c-format
msgid "<corrupt info> %s"
msgstr "<оштећени подаци> %s"
-#: coffgen.c:2676 elflink.c:14969 linker.c:2967
+#: coffgen.c:2684 elflink.c:14829 linker.c:2965
msgid "%F%P: already_linked_table: %E\n"
msgstr "%F%P: већ_повезана_табела: %E\n"
-#: coffgen.c:3017 elflink.c:13959
+#: coffgen.c:3026 elflink.c:13816
#, c-format
msgid "removing unused section '%pA' in file '%pB'"
msgstr "уклањам некоришћени одељак „%pA“ у датотеци „%pB“"
-#: coffgen.c:3094 elflink.c:14176
+#: coffgen.c:3103 elflink.c:14036
msgid "warning: gc-sections option ignored"
msgstr "упозорење: опција „gc“ одељака је занемарена"
@@ -508,7 +540,7 @@ msgstr "упозорење: опција „gc“ одељака је занем
msgid "warning: symbol `%s' is both section and non-section"
msgstr "упозорење: симбол „%s“ је и одељак и није одељак"
-#: cofflink.c:471 elf64-ia64-vms.c:5202 elflink.c:5200
+#: cofflink.c:471 elf64-ia64-vms.c:5202 elflink.c:5207
#, c-format
msgid "warning: type of symbol `%s' changed from %d to %d in %pB"
msgstr "упозорење: врста симбола „%s“ је измењена из „%d“ у „%d“ за „%pB“"
@@ -518,37 +550,41 @@ msgstr "упозорење: врста симбола „%s“ је измење
msgid "%pB: relocs in section `%pA', but it has no contents"
msgstr "%pB: премештања у одељку „%pA“, али нема никаквог садржаја"
-#: cofflink.c:2415 elflink.c:11299
+#: cofflink.c:2415 elflink.c:11342
#, c-format
msgid "%X`%s' referenced in section `%pA' of %pB: defined in discarded section `%pA' of %pB\n"
msgstr "%X„%s“ је упутно у одељку „%pA“ од „%pB“: дефинисано је у одбаченом одељку „%pA“ од „%pB“\n"
-#: cofflink.c:2717
+#: cofflink.c:2610
+msgid "%pB: stripping non-representable symbol '%s' (value %"
+msgstr "%pB: уклањам непредстављајући симбол „%s“ (вредност %"
+
+#: cofflink.c:2728
#, c-format
msgid "%pB: %pA: reloc overflow: %#x > 0xffff"
msgstr "%pB: %pA: прекорачење премештања: %#x > 0xffff"
-#: cofflink.c:2725
+#: cofflink.c:2736
#, c-format
msgid "%pB: warning: %pA: line number overflow: %#x > 0xffff"
msgstr "%pB: упозорење: %pA: прекорачење броја редова: %#x > 0xffff"
-#: cofflink.c:3116
+#: cofflink.c:3127
#, c-format
msgid "%pB: bad reloc address %#<PRIx64> in section `%pA'"
msgstr "%pB: погрешна адреса премештања %#<PRIx64> у одељку „%pA“"
-#: coffswap.h:799
+#: coffswap.h:806
#, c-format
msgid "%pB: %s: reloc overflow: 0x%lx > 0xffff"
msgstr "%pB: %s: прекорачење премештања: 0x%lx > 0xffff"
-#: compress.c:271
+#: compress.c:270
#, c-format
msgid "error: %pB(%pA) section size (%#<PRIx64> bytes) is larger than file size (%#<PRIx64> bytes)"
msgstr "грешка: %pB(%pA) величина одељка (%#<PRIx64> бајтова) је већа од величине датотеке (%#<PRIx64> бајта)"
-#: compress.c:282
+#: compress.c:281
#, c-format
msgid "error: %pB(%pA) is too large (%#<PRIx64> bytes)"
msgstr "грешка: %pB(%pA) је превелико (%#<PRIx64> бајта)"
@@ -563,138 +599,138 @@ msgstr "грешка: %pB је преведен за EP9312, док је %pB п
msgid "warning: unable to update contents of %s section in %pB"
msgstr "упозорење: не могу да освежим садржај „%s“ одељка у %pB"
-#: dwarf2.c:553
+#: dwarf2.c:552
#, c-format
msgid "DWARF error: can't find %s section."
msgstr "„DWARF“ грешка: не могу да нађем одељак „%s“."
#. PR 26946
-#: dwarf2.c:564
+#: dwarf2.c:563
#, c-format
msgid "DWARF error: section %s is larger than its filesize! (0x%lx vs 0x%lx)"
msgstr "„DWARF“ грешка: одељак „%s“ је већи од своје величине датотеке! (0x%lx vs 0x%lx)"
-#: dwarf2.c:599
+#: dwarf2.c:598
#, c-format
msgid "DWARF error: offset (%<PRIu64>) greater than or equal to %s size (%<PRIu64>)"
msgstr "„DWARF“ грешка: померај (%<PRIu64>) је већи или једнак величини %s (%<PRIu64>)"
-#: dwarf2.c:1186
+#: dwarf2.c:1201
msgid "DWARF error: info pointer extends beyond end of attributes"
msgstr "„DWARF“ грешка: инфо указивач превазилази крај атрибута"
-#: dwarf2.c:1365
+#: dwarf2.c:1349
#, c-format
msgid "DWARF error: invalid or unhandled FORM value: %#x"
msgstr "„DWARF“ грешка: неисправна или непозната вредност „FORM“: %#x"
-#: dwarf2.c:1678
+#: dwarf2.c:1664
msgid "DWARF error: mangled line number section (bad file number)"
msgstr "„DWARF“ грешка: број реда одељка је одсечен (лош број датотеке)"
-#: dwarf2.c:2026
+#: dwarf2.c:2007
msgid "DWARF error: zero format count"
msgstr "„DWARF“ грешка: нулти број записа"
-#: dwarf2.c:2036
+#: dwarf2.c:2017
#, c-format
msgid "DWARF error: data count (%<PRIx64>) larger than buffer size"
msgstr "„DWARF“ грешка: број података (%<PRIx64>) је већи од величине међумеморије"
-#: dwarf2.c:2077
+#: dwarf2.c:2056
#, c-format
msgid "DWARF error: unknown format content type %<PRIu64>"
msgstr "„DWARF“ грешка: непозната врста садржаја записа „%<PRIu64>“"
-#: dwarf2.c:2150
+#: dwarf2.c:2126
#, c-format
msgid "DWARF error: line info section is too small (%<PRId64>)"
msgstr "„DWARF“ грешка: одељак података реда је премали (%<PRId64>)"
-#: dwarf2.c:2180
+#: dwarf2.c:2153
#, c-format
msgid "DWARF error: line info data is bigger (%#<PRIx64>) than the space remaining in the section (%#lx)"
msgstr "„DWARF“ грешка: одељак података реда је већи (%#<PRIx64>) од простора преосталог у одељку (%#lx)"
-#: dwarf2.c:2193
+#: dwarf2.c:2166
#, c-format
msgid "DWARF error: unhandled .debug_line version %d"
msgstr "„DWARF“ грешка: необрађено „.debug_line“ издање %d"
-#: dwarf2.c:2203
+#: dwarf2.c:2175
msgid "DWARF error: ran out of room reading prologue"
msgstr "„DWARFд грешка: пнестало је простора читајући пролог"
-#: dwarf2.c:2221
+#: dwarf2.c:2191
#, c-format
msgid "DWARF error: line info unsupported segment selector size %u"
msgstr "„DWARF“ грешка: неподржана величина избирача подеока података реда %u"
-#: dwarf2.c:2248
+#: dwarf2.c:2213
msgid "DWARF error: invalid maximum operations per instruction"
msgstr "„DWARF“ грешка: Неисправан највећи број операција по инструкцији"
-#: dwarf2.c:2267
+#: dwarf2.c:2225
msgid "DWARF error: ran out of room reading opcodes"
msgstr "„DWARFд грешка: пнестало је простора читајући опкодове"
-#: dwarf2.c:2458
+#: dwarf2.c:2393
msgid "DWARF error: mangled line number section"
msgstr "„DWARF“ грешка: број реда одељка је одсечен"
-#: dwarf2.c:2956
+#: dwarf2.c:2881
msgid "DWARF error: abstract instance recursion detected"
msgstr "„DWARF“ грешка: дубачење апстрактног примерка је откривено"
-#: dwarf2.c:2990 dwarf2.c:3084
+#: dwarf2.c:2915 dwarf2.c:3009
msgid "DWARF error: invalid abstract instance DIE ref"
msgstr "„DWARF“ грешка: неисправан апстрактан примерак „DIE“ упуте"
-#: dwarf2.c:3006
+#: dwarf2.c:2931
#, c-format
msgid "DWARF error: unable to read alt ref %<PRIu64>"
msgstr "„DWARF“ грешка: не могу да прочитам „alt“ упуту %<PRIu64>"
-#: dwarf2.c:3062
+#: dwarf2.c:2987
#, c-format
msgid "DWARF error: unable to locate abstract instance DIE ref %<PRIu64>"
msgstr "„DWARF“ грешка: не могу да пронађем апстрактни примерак „DIE“ упуте %<PRIu64>"
-#: dwarf2.c:3101 dwarf2.c:3384 dwarf2.c:3771
+#: dwarf2.c:3024 dwarf2.c:3305 dwarf2.c:3750
#, c-format
msgid "DWARF error: could not find abbrev number %u"
msgstr "„DWARF“ грешка: не могу да нађем скраћени број %u"
-#: dwarf2.c:3534
+#: dwarf2.c:3538
#, c-format
-msgid "DWARF error: could not find variable specification at offset %lx"
-msgstr "„DWARF“ грешка: не могу да нађем одредбу променљиве на померају %lx"
+msgid "DWARF error: could not find variable specification at offset 0x%lx"
+msgstr "„DWARF“ грешка: не могу да нађем одредбу променљиве на померају 0×%lx"
-#: dwarf2.c:3690
+#: dwarf2.c:3677
#, c-format
msgid "DWARF error: found dwarf version '%u', this reader only handles version 2, 3, 4 and 5 information"
msgstr "„DWARF“ грешка: нађох „DWARF“ издање „%u“, овај читач ради само са подацима издања 2, 3, 4 и 5"
-#: dwarf2.c:3734
+#: dwarf2.c:3714
#, c-format
msgid "DWARF error: found address size '%u', this reader can not handle sizes greater than '%u'"
msgstr "„DWARF“ грешка: нађох величину адресе „%u“, овај читач не може да ради са величинама већим од „%u“"
-#: dwarf2.c:3838
+#: dwarf2.c:3817
msgid "DWARF error: DW_AT_comp_dir attribute encountered with a non-string form"
msgstr "„DWARF“ грешка: особина „DW_AT_comp_dir“ је нађена са записом не-ниске"
-#: ecoff.c:941
+#: ecoff.c:940
#, c-format
msgid "%pB: warning: isymMax (%ld) is greater than ifdMax (%ld)"
msgstr "%pB: упозорење: „isymMax“ (%ld) је веће од „ifdMax“ (%ld)"
-#: ecoff.c:1237
+#: ecoff.c:1236
#, c-format
msgid "unknown basic type %d"
msgstr "непозната основна врста „%d“"
-#: ecoff.c:1493
+#: ecoff.c:1492
#, c-format
msgid ""
"\n"
@@ -703,7 +739,7 @@ msgstr ""
"\n"
" Последњи+1 симбол: %ld"
-#: ecoff.c:1500 ecoff.c:1503
+#: ecoff.c:1499 ecoff.c:1502
#, c-format
msgid ""
"\n"
@@ -712,7 +748,7 @@ msgstr ""
"\n"
" Први симбол: %ld"
-#: ecoff.c:1518
+#: ecoff.c:1517
#, c-format
msgid ""
"\n"
@@ -721,7 +757,7 @@ msgstr ""
"\n"
" Последњи+1 симбол: %-7ld Врста: %s"
-#: ecoff.c:1526
+#: ecoff.c:1525
#, c-format
msgid ""
"\n"
@@ -730,7 +766,7 @@ msgstr ""
"\n"
" Локални симбол: %ld"
-#: ecoff.c:1534
+#: ecoff.c:1533
#, c-format
msgid ""
"\n"
@@ -739,7 +775,7 @@ msgstr ""
"\n"
" struct; Последњи+1 симбол: %ld"
-#: ecoff.c:1539
+#: ecoff.c:1538
#, c-format
msgid ""
"\n"
@@ -748,7 +784,7 @@ msgstr ""
"\n"
" union; Последњи+1 симбол: %ld"
-#: ecoff.c:1544
+#: ecoff.c:1543
#, c-format
msgid ""
"\n"
@@ -757,7 +793,7 @@ msgstr ""
"\n"
" enum; Последњи+1 симбол: %ld"
-#: ecoff.c:1552
+#: ecoff.c:1551
#, c-format
msgid ""
"\n"
@@ -766,22 +802,22 @@ msgstr ""
"\n"
" Врста: %s"
-#: elf-attrs.c:449
+#: elf-attrs.c:477
#, c-format
msgid "%pB: error: attribute section '%pA' too big: %#llx"
msgstr "%pB: грешка: одељак особине „%pA“ је превелик: %#llx"
-#: elf-attrs.c:490
+#: elf-attrs.c:514
#, c-format
-msgid "%pB: error: attribute section length too small: %<PRId64>"
-msgstr "%pB: грешка: величина одељка особине је премала: %<PRId64>"
+msgid "%pB: error: attribute section length too small: %ld"
+msgstr "%pB: грешка: величина одељка особине је премала: %ld"
-#: elf-attrs.c:618
+#: elf-attrs.c:644
#, c-format
msgid "error: %pB: object has vendor-specific contents that must be processed by the '%s' toolchain"
msgstr "грешка: %pB: објекат има садржај продавцу специфичан који мора бити обрађен алатним ланцем „%s“"
-#: elf-attrs.c:628
+#: elf-attrs.c:654
#, c-format
msgid "error: %pB: object tag '%d, %s' is incompatible with tag '%d, %s'"
msgstr "грешка: %pB: ознака објекта „%d, %s“ није сагласна са ознаком „%d, %s“"
@@ -847,45 +883,45 @@ msgstr "„.eh_frame_hdr“ упућује на преклапајуће „FDE
msgid "%F%P: dynamic STT_GNU_IFUNC symbol `%s' with pointer equality in `%pB' can not be used when making an executable; recompile with -fPIE and relink with -pie\n"
msgstr "%F%P: динамички „STT_GNU_IFUNC“ симбол „%s“ са једнакошћу показивача у „%pB“ се не може користити приликом стварања извршне; преведите поново са „-fPIE“ и повежите поново са „-pie“\n"
-#: elf-m10200.c:434 elf-m10300.c:2146 elf32-avr.c:1508 elf32-bfin.c:3130
+#: elf-m10200.c:434 elf-m10300.c:2146 elf32-avr.c:1508 elf32-bfin.c:3131
#: elf32-cr16.c:1432 elf32-cris.c:2034 elf32-crx.c:913 elf32-d10v.c:510
-#: elf32-epiphany.c:562 elf32-fr30.c:594 elf32-frv.c:4049 elf32-ft32.c:494
+#: elf32-epiphany.c:562 elf32-fr30.c:594 elf32-frv.c:4049 elf32-ft32.c:493
#: elf32-h8300.c:523 elf32-ip2k.c:1477 elf32-iq2000.c:691 elf32-lm32.c:1070
-#: elf32-m32c.c:624 elf32-m32r.c:2837 elf32-m68hc1x.c:1272 elf32-mep.c:522
+#: elf32-m32c.c:624 elf32-m32r.c:2837 elf32-m68hc1x.c:1271 elf32-mep.c:522
#: elf32-metag.c:1984 elf32-microblaze.c:1623 elf32-moxie.c:288 elf32-mt.c:402
-#: elf32-nds32.c:6044 elf32-or1k.c:1815 elf32-score.c:2743 elf32-score7.c:2552
+#: elf32-nds32.c:6044 elf32-or1k.c:1861 elf32-score.c:2743 elf32-score7.c:2552
#: elf32-spu.c:5084 elf32-tilepro.c:3372 elf32-v850.c:2294 elf32-visium.c:680
#: elf32-xstormy16.c:930 elf64-bpf.c:552 elf64-mmix.c:1541 elfxx-tilegx.c:3742
msgid "internal error: out of range error"
msgstr "унутрашња грешка: изван опсега"
-#: elf-m10200.c:438 elf-m10300.c:2150 elf32-avr.c:1512 elf32-bfin.c:3134
+#: elf-m10200.c:438 elf-m10300.c:2150 elf32-avr.c:1512 elf32-bfin.c:3135
#: elf32-cr16.c:1436 elf32-cris.c:2038 elf32-crx.c:917 elf32-d10v.c:514
-#: elf32-fr30.c:598 elf32-frv.c:4053 elf32-ft32.c:498 elf32-h8300.c:527
+#: elf32-fr30.c:598 elf32-frv.c:4053 elf32-ft32.c:497 elf32-h8300.c:527
#: elf32-iq2000.c:695 elf32-lm32.c:1074 elf32-m32c.c:628 elf32-m32r.c:2841
-#: elf32-m68hc1x.c:1276 elf32-mep.c:526 elf32-metag.c:1988
+#: elf32-m68hc1x.c:1275 elf32-mep.c:526 elf32-metag.c:1988
#: elf32-microblaze.c:1627 elf32-moxie.c:292 elf32-msp430.c:1510
-#: elf32-nds32.c:6048 elf32-or1k.c:1819 elf32-score.c:2747 elf32-score7.c:2556
+#: elf32-nds32.c:6048 elf32-or1k.c:1865 elf32-score.c:2747 elf32-score7.c:2556
#: elf32-spu.c:5088 elf32-tilepro.c:3376 elf32-v850.c:2298 elf32-visium.c:684
-#: elf32-xstormy16.c:934 elf64-mmix.c:1545 elfxx-mips.c:10554
+#: elf32-xstormy16.c:934 elf64-mmix.c:1545 elfxx-mips.c:10558
#: elfxx-tilegx.c:3746
msgid "internal error: unsupported relocation error"
msgstr "унутрашња грешка: премештање није подржано"
#: elf-m10200.c:442 elf32-cr16.c:1440 elf32-crx.c:921 elf32-d10v.c:518
-#: elf32-h8300.c:531 elf32-lm32.c:1078 elf32-m32r.c:2845 elf32-m68hc1x.c:1280
+#: elf32-h8300.c:531 elf32-lm32.c:1078 elf32-m32r.c:2845 elf32-m68hc1x.c:1279
#: elf32-microblaze.c:1631 elf32-nds32.c:6052 elf32-score.c:2751
#: elf32-score7.c:2560 elf32-spu.c:5092
msgid "internal error: dangerous error"
msgstr "унутрашња грешка: грешка опасности"
-#: elf-m10200.c:446 elf-m10300.c:2167 elf32-avr.c:1520 elf32-bfin.c:3142
+#: elf-m10200.c:446 elf-m10300.c:2167 elf32-avr.c:1520 elf32-bfin.c:3143
#: elf32-cr16.c:1444 elf32-cris.c:2046 elf32-crx.c:925 elf32-d10v.c:522
-#: elf32-epiphany.c:577 elf32-fr30.c:606 elf32-frv.c:4061 elf32-ft32.c:506
+#: elf32-epiphany.c:577 elf32-fr30.c:606 elf32-frv.c:4061 elf32-ft32.c:505
#: elf32-h8300.c:535 elf32-ip2k.c:1492 elf32-iq2000.c:703 elf32-lm32.c:1082
-#: elf32-m32c.c:636 elf32-m32r.c:2849 elf32-m68hc1x.c:1284 elf32-mep.c:534
+#: elf32-m32c.c:636 elf32-m32r.c:2849 elf32-m68hc1x.c:1283 elf32-mep.c:534
#: elf32-metag.c:1996 elf32-microblaze.c:1635 elf32-moxie.c:300
-#: elf32-msp430.c:1518 elf32-mt.c:410 elf32-nds32.c:6056 elf32-or1k.c:1827
+#: elf32-msp430.c:1518 elf32-mt.c:410 elf32-nds32.c:6056 elf32-or1k.c:1873
#: elf32-score.c:2760 elf32-score7.c:2564 elf32-spu.c:5096
#: elf32-tilepro.c:3384 elf32-v850.c:2318 elf32-visium.c:692
#: elf32-xstormy16.c:942 elf64-bpf.c:565 elf64-mmix.c:1553 elfxx-tilegx.c:3754
@@ -902,9 +938,9 @@ msgstr "%pB: неподржан прелазак са „%s“ на „%s“"
msgid "%pB: %s' accessed both as normal and thread local symbol"
msgstr "%pB: „%s“ се приступило и као нормалном и као симболу локалне нити"
-#: elf-m10300.c:2093 elf32-arm.c:13396 elf32-i386.c:3403 elf32-m32r.c:2331
-#: elf32-m68k.c:3929 elf32-s390.c:3080 elf32-sh.c:3673 elf32-tilepro.c:3275
-#: elf32-xtensa.c:3024 elf64-s390.c:3029 elf64-x86-64.c:4062
+#: elf-m10300.c:2093 elf32-arm.c:13376 elf32-i386.c:3426 elf32-m32r.c:2331
+#: elf32-m68k.c:3929 elf32-s390.c:3080 elf32-sh.c:3671 elf32-tilepro.c:3275
+#: elf32-xtensa.c:3024 elf64-s390.c:3029 elf64-x86-64.c:4082
#: elfxx-sparc.c:2917 elfxx-sparc.c:3814 elfxx-tilegx.c:3665
#: elfnn-aarch64.c:5501 elfnn-aarch64.c:7104
#, c-format
@@ -924,8 +960,8 @@ msgstr "%pB: узимање адресе заштићене функције „
msgid "internal error: suspicious relocation type used in shared library"
msgstr "унутрашња грешка: сумњива врста премештања је коришћена у дељеној библиотеци"
-#: elf-m10300.c:2650 elf32-avr.c:2489 elf32-frv.c:5622 elf64-ia64-vms.c:365
-#: elfxx-sparc.c:2684 reloc.c:8271 reloc16.c:155 elfnn-ia64.c:365
+#: elf-m10300.c:2650 elf32-avr.c:2486 elf32-frv.c:5621 elf64-ia64-vms.c:365
+#: elfxx-sparc.c:2684 reloc.c:8282 reloc16.c:155 elfnn-ia64.c:365
msgid "%P%F: --relax and -r may not be used together\n"
msgstr "%P%F: „--relax“ и „-r“ се не могу користити заједно\n"
@@ -954,45 +990,50 @@ msgstr "упозорење: %pB: оштећена величина спремн
msgid "warning: %pB: corrupt no copy on protected size: 0x%x"
msgstr "упозорење: %pB: оштећење не умножава на заштићеној величине: 0x%x"
-#: elf-properties.c:186
+#: elf-properties.c:189
+#, c-format
+msgid "error: %pB: <corrupt property (0x%x) size: 0x%x>"
+msgstr "грешка: %pB: <оштећено својство (0x%x) величине: 0x%x>"
+
+#: elf-properties.c:205
#, c-format
msgid "warning: %pB: unsupported GNU_PROPERTY_TYPE (%ld) type: 0x%x"
msgstr "упозорење: %pB: неподржано „GNU_PROPERTY_TYPE“ (%ld) врста: 0x%x"
-#: elf-properties.c:301
+#: elf-properties.c:391
msgid "Removed property %W to merge %pB (0x%v) and %pB (0x%v)\n"
msgstr "Уклоњено својство „%W“ за стапање „%pB“ (0x%v) и „%pB“ (0x%v)\n"
-#: elf-properties.c:307
+#: elf-properties.c:397
msgid "Removed property %W to merge %pB (0x%v) and %pB (not found)\n"
msgstr "Уклоњено својство „%W“ за стапање „%pB“ (0x%v) и „%pB“ (нисам нашао)\n"
-#: elf-properties.c:316 elf-properties.c:394
+#: elf-properties.c:406 elf-properties.c:484
msgid "Removed property %W to merge %pB and %pB\n"
msgstr "Уклоњено својство „%W“ за стапање „%pB“ и „%pB“\n"
-#: elf-properties.c:320
+#: elf-properties.c:410
msgid "Removed property %W to merge %pB and %pB (not found)\n"
msgstr "Уклоњено својство „%W“ за стапање „%pB“ и „%pB“ (нисам нашао)\n"
-#: elf-properties.c:337
+#: elf-properties.c:427
msgid "Updated property %W (0x%v) to merge %pB (0x%v) and %pB (0x%v)\n"
msgstr "Освежено својство „%W“ (0x%v) за стапање „%pB“ (0x%v) и „%pB“ (0x%v)\n"
-#: elf-properties.c:346
+#: elf-properties.c:436
msgid "Updated property %W (%v) to merge %pB (0x%v) and %pB (not found)\n"
msgstr "Освежено својство „%W“ (%v) за стапање „%pB“ (0x%v) и „%pB“ (нисам нашао)\n"
-#: elf-properties.c:388
+#: elf-properties.c:478
msgid "Removed property %W to merge %pB (not found) and %pB (0x%v)\n"
msgstr "Уклоњено својство „%W“ за стапање „%pB“ (нисам нашао) и „%pB“ (0x%v)\n"
#. Merge .note.gnu.property sections.
-#: elf-properties.c:550 elf-properties.c:552
+#: elf-properties.c:640 elf-properties.c:642
msgid "\n"
msgstr "\n"
-#: elf-properties.c:551
+#: elf-properties.c:641
msgid "Merging program properties\n"
msgstr "Стапам својства програма\n"
@@ -1007,7 +1048,7 @@ msgstr "%pB: покушавам да учитам ниске из одељка
msgid "%pB: invalid string offset %u >= %<PRIu64> for section `%s'"
msgstr "%pB: неисправан померај ниске „%u >= %<PRIu64>“ за одељак „%s“"
-#: elf.c:514 elfnn-aarch64.c:8096
+#: elf.c:514 elfnn-aarch64.c:8104
#, c-format
msgid "%pB symbol number %lu references nonexistent SHT_SYMTAB_SHNDX section"
msgstr "„%pB“ симбол број %lu упућује на непостојећи одељак „SHT_SYMTAB_SHNDX“"
@@ -1058,22 +1099,22 @@ msgstr "%pB: број одељка уноса групе %u је оштећен"
msgid "%pB: unknown type [%#x] section `%s' in group [%pA]"
msgstr "%pB: непозната врста [%#x] одељак „%s“ у групи [%pA]"
-#: elf.c:1440
+#: elf.c:1453
#, c-format
msgid "%pB: invalid sh_link field (%d) in section number %d"
msgstr "%pB: неисправно „sh_link“ поље (%d) у броју одељка %d"
-#: elf.c:1456
+#: elf.c:1469
#, c-format
msgid "%pB: failed to find link section for section %d"
msgstr "%pB: нисам успео да нађем одељак везе за одељак %d"
-#: elf.c:1483
+#: elf.c:1496
#, c-format
msgid "%pB: failed to find info section for section %d"
msgstr "%pB: нисам успео да нађем одељак података за одељак %d"
-#: elf.c:1655
+#: elf.c:1668
#, c-format
msgid ""
"\n"
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/gnu-master-arm-stable-allyesconfig - Build # 14 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/gnu-master-arm-stable-allyesconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/gnu-master-arm-stable-allyesconfig
Culprit:
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
</cut>
Results regressed to (for first_bad == 341db343768bc44f3512facc464021730d64071c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
19543
# First few build errors in logs:
# 00:19:50 drivers/power/supply/ab8500_fg.c:3061:39: error: ‘np’ undeclared (first use in this function); did you mean ‘up’?
# 00:19:50 make[3]: *** [scripts/Makefile.build:273: drivers/power/supply/ab8500_fg.o] Error 1
# 00:21:18 make[2]: *** [scripts/Makefile.build:516: drivers/power/supply] Error 2
# 00:21:18 make[1]: *** [scripts/Makefile.build:516: drivers/power] Error 2
# 00:30:44 make: *** [Makefile:1847: drivers] Error 2
from (for last_good == dc72a15859b2e604abb8a4bff123fbac8a0be92a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
19631
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-341db343768bc44f3512facc464021730d64071c
cd investigate-linux-341db343768bc44f3512facc464021730d64071c
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 341db343768bc44f3512facc464021730d64071c
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dc72a15859b2e604abb8a4bff123fbac8a0be92a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally…
Build log: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-master-arm-stable-ally…
Full commit (up to 1000 lines):
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/power/supply/ab8500-bm.h | 4 +
drivers/power/supply/ab8500_btemp.c | 118 +++++-------
drivers/power/supply/ab8500_charger.c | 339 +++++++++++++++++++--------------
drivers/power/supply/ab8500_fg.c | 136 +++++++------
drivers/power/supply/abx500_chargalg.c | 116 ++++++-----
5 files changed, 379 insertions(+), 334 deletions(-)
diff --git a/drivers/power/supply/ab8500-bm.h b/drivers/power/supply/ab8500-bm.h
index 41c69a4f2a1f..012595a9d269 100644
--- a/drivers/power/supply/ab8500-bm.h
+++ b/drivers/power/supply/ab8500-bm.h
@@ -730,4 +730,8 @@ int ab8500_bm_of_probe(struct device *dev,
struct device_node *np,
struct abx500_bm_data *bm);
+extern struct platform_driver ab8500_fg_driver;
+extern struct platform_driver ab8500_btemp_driver;
+extern struct platform_driver abx500_chargalg_driver;
+
#endif /* _AB8500_CHARGER_H_ */
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index fdfcd59fc43e..3598b5a748e7 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/slab.h>
@@ -932,26 +933,6 @@ static int __maybe_unused ab8500_btemp_suspend(struct device *dev)
return 0;
}
-static int ab8500_btemp_remove(struct platform_device *pdev)
-{
- struct ab8500_btemp *di = platform_get_drvdata(pdev);
- int i, irq;
-
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
-
- /* Delete the work queue */
- destroy_workqueue(di->btemp_wq);
-
- flush_scheduled_work();
- power_supply_unregister(di->btemp_psy);
-
- return 0;
-}
-
static char *supply_interface[] = {
"ab8500_chargalg",
"ab8500_fg",
@@ -966,6 +947,40 @@ static const struct power_supply_desc ab8500_btemp_desc = {
.external_power_changed = ab8500_btemp_external_power_changed,
};
+static int ab8500_btemp_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for the btemp */
+ di->btemp_wq =
+ alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
+ if (di->btemp_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Kick off periodic temperature measurements */
+ ab8500_btemp_periodic(di, true);
+
+ return 0;
+}
+
+static void ab8500_btemp_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Delete the work queue */
+ destroy_workqueue(di->btemp_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_btemp_component_ops = {
+ .bind = ab8500_btemp_bind,
+ .unbind = ab8500_btemp_unbind,
+};
+
static int ab8500_btemp_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -1011,14 +1026,6 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
psy_cfg.num_supplicants = ARRAY_SIZE(supply_interface);
psy_cfg.drv_data = di;
- /* Create a work queue for the btemp */
- di->btemp_wq =
- alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
- if (di->btemp_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for measuring temperature periodically */
INIT_DEFERRABLE_WORK(&di->btemp_periodic_work,
ab8500_btemp_periodic_work);
@@ -1031,7 +1038,7 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
AB8500_BTEMP_HIGH_TH, &val);
if (ret < 0) {
dev_err(dev, "%s ab8500 read failed\n", __func__);
- goto free_btemp_wq;
+ return ret;
}
switch (val) {
case BTEMP_HIGH_TH_57_0:
@@ -1050,30 +1057,28 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
}
/* Register BTEMP power supply class */
- di->btemp_psy = power_supply_register(dev, &ab8500_btemp_desc,
- &psy_cfg);
+ di->btemp_psy = devm_power_supply_register(dev, &ab8500_btemp_desc,
+ &psy_cfg);
if (IS_ERR(di->btemp_psy)) {
dev_err(dev, "failed to register BTEMP psy\n");
- ret = PTR_ERR(di->btemp_psy);
- goto free_btemp_wq;
+ return PTR_ERR(di->btemp_psy);
}
/* Register interrupts */
for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_btemp_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_btemp_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_btemp_irq[i].name, di);
if (ret) {
dev_err(dev, "failed to request %s IRQ %d: %d\n"
, ab8500_btemp_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_btemp_irq[i].name, irq, ret);
@@ -1081,23 +1086,16 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, di);
- /* Kick off periodic temperature measurements */
- ab8500_btemp_periodic(di, true);
list_add_tail(&di->node, &ab8500_btemp_list);
- return ret;
+ return component_add(dev, &ab8500_btemp_component_ops);
+}
-free_irq:
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_btemp_remove(struct platform_device *pdev)
+{
+ component_del(&pdev->dev, &ab8500_btemp_component_ops);
- power_supply_unregister(di->btemp_psy);
-free_btemp_wq:
- destroy_workqueue(di->btemp_wq);
- return ret;
+ return 0;
}
static SIMPLE_DEV_PM_OPS(ab8500_btemp_pm_ops, ab8500_btemp_suspend, ab8500_btemp_resume);
@@ -1107,7 +1105,7 @@ static const struct of_device_id ab8500_btemp_match[] = {
{ },
};
-static struct platform_driver ab8500_btemp_driver = {
+struct platform_driver ab8500_btemp_driver = {
.probe = ab8500_btemp_probe,
.remove = ab8500_btemp_remove,
.driver = {
@@ -1116,20 +1114,6 @@ static struct platform_driver ab8500_btemp_driver = {
.pm = &ab8500_btemp_pm_ops,
},
};
-
-static int __init ab8500_btemp_init(void)
-{
- return platform_driver_register(&ab8500_btemp_driver);
-}
-
-static void __exit ab8500_btemp_exit(void)
-{
- platform_driver_unregister(&ab8500_btemp_driver);
-}
-
-device_initcall(ab8500_btemp_init);
-module_exit(ab8500_btemp_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski, Arun R Murthy");
MODULE_ALIAS("platform:ab8500-btemp");
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index a9be10eb2c22..af32cfae9f19 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/notifier.h>
@@ -3276,10 +3277,74 @@ static struct notifier_block charger_nb = {
.notifier_call = ab8500_external_charger_prepare,
};
-static int ab8500_charger_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_chargalg",
+ "ab8500_fg",
+ "ab8500_btemp",
+};
+
+static const struct power_supply_desc ab8500_ac_chg_desc = {
+ .name = "ab8500_ac",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = ab8500_charger_ac_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
+ .get_property = ab8500_charger_ac_get_property,
+};
+
+static const struct power_supply_desc ab8500_usb_chg_desc = {
+ .name = "ab8500_usb",
+ .type = POWER_SUPPLY_TYPE_USB,
+ .properties = ab8500_charger_usb_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
+ .get_property = ab8500_charger_usb_get_property,
+};
+
+static int ab8500_charger_bind(struct device *dev)
{
- struct ab8500_charger *di = platform_get_drvdata(pdev);
- int i, irq, ret;
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ch_stat;
+ int ret;
+
+ /* Create a work queue for the charger */
+ di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
+ WQ_MEM_RECLAIM);
+ if (di->charger_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ ch_stat = ab8500_charger_detect_chargers(di, false);
+
+ if (ch_stat & AC_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->ac_charger_attached_work,
+ HZ);
+ }
+ if (ch_stat & USB_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->usb_charger_attached_work,
+ HZ);
+ di->vbus_detected = true;
+ di->vbus_detected_start = true;
+ queue_work(di->charger_wq,
+ &di->detect_usb_type_work);
+ }
+
+ ret = component_bind_all(dev, di);
+ if (ret) {
+ dev_err(dev, "can't bind component devices\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static void ab8500_charger_unbind(struct device *dev)
+{
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ret;
/* Disable AC charging */
ab8500_charger_ac_en(&di->ac_chg, false, 0, 0);
@@ -3287,68 +3352,47 @@ static int ab8500_charger_remove(struct platform_device *pdev)
/* Disable USB charging */
ab8500_charger_usb_en(&di->usb_chg, false, 0, 0);
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
-
/* Backup battery voltage and current disable */
ret = abx500_mask_and_set_register_interruptible(di->dev,
AB8500_RTC, AB8500_RTC_CTRL_REG, RTC_BUP_CH_ENA, 0);
if (ret < 0)
dev_err(di->dev, "%s mask and set failed\n", __func__);
- usb_unregister_notifier(di->usb_phy, &di->nb);
- usb_put_phy(di->usb_phy);
-
/* Delete the work queue */
destroy_workqueue(di->charger_wq);
- /* Unregister external charger enable notifier */
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_unregister(
- &charger_notifier_list, &charger_nb);
-
flush_scheduled_work();
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-
- if (di->ac_chg.enabled && !di->ac_chg.external)
- power_supply_unregister(di->ac_chg.psy);
- return 0;
+ /* Unbind fg, btemp, algorithm */
+ component_unbind_all(dev, di);
}
-static char *supply_interface[] = {
- "ab8500_chargalg",
- "ab8500_fg",
- "ab8500_btemp",
+static const struct component_master_ops ab8500_charger_comp_ops = {
+ .bind = ab8500_charger_bind,
+ .unbind = ab8500_charger_unbind,
};
-static const struct power_supply_desc ab8500_ac_chg_desc = {
- .name = "ab8500_ac",
- .type = POWER_SUPPLY_TYPE_MAINS,
- .properties = ab8500_charger_ac_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
- .get_property = ab8500_charger_ac_get_property,
+static struct platform_driver *const ab8500_charger_component_drivers[] = {
+ &ab8500_fg_driver,
+ &ab8500_btemp_driver,
+ &abx500_chargalg_driver,
};
-static const struct power_supply_desc ab8500_usb_chg_desc = {
- .name = "ab8500_usb",
- .type = POWER_SUPPLY_TYPE_USB,
- .properties = ab8500_charger_usb_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
- .get_property = ab8500_charger_usb_get_property,
-};
+static int ab8500_charger_compare_dev(struct device *dev, void *data)
+{
+ return dev == data;
+}
static int ab8500_charger_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct component_match *match = NULL;
struct power_supply_config ac_psy_cfg = {}, usb_psy_cfg = {};
struct ab8500_charger *di;
- int irq, i, charger_status, ret = 0, ch_stat;
- struct device *dev = &pdev->dev;
+ int charger_status;
+ int i, irq;
+ int ret;
di = devm_kzalloc(dev, sizeof(*di), GFP_KERNEL);
if (!di)
@@ -3393,6 +3437,38 @@ static int ab8500_charger_probe(struct platform_device *pdev)
return ret;
}
+ /*
+ * VDD ADC supply needs to be enabled from this driver when there
+ * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
+ * interrupts during charging
+ */
+ di->regu = devm_regulator_get(dev, "vddadc");
+ if (IS_ERR(di->regu)) {
+ ret = PTR_ERR(di->regu);
+ dev_err(dev, "failed to get vddadc regulator\n");
+ return ret;
+ }
+
+ /* Request interrupts */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
+ irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+ if (irq < 0)
+ return irq;
+
+ ret = devm_request_threaded_irq(dev,
+ irq, NULL, ab8500_charger_irq[i].isr,
+ IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
+ ab8500_charger_irq[i].name, di);
+
+ if (ret != 0) {
+ dev_err(dev, "failed to request %s IRQ %d: %d\n"
+ , ab8500_charger_irq[i].name, irq, ret);
+ return ret;
+ }
+ dev_dbg(dev, "Requested %s IRQ %d: %d\n",
+ ab8500_charger_irq[i].name, irq, ret);
+ }
+
/* initialize lock */
spin_lock_init(&di->usb_state.usb_lock);
mutex_init(&di->usb_ipt_crnt_lock);
@@ -3422,11 +3498,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->ac_chg.enabled = di->bm->ac_enabled;
di->ac_chg.external = false;
- /*notifier for external charger enabling*/
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_register(
- &charger_notifier_list, &charger_nb);
-
/* USB supply */
/* ux500_charger sub-class */
di->usb_chg.ops.enable = &ab8500_charger_usb_en;
@@ -3442,14 +3513,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->usb_chg.external = false;
di->usb_state.usb_current = -1;
- /* Create a work queue for the charger */
- di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
- WQ_MEM_RECLAIM);
- if (di->charger_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
mutex_init(&di->charger_attached_mutex);
/* Init work for HW failure check */
@@ -3500,63 +3563,36 @@ static int ab8500_charger_probe(struct platform_device *pdev)
INIT_WORK(&di->check_usb_thermal_prot_work,
ab8500_charger_check_usb_thermal_prot_work);
- /*
- * VDD ADC supply needs to be enabled from this driver when there
- * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
- * interrupts during charging
- */
- di->regu = devm_regulator_get(dev, "vddadc");
- if (IS_ERR(di->regu)) {
- ret = PTR_ERR(di->regu);
- dev_err(dev, "failed to get vddadc regulator\n");
- goto free_charger_wq;
- }
-
/* Initialize OVV, and other registers */
ret = ab8500_charger_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize ABB registers\n");
- goto free_charger_wq;
+ return ret;
}
/* Register AC charger class */
if (di->ac_chg.enabled) {
- di->ac_chg.psy = power_supply_register(dev,
+ di->ac_chg.psy = devm_power_supply_register(dev,
&ab8500_ac_chg_desc,
&ac_psy_cfg);
if (IS_ERR(di->ac_chg.psy)) {
dev_err(dev, "failed to register AC charger\n");
- ret = PTR_ERR(di->ac_chg.psy);
- goto free_charger_wq;
+ return PTR_ERR(di->ac_chg.psy);
}
}
/* Register USB charger class */
if (di->usb_chg.enabled) {
- di->usb_chg.psy = power_supply_register(dev,
+ di->usb_chg.psy = devm_power_supply_register(dev,
&ab8500_usb_chg_desc,
&usb_psy_cfg);
if (IS_ERR(di->usb_chg.psy)) {
dev_err(dev, "failed to register USB charger\n");
- ret = PTR_ERR(di->usb_chg.psy);
- goto free_ac;
+ return PTR_ERR(di->usb_chg.psy);
}
}
- di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
- if (IS_ERR_OR_NULL(di->usb_phy)) {
- dev_err(dev, "failed to get usb transceiver\n");
- ret = -EINVAL;
- goto free_usb;
- }
- di->nb.notifier_call = ab8500_charger_usb_notifier_call;
- ret = usb_register_notifier(di->usb_phy, &di->nb);
- if (ret) {
- dev_err(dev, "failed to register usb notifier\n");
- goto put_usb_phy;
- }
-
/* Identify the connected charger types during startup */
charger_status = ab8500_charger_detect_chargers(di, true);
if (charger_status & AC_PW_CONN) {
@@ -3566,78 +3602,86 @@ static int ab8500_charger_probe(struct platform_device *pdev)
sysfs_notify(&di->ac_chg.psy->dev.kobj, NULL, "present");
}
- if (charger_status & USB_PW_CONN) {
- di->vbus_detected = true;
- di->vbus_detected_start = true;
- queue_work(di->charger_wq,
- &di->detect_usb_type_work);
- }
-
- /* Register interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ platform_set_drvdata(pdev, di);
- ret = request_threaded_irq(irq, NULL, ab8500_charger_irq[i].isr,
- IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
- ab8500_charger_irq[i].name, di);
+ /* Create something that will match the subdrivers when we bind */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_component_drivers); i++) {
+ struct device_driver *drv = &ab8500_charger_component_drivers[i]->driver;
+ struct device *p = NULL, *d;
- if (ret != 0) {
- dev_err(dev, "failed to request %s IRQ %d: %d\n"
- , ab8500_charger_irq[i].name, irq, ret);
- goto free_irq;
+ while ((d = platform_find_device_by_driver(p, drv))) {
+ put_device(p);
+ component_match_add(dev, &match,
+ ab8500_charger_compare_dev, d);
+ p = d;
}
- dev_dbg(dev, "Requested %s IRQ %d: %d\n",
- ab8500_charger_irq[i].name, irq, ret);
+ put_device(p);
+ }
+ if (!match) {
+ dev_err(dev, "no matching components\n");
+ return -ENODEV;
+ }
+ if (IS_ERR(match)) {
+ dev_err(dev, "could not create component match\n");
+ return PTR_ERR(match);
}
- platform_set_drvdata(pdev, di);
+ /* Notifier for external charger enabling */
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_register(
+ &charger_notifier_list, &charger_nb);
- mutex_lock(&di->charger_attached_mutex);
- ch_stat = ab8500_charger_detect_chargers(di, false);
-
- if ((ch_stat & AC_PW_CONN) == AC_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->ac_charger_attached_work,
- HZ);
+ di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
+ if (IS_ERR_OR_NULL(di->usb_phy)) {
+ dev_err(dev, "failed to get usb transceiver\n");
+ ret = -EINVAL;
+ goto out_charger_notifier;
}
- if ((ch_stat & USB_PW_CONN) == USB_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->usb_charger_attached_work,
- HZ);
+ di->nb.notifier_call = ab8500_charger_usb_notifier_call;
+ ret = usb_register_notifier(di->usb_phy, &di->nb);
+ if (ret) {
+ dev_err(dev, "failed to register usb notifier\n");
+ goto put_usb_phy;
}
- mutex_unlock(&di->charger_attached_mutex);
- return ret;
+ ret = component_master_add_with_match(&pdev->dev,
+ &ab8500_charger_comp_ops,
+ match);
+ if (ret) {
+ dev_err(dev, "failed to add component master\n");
+ goto free_notifier;
+ }
-free_irq:
- usb_unregister_notifier(di->usb_phy, &di->nb);
+ return 0;
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
+free_notifier:
+ usb_unregister_notifier(di->usb_phy, &di->nb);
put_usb_phy:
usb_put_phy(di->usb_phy);
-free_usb:
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-free_ac:
- if (di->ac_chg.enabled)
- power_supply_unregister(di->ac_chg.psy);
-free_charger_wq:
- destroy_workqueue(di->charger_wq);
+out_charger_notifier:
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
return ret;
}
+static int ab8500_charger_remove(struct platform_device *pdev)
+{
+ struct ab8500_charger *di = platform_get_drvdata(pdev);
+
+ component_master_del(&pdev->dev, &ab8500_charger_comp_ops);
+
+ usb_unregister_notifier(di->usb_phy, &di->nb);
+ usb_put_phy(di->usb_phy);
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
+
+ return 0;
+}
+
static SIMPLE_DEV_PM_OPS(ab8500_charger_pm_ops, ab8500_charger_suspend, ab8500_charger_resume);
static const struct of_device_id ab8500_charger_match[] = {
@@ -3657,15 +3701,24 @@ static struct platform_driver ab8500_charger_driver = {
static int __init ab8500_charger_init(void)
{
+ int ret;
+
+ ret = platform_register_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
+ if (ret)
+ return ret;
+
return platform_driver_register(&ab8500_charger_driver);
}
static void __exit ab8500_charger_exit(void)
{
+ platform_unregister_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
platform_driver_unregister(&ab8500_charger_driver);
}
-subsys_initcall_sync(ab8500_charger_init);
+module_init(ab8500_charger_init);
module_exit(ab8500_charger_exit);
MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index 0c7c01a0d979..acf0f2471c0b 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/component.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
@@ -2980,27 +2981,6 @@ static int __maybe_unused ab8500_fg_suspend(struct device *dev)
return 0;
}
-static int ab8500_fg_remove(struct platform_device *pdev)
-{
- int ret = 0;
- struct ab8500_fg *di = platform_get_drvdata(pdev);
-
- list_del(&di->node);
-
- /* Disable coulomb counter */
- ret = ab8500_fg_coulomb_counter(di, false);
- if (ret)
- dev_err(di->dev, "failed to disable coulomb counter\n");
-
- destroy_workqueue(di->fg_wq);
- ab8500_fg_sysfs_exit(di);
-
- flush_scheduled_work();
- ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
- return ret;
-}
-
/* ab8500 fg driver interrupts and their respective isr */
static struct ab8500_fg_interrupts ab8500_fg_irq[] = {
{"NCONV_ACCU", ab8500_fg_cc_convend_handler},
@@ -3024,11 +3004,50 @@ static const struct power_supply_desc ab8500_fg_desc = {
.external_power_changed = ab8500_fg_external_power_changed,
};
+static int ab8500_fg_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for running the FG algorithm */
+ di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
+ if (di->fg_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Start the coulomb counter */
+ ab8500_fg_coulomb_counter(di, true);
+ /* Run the FG algorithm */
+ queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+
+ return 0;
+}
+
+static void ab8500_fg_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+ int ret;
+
+ /* Disable coulomb counter */
+ ret = ab8500_fg_coulomb_counter(di, false);
+ if (ret)
+ dev_err(dev, "failed to disable coulomb counter\n");
+
+ destroy_workqueue(di->fg_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_fg_component_ops = {
+ .bind = ab8500_fg_bind,
+ .unbind = ab8500_fg_unbind,
+};
+
static int ab8500_fg_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
- struct power_supply_config psy_cfg = {};
struct device *dev = &pdev->dev;
+ struct power_supply_config psy_cfg = {};
struct ab8500_fg *di;
int i, irq;
int ret = 0;
@@ -3074,13 +3093,6 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INIT);
- /* Create a work queue for running the FG algorithm */
- di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
- if (di->fg_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for running the fg algorithm instantly */
INIT_WORK(&di->fg_work, ab8500_fg_instant_work);
@@ -3113,7 +3125,7 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize registers\n");
- goto free_inst_curr_wq;
+ return ret;
}
/* Consider battery unknown until we're informed otherwise */
@@ -3121,15 +3133,13 @@ static int ab8500_fg_probe(struct platform_device *pdev)
di->flags.batt_id_received = false;
/* Register FG power supply class */
- di->fg_psy = power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
+ di->fg_psy = devm_power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
if (IS_ERR(di->fg_psy)) {
dev_err(dev, "failed to register FG psy\n");
- ret = PTR_ERR(di->fg_psy);
- goto free_inst_curr_wq;
+ return PTR_ERR(di->fg_psy);
}
di->fg_samples = SEC_TO_SAMPLE(di->bm->fg_params->init_timer);
- ab8500_fg_coulomb_counter(di, true);
/*
* Initialize completion used to notify completion and start
@@ -3141,19 +3151,18 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Register primary interrupt handlers */
for (i = 0; i < ARRAY_SIZE(ab8500_fg_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_fg_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_fg_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_fg_irq[i].name, di);
if (ret != 0) {
dev_err(dev, "failed to request %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
@@ -3168,14 +3177,14 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_sysfs_init(di);
if (ret) {
dev_err(dev, "failed to create sysfs entry\n");
- goto free_irq;
+ return ret;
}
ret = ab8500_fg_sysfs_psy_create_attrs(di);
if (ret) {
dev_err(dev, "failed to create FG psy\n");
ab8500_fg_sysfs_exit(di);
- goto free_irq;
+ return ret;
}
/* Calibrate the fg first time */
@@ -3185,24 +3194,21 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Use room temp as default value until we get an update from driver. */
di->bat_temp = 210;
- /* Run the FG algorithm */
- queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
-
list_add_tail(&di->node, &ab8500_fg_list);
- return ret;
+ return component_add(dev, &ab8500_fg_component_ops);
+}
-free_irq:
- /* We also have to free all registered irqs */
- while (--i >= 0) {
- /* Last assignment of i from primary interrupt handlers */
- irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_fg_remove(struct platform_device *pdev)
+{
+ int ret = 0;
+ struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+ component_del(&pdev->dev, &ab8500_fg_component_ops);
+ list_del(&di->node);
+ ab8500_fg_sysfs_exit(di);
+ ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
-free_inst_curr_wq:
- destroy_workqueue(di->fg_wq);
return ret;
}
@@ -3213,7 +3219,7 @@ static const struct of_device_id ab8500_fg_match[] = {
{ },
};
-static struct platform_driver ab8500_fg_driver = {
+struct platform_driver ab8500_fg_driver = {
.probe = ab8500_fg_probe,
.remove = ab8500_fg_remove,
.driver = {
@@ -3222,20 +3228,6 @@ static struct platform_driver ab8500_fg_driver = {
.pm = &ab8500_fg_pm_ops,
},
};
-
-static int __init ab8500_fg_init(void)
-{
- return platform_driver_register(&ab8500_fg_driver);
-}
-
-static void __exit ab8500_fg_exit(void)
-{
- platform_driver_unregister(&ab8500_fg_driver);
-}
-
-subsys_initcall_sync(ab8500_fg_init);
-module_exit(ab8500_fg_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski");
MODULE_ALIAS("platform:ab8500-fg");
diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c
index f5b792243727..599684ce0e4b 100644
--- a/drivers/power/supply/abx500_chargalg.c
+++ b/drivers/power/supply/abx500_chargalg.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
@@ -1943,13 +1944,44 @@ static int __maybe_unused abx500_chargalg_suspend(struct device *dev)
return 0;
}
-static int abx500_chargalg_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_fg",
+};
+
</cut>
4 years, 1 month
- 3
- 2
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 22 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit 4c4503bf8c538bdbd8db8940aae3d7000885776e
Author: Martin Liska <mliska(a)suse.cz>
Date: Thu Nov 14 13:04:45 2019 +0100
Remove dead code in switch conv pass.
2019-11-14 Martin Liska <mliska(a)suse.cz>
* tree-switch-conversion.c (switch_conversion::switch_conversion):
Do not initialize m_other_count.
(switch_conversion::collect): Do not count m_default_count and
m_other_count as we use frequencies for edges.
* tree-switch-conversion.h: Remove m_default_count and m_other_count.
From-SVN: r278217
</cut>
Results regressed to (for first_bad == 4c4503bf8c538bdbd8db8940aae3d7000885776e)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-4c4503bf8c538bdbd8db8940aae3d7000885776e/results_id:
1
# 401.bzip2,bzip2_base.default regressed by 104
# 401.bzip2,[.] mainSort regressed by 116
from (for last_good == e61d0e4e2ed8170491e7dfe597340f86a75a31cd)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-baseline/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/baseline-gnu-release-aarch64-spec2k6-O2/3251
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3279
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-4c4503bf8c538bdbd8db8940aae3d7000885776e
cd investigate-gcc-4c4503bf8c538bdbd8db8940aae3d7000885776e
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 4c4503bf8c538bdbd8db8940aae3d7000885776e
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach e61d0e4e2ed8170491e7dfe597340f86a75a31cd
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit 4c4503bf8c538bdbd8db8940aae3d7000885776e
Author: Martin Liska <mliska(a)suse.cz>
Date: Thu Nov 14 13:04:45 2019 +0100
Remove dead code in switch conv pass.
2019-11-14 Martin Liska <mliska(a)suse.cz>
* tree-switch-conversion.c (switch_conversion::switch_conversion):
Do not initialize m_other_count.
(switch_conversion::collect): Do not count m_default_count and
m_other_count as we use frequencies for edges.
* tree-switch-conversion.h: Remove m_default_count and m_other_count.
From-SVN: r278217
---
gcc/ChangeLog | 8 ++++++++
gcc/tree-switch-conversion.c | 6 +-----
gcc/tree-switch-conversion.h | 6 ------
3 files changed, 9 insertions(+), 11 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 6060edff243..6b77d87a97d 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2019-11-14 Martin Liska <mliska(a)suse.cz>
+
+ * tree-switch-conversion.c (switch_conversion::switch_conversion):
+ Do not initialize m_other_count.
+ (switch_conversion::collect): Do not count m_default_count and
+ m_other_count as we use frequencies for edges.
+ * tree-switch-conversion.h: Remove m_default_count and m_other_count.
+
2019-11-14 Martin Liska <mliska(a)suse.cz>
PR other/92329
diff --git a/gcc/tree-switch-conversion.c b/gcc/tree-switch-conversion.c
index af4fd5e33bd..e741f56b520 100644
--- a/gcc/tree-switch-conversion.c
+++ b/gcc/tree-switch-conversion.c
@@ -61,7 +61,7 @@ using namespace tree_switch_conversion;
/* Constructor. */
-switch_conversion::switch_conversion (): m_final_bb (NULL), m_other_count (),
+switch_conversion::switch_conversion (): m_final_bb (NULL),
m_constructors (NULL), m_default_values (NULL),
m_arr_ref_first (NULL), m_arr_ref_last (NULL),
m_reason (NULL), m_default_case_nonstandard (false), m_cfg_altered (false)
@@ -89,10 +89,6 @@ switch_conversion::collect (gswitch *swtch)
e_default = gimple_switch_default_edge (cfun, swtch);
m_default_bb = e_default->dest;
m_default_prob = e_default->probability;
- m_default_count = e_default->count ();
- FOR_EACH_EDGE (e, ei, m_switch_bb->succs)
- if (e != e_default)
- m_other_count += e->count ();
/* Get upper and lower bounds of case values, and the covered range. */
min_case = gimple_switch_label (swtch, 1);
diff --git a/gcc/tree-switch-conversion.h b/gcc/tree-switch-conversion.h
index c58bccea7f1..a0639fc5477 100644
--- a/gcc/tree-switch-conversion.h
+++ b/gcc/tree-switch-conversion.h
@@ -819,12 +819,6 @@ public:
/* The probability of the default edge in the replaced switch. */
profile_probability m_default_prob;
- /* The count of the default edge in the replaced switch. */
- profile_count m_default_count;
-
- /* Combined count of all other (non-default) edges in the replaced switch. */
- profile_count m_other_count;
-
/* Number of phi nodes in the final bb (that we'll be replacing). */
int m_phi_count;
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3 - Build # 17 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3
Culprit:
<cut>
commit 5c315bee8c9db27d12cead928eea5a3fef97f34f
Author: Dawid Jurczak <dawid_jurek(a)vp.pl>
Date: Mon Jul 5 11:42:17 2021 +0200
[DSE] Transform memset + malloc --> calloc (PR25892)
After this change DSE can eliminate malloc + memset and emit calloc.
It's https://reviews.llvm.org/D101440 follow-up.
Differential Revision: https://reviews.llvm.org/D103009
</cut>
Results regressed to (for first_bad == 5c315bee8c9db27d12cead928eea5a3fef97f34f)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-5c315bee8c9db27d12cead928eea5a3fef97f34f/results_id:
1
# 464.h264ref,h264ref_base.default regressed by 105
# 464.h264ref,[.] FastFullPelBlockMotionSearch regressed by 146
from (for last_good == bc5b5ea037dbadd281c59248ae9d2742b51c69ed)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-bc5b5ea037dbadd281c59248ae9d2742b51c69ed/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3221
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3210
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-5c315bee8c9db27d12cead928eea5a3fef97f34f
cd investigate-llvm-5c315bee8c9db27d12cead928eea5a3fef97f34f
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 5c315bee8c9db27d12cead928eea5a3fef97f34f
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach bc5b5ea037dbadd281c59248ae9d2742b51c69ed
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 5c315bee8c9db27d12cead928eea5a3fef97f34f
Author: Dawid Jurczak <dawid_jurek(a)vp.pl>
Date: Mon Jul 5 11:42:17 2021 +0200
[DSE] Transform memset + malloc --> calloc (PR25892)
After this change DSE can eliminate malloc + memset and emit calloc.
It's https://reviews.llvm.org/D101440 follow-up.
Differential Revision: https://reviews.llvm.org/D103009
---
.../lib/Transforms/Scalar/DeadStoreElimination.cpp | 81 +++++++++--
.../Transforms/DeadStoreElimination/noop-stores.ll | 153 ++++++++++++++++++++-
2 files changed, 219 insertions(+), 15 deletions(-)
diff --git a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
index d22b3f409585..0ada5c6e72c9 100644
--- a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
@@ -56,6 +56,7 @@
#include "llvm/IR/DataLayout.h"
#include "llvm/IR/Dominators.h"
#include "llvm/IR/Function.h"
+#include "llvm/IR/IRBuilder.h"
#include "llvm/IR/InstIterator.h"
#include "llvm/IR/InstrTypes.h"
#include "llvm/IR/Instruction.h"
@@ -78,6 +79,7 @@
#include "llvm/Support/raw_ostream.h"
#include "llvm/Transforms/Scalar.h"
#include "llvm/Transforms/Utils/AssumeBundleBuilder.h"
+#include "llvm/Transforms/Utils/BuildLibCalls.h"
#include "llvm/Transforms/Utils/Local.h"
#include <algorithm>
#include <cassert>
@@ -505,7 +507,12 @@ memoryIsNotModifiedBetween(Instruction *FirstI, Instruction *SecondI,
BasicBlock::iterator SecondBBI(SecondI);
BasicBlock *FirstBB = FirstI->getParent();
BasicBlock *SecondBB = SecondI->getParent();
- MemoryLocation MemLoc = MemoryLocation::get(SecondI);
+ MemoryLocation MemLoc;
+ if (auto *MemSet = dyn_cast<MemSetInst>(SecondI))
+ MemLoc = MemoryLocation::getForDest(MemSet);
+ else
+ MemLoc = MemoryLocation::get(SecondI);
+
auto *MemLocPtr = const_cast<Value *>(MemLoc.Ptr);
// Start checking the SecondBB.
@@ -819,14 +826,17 @@ bool isNoopIntrinsic(Instruction *I) {
}
// Check if we can ignore \p D for DSE.
-bool canSkipDef(MemoryDef *D, bool DefVisibleToCaller) {
+bool canSkipDef(MemoryDef *D, bool DefVisibleToCaller,
+ const TargetLibraryInfo &TLI) {
Instruction *DI = D->getMemoryInst();
// Calls that only access inaccessible memory cannot read or write any memory
// locations we consider for elimination.
if (auto *CB = dyn_cast<CallBase>(DI))
- if (CB->onlyAccessesInaccessibleMemory())
+ if (CB->onlyAccessesInaccessibleMemory()) {
+ if (isAllocLikeFn(DI, &TLI))
+ return false;
return true;
-
+ }
// We can eliminate stores to locations not visible to the caller across
// throwing instructions.
if (DI->mayThrow() && !DefVisibleToCaller)
@@ -841,7 +851,7 @@ bool canSkipDef(MemoryDef *D, bool DefVisibleToCaller) {
return true;
// Skip intrinsics that do not really read or modify memory.
- if (isNoopIntrinsic(D->getMemoryInst()))
+ if (isNoopIntrinsic(DI))
return true;
return false;
@@ -1389,7 +1399,7 @@ struct DSEState {
MemoryDef *CurrentDef = cast<MemoryDef>(Current);
Instruction *CurrentI = CurrentDef->getMemoryInst();
- if (canSkipDef(CurrentDef, !isInvisibleToCallerBeforeRet(DefUO)))
+ if (canSkipDef(CurrentDef, !isInvisibleToCallerBeforeRet(DefUO), TLI))
continue;
// Before we try to remove anything, check for any extra throwing
@@ -1816,13 +1826,58 @@ struct DSEState {
if (StoredConstant && StoredConstant->isNullValue()) {
auto *DefUOInst = dyn_cast<Instruction>(DefUO);
- if (DefUOInst && isCallocLikeFn(DefUOInst, &TLI)) {
- auto *UnderlyingDef = cast<MemoryDef>(MSSA.getMemoryAccess(DefUOInst));
- // If UnderlyingDef is the clobbering access of Def, no instructions
- // between them can modify the memory location.
- auto *ClobberDef =
- MSSA.getSkipSelfWalker()->getClobberingMemoryAccess(Def);
- return UnderlyingDef == ClobberDef;
+ if (DefUOInst) {
+ if (isCallocLikeFn(DefUOInst, &TLI)) {
+ auto *UnderlyingDef =
+ cast<MemoryDef>(MSSA.getMemoryAccess(DefUOInst));
+ // If UnderlyingDef is the clobbering access of Def, no instructions
+ // between them can modify the memory location.
+ auto *ClobberDef =
+ MSSA.getSkipSelfWalker()->getClobberingMemoryAccess(Def);
+ return UnderlyingDef == ClobberDef;
+ }
+
+ if (MemSet) {
+ if (F.hasFnAttribute(Attribute::SanitizeMemory) ||
+ F.hasFnAttribute(Attribute::SanitizeAddress) ||
+ F.hasFnAttribute(Attribute::SanitizeHWAddress) ||
+ F.getName() == "calloc")
+ return false;
+ auto *Malloc = const_cast<CallInst *>(dyn_cast<CallInst>(DefUOInst));
+ if (!Malloc)
+ return false;
+ auto *InnerCallee = Malloc->getCalledFunction();
+ if (!InnerCallee)
+ return false;
+ LibFunc Func;
+ if (!TLI.getLibFunc(*InnerCallee, Func) || !TLI.has(Func) ||
+ Func != LibFunc_malloc)
+ return false;
+ if (Malloc->getOperand(0) == MemSet->getLength()) {
+ if (DT.dominates(Malloc, MemSet) &&
+ memoryIsNotModifiedBetween(Malloc, MemSet, BatchAA, DL, &DT)) {
+ IRBuilder<> IRB(Malloc);
+ const auto &DL = Malloc->getModule()->getDataLayout();
+ AttributeList EmptyList;
+ if (auto *Calloc = emitCalloc(
+ ConstantInt::get(IRB.getIntPtrTy(DL), 1),
+ Malloc->getArgOperand(0), EmptyList, IRB, TLI)) {
+ MemorySSAUpdater Updater(&MSSA);
+ auto *LastDef = cast<MemoryDef>(
+ Updater.getMemorySSA()->getMemoryAccess(Malloc));
+ auto *NewAccess = Updater.createMemoryAccessAfter(
+ cast<Instruction>(Calloc), LastDef, LastDef);
+ auto *NewAccessMD = cast<MemoryDef>(NewAccess);
+ Updater.insertDef(NewAccessMD, /*RenameUses=*/true);
+ Updater.removeMemoryAccess(Malloc);
+ Malloc->replaceAllUsesWith(Calloc);
+ Malloc->eraseFromParent();
+ return true;
+ }
+ return false;
+ }
+ }
+ }
}
}
diff --git a/llvm/test/Transforms/DeadStoreElimination/noop-stores.ll b/llvm/test/Transforms/DeadStoreElimination/noop-stores.ll
index 184653982a6a..12534b6047c5 100644
--- a/llvm/test/Transforms/DeadStoreElimination/noop-stores.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/noop-stores.ll
@@ -1,9 +1,8 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
; RUN: opt < %s -basic-aa -dse -S | FileCheck %s
-; RUN: opt < %s -aa-pipeline=basic-aa -passes=dse -S | FileCheck %s
+; RUN: opt < %s -aa-pipeline=basic-aa -passes='dse,verify<memoryssa>' -S | FileCheck %s
target datalayout = "E-p:64:64:64-a0:0:8-f32:32:32-f64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:32:64-v64:64:64-v128:128:128"
-declare i8* @calloc(i64, i64)
declare void @memset_pattern16(i8*, i8*, i64)
declare void @llvm.memset.p0i8.i64(i8* nocapture, i8, i64, i1) nounwind
@@ -309,6 +308,156 @@ entry:
ret void
}
+declare noalias i8* @malloc(i64)
+declare noalias i8* @_Znwm(i64)
+declare void @clobber_memory(float*)
+
+; based on pr25892_lite
+define i8* @zero_memset_after_malloc(i64 %size) {
+; CHECK-LABEL: @zero_memset_after_malloc(
+; CHECK-NEXT: [[CALL:%.*]] = call i8* @calloc(i64 1, i64 [[SIZE:%.*]])
+; CHECK-NEXT: ret i8* [[CALL]]
+;
+ %call = call i8* @malloc(i64 %size) inaccessiblememonly
+ call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 %size, i1 false)
+ ret i8* %call
+}
+
+; based on pr25892_lite
+define i8* @zero_memset_after_malloc_with_intermediate_clobbering(i64 %size) {
+; CHECK-LABEL: @zero_memset_after_malloc_with_intermediate_clobbering(
+; CHECK-NEXT: [[CALL:%.*]] = call i8* @malloc(i64 [[SIZE:%.*]])
+; CHECK-NEXT: [[BC:%.*]] = bitcast i8* [[CALL]] to float*
+; CHECK-NEXT: call void @clobber_memory(float* [[BC]])
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 0, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: ret i8* [[CALL]]
+;
+ %call = call i8* @malloc(i64 %size) inaccessiblememonly
+ %bc = bitcast i8* %call to float*
+ call void @clobber_memory(float* %bc)
+ call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 %size, i1 false)
+ ret i8* %call
+}
+
+; based on pr25892_lite
+define i8* @zero_memset_after_malloc_with_different_sizes(i64 %size) {
+; CHECK-LABEL: @zero_memset_after_malloc_with_different_sizes(
+; CHECK-NEXT: [[CALL:%.*]] = call i8* @malloc(i64 [[SIZE:%.*]])
+; CHECK-NEXT: [[SIZE2:%.*]] = add nsw i64 [[SIZE]], -1
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 0, i64 [[SIZE2]], i1 false)
+; CHECK-NEXT: ret i8* [[CALL]]
+;
+ %call = call i8* @malloc(i64 %size) inaccessiblememonly
+ %size2 = add nsw i64 %size, -1
+ call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 %size2, i1 false)
+ ret i8* %call
+}
+
+; based on pr25892_lite
+define i8* @zero_memset_after_new(i64 %size) {
+; CHECK-LABEL: @zero_memset_after_new(
+; CHECK-NEXT: [[CALL:%.*]] = call i8* @_Znwm(i64 [[SIZE:%.*]])
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL]], i8 0, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: ret i8* [[CALL]]
+;
+ %call = call i8* @_Znwm(i64 %size)
+ call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 %size, i1 false)
+ ret i8* %call
+}
+
+; This should not create a calloc and should not crash the compiler.
+define i8* @notmalloc_memset(i64 %size, i8*(i64)* %notmalloc) {
+; CHECK-LABEL: @notmalloc_memset(
+; CHECK-NEXT: [[CALL1:%.*]] = call i8* [[NOTMALLOC:%.*]](i64 [[SIZE:%.*]])
+; CHECK-NEXT: call void @llvm.memset.p0i8.i64(i8* [[CALL1]], i8 0, i64 [[SIZE]], i1 false)
+; CHECK-NEXT: ret i8* [[CALL1]]
+;
+ %call1 = call i8* %notmalloc(i64 %size)
+ call void @llvm.memset.p0i8.i64(i8* %call1, i8 0, i64 %size, i1 false)
+ ret i8* %call1
+}
+
+; This should not create recursive call to calloc.
+define i8* @calloc(i64 %nmemb, i64 %size) {
+; CHECK-LABEL: @calloc(
+; CHECK: entry:
+; CHECK-NEXT: [[MUL:%.*]] = mul i64 [[SIZE:%.*]], [[NMEMB:%.*]]
+; CHECK-NEXT: [[CALL:%.*]] = tail call noalias align 16 i8* @malloc(i64 [[MUL]])
+; CHECK-NEXT: [[TOBOOL_NOT:%.*]] = icmp eq i8* [[CALL]], null
+; CHECK-NEXT: br i1 [[TOBOOL_NOT]], label [[IF_END:%.*]], label [[IF_THEN:%.*]]
+; CHECK: if.then:
+; CHECK-NEXT: tail call void @llvm.memset.p0i8.i64(i8* nonnull align 16 [[CALL]], i8 0, i64 [[MUL]], i1 false)
+; CHECK-NEXT: br label [[IF_END]]
+; CHECK: if.end:
+; CHECK-NEXT: ret i8* [[CALL]]
+;
+entry:
+ %mul = mul i64 %size, %nmemb
+ %call = tail call noalias align 16 i8* @malloc(i64 %mul)
+ %tobool.not = icmp eq i8* %call, null
+ br i1 %tobool.not, label %if.end, label %if.then
+
+if.then: ; preds = %entry
+ tail call void @llvm.memset.p0i8.i64(i8* nonnull align 16 %call, i8 0, i64 %mul, i1 false)
+ br label %if.end
+
+if.end: ; preds = %if.then, %entry
+ ret i8* %call
+}
+
+define float* @pr25892(i64 %size) {
+; CHECK-LABEL: @pr25892(
+; CHECK: entry:
+; CHECK-NEXT: [[CALL:%.*]] = call i8* @calloc(i64 1, i64 [[SIZE:%.*]])
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8* [[CALL]], null
+; CHECK-NEXT: br i1 [[CMP]], label [[CLEANUP:%.*]], label [[IF_END:%.*]]
+; CHECK: if.end:
+; CHECK-NEXT: [[BC:%.*]] = bitcast i8* [[CALL]] to float*
+; CHECK-NEXT: br label [[CLEANUP]]
+; CHECK: cleanup:
+; CHECK-NEXT: [[RETVAL_0:%.*]] = phi float* [ [[BC]], [[IF_END]] ], [ null, [[ENTRY:%.*]] ]
+; CHECK-NEXT: ret float* [[RETVAL_0]]
+;
+entry:
+ %call = call i8* @malloc(i64 %size) inaccessiblememonly
+ %cmp = icmp eq i8* %call, null
+ br i1 %cmp, label %cleanup, label %if.end
+if.end:
+ %bc = bitcast i8* %call to float*
+ call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 %size, i1 false)
+ br label %cleanup
+cleanup:
+ %retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ]
+ ret float* %retval.0
+}
+
+define float* @pr25892_with_extra_store(i64 %size) {
+; CHECK-LABEL: @pr25892_with_extra_store(
+; CHECK: entry:
+; CHECK-NEXT: [[CALL:%.*]] = call i8* @calloc(i64 1, i64 [[SIZE:%.*]])
+; CHECK-NEXT: [[CMP:%.*]] = icmp eq i8* [[CALL]], null
+; CHECK-NEXT: br i1 [[CMP]], label [[CLEANUP:%.*]], label [[IF_END:%.*]]
+; CHECK: if.end:
+; CHECK-NEXT: [[BC:%.*]] = bitcast i8* [[CALL]] to float*
+; CHECK-NEXT: br label [[CLEANUP]]
+; CHECK: cleanup:
+; CHECK-NEXT: [[RETVAL_0:%.*]] = phi float* [ [[BC]], [[IF_END]] ], [ null, [[ENTRY:%.*]] ]
+; CHECK-NEXT: ret float* [[RETVAL_0]]
+;
+entry:
+ %call = call i8* @malloc(i64 %size) inaccessiblememonly
+ %cmp = icmp eq i8* %call, null
+ br i1 %cmp, label %cleanup, label %if.end
+if.end:
+ %bc = bitcast i8* %call to float*
+ call void @llvm.memset.p0i8.i64(i8* %call, i8 0, i64 %size, i1 false)
+ store i8 0, i8* %call, align 1
+ br label %cleanup
+cleanup:
+ %retval.0 = phi float* [ %bc, %if.end ], [ null, %entry ]
+ ret float* %retval.0
+}
+
; PR50143
define i8* @store_zero_after_calloc_inaccessiblememonly() {
; CHECK-LABEL: @store_zero_after_calloc_inaccessiblememonly(
</cut>
4 years, 1 month
- 1
- 0
[ACTIVITY] 2 - 6 August 2021
by Prathamesh Kulkarni
== This Week ==
* GNU-708 (Attribute to mark param as const)
- Created prototype patch
- Discussions on gcc mailing list
* PR66791 (replace builtins in intrinsics with vector extensions)
- Fixed issue with PR98435 test-case as suggested by Christophe
- Pinged patches for review.
== Next Week ==
- GNU-708, PR66791
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/gnu-master-arm-spec2k6-O3_LTO - Build # 34 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O3_LTO
Culprit:
<cut>
commit f31da42e047e8018ca6ad9809273bc7efb6ffcaf
Author: Richard Biener <rguenther(a)suse.de>
Date: Fri Aug 6 14:39:05 2021 +0200
tree-optimization/101801 - remove vect_worthwhile_without_simd_p
This removes the cost part of vect_worthwhile_without_simd_p, retaining
only the correctness bits. The reason is that the cost heuristic
do not properly account for SLP plus the check whether "without simd"
applies misfires for AVX512 mask vectors at the moment, leading to
missed vectorizations there.
Any costing decision should take place in the cost modeling, no
single stmt is to disable all vectorization on its own.
2021-08-06 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/101801
* tree-vectorizer.h (vect_worthwhile_without_simd_p): Rename...
(vect_can_vectorize_without_simd_p): ... to this.
* tree-vect-loop.c (vect_worthwhile_without_simd_p): Rename...
(vect_can_vectorize_without_simd_p): ... to this and fold
in vect_min_worthwhile_factor.
(vect_min_worthwhile_factor): Remove.
(vectorizable_reduction): Adjust and remove the cost part.
* tree-vect-stmts.c (vectorizable_shift): Likewise.
(vectorizable_operation): Likewise.
</cut>
Results regressed to (for first_bad == f31da42e047e8018ca6ad9809273bc7efb6ffcaf)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-f31da42e047e8018ca6ad9809273bc7efb6ffcaf/results_id:
1
# 482.sphinx3,sphinx_livepretend_base.default regressed by 105
from (for last_good == c2a984a3570b908a44a35e43bb48f0a05196156a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O3_LTO_marm artifacts/build-c2a984a3570b908a44a35e43bb48f0a05196156a/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of last_good: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O3_LTO/3203
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of first_bad: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O3_LTO/3211
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-f31da42e047e8018ca6ad9809273bc7efb6ffcaf
cd investigate-gcc-f31da42e047e8018ca6ad9809273bc7efb6ffcaf
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach f31da42e047e8018ca6ad9809273bc7efb6ffcaf
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c2a984a3570b908a44a35e43bb48f0a05196156a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Full commit (up to 1000 lines):
<cut>
commit f31da42e047e8018ca6ad9809273bc7efb6ffcaf
Author: Richard Biener <rguenther(a)suse.de>
Date: Fri Aug 6 14:39:05 2021 +0200
tree-optimization/101801 - remove vect_worthwhile_without_simd_p
This removes the cost part of vect_worthwhile_without_simd_p, retaining
only the correctness bits. The reason is that the cost heuristic
do not properly account for SLP plus the check whether "without simd"
applies misfires for AVX512 mask vectors at the moment, leading to
missed vectorizations there.
Any costing decision should take place in the cost modeling, no
single stmt is to disable all vectorization on its own.
2021-08-06 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/101801
* tree-vectorizer.h (vect_worthwhile_without_simd_p): Rename...
(vect_can_vectorize_without_simd_p): ... to this.
* tree-vect-loop.c (vect_worthwhile_without_simd_p): Rename...
(vect_can_vectorize_without_simd_p): ... to this and fold
in vect_min_worthwhile_factor.
(vect_min_worthwhile_factor): Remove.
(vectorizable_reduction): Adjust and remove the cost part.
* tree-vect-stmts.c (vectorizable_shift): Likewise.
(vectorizable_operation): Likewise.
---
gcc/tree-vect-loop.c | 43 +++++++------------------------------------
gcc/tree-vect-stmts.c | 26 ++------------------------
gcc/tree-vectorizer.h | 2 +-
3 files changed, 10 insertions(+), 61 deletions(-)
diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
index 1e21fe6b13d..37c7daa7f9e 100644
--- a/gcc/tree-vect-loop.c
+++ b/gcc/tree-vect-loop.c
@@ -7227,24 +7227,13 @@ vectorizable_reduction (loop_vec_info loop_vinfo,
if (dump_enabled_p ())
dump_printf (MSG_NOTE, "op not supported by target.\n");
if (maybe_ne (GET_MODE_SIZE (vec_mode), UNITS_PER_WORD)
- || !vect_worthwhile_without_simd_p (loop_vinfo, code))
+ || !vect_can_vectorize_without_simd_p (code))
ok = false;
else
if (dump_enabled_p ())
dump_printf (MSG_NOTE, "proceeding using word mode.\n");
}
- /* Worthwhile without SIMD support? */
- if (ok
- && !VECTOR_MODE_P (TYPE_MODE (vectype_in))
- && !vect_worthwhile_without_simd_p (loop_vinfo, code))
- {
- if (dump_enabled_p ())
- dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
- "not worthwhile without SIMD support.\n");
- ok = false;
- }
-
/* lane-reducing operations have to go through vect_transform_reduction.
For the other cases try without the single cycle optimization. */
if (!ok)
@@ -7948,46 +7937,28 @@ vectorizable_phi (vec_info *,
}
-/* Function vect_min_worthwhile_factor.
+/* Return true if we can emulate CODE on an integer mode representation
+ of a vector. */
- For a loop where we could vectorize the operation indicated by CODE,
- return the minimum vectorization factor that makes it worthwhile
- to use generic vectors. */
-static unsigned int
-vect_min_worthwhile_factor (enum tree_code code)
+bool
+vect_can_vectorize_without_simd_p (tree_code code)
{
switch (code)
{
case PLUS_EXPR:
case MINUS_EXPR:
case NEGATE_EXPR:
- return 4;
-
case BIT_AND_EXPR:
case BIT_IOR_EXPR:
case BIT_XOR_EXPR:
case BIT_NOT_EXPR:
- return 2;
+ return true;
default:
- return INT_MAX;
+ return false;
}
}
-/* Return true if VINFO indicates we are doing loop vectorization and if
- it is worth decomposing CODE operations into scalar operations for
- that loop's vectorization factor. */
-
-bool
-vect_worthwhile_without_simd_p (vec_info *vinfo, tree_code code)
-{
- loop_vec_info loop_vinfo = dyn_cast <loop_vec_info> (vinfo);
- unsigned HOST_WIDE_INT value;
- return (loop_vinfo
- && LOOP_VINFO_VECT_FACTOR (loop_vinfo).is_constant (&value)
- && value >= vect_min_worthwhile_factor (code));
-}
-
/* Function vectorizable_induction
Check if STMT_INFO performs an induction computation that can be vectorized.
diff --git a/gcc/tree-vect-stmts.c b/gcc/tree-vect-stmts.c
index 94bdb74ea8d..5b94d41e292 100644
--- a/gcc/tree-vect-stmts.c
+++ b/gcc/tree-vect-stmts.c
@@ -5685,24 +5685,13 @@ vectorizable_shift (vec_info *vinfo,
/* Check only during analysis. */
if (maybe_ne (GET_MODE_SIZE (vec_mode), UNITS_PER_WORD)
|| (!vec_stmt
- && !vect_worthwhile_without_simd_p (vinfo, code)))
+ && !vect_can_vectorize_without_simd_p (code)))
return false;
if (dump_enabled_p ())
dump_printf_loc (MSG_NOTE, vect_location,
"proceeding using word mode.\n");
}
- /* Worthwhile without SIMD support? Check only during analysis. */
- if (!vec_stmt
- && !VECTOR_MODE_P (TYPE_MODE (vectype))
- && !vect_worthwhile_without_simd_p (vinfo, code))
- {
- if (dump_enabled_p ())
- dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
- "not worthwhile without SIMD support.\n");
- return false;
- }
-
if (!vec_stmt) /* transformation not required. */
{
if (slp_node
@@ -6094,24 +6083,13 @@ vectorizable_operation (vec_info *vinfo,
"op not supported by target.\n");
/* Check only during analysis. */
if (maybe_ne (GET_MODE_SIZE (vec_mode), UNITS_PER_WORD)
- || (!vec_stmt && !vect_worthwhile_without_simd_p (vinfo, code)))
+ || (!vec_stmt && !vect_can_vectorize_without_simd_p (code)))
return false;
if (dump_enabled_p ())
dump_printf_loc (MSG_NOTE, vect_location,
"proceeding using word mode.\n");
}
- /* Worthwhile without SIMD support? Check only during analysis. */
- if (!VECTOR_MODE_P (vec_mode)
- && !vec_stmt
- && !vect_worthwhile_without_simd_p (vinfo, code))
- {
- if (dump_enabled_p ())
- dump_printf_loc (MSG_MISSED_OPTIMIZATION, vect_location,
- "not worthwhile without SIMD support.\n");
- return false;
- }
-
int reduc_idx = STMT_VINFO_REDUC_IDX (stmt_info);
vec_loop_masks *masks = (loop_vinfo ? &LOOP_VINFO_MASKS (loop_vinfo) : NULL);
internal_fn cond_fn = get_conditional_internal_fn (code);
diff --git a/gcc/tree-vectorizer.h b/gcc/tree-vectorizer.h
index 5571b3cce3b..de0ecf86478 100644
--- a/gcc/tree-vectorizer.h
+++ b/gcc/tree-vectorizer.h
@@ -2061,7 +2061,7 @@ extern bool vectorizable_lc_phi (loop_vec_info, stmt_vec_info,
gimple **, slp_tree);
extern bool vectorizable_phi (vec_info *, stmt_vec_info, gimple **, slp_tree,
stmt_vector_for_cost *);
-extern bool vect_worthwhile_without_simd_p (vec_info *, tree_code);
+extern bool vect_can_vectorize_without_simd_p (tree_code);
extern int vect_get_known_peeling_cost (loop_vec_info, int, int *,
stmt_vector_for_cost *,
stmt_vector_for_cost *,
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-release-arm-spec2k6-Os - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_apm/llvm-release-arm-spec2k6-Os. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-release-arm-spec2k6-Os
Culprit:
<cut>
commit b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8
Author: Jakub Jelinek <jakub(a)redhat.com>
Date: Tue Aug 11 16:46:49 2020 +0200
c-family: Fix ICE in get_atomic_generic_size [PR96545]
As the testcase shows, we would ICE if the type of the first argument of
various atomic builtins was pointer to (non-void) incomplete type, we would
assume that TYPE_SIZE_UNIT must be non-NULL. This patch diagnoses it
instead. And also changes the TREE_CODE != INTEGER_CST check to
!tree_fits_uhwi_p, as we use tree_to_uhwi after this and at least in theory
the int could be too large and not fit.
2020-08-11 Jakub Jelinek <jakub(a)redhat.com>
PR c/96545
* c-common.c (get_atomic_generic_size): Require that first argument's
type points to a complete type and use tree_fits_uhwi_p instead of
just INTEGER_CST TREE_CODE check for the TYPE_SIZE_UNIT.
* c-c++-common/pr96545.c: New test.
(cherry picked from commit 7840b4dc05539cf5575b3e9ff57ff5f6c3da2cae)
</cut>
Results regressed to (for first_bad == b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os_mthumb artifacts/build-b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8/results_id:
1
# 429.mcf,mcf_base.default regressed by 104
# 470.lbm,lbm_base.default regressed by 103
from (for last_good == db00336a49707327552e678b59da8e85384bdae6)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os_mthumb artifacts/build-db00336a49707327552e678b59da8e85384bdae6/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release…
Results ID of last_good: apm_32/tcwg_bmk_llvm_apm/bisect-llvm-release-arm-spec2k6-Os/3201
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release…
Results ID of first_bad: apm_32/tcwg_bmk_llvm_apm/bisect-llvm-release-arm-spec2k6-Os/3141
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8
cd investigate-gcc-b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach db00336a49707327552e678b59da8e85384bdae6
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit b9bb6a5e12cae44a1cbf298b69f28fc6871f81c8
Author: Jakub Jelinek <jakub(a)redhat.com>
Date: Tue Aug 11 16:46:49 2020 +0200
c-family: Fix ICE in get_atomic_generic_size [PR96545]
As the testcase shows, we would ICE if the type of the first argument of
various atomic builtins was pointer to (non-void) incomplete type, we would
assume that TYPE_SIZE_UNIT must be non-NULL. This patch diagnoses it
instead. And also changes the TREE_CODE != INTEGER_CST check to
!tree_fits_uhwi_p, as we use tree_to_uhwi after this and at least in theory
the int could be too large and not fit.
2020-08-11 Jakub Jelinek <jakub(a)redhat.com>
PR c/96545
* c-common.c (get_atomic_generic_size): Require that first argument's
type points to a complete type and use tree_fits_uhwi_p instead of
just INTEGER_CST TREE_CODE check for the TYPE_SIZE_UNIT.
* c-c++-common/pr96545.c: New test.
(cherry picked from commit 7840b4dc05539cf5575b3e9ff57ff5f6c3da2cae)
---
gcc/c-family/c-common.c | 9 ++++++++-
gcc/testsuite/c-c++-common/pr96545.c | 31 +++++++++++++++++++++++++++++++
2 files changed, 39 insertions(+), 1 deletion(-)
diff --git a/gcc/c-family/c-common.c b/gcc/c-family/c-common.c
index 20258c331af..b6eb40c8122 100644
--- a/gcc/c-family/c-common.c
+++ b/gcc/c-family/c-common.c
@@ -6948,8 +6948,15 @@ get_atomic_generic_size (location_t loc, tree function,
return 0;
}
+ if (!COMPLETE_TYPE_P (TREE_TYPE (type_0)))
+ {
+ error_at (loc, "argument 1 of %qE must be a pointer to a complete type",
+ function);
+ return 0;
+ }
+
/* Types must be compile time constant sizes. */
- if (TREE_CODE ((TYPE_SIZE_UNIT (TREE_TYPE (type_0)))) != INTEGER_CST)
+ if (!tree_fits_uhwi_p ((TYPE_SIZE_UNIT (TREE_TYPE (type_0)))))
{
error_at (loc,
"argument 1 of %qE must be a pointer to a constant size type",
diff --git a/gcc/testsuite/c-c++-common/pr96545.c b/gcc/testsuite/c-c++-common/pr96545.c
new file mode 100644
index 00000000000..bc6b0cf345c
--- /dev/null
+++ b/gcc/testsuite/c-c++-common/pr96545.c
@@ -0,0 +1,31 @@
+/* PR c/96545 */
+/* { dg-do compile } */
+
+extern char x[], y[], z[];
+struct S;
+extern struct S s, t, u;
+int v, w;
+
+void
+foo (void)
+{
+ __atomic_exchange (&x, &y, &z, 0); /* { dg-error "must be a pointer to a complete type" } */
+}
+
+void
+bar (void)
+{
+ __atomic_exchange (&s, &t, &u, 0); /* { dg-error "must be a pointer to a complete type" } */
+}
+
+void
+baz (void)
+{
+ __atomic_exchange (&v, &t, &w, 0); /* { dg-error "size mismatch in argument 2 of" } */
+}
+
+void
+qux (void)
+{
+ __atomic_exchange (&v, &w, &t, 0); /* { dg-error "size mismatch in argument 3 of" } */
+}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 21 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit e61d0e4e2ed8170491e7dfe597340f86a75a31cd
Author: Martin Liska <mliska(a)suse.cz>
Date: Thu Nov 14 09:57:57 2019 +0100
Remove wrong lto-dump: lto1 makefile dependency.
2019-11-14 Martin Liska <mliska(a)suse.cz>
* Make-lang.in: Remove wrong dependency
of LTO_DUMP_EXE on LTO_EXE.
From-SVN: r278212
</cut>
Results regressed to (for first_bad == e61d0e4e2ed8170491e7dfe597340f86a75a31cd)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-e61d0e4e2ed8170491e7dfe597340f86a75a31cd/results_id:
1
# 447.dealII,dealII_base.default regressed by 103
from (for last_good == 0840ffdf4e3568ba586371682ef485f9e5d31ae2)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-0840ffdf4e3568ba586371682ef485f9e5d31ae2/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3123
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/3116
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-e61d0e4e2ed8170491e7dfe597340f86a75a31cd
cd investigate-gcc-e61d0e4e2ed8170491e7dfe597340f86a75a31cd
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach e61d0e4e2ed8170491e7dfe597340f86a75a31cd
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 0840ffdf4e3568ba586371682ef485f9e5d31ae2
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit e61d0e4e2ed8170491e7dfe597340f86a75a31cd
Author: Martin Liska <mliska(a)suse.cz>
Date: Thu Nov 14 09:57:57 2019 +0100
Remove wrong lto-dump: lto1 makefile dependency.
2019-11-14 Martin Liska <mliska(a)suse.cz>
* Make-lang.in: Remove wrong dependency
of LTO_DUMP_EXE on LTO_EXE.
From-SVN: r278212
---
gcc/lto/ChangeLog | 5 +++++
gcc/lto/Make-lang.in | 2 +-
2 files changed, 6 insertions(+), 1 deletion(-)
diff --git a/gcc/lto/ChangeLog b/gcc/lto/ChangeLog
index cd035e60b9b..ba3e38aa364 100644
--- a/gcc/lto/ChangeLog
+++ b/gcc/lto/ChangeLog
@@ -1,3 +1,8 @@
+2019-11-14 Martin Liska <mliska(a)suse.cz>
+
+ * Make-lang.in: Remove wrong dependency
+ of LTO_DUMP_EXE on LTO_EXE.
+
2019-11-12 Martin Liska <mliska(a)suse.cz>
* lto-common.c: Do not include params.h.
diff --git a/gcc/lto/Make-lang.in b/gcc/lto/Make-lang.in
index faee8899502..46df75ab59b 100644
--- a/gcc/lto/Make-lang.in
+++ b/gcc/lto/Make-lang.in
@@ -88,7 +88,7 @@ $(LTO_EXE): $(LTO_OBJS) $(BACKEND) $(LIBDEPS)
+$(LLINKER) $(ALL_LINKERFLAGS) $(LDFLAGS) -o $@ \
$(LTO_OBJS) $(BACKEND) $(BACKENDLIBS) $(LIBS)
-$(LTO_DUMP_EXE): $(LTO_EXE) $(LTO_DUMP_OBJS) $(BACKEND) $(LIBDEPS)
+$(LTO_DUMP_EXE): $(LTO_DUMP_OBJS) $(BACKEND) $(LIBDEPS)
+$(LLINKER) $(ALL_LINKERFLAGS) $(LDFLAGS) -o $@ \
$(LTO_DUMP_OBJS) $(BACKEND) $(BACKENDLIBS) $(LIBS)
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-aarch64-spec2k6-Oz - Build # 2 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *binutils* in CI configuration tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-aarch64-spec2k6-Oz
Culprit:
<cut>
commit b4ee29a4450a88a64d99db0e49bac2e8670e086b
Author: GDB Administrator <gdbadmin(a)sourceware.org>
Date: Tue Jun 22 00:00:08 2021 +0000
Automatic date update in version.in
</cut>
Results regressed to (for first_bad == b4ee29a4450a88a64d99db0e49bac2e8670e086b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-b4ee29a4450a88a64d99db0e49bac2e8670e086b/results_id:
1
# 482.sphinx3,[.] OUTLINED_FUNCTION_4 regressed by 150
from (for last_good == 96f842cbdb37bb84fb1bab914304a3eff152ad0d)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Oz artifacts/build-96f842cbdb37bb84fb1bab914304a3eff152ad0d/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/3096
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_64/tcwg_bmk_llvm_apm/bisect-llvm-master-aarch64-spec2k6-Oz/3110
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-binutils-b4ee29a4450a88a64d99db0e49bac2e8670e086b
cd investigate-binutils-b4ee29a4450a88a64d99db0e49bac2e8670e086b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /binutils/ ./ ./bisect/baseline/
cd binutils
# Reproduce first_bad build
git checkout --detach b4ee29a4450a88a64d99db0e49bac2e8670e086b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 96f842cbdb37bb84fb1bab914304a3eff152ad0d
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit b4ee29a4450a88a64d99db0e49bac2e8670e086b
Author: GDB Administrator <gdbadmin(a)sourceware.org>
Date: Tue Jun 22 00:00:08 2021 +0000
Automatic date update in version.in
---
bfd/version.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/bfd/version.h b/bfd/version.h
index 087c9d0e80d..6c42e8315f3 100644
--- a/bfd/version.h
+++ b/bfd/version.h
@@ -16,7 +16,7 @@
In releases, the date is not included in either version strings or
sonames. */
-#define BFD_VERSION_DATE 20210621
+#define BFD_VERSION_DATE 20210622
#define BFD_VERSION @bfd_version@
#define BFD_VERSION_STRING @bfd_version_package@ @bfd_version_string@
#define REPORT_BUGS_TO @report_bugs_to@
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-master-arm-spec2k6-O2_LTO - Build # 13 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *binutils* in CI configuration tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O2_LTO
Culprit:
<cut>
commit 8179e388b60acc6ac35b40cd154f8d56234d1c3b
Author: GDB Administrator <gdbadmin(a)sourceware.org>
Date: Fri Aug 6 00:00:23 2021 +0000
Automatic date update in version.in
</cut>
Results regressed to (for first_bad == 8179e388b60acc6ac35b40cd154f8d56234d1c3b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-8179e388b60acc6ac35b40cd154f8d56234d1c3b/results_id:
1
# 456.hmmer,hmmer_base.default regressed by 103
from (for last_good == c2bc854c8bfa24c51c902563e6b145c297d577c9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O2_LTO_marm artifacts/build-c2bc854c8bfa24c51c902563e6b145c297d577c9/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-O2_LTO/3089
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-O2_LTO/3057
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-binutils-8179e388b60acc6ac35b40cd154f8d56234d1c3b
cd investigate-binutils-8179e388b60acc6ac35b40cd154f8d56234d1c3b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /binutils/ ./ ./bisect/baseline/
cd binutils
# Reproduce first_bad build
git checkout --detach 8179e388b60acc6ac35b40cd154f8d56234d1c3b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c2bc854c8bfa24c51c902563e6b145c297d577c9
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 8179e388b60acc6ac35b40cd154f8d56234d1c3b
Author: GDB Administrator <gdbadmin(a)sourceware.org>
Date: Fri Aug 6 00:00:23 2021 +0000
Automatic date update in version.in
---
bfd/version.h | 2 +-
1 file changed, 1 insertion(+), 1 deletion(-)
diff --git a/bfd/version.h b/bfd/version.h
index 83f1bc16ee7..ecc15ad12a6 100644
--- a/bfd/version.h
+++ b/bfd/version.h
@@ -16,7 +16,7 @@
In releases, the date is not included in either version strings or
sonames. */
-#define BFD_VERSION_DATE 20210805
+#define BFD_VERSION_DATE 20210806
#define BFD_VERSION @bfd_version@
#define BFD_VERSION_STRING @bfd_version_package@ @bfd_version_string@
#define REPORT_BUGS_TO @report_bugs_to@
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3 - Build # 16 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3
Culprit:
<cut>
commit f1ab60e40d16970381a003e145be6d5932823597
Author: Tomasz Kamiński <tomasz.kaminski(a)sonarsource.com>
Date: Thu Jul 29 10:55:24 2021 +0200
Fix FindZ3.cmake to support static libraries and Windows
Use absolute path to link z3 to allow builds both on windows and linux
since the library name is platform dependent for Z3 (libz3 on Windows
and z3 on Linux) and MSVC does not recognized -L and -l options.
Fix CMAKE_CROSSCOMPILING that does not work correctly since it uses
Z3_BUILD_VERSION instead of Z3_BUILD_NUMBER
Fix building with the static version of z3 library (supersedes D80227).
- Build the Z3 version detection code as C++, since the static
library brings in libstdc++ symbols
- Detect threading support and link against threading, in the
(likely) case Z3 was built with threads
Exposed compilation error from building a program that is used to detect
z3 version in the warning message, to simplify troubleshooting.
Reviewed By: JDevlieghere
Differential Revision: https://reviews.llvm.org/D106131
</cut>
Results regressed to (for first_bad == f1ab60e40d16970381a003e145be6d5932823597)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-f1ab60e40d16970381a003e145be6d5932823597/results_id:
1
# 464.h264ref,h264ref_base.default regressed by 106
# 464.h264ref,[.] FastFullPelBlockMotionSearch regressed by 131
from (for last_good == 2df8bf9339e43de63d8d28e07182e1d6d7ffb843)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-2df8bf9339e43de63d8d28e07182e1d6d7ffb843/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3087
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/3058
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-f1ab60e40d16970381a003e145be6d5932823597
cd investigate-llvm-f1ab60e40d16970381a003e145be6d5932823597
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach f1ab60e40d16970381a003e145be6d5932823597
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 2df8bf9339e43de63d8d28e07182e1d6d7ffb843
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit f1ab60e40d16970381a003e145be6d5932823597
Author: Tomasz Kamiński <tomasz.kaminski(a)sonarsource.com>
Date: Thu Jul 29 10:55:24 2021 +0200
Fix FindZ3.cmake to support static libraries and Windows
Use absolute path to link z3 to allow builds both on windows and linux
since the library name is platform dependent for Z3 (libz3 on Windows
and z3 on Linux) and MSVC does not recognized -L and -l options.
Fix CMAKE_CROSSCOMPILING that does not work correctly since it uses
Z3_BUILD_VERSION instead of Z3_BUILD_NUMBER
Fix building with the static version of z3 library (supersedes D80227).
- Build the Z3 version detection code as C++, since the static
library brings in libstdc++ symbols
- Detect threading support and link against threading, in the
(likely) case Z3 was built with threads
Exposed compilation error from building a program that is used to detect
z3 version in the warning message, to simplify troubleshooting.
Reviewed By: JDevlieghere
Differential Revision: https://reviews.llvm.org/D106131
---
llvm/cmake/modules/FindZ3.cmake | 29 ++++++++++++++++++++++-------
1 file changed, 22 insertions(+), 7 deletions(-)
diff --git a/llvm/cmake/modules/FindZ3.cmake b/llvm/cmake/modules/FindZ3.cmake
index 95dd37789a87..118b1eac3b32 100644
--- a/llvm/cmake/modules/FindZ3.cmake
+++ b/llvm/cmake/modules/FindZ3.cmake
@@ -2,8 +2,21 @@ INCLUDE(CheckCXXSourceRuns)
# Function to check Z3's version
function(check_z3_version z3_include z3_lib)
+ # Get lib path
+ set(z3_link_libs "${z3_lib}")
+
+ # Try to find a threading module in case Z3 was built with threading support.
+ # Threads are required elsewhere in LLVM, but not marked as required here because
+ # Z3 could have been compiled without threading support.
+ find_package(Threads)
+ # CMAKE_THREAD_LIBS_INIT may be empty if the thread functions are provided by the
+ # system libraries and no special flags are needed.
+ if(CMAKE_THREAD_LIBS_INIT)
+ list(APPEND z3_link_libs "${CMAKE_THREAD_LIBS_INIT}")
+ endif()
+
# The program that will be executed to print Z3's version.
- file(WRITE ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeTmp/testz3.c
+ file(WRITE ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeTmp/testz3.cpp
"#include <assert.h>
#include <z3.h>
int main() {
@@ -13,16 +26,14 @@ function(check_z3_version z3_include z3_lib)
return 0;
}")
- # Get lib path
- get_filename_component(z3_lib_path ${z3_lib} PATH)
-
try_run(
Z3_RETURNCODE
Z3_COMPILED
${CMAKE_BINARY_DIR}
- ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeTmp/testz3.c
+ ${CMAKE_BINARY_DIR}${CMAKE_FILES_DIRECTORY}/CMakeTmp/testz3.cpp
COMPILE_DEFINITIONS -I"${z3_include}"
- LINK_LIBRARIES -L${z3_lib_path} -lz3
+ LINK_LIBRARIES ${z3_link_libs}
+ COMPILE_OUTPUT_VARIABLE COMPILE_OUTPUT
RUN_OUTPUT_VARIABLE SRC_OUTPUT
)
@@ -30,6 +41,9 @@ function(check_z3_version z3_include z3_lib)
string(REGEX REPLACE "([0-9]*\\.[0-9]*\\.[0-9]*)" "\\1"
z3_version "${SRC_OUTPUT}")
set(Z3_VERSION_STRING ${z3_version} PARENT_SCOPE)
+ else()
+ message(NOTICE "${COMPILE_OUTPUT}")
+ message(WARNING "Failed to compile Z3 program that is used to determine library version.")
endif()
endfunction(check_z3_version)
@@ -86,7 +100,7 @@ if(NOT Z3_VERSION_STRING AND (CMAKE_CROSSCOMPILING AND
file(STRINGS "${Z3_INCLUDE_DIR}/z3_version.h"
z3_version_str REGEX "^#define[\t ]+Z3_BUILD_NUMBER[\t ]+.*")
- string(REGEX REPLACE "^.*Z3_BUILD_VERSION[\t ]+([0-9]).*$" "\\1"
+ string(REGEX REPLACE "^.*Z3_BUILD_NUMBER[\t ]+([0-9]).*$" "\\1"
Z3_BUILD "${z3_version_str}")
set(Z3_VERSION_STRING ${Z3_MAJOR}.${Z3_MINOR}.${Z3_BUILD})
@@ -98,6 +112,7 @@ if(NOT Z3_VERSION_STRING)
# conservative and force the found version to 0.0.0 to make version
# checks always fail.
set(Z3_VERSION_STRING "0.0.0")
+ message(WARNING "Failed to determine Z3 library version, defaulting to 0.0.0.")
endif()
# handle the QUIETLY and REQUIRED arguments and set Z3_FOUND to TRUE if
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/llvm-master-arm-spec2k6-Os_LTO - Build # 3 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_apm/llvm-master-arm-spec2k6-Os_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_apm/llvm-master-arm-spec2k6-Os_LTO
Culprit:
<cut>
commit 0276db14167b9348904322084e7fc1a04cc72452
Author: Jose M Monsalve Diaz <jmonsalvediaz(a)anl.gov>
Date: Tue Jul 27 17:20:47 2021 -0400
[OpenMP] Creating the `omp_target_num_teams` and `omp_target_thread_limit` attributes to outlined functions
The device runtime contains several calls to __kmpc_get_hardware_num_threads_in_block
and __kmpc_get_hardware_num_blocks. If the thread_limit and the num_teams are constant,
these calls can be folded to the constant value.
In commit D106033 we have the optimization phase. This commit adds the attributes to
the outlined function for the grid size. the two attributes are `omp_target_num_teams` and
`omp_target_thread_limit`. These values are added as long as they are constant.
Two functions are created `getNumThreadsExprForTargetDirective` and
`getNumTeamsExprForTargetDirective`. The original functions `emitNumTeamsForTargetDirective`
and `emitNumThreadsForTargetDirective` identify the expresion and emit the code.
However, for the Device version of the outlined function, we cannot emit anything.
Therefore, this is a first attempt to separate emision of code from deduction of the
values.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D106298
</cut>
Results regressed to (for first_bad == 0276db14167b9348904322084e7fc1a04cc72452)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os_LTO_mthumb artifacts/build-0276db14167b9348904322084e7fc1a04cc72452/results_id:
1
# 456.hmmer,hmmer_base.default regressed by 102
from (for last_good == c49df15c278857adecd12db6bb1cdc96885f7079)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -Os_LTO_mthumb artifacts/build-c49df15c278857adecd12db6bb1cdc96885f7079/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of last_good: apm_32/tcwg_bmk_llvm_apm/bisect-llvm-master-arm-spec2k6-Os_LTO/3026
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Results ID of first_bad: apm_32/tcwg_bmk_llvm_apm/bisect-llvm-master-arm-spec2k6-Os_LTO/3024
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-0276db14167b9348904322084e7fc1a04cc72452
cd investigate-llvm-0276db14167b9348904322084e7fc1a04cc72452
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 0276db14167b9348904322084e7fc1a04cc72452
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c49df15c278857adecd12db6bb1cdc96885f7079
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_apm-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 0276db14167b9348904322084e7fc1a04cc72452
Author: Jose M Monsalve Diaz <jmonsalvediaz(a)anl.gov>
Date: Tue Jul 27 17:20:47 2021 -0400
[OpenMP] Creating the `omp_target_num_teams` and `omp_target_thread_limit` attributes to outlined functions
The device runtime contains several calls to __kmpc_get_hardware_num_threads_in_block
and __kmpc_get_hardware_num_blocks. If the thread_limit and the num_teams are constant,
these calls can be folded to the constant value.
In commit D106033 we have the optimization phase. This commit adds the attributes to
the outlined function for the grid size. the two attributes are `omp_target_num_teams` and
`omp_target_thread_limit`. These values are added as long as they are constant.
Two functions are created `getNumThreadsExprForTargetDirective` and
`getNumTeamsExprForTargetDirective`. The original functions `emitNumTeamsForTargetDirective`
and `emitNumThreadsForTargetDirective` identify the expresion and emit the code.
However, for the Device version of the outlined function, we cannot emit anything.
Therefore, this is a first attempt to separate emision of code from deduction of the
values.
Reviewed By: jdoerfert
Differential Revision: https://reviews.llvm.org/D106298
---
clang/lib/CodeGen/CGOpenMPRuntime.cpp | 252 +++++++--
clang/lib/CodeGen/CGOpenMPRuntime.h | 29 ++
.../declare_target_codegen_globalization.cpp | 12 +-
clang/test/OpenMP/nvptx_lambda_capturing.cpp | 24 +-
.../OpenMP/nvptx_multi_target_parallel_codegen.cpp | 54 +-
clang/test/OpenMP/nvptx_target_codegen.cpp | 96 ++--
.../test/OpenMP/nvptx_target_parallel_codegen.cpp | 24 +-
.../nvptx_target_parallel_num_threads_codegen.cpp | 24 +-
...arget_teams_distribute_parallel_for_codegen.cpp | 152 +++---
..._teams_distribute_parallel_for_simd_codegen.cpp | 78 +--
clang/test/OpenMP/target_map_codegen_03.cpp | 73 ++-
.../target_num_teams_num_threads_attributes.cpp | 175 +++++++
clang/test/OpenMP/target_parallel_codegen.cpp | 512 +++++++++---------
.../test/OpenMP/target_parallel_debug_codegen.cpp | 6 +-
clang/test/OpenMP/target_parallel_for_codegen.cpp | 576 ++++++++++-----------
.../OpenMP/target_parallel_for_debug_codegen.cpp | 6 +-
.../OpenMP/target_parallel_for_simd_codegen.cpp | 560 ++++++++++----------
clang/test/OpenMP/target_parallel_if_codegen.cpp | 481 +++++++++--------
.../OpenMP/target_parallel_num_threads_codegen.cpp | 305 ++++++-----
.../target_teams_distribute_simd_codegen.cpp | 560 ++++++++++----------
...rget_teams_distribute_simd_collapse_codegen.cpp | 408 +++++++--------
...teams_distribute_simd_dist_schedule_codegen.cpp | 168 +++---
..._teams_distribute_simd_firstprivate_codegen.cpp | 316 +++++------
...t_teams_distribute_simd_lastprivate_codegen.cpp | 496 +++++++++---------
...arget_teams_distribute_simd_private_codegen.cpp | 316 +++++------
...get_teams_distribute_simd_reduction_codegen.cpp | 284 +++++-----
.../test/OpenMP/target_teams_num_teams_codegen.cpp | 80 +--
.../OpenMP/target_teams_thread_limit_codegen.cpp | 112 ++--
clang/test/OpenMP/teams_codegen.cpp | 16 +-
29 files changed, 3279 insertions(+), 2916 deletions(-)
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.cpp b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
index e7aa84ef3d90..c09797e91b99 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.cpp
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.cpp
@@ -6551,6 +6551,20 @@ void CGOpenMPRuntime::emitTargetOutlinedFunctionHelper(
OffloadEntriesInfoManager.registerTargetRegionEntryInfo(
DeviceID, FileID, ParentName, Line, OutlinedFn, OutlinedFnID,
OffloadEntriesInfoManagerTy::OMPTargetRegionEntryTargetRegion);
+
+ // Add NumTeams and ThreadLimit attributes to the outlined GPU function
+ int32_t DefaultValTeams = -1;
+ getNumTeamsExprForTargetDirective(CGF, D, DefaultValTeams);
+ if (DefaultValTeams > 0) {
+ OutlinedFn->addFnAttr("omp_target_num_teams",
+ std::to_string(DefaultValTeams));
+ }
+ int32_t DefaultValThreads = -1;
+ getNumThreadsExprForTargetDirective(CGF, D, DefaultValThreads);
+ if (DefaultValThreads > 0) {
+ OutlinedFn->addFnAttr("omp_target_thread_limit",
+ std::to_string(DefaultValThreads));
+ }
}
/// Checks if the expression is constant or does not have non-trivial function
@@ -6605,24 +6619,13 @@ const Stmt *CGOpenMPRuntime::getSingleCompoundChild(ASTContext &Ctx,
return Child;
}
-/// Emit the number of teams for a target directive. Inspect the num_teams
-/// clause associated with a teams construct combined or closely nested
-/// with the target directive.
-///
-/// Emit a team of size one for directives such as 'target parallel' that
-/// have no associated teams construct.
-///
-/// Otherwise, return nullptr.
-static llvm::Value *
-emitNumTeamsForTargetDirective(CodeGenFunction &CGF,
- const OMPExecutableDirective &D) {
- assert(!CGF.getLangOpts().OpenMPIsDevice &&
- "Clauses associated with the teams directive expected to be emitted "
- "only for the host!");
+const Expr *CGOpenMPRuntime::getNumTeamsExprForTargetDirective(
+ CodeGenFunction &CGF, const OMPExecutableDirective &D,
+ int32_t &DefaultVal) {
+
OpenMPDirectiveKind DirectiveKind = D.getDirectiveKind();
assert(isOpenMPTargetExecutionDirective(DirectiveKind) &&
"Expected target-based executable directive.");
- CGBuilderTy &Bld = CGF.Builder;
switch (DirectiveKind) {
case OMPD_target: {
const auto *CS = D.getInnermostCapturedStmt();
@@ -6634,23 +6637,27 @@ emitNumTeamsForTargetDirective(CodeGenFunction &CGF,
dyn_cast_or_null<OMPExecutableDirective>(ChildStmt)) {
if (isOpenMPTeamsDirective(NestedDir->getDirectiveKind())) {
if (NestedDir->hasClausesOfKind<OMPNumTeamsClause>()) {
- CGOpenMPInnerExprInfo CGInfo(CGF, *CS);
- CodeGenFunction::CGCapturedStmtRAII CapInfoRAII(CGF, &CGInfo);
const Expr *NumTeams =
NestedDir->getSingleClause<OMPNumTeamsClause>()->getNumTeams();
- llvm::Value *NumTeamsVal =
- CGF.EmitScalarExpr(NumTeams,
- /*IgnoreResultAssign*/ true);
- return Bld.CreateIntCast(NumTeamsVal, CGF.Int32Ty,
- /*isSigned=*/true);
+ if (NumTeams->isIntegerConstantExpr(CGF.getContext()))
+ if (auto Constant =
+ NumTeams->getIntegerConstantExpr(CGF.getContext()))
+ DefaultVal = Constant->getExtValue();
+ return NumTeams;
}
- return Bld.getInt32(0);
+ DefaultVal = 0;
+ return nullptr;
}
if (isOpenMPParallelDirective(NestedDir->getDirectiveKind()) ||
- isOpenMPSimdDirective(NestedDir->getDirectiveKind()))
- return Bld.getInt32(1);
- return Bld.getInt32(0);
+ isOpenMPSimdDirective(NestedDir->getDirectiveKind())) {
+ DefaultVal = 1;
+ return nullptr;
+ }
+ DefaultVal = 1;
+ return nullptr;
}
+ // A value of -1 is used to check if we need to emit no teams region
+ DefaultVal = -1;
return nullptr;
}
case OMPD_target_teams:
@@ -6659,22 +6666,22 @@ emitNumTeamsForTargetDirective(CodeGenFunction &CGF,
case OMPD_target_teams_distribute_parallel_for:
case OMPD_target_teams_distribute_parallel_for_simd: {
if (D.hasClausesOfKind<OMPNumTeamsClause>()) {
- CodeGenFunction::RunCleanupsScope NumTeamsScope(CGF);
const Expr *NumTeams =
D.getSingleClause<OMPNumTeamsClause>()->getNumTeams();
- llvm::Value *NumTeamsVal =
- CGF.EmitScalarExpr(NumTeams,
- /*IgnoreResultAssign*/ true);
- return Bld.CreateIntCast(NumTeamsVal, CGF.Int32Ty,
- /*isSigned=*/true);
+ if (NumTeams->isIntegerConstantExpr(CGF.getContext()))
+ if (auto Constant = NumTeams->getIntegerConstantExpr(CGF.getContext()))
+ DefaultVal = Constant->getExtValue();
+ return NumTeams;
}
- return Bld.getInt32(0);
+ DefaultVal = 0;
+ return nullptr;
}
case OMPD_target_parallel:
case OMPD_target_parallel_for:
case OMPD_target_parallel_for_simd:
case OMPD_target_simd:
- return Bld.getInt32(1);
+ DefaultVal = 1;
+ return nullptr;
case OMPD_parallel:
case OMPD_for:
case OMPD_parallel_for:
@@ -6740,6 +6747,48 @@ emitNumTeamsForTargetDirective(CodeGenFunction &CGF,
llvm_unreachable("Unexpected directive kind.");
}
+llvm::Value *CGOpenMPRuntime::emitNumTeamsForTargetDirective(
+ CodeGenFunction &CGF, const OMPExecutableDirective &D) {
+ assert(!CGF.getLangOpts().OpenMPIsDevice &&
+ "Clauses associated with the teams directive expected to be emitted "
+ "only for the host!");
+ CGBuilderTy &Bld = CGF.Builder;
+ int32_t DefaultNT = -1;
+ const Expr *NumTeams = getNumTeamsExprForTargetDirective(CGF, D, DefaultNT);
+ if (NumTeams != nullptr) {
+ OpenMPDirectiveKind DirectiveKind = D.getDirectiveKind();
+
+ switch (DirectiveKind) {
+ case OMPD_target: {
+ const auto *CS = D.getInnermostCapturedStmt();
+ CGOpenMPInnerExprInfo CGInfo(CGF, *CS);
+ CodeGenFunction::CGCapturedStmtRAII CapInfoRAII(CGF, &CGInfo);
+ llvm::Value *NumTeamsVal = CGF.EmitScalarExpr(NumTeams,
+ /*IgnoreResultAssign*/ true);
+ return Bld.CreateIntCast(NumTeamsVal, CGF.Int32Ty,
+ /*isSigned=*/true);
+ }
+ case OMPD_target_teams:
+ case OMPD_target_teams_distribute:
+ case OMPD_target_teams_distribute_simd:
+ case OMPD_target_teams_distribute_parallel_for:
+ case OMPD_target_teams_distribute_parallel_for_simd: {
+ CodeGenFunction::RunCleanupsScope NumTeamsScope(CGF);
+ llvm::Value *NumTeamsVal = CGF.EmitScalarExpr(NumTeams,
+ /*IgnoreResultAssign*/ true);
+ return Bld.CreateIntCast(NumTeamsVal, CGF.Int32Ty,
+ /*isSigned=*/true);
+ }
+ default:
+ break;
+ }
+ } else if (DefaultNT == -1) {
+ return nullptr;
+ }
+
+ return Bld.getInt32(DefaultNT);
+}
+
static llvm::Value *getNumThreads(CodeGenFunction &CGF, const CapturedStmt *CS,
llvm::Value *DefaultThreadLimitVal) {
const Stmt *Child = CGOpenMPRuntime::getSingleCompoundChild(
@@ -6832,17 +6881,130 @@ static llvm::Value *getNumThreads(CodeGenFunction &CGF, const CapturedStmt *CS,
: CGF.Builder.getInt32(0);
}
-/// Emit the number of threads for a target directive. Inspect the
-/// thread_limit clause associated with a teams construct combined or closely
-/// nested with the target directive.
-///
-/// Emit the num_threads clause for directives such as 'target parallel' that
-/// have no associated teams construct.
-///
-/// Otherwise, return nullptr.
-static llvm::Value *
-emitNumThreadsForTargetDirective(CodeGenFunction &CGF,
- const OMPExecutableDirective &D) {
+const Expr *CGOpenMPRuntime::getNumThreadsExprForTargetDirective(
+ CodeGenFunction &CGF, const OMPExecutableDirective &D,
+ int32_t &DefaultVal) {
+ OpenMPDirectiveKind DirectiveKind = D.getDirectiveKind();
+ assert(isOpenMPTargetExecutionDirective(DirectiveKind) &&
+ "Expected target-based executable directive.");
+
+ switch (DirectiveKind) {
+ case OMPD_target:
+ // Teams have no clause thread_limit
+ return nullptr;
+ case OMPD_target_teams:
+ case OMPD_target_teams_distribute:
+ if (D.hasClausesOfKind<OMPThreadLimitClause>()) {
+ const auto *ThreadLimitClause = D.getSingleClause<OMPThreadLimitClause>();
+ const Expr *ThreadLimit = ThreadLimitClause->getThreadLimit();
+ if (ThreadLimit->isIntegerConstantExpr(CGF.getContext()))
+ if (auto Constant =
+ ThreadLimit->getIntegerConstantExpr(CGF.getContext()))
+ DefaultVal = Constant->getExtValue();
+ return ThreadLimit;
+ }
+ return nullptr;
+ case OMPD_target_parallel:
+ case OMPD_target_parallel_for:
+ case OMPD_target_parallel_for_simd:
+ case OMPD_target_teams_distribute_parallel_for:
+ case OMPD_target_teams_distribute_parallel_for_simd: {
+ Expr *ThreadLimit = nullptr;
+ Expr *NumThreads = nullptr;
+ if (D.hasClausesOfKind<OMPThreadLimitClause>()) {
+ const auto *ThreadLimitClause = D.getSingleClause<OMPThreadLimitClause>();
+ ThreadLimit = ThreadLimitClause->getThreadLimit();
+ if (ThreadLimit->isIntegerConstantExpr(CGF.getContext()))
+ if (auto Constant =
+ ThreadLimit->getIntegerConstantExpr(CGF.getContext()))
+ DefaultVal = Constant->getExtValue();
+ }
+ if (D.hasClausesOfKind<OMPNumThreadsClause>()) {
+ const auto *NumThreadsClause = D.getSingleClause<OMPNumThreadsClause>();
+ NumThreads = NumThreadsClause->getNumThreads();
+ if (NumThreads->isIntegerConstantExpr(CGF.getContext())) {
+ if (auto Constant =
+ NumThreads->getIntegerConstantExpr(CGF.getContext())) {
+ if (Constant->getExtValue() < DefaultVal) {
+ DefaultVal = Constant->getExtValue();
+ ThreadLimit = NumThreads;
+ }
+ }
+ }
+ }
+ return ThreadLimit;
+ }
+ case OMPD_target_teams_distribute_simd:
+ case OMPD_target_simd:
+ DefaultVal = 1;
+ return nullptr;
+ case OMPD_parallel:
+ case OMPD_for:
+ case OMPD_parallel_for:
+ case OMPD_parallel_master:
+ case OMPD_parallel_sections:
+ case OMPD_for_simd:
+ case OMPD_parallel_for_simd:
+ case OMPD_cancel:
+ case OMPD_cancellation_point:
+ case OMPD_ordered:
+ case OMPD_threadprivate:
+ case OMPD_allocate:
+ case OMPD_task:
+ case OMPD_simd:
+ case OMPD_tile:
+ case OMPD_unroll:
+ case OMPD_sections:
+ case OMPD_section:
+ case OMPD_single:
+ case OMPD_master:
+ case OMPD_critical:
+ case OMPD_taskyield:
+ case OMPD_barrier:
+ case OMPD_taskwait:
+ case OMPD_taskgroup:
+ case OMPD_atomic:
+ case OMPD_flush:
+ case OMPD_depobj:
+ case OMPD_scan:
+ case OMPD_teams:
+ case OMPD_target_data:
+ case OMPD_target_exit_data:
+ case OMPD_target_enter_data:
+ case OMPD_distribute:
+ case OMPD_distribute_simd:
+ case OMPD_distribute_parallel_for:
+ case OMPD_distribute_parallel_for_simd:
+ case OMPD_teams_distribute:
+ case OMPD_teams_distribute_simd:
+ case OMPD_teams_distribute_parallel_for:
+ case OMPD_teams_distribute_parallel_for_simd:
+ case OMPD_target_update:
+ case OMPD_declare_simd:
+ case OMPD_declare_variant:
+ case OMPD_begin_declare_variant:
+ case OMPD_end_declare_variant:
+ case OMPD_declare_target:
+ case OMPD_end_declare_target:
+ case OMPD_declare_reduction:
+ case OMPD_declare_mapper:
+ case OMPD_taskloop:
+ case OMPD_taskloop_simd:
+ case OMPD_master_taskloop:
+ case OMPD_master_taskloop_simd:
+ case OMPD_parallel_master_taskloop:
+ case OMPD_parallel_master_taskloop_simd:
+ case OMPD_requires:
+ case OMPD_unknown:
+ break;
+ default:
+ break;
+ }
+ llvm_unreachable("Unsupported directive kind.");
+}
+
+llvm::Value *CGOpenMPRuntime::emitNumThreadsForTargetDirective(
+ CodeGenFunction &CGF, const OMPExecutableDirective &D) {
assert(!CGF.getLangOpts().OpenMPIsDevice &&
"Clauses associated with the teams directive expected to be emitted "
"only for the host!");
diff --git a/clang/lib/CodeGen/CGOpenMPRuntime.h b/clang/lib/CodeGen/CGOpenMPRuntime.h
index 491ef9b7aaf3..c24648aae7e1 100644
--- a/clang/lib/CodeGen/CGOpenMPRuntime.h
+++ b/clang/lib/CodeGen/CGOpenMPRuntime.h
@@ -340,6 +340,35 @@ protected:
llvm::Value *emitUpdateLocation(CodeGenFunction &CGF, SourceLocation Loc,
unsigned Flags = 0);
+ /// Emit the number of teams for a target directive. Inspect the num_teams
+ /// clause associated with a teams construct combined or closely nested
+ /// with the target directive.
+ ///
+ /// Emit a team of size one for directives such as 'target parallel' that
+ /// have no associated teams construct.
+ ///
+ /// Otherwise, return nullptr.
+ const Expr *getNumTeamsExprForTargetDirective(CodeGenFunction &CGF,
+ const OMPExecutableDirective &D,
+ int32_t &DefaultVal);
+ llvm::Value *emitNumTeamsForTargetDirective(CodeGenFunction &CGF,
+ const OMPExecutableDirective &D);
+ /// Emit the number of threads for a target directive. Inspect the
+ /// thread_limit clause associated with a teams construct combined or closely
+ /// nested with the target directive.
+ ///
+ /// Emit the num_threads clause for directives such as 'target parallel' that
+ /// have no associated teams construct.
+ ///
+ /// Otherwise, return nullptr.
+ const Expr *
+ getNumThreadsExprForTargetDirective(CodeGenFunction &CGF,
+ const OMPExecutableDirective &D,
+ int32_t &DefaultVal);
+ llvm::Value *
+ emitNumThreadsForTargetDirective(CodeGenFunction &CGF,
+ const OMPExecutableDirective &D);
+
/// Returns pointer to ident_t type.
llvm::Type *getIdentTyPointerTy();
diff --git a/clang/test/OpenMP/declare_target_codegen_globalization.cpp b/clang/test/OpenMP/declare_target_codegen_globalization.cpp
index f8e2a33ca959..47610f7b84a8 100644
--- a/clang/test/OpenMP/declare_target_codegen_globalization.cpp
+++ b/clang/test/OpenMP/declare_target_codegen_globalization.cpp
@@ -48,7 +48,7 @@ int maini1() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__
-// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
@@ -58,15 +58,15 @@ int maini1() {
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = load i32*, i32** [[A_ADDR]], align 8
-// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_Z3fooRi(i32* nonnull align 4 dereferenceable(4) [[B]]) #[[ATTR3:[0-9]+]]
-// CHECK1-NEXT: [[CALL1:%.*]] = call i32 @_Z3barv() #[[ATTR3]]
+// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_Z3fooRi(i32* nonnull align 4 dereferenceable(4) [[B]]) #[[ATTR4:[0-9]+]]
+// CHECK1-NEXT: [[CALL1:%.*]] = call i32 @_Z3barv() #[[ATTR4]]
// CHECK1-NEXT: [[ADD:%.*]] = add nsw i32 [[CALL]], [[CALL1]]
// CHECK1-NEXT: store i32 [[ADD]], i32* [[TMP0]], align 4
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3fooRi
-// CHECK1-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR1:[0-9]+]] {
+// CHECK1-SAME: (i32* nonnull align 4 dereferenceable(4) [[A:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: store i32* [[A]], i32** [[A_ADDR]], align 8
@@ -76,11 +76,11 @@ int maini1() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3barv
-// CHECK1-SAME: () #[[ATTR1]] {
+// CHECK1-SAME: () #[[ATTR2]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A:%.*]] = call i8* @__kmpc_alloc_shared(i64 4)
// CHECK1-NEXT: [[A_ON_STACK:%.*]] = bitcast i8* [[A]] to i32*
-// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_Z3fooRi(i32* nonnull align 4 dereferenceable(4) [[A_ON_STACK]]) #[[ATTR3]]
+// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_Z3fooRi(i32* nonnull align 4 dereferenceable(4) [[A_ON_STACK]]) #[[ATTR4]]
// CHECK1-NEXT: call void @__kmpc_free_shared(i8* [[A]], i64 4)
// CHECK1-NEXT: ret i32 [[CALL]]
//
diff --git a/clang/test/OpenMP/nvptx_lambda_capturing.cpp b/clang/test/OpenMP/nvptx_lambda_capturing.cpp
index 6fe58725a623..b19806df1aee 100644
--- a/clang/test/OpenMP/nvptx_lambda_capturing.cpp
+++ b/clang/test/OpenMP/nvptx_lambda_capturing.cpp
@@ -397,7 +397,7 @@ int main(int argc, char **argv) {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l43
-// CHECK1-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR1]] {
+// CHECK1-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR2:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca i32*, align 8
@@ -630,7 +630,7 @@ int main(int argc, char **argv) {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN1S3fooEv_l29
-// CHECK1-SAME: (%struct.S* [[THIS:%.*]], %class.anon.0* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR1]] {
+// CHECK1-SAME: (%struct.S* [[THIS:%.*]], %class.anon.0* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK1-NEXT: [[L_ADDR:%.*]] = alloca %class.anon.0*, align 8
@@ -715,7 +715,7 @@ int main(int argc, char **argv) {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooIZN1S3fooEvEUlvE_EiRKT__l18
-// CHECK1-SAME: (%class.anon.0* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR1]] {
+// CHECK1-SAME: (%class.anon.0* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR2]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[T_ADDR:%.*]] = alloca %class.anon.0*, align 8
// CHECK1-NEXT: [[TMP:%.*]] = alloca %class.anon.0*, align 8
@@ -805,7 +805,7 @@ int main(int argc, char **argv) {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN1S3fooEv_l29
-// CHECK2-SAME: (%struct.S* [[THIS:%.*]], %class.anon* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (%struct.S* [[THIS:%.*]], %class.anon* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK2-NEXT: [[L_ADDR:%.*]] = alloca %class.anon*, align 8
@@ -937,7 +937,7 @@ int main(int argc, char **argv) {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l43
-// CHECK2-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon.0* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon.0* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK2-NEXT: [[B_ADDR:%.*]] = alloca i32*, align 8
@@ -1072,7 +1072,7 @@ int main(int argc, char **argv) {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooIZN1S3fooEvEUlvE_EiRKT__l18
-// CHECK2-SAME: (%class.anon* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (%class.anon* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[T_ADDR:%.*]] = alloca %class.anon*, align 8
// CHECK2-NEXT: [[TMP:%.*]] = alloca %class.anon*, align 8
@@ -1193,7 +1193,7 @@ int main(int argc, char **argv) {
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l43
-// CHECK3-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR0]] {
+// CHECK3-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK3-NEXT: [[B_ADDR:%.*]] = alloca i32*, align 8
@@ -1374,7 +1374,7 @@ int main(int argc, char **argv) {
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN1S3fooEv_l29
-// CHECK3-SAME: (%struct.S* [[THIS:%.*]], %class.anon.0* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR0]] {
+// CHECK3-SAME: (%struct.S* [[THIS:%.*]], %class.anon.0* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR1]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK3-NEXT: [[L_ADDR:%.*]] = alloca %class.anon.0*, align 8
@@ -1436,7 +1436,7 @@ int main(int argc, char **argv) {
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooIZN1S3fooEvEUlvE_EiRKT__l18
-// CHECK3-SAME: (%class.anon.0* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR0]] {
+// CHECK3-SAME: (%class.anon.0* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR1]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[T_ADDR:%.*]] = alloca %class.anon.0*, align 8
// CHECK3-NEXT: [[TMP:%.*]] = alloca %class.anon.0*, align 8
@@ -1557,7 +1557,7 @@ int main(int argc, char **argv) {
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l43
-// CHECK4-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR0]] {
+// CHECK4-SAME: (i32* nonnull align 4 dereferenceable(4) [[ARGC:%.*]], i32* nonnull align 4 dereferenceable(4) [[B:%.*]], i32* nonnull align 4 dereferenceable(4) [[C:%.*]], i32* [[D:%.*]], i32* nonnull align 4 dereferenceable(4) [[A:%.*]], %class.anon* nonnull align 8 dereferenceable(40) [[L:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[ARGC_ADDR:%.*]] = alloca i32*, align 8
// CHECK4-NEXT: [[B_ADDR:%.*]] = alloca i32*, align 8
@@ -1738,7 +1738,7 @@ int main(int argc, char **argv) {
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN1S3fooEv_l29
-// CHECK4-SAME: (%struct.S* [[THIS:%.*]], %class.anon.0* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR0]] {
+// CHECK4-SAME: (%struct.S* [[THIS:%.*]], %class.anon.0* nonnull align 8 dereferenceable(8) [[L:%.*]]) #[[ATTR1]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S*, align 8
// CHECK4-NEXT: [[L_ADDR:%.*]] = alloca %class.anon.0*, align 8
@@ -1800,7 +1800,7 @@ int main(int argc, char **argv) {
//
//
// CHECK4-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooIZN1S3fooEvEUlvE_EiRKT__l18
-// CHECK4-SAME: (%class.anon.0* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR0]] {
+// CHECK4-SAME: (%class.anon.0* nonnull align 8 dereferenceable(8) [[T:%.*]]) #[[ATTR1]] {
// CHECK4-NEXT: entry:
// CHECK4-NEXT: [[T_ADDR:%.*]] = alloca %class.anon.0*, align 8
// CHECK4-NEXT: [[TMP:%.*]] = alloca %class.anon.0*, align 8
diff --git a/clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp b/clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
index e04e83527afc..232a2a33e903 100644
--- a/clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_multi_target_parallel_codegen.cpp
@@ -43,18 +43,18 @@ int main() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__
-// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
-// CHECK1-NEXT: call void @_Z3usev() #[[ATTR5:[0-9]+]]
+// CHECK1-NEXT: call void @_Z3usev() #[[ATTR6:[0-9]+]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3usev
-// CHECK1-SAME: () #[[ATTR1:[0-9]+]] {
+// CHECK1-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 8
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
@@ -64,13 +64,13 @@ int main() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l23
-// CHECK1-SAME: () #[[ATTR0]] {
+// CHECK1-SAME: () #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 true, i1 true)
// CHECK1-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK1-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK1: user_code.entry:
-// CHECK1-NEXT: call void @_Z3usev() #[[ATTR5]]
+// CHECK1-NEXT: call void @_Z3usev() #[[ATTR6]]
// CHECK1-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 false, i1 true)
// CHECK1-NEXT: ret void
// CHECK1: worker.exit:
@@ -78,18 +78,18 @@ int main() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1
-// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 8
// CHECK1-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 8
-// CHECK1-NEXT: call void @_Z4workv() #[[ATTR5]]
+// CHECK1-NEXT: call void @_Z4workv() #[[ATTR6]]
// CHECK1-NEXT: ret void
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
-// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
+// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
@@ -99,7 +99,7 @@ int main() {
// CHECK1-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK1-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK1-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
-// CHECK1-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR2:[0-9]+]]
+// CHECK1-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3:[0-9]+]]
// CHECK1-NEXT: ret void
//
//
@@ -121,18 +121,18 @@ int main() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__
-// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
-// CHECK2-NEXT: call void @_Z3usev() #[[ATTR5:[0-9]+]]
+// CHECK2-NEXT: call void @_Z3usev() #[[ATTR6:[0-9]+]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@_Z3usev
-// CHECK2-SAME: () #[[ATTR1:[0-9]+]] {
+// CHECK2-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 4
// CHECK2-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
@@ -142,13 +142,13 @@ int main() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l23
-// CHECK2-SAME: () #[[ATTR0]] {
+// CHECK2-SAME: () #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 true, i1 true)
// CHECK2-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK2-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK2: user_code.entry:
-// CHECK2-NEXT: call void @_Z3usev() #[[ATTR5]]
+// CHECK2-NEXT: call void @_Z3usev() #[[ATTR6]]
// CHECK2-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 false, i1 true)
// CHECK2-NEXT: ret void
// CHECK2: worker.exit:
@@ -156,18 +156,18 @@ int main() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__1
-// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK2-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
-// CHECK2-NEXT: call void @_Z4workv() #[[ATTR5]]
+// CHECK2-NEXT: call void @_Z4workv() #[[ATTR6]]
// CHECK2-NEXT: ret void
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
-// CHECK2-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
+// CHECK2-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK2-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
@@ -177,7 +177,7 @@ int main() {
// CHECK2-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK2-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK2-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
-// CHECK2-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR2:[0-9]+]]
+// CHECK2-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3:[0-9]+]]
// CHECK2-NEXT: ret void
//
//
@@ -199,18 +199,18 @@ int main() {
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__
-// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
+// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
-// CHECK3-NEXT: call void @_Z3usev() #[[ATTR5:[0-9]+]]
+// CHECK3-NEXT: call void @_Z3usev() #[[ATTR6:[0-9]+]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@_Z3usev
-// CHECK3-SAME: () #[[ATTR1:[0-9]+]] {
+// CHECK3-SAME: () #[[ATTR2:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [0 x i8*], align 4
// CHECK3-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_global_thread_num(%struct.ident_t* @[[GLOB3:[0-9]+]])
@@ -220,13 +220,13 @@ int main() {
//
//
// CHECK3-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}_main_l23
-// CHECK3-SAME: () #[[ATTR0]] {
+// CHECK3-SAME: () #[[ATTR1]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 true, i1 true)
// CHECK3-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK3-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK3: user_code.entry:
-// CHECK3-NEXT: call void @_Z3usev() #[[ATTR5]]
+// CHECK3-NEXT: call void @_Z3usev() #[[ATTR6]]
// CHECK3-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 false, i1 true)
// CHECK3-NEXT: ret void
// CHECK3: worker.exit:
@@ -234,18 +234,18 @@ int main() {
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__1
-// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR0]] {
+// CHECK3-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]]) #[[ATTR1]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK3-NEXT: store i32* [[DOTGLOBAL_TID_]], i32** [[DOTGLOBAL_TID__ADDR]], align 4
// CHECK3-NEXT: store i32* [[DOTBOUND_TID_]], i32** [[DOTBOUND_TID__ADDR]], align 4
-// CHECK3-NEXT: call void @_Z4workv() #[[ATTR5]]
+// CHECK3-NEXT: call void @_Z4workv() #[[ATTR6]]
// CHECK3-NEXT: ret void
//
//
// CHECK3-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
-// CHECK3-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
+// CHECK3-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK3-NEXT: entry:
// CHECK3-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK3-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
@@ -255,6 +255,6 @@ int main() {
// CHECK3-NEXT: store i16 [[TMP0]], i16* [[DOTADDR]], align 2
// CHECK3-NEXT: store i32 [[TMP1]], i32* [[DOTADDR1]], align 4
// CHECK3-NEXT: call void @__kmpc_get_shared_variables(i8*** [[GLOBAL_ARGS]])
-// CHECK3-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR2:[0-9]+]]
+// CHECK3-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]]) #[[ATTR3:[0-9]+]]
// CHECK3-NEXT: ret void
//
diff --git a/clang/test/OpenMP/nvptx_target_codegen.cpp b/clang/test/OpenMP/nvptx_target_codegen.cpp
index c1a3b5b699e0..5bf54060b85a 100644
--- a/clang/test/OpenMP/nvptx_target_codegen.cpp
+++ b/clang/test/OpenMP/nvptx_target_codegen.cpp
@@ -173,7 +173,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__
-// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR1:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR2:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR1:%.*]], i32** nonnull align 8 dereferenceable(8) [[PTR2:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
@@ -193,7 +193,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39
-// CHECK1-SAME: () #[[ATTR0]] {
+// CHECK1-SAME: () #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 true, i1 true)
// CHECK1-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
@@ -206,7 +206,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47
-// CHECK1-SAME: (i64 [[AA:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i64 [[AA:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: store i64 [[AA]], i64* [[AA_ADDR]], align 8
@@ -232,7 +232,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53
-// CHECK1-SAME: (i64 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i64 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i64 [[VLA1:%.*]], i64 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i64 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i64 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i64 [[VLA1:%.*]], i64 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca [10 x float]*, align 8
@@ -301,7 +301,7 @@ void unreachable_call() {
// CHECK1-NEXT: [[ADD20:%.*]] = add nsw i32 [[CONV19]], 1
// CHECK1-NEXT: [[CONV21:%.*]] = trunc i32 [[ADD20]] to i8
// CHECK1-NEXT: store i8 [[CONV21]], i8* [[Y]], align 8
-// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull align 8 dereferenceable(16) [[TMP7]], i32 0) #[[ATTR5:[0-9]+]]
+// CHECK1-NEXT: [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull align 8 dereferenceable(16) [[TMP7]], i32 0) #[[ATTR6:[0-9]+]]
// CHECK1-NEXT: [[TMP17:%.*]] = load i64, i64* [[CALL]], align 8
// CHECK1-NEXT: [[ADD22:%.*]] = add nsw i64 [[TMP17]], 1
// CHECK1-NEXT: store i64 [[ADD22]], i64* [[CALL]], align 8
@@ -312,7 +312,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@_ZN2TTIxcEixEi
-// CHECK1-SAME: (%struct.TT* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR2:[0-9]+]] comdat align 2 {
+// CHECK1-SAME: (%struct.TT* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR3:[0-9]+]] comdat align 2 {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.TT*, align 8
// CHECK1-NEXT: [[I_ADDR:%.*]] = alloca i32, align 4
@@ -324,7 +324,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90
-// CHECK1-SAME: (i64 [[A:%.*]], i64 [[AA:%.*]], i64 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i64 [[A:%.*]], i64 [[AA:%.*]], i64 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i64, align 8
@@ -366,7 +366,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108
-// CHECK1-SAME: (%struct.S1* [[THIS:%.*]], i64 [[B:%.*]], i64 [[VLA:%.*]], i64 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (%struct.S1* [[THIS:%.*]], i64 [[B:%.*]], i64 [[VLA:%.*]], i64 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 8
// CHECK1-NEXT: [[B_ADDR:%.*]] = alloca i64, align 8
@@ -405,7 +405,7 @@ void unreachable_call() {
// CHECK1-NEXT: [[TMP8:%.*]] = load double, double* [[A7]], align 8
// CHECK1-NEXT: [[CONV8:%.*]] = fptosi double [[TMP8]] to i32
// CHECK1-NEXT: [[A9:%.*]] = getelementptr inbounds [[STRUCT_S1]], %struct.S1* [[TMP0]], i32 0, i32 0
-// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_Z3baziRd(i32 [[CONV8]], double* nonnull align 8 dereferenceable(8) [[A9]]) #[[ATTR5]]
+// CHECK1-NEXT: [[CALL:%.*]] = call i32 @_Z3baziRd(i32 [[CONV8]], double* nonnull align 8 dereferenceable(8) [[A9]]) #[[ATTR6]]
// CHECK1-NEXT: call void @__kmpc_target_deinit(%struct.ident_t* @[[GLOB1]], i1 false, i1 true)
// CHECK1-NEXT: ret void
// CHECK1: worker.exit:
@@ -413,7 +413,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@_Z3baziRd
-// CHECK1-SAME: (i32 [[F1:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR2]] {
+// CHECK1-SAME: (i32 [[F1:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR3]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca double*, align 8
// CHECK1-NEXT: [[CAPTURED_VARS_ADDRS:%.*]] = alloca [2 x i8*], align 8
@@ -437,13 +437,13 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z16unreachable_callv_l142
-// CHECK1-SAME: () #[[ATTR0]] {
+// CHECK1-SAME: () #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 true, i1 true)
// CHECK1-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
// CHECK1-NEXT: br i1 [[EXEC_USER_CODE]], label [[USER_CODE_ENTRY:%.*]], label [[WORKER_EXIT:%.*]]
// CHECK1: user_code.entry:
-// CHECK1-NEXT: call void @_Z6asserti(i32 0) #[[ATTR6:[0-9]+]]
+// CHECK1-NEXT: call void @_Z6asserti(i32 0) #[[ATTR7:[0-9]+]]
// CHECK1-NEXT: unreachable
// CHECK1: worker.exit:
// CHECK1-NEXT: ret void
@@ -453,7 +453,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z9ftemplateIiET_i_l74
-// CHECK1-SAME: (i64 [[A:%.*]], i64 [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i64 [[A:%.*]], i64 [[AA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[A_ADDR:%.*]] = alloca i64, align 8
// CHECK1-NEXT: [[AA_ADDR:%.*]] = alloca i64, align 8
@@ -487,7 +487,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1
-// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[F:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR0]] {
+// CHECK1-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32* nonnull align 4 dereferenceable(4) [[F:%.*]], double* nonnull align 8 dereferenceable(8) [[A:%.*]]) #[[ATTR1]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 8
// CHECK1-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 8
@@ -510,7 +510,7 @@ void unreachable_call() {
//
//
// CHECK1-LABEL: define {{[^@]+}}@__omp_outlined__1_wrapper
-// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR4:[0-9]+]] {
+// CHECK1-SAME: (i16 zeroext [[TMP0:%.*]], i32 [[TMP1:%.*]]) #[[ATTR5:[0-9]+]] {
// CHECK1-NEXT: entry:
// CHECK1-NEXT: [[DOTADDR:%.*]] = alloca i16, align 2
// CHECK1-NEXT: [[DOTADDR1:%.*]] = alloca i32, align 4
@@ -527,7 +527,7 @@ void unreachable_call() {
// CHECK1-NEXT: [[TMP6:%.*]] = getelementptr inbounds i8*, i8** [[TMP2]], i64 1
// CHECK1-NEXT: [[TMP7:%.*]] = bitcast i8** [[TMP6]] to double**
// CHECK1-NEXT: [[TMP8:%.*]] = load double*, double** [[TMP7]], align 8
-// CHECK1-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]], double* [[TMP8]]) #[[ATTR1:[0-9]+]]
+// CHECK1-NEXT: call void @__omp_outlined__1(i32* [[DOTADDR1]], i32* [[DOTZERO_ADDR]], i32* [[TMP5]], double* [[TMP8]]) #[[ATTR2:[0-9]+]]
// CHECK1-NEXT: ret void
//
//
@@ -560,7 +560,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@__omp_outlined__
-// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR1:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR2:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32* noalias [[DOTGLOBAL_TID_:%.*]], i32* noalias [[DOTBOUND_TID_:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR1:%.*]], i32** nonnull align 4 dereferenceable(4) [[PTR2:%.*]]) #[[ATTR1:[0-9]+]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[DOTGLOBAL_TID__ADDR:%.*]] = alloca i32*, align 4
// CHECK2-NEXT: [[DOTBOUND_TID__ADDR:%.*]] = alloca i32*, align 4
@@ -580,7 +580,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l39
-// CHECK2-SAME: () #[[ATTR0]] {
+// CHECK2-SAME: () #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[TMP0:%.*]] = call i32 @__kmpc_target_init(%struct.ident_t* @[[GLOB1]], i1 false, i1 true, i1 true)
// CHECK2-NEXT: [[EXEC_USER_CODE:%.*]] = icmp eq i32 [[TMP0]], -1
@@ -593,7 +593,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l47
-// CHECK2-SAME: (i32 [[AA:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32 [[AA:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[AA_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: store i32 [[AA]], i32* [[AA_ADDR]], align 4
@@ -619,7 +619,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__Z3fooi_l53
-// CHECK2-SAME: (i32 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i32 [[VLA1:%.*]], i32 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32 [[A:%.*]], [10 x float]* nonnull align 4 dereferenceable(40) [[B:%.*]], i32 [[VLA:%.*]], float* nonnull align 4 dereferenceable(4) [[BN:%.*]], [5 x [10 x double]]* nonnull align 8 dereferenceable(400) [[C:%.*]], i32 [[VLA1:%.*]], i32 [[VLA3:%.*]], double* nonnull align 8 dereferenceable(8) [[CN:%.*]], %struct.TT* nonnull align 8 dereferenceable(16) [[D:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[B_ADDR:%.*]] = alloca [10 x float]*, align 4
@@ -687,7 +687,7 @@ void unreachable_call() {
// CHECK2-NEXT: [[ADD19:%.*]] = add nsw i32 [[CONV18]], 1
// CHECK2-NEXT: [[CONV20:%.*]] = trunc i32 [[ADD19]] to i8
// CHECK2-NEXT: store i8 [[CONV20]], i8* [[Y]], align 8
-// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull align 8 dereferenceable(16) [[TMP7]], i32 0) #[[ATTR5:[0-9]+]]
+// CHECK2-NEXT: [[CALL:%.*]] = call nonnull align 8 dereferenceable(8) i64* @_ZN2TTIxcEixEi(%struct.TT* nonnull align 8 dereferenceable(16) [[TMP7]], i32 0) #[[ATTR6:[0-9]+]]
// CHECK2-NEXT: [[TMP17:%.*]] = load i64, i64* [[CALL]], align 8
// CHECK2-NEXT: [[ADD21:%.*]] = add nsw i64 [[TMP17]], 1
// CHECK2-NEXT: store i64 [[ADD21]], i64* [[CALL]], align 8
@@ -698,7 +698,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@_ZN2TTIxcEixEi
-// CHECK2-SAME: (%struct.TT* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR2:[0-9]+]] comdat align 2 {
+// CHECK2-SAME: (%struct.TT* nonnull align 8 dereferenceable(16) [[THIS:%.*]], i32 [[I:%.*]]) #[[ATTR3:[0-9]+]] comdat align 2 {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.TT*, align 4
// CHECK2-NEXT: [[I_ADDR:%.*]] = alloca i32, align 4
@@ -710,7 +710,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZL7fstatici_l90
-// CHECK2-SAME: (i32 [[A:%.*]], i32 [[AA:%.*]], i32 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (i32 [[A:%.*]], i32 [[AA:%.*]], i32 [[AAA:%.*]], [10 x i32]* nonnull align 4 dereferenceable(40) [[B:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[A_ADDR:%.*]] = alloca i32, align 4
// CHECK2-NEXT: [[AA_ADDR:%.*]] = alloca i32, align 4
@@ -751,7 +751,7 @@ void unreachable_call() {
//
//
// CHECK2-LABEL: define {{[^@]+}}@{{__omp_offloading_[0-9a-z]+_[0-9a-z]+}}__ZN2S12r1Ei_l108
-// CHECK2-SAME: (%struct.S1* [[THIS:%.*]], i32 [[B:%.*]], i32 [[VLA:%.*]], i32 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR0]] {
+// CHECK2-SAME: (%struct.S1* [[THIS:%.*]], i32 [[B:%.*]], i32 [[VLA:%.*]], i32 [[VLA1:%.*]], i16* nonnull align 2 dereferenceable(2) [[C:%.*]]) #[[ATTR1]] {
// CHECK2-NEXT: entry:
// CHECK2-NEXT: [[THIS_ADDR:%.*]] = alloca %struct.S1*, align 4
// CHECK2-NEXT: [[B_ADDR:%.*]] = alloca i32, align 4
@@ -789,7 +789,7 @@ void unreachable_call() {
// CHECK2-NEXT: [[TMP8:%.*]] = load double, double* [[A6]], align 8
// CHECK2-NEXT: [[CONV7:%.*]] = fptosi double [[TMP8]] to i32
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gcc_check/master-arm - Build # 2 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gcc_check/master-arm. So far, this commit has regressed CI configurations:
- tcwg_gcc_check/master-arm
Culprit:
<cut>
commit 0cbf03689e3e7d9d6002b8e5d159ef3716d0404c
Author: Tobias Burnus <tobias(a)codesourcery.com>
Date: Mon Jul 26 14:20:46 2021 +0200
PR fortran/93308/93963/94327/94331/97046 problems raised by descriptor handling
Fortran: Fix attributes and bounds in ISO_Fortran_binding.
2021-07-26 José Rui Faustino de Sousa <jrfsousa(a)gmail.com>
Tobias Burnus <tobias(a)codesourcery.com>
PR fortran/93308
PR fortran/93963
PR fortran/94327
PR fortran/94331
PR fortran/97046
gcc/fortran/ChangeLog:
* trans-decl.c (convert_CFI_desc): Only copy out the descriptor
if necessary.
* trans-expr.c (gfc_conv_gfc_desc_to_cfi_desc): Updated attribute
handling which reflect a previous intermediate version of the
standard. Only copy out the descriptor if necessary.
libgfortran/ChangeLog:
* runtime/ISO_Fortran_binding.c (cfi_desc_to_gfc_desc): Add code
to verify the descriptor. Correct bounds calculation.
(gfc_desc_to_cfi_desc): Add code to verify the descriptor.
gcc/testsuite/ChangeLog:
* gfortran.dg/ISO_Fortran_binding_1.f90: Add pointer attribute,
this test is still erroneous but now it compiles.
* gfortran.dg/bind_c_array_params_2.f90: Update regex to match
code changes.
* gfortran.dg/PR93308.f90: New test.
* gfortran.dg/PR93963.f90: New test.
* gfortran.dg/PR94327.c: New test.
* gfortran.dg/PR94327.f90: New test.
* gfortran.dg/PR94331.c: New test.
* gfortran.dg/PR94331.f90: New test.
* gfortran.dg/PR97046.f90: New test.
</cut>
Results regressed to (for first_bad == 0cbf03689e3e7d9d6002b8e5d159ef3716d0404c)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=gcc.dg/dg.exp --set runtestflags=gcc.dg/guality/guality.exp --set runtestflags=gcc.dg/ipa/ipa.exp --set runtestflags=gcc.dg/tree-prof/tree-prof.exp --set runtestflags=gcc.target/arm/arm.exp --set runtestflags=gfortran.dg/dg.exp --set runtestflags=libstdc++-dg/conformance.exp:
1
# Getting actual results from build directory /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/libstdc++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/gfortran.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/libitm.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/libgomp.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/libatomic.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/g++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c/sumfiles/gcc.sum
# Manifest: gcc-compare-results/contrib/testsuite-management/flaky.xfail
# Getting actual results from build directory base-artifacts/sumfiles
# base-artifacts/sumfiles/libstdc++.sum
# base-artifacts/sumfiles/gfortran.sum
# base-artifacts/sumfiles/libitm.sum
# base-artifacts/sumfiles/libgomp.sum
# base-artifacts/sumfiles/libatomic.sum
# base-artifacts/sumfiles/g++.sum
# base-artifacts/sumfiles/gcc.sum
#
#
# Unexpected results in this build (new failures)
# === gcc tests ===
#
# Running gfortran.dg/dg.exp ...
# FAIL: gfortran.dg/PR93308.f90 -O0 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93308.f90 -O0 compilation failed to produce executable
# FAIL: gfortran.dg/PR93308.f90 -O1 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93308.f90 -O1 compilation failed to produce executable
# FAIL: gfortran.dg/PR93308.f90 -O2 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93308.f90 -O2 compilation failed to produce executable
# FAIL: gfortran.dg/PR93308.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93308.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions compilation failed to produce executable
# FAIL: gfortran.dg/PR93308.f90 -O3 -g (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93308.f90 -O3 -g compilation failed to produce executable
# FAIL: gfortran.dg/PR93308.f90 -Os (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93308.f90 -Os compilation failed to produce executable
# FAIL: gfortran.dg/PR93963.f90 -O0 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93963.f90 -O0 compilation failed to produce executable
# FAIL: gfortran.dg/PR93963.f90 -O1 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93963.f90 -O1 compilation failed to produce executable
# FAIL: gfortran.dg/PR93963.f90 -O2 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93963.f90 -O2 compilation failed to produce executable
# FAIL: gfortran.dg/PR93963.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93963.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions compilation failed to produce executable
# FAIL: gfortran.dg/PR93963.f90 -O3 -g (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93963.f90 -O3 -g compilation failed to produce executable
# FAIL: gfortran.dg/PR93963.f90 -Os (test for excess errors)
# UNRESOLVED: gfortran.dg/PR93963.f90 -Os compilation failed to produce executable
# FAIL: gfortran.dg/PR94327.f90 -O0 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94327.f90 -O0 compilation failed to produce executable
# FAIL: gfortran.dg/PR94327.f90 -O1 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94327.f90 -O1 compilation failed to produce executable
# FAIL: gfortran.dg/PR94327.f90 -O2 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94327.f90 -O2 compilation failed to produce executable
# FAIL: gfortran.dg/PR94327.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94327.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions compilation failed to produce executable
# FAIL: gfortran.dg/PR94327.f90 -O3 -g (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94327.f90 -O3 -g compilation failed to produce executable
# FAIL: gfortran.dg/PR94327.f90 -Os (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94327.f90 -Os compilation failed to produce executable
# FAIL: gfortran.dg/PR94331.f90 -O0 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94331.f90 -O0 compilation failed to produce executable
# FAIL: gfortran.dg/PR94331.f90 -O1 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94331.f90 -O1 compilation failed to produce executable
# FAIL: gfortran.dg/PR94331.f90 -O2 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94331.f90 -O2 compilation failed to produce executable
# FAIL: gfortran.dg/PR94331.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94331.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions compilation failed to produce executable
# FAIL: gfortran.dg/PR94331.f90 -O3 -g (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94331.f90 -O3 -g compilation failed to produce executable
# FAIL: gfortran.dg/PR94331.f90 -Os (test for excess errors)
# UNRESOLVED: gfortran.dg/PR94331.f90 -Os compilation failed to produce executable
# FAIL: gfortran.dg/PR97046.f90 -O0 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR97046.f90 -O0 compilation failed to produce executable
# FAIL: gfortran.dg/PR97046.f90 -O1 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR97046.f90 -O1 compilation failed to produce executable
# FAIL: gfortran.dg/PR97046.f90 -O2 (test for excess errors)
# UNRESOLVED: gfortran.dg/PR97046.f90 -O2 compilation failed to produce executable
# FAIL: gfortran.dg/PR97046.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions (test for excess errors)
# UNRESOLVED: gfortran.dg/PR97046.f90 -O3 -fomit-frame-pointer -funroll-loops -fpeel-loops -ftracer -finline-functions compilation failed to produce executable
# FAIL: gfortran.dg/PR97046.f90 -O3 -g (test for excess errors)
# UNRESOLVED: gfortran.dg/PR97046.f90 -O3 -g compilation failed to produce executable
# FAIL: gfortran.dg/PR97046.f90 -Os (test for excess errors)
# UNRESOLVED: gfortran.dg/PR97046.f90 -Os compilation failed to produce executable
#
# === Results Summary ===
#
#
# Expected results not present in this build (fixed tests)
#
# NOTE: This is not a failure. It just means that these tests were expected
# to fail, but either they worked in this configuration or they were not
# present at all.
#
# === gfortran tests ===
#
# Running gfortran.dg/dg.exp ...
# FAIL: gfortran.dg/nearest_2.f90 -O0 execution test
#
# === Results Summary ===
from (for last_good == 32f7506bdc3956762bcc7dc84133fd7c3a00bb7b)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=gcc.dg/dg.exp --set runtestflags=gcc.dg/guality/guality.exp --set runtestflags=gcc.dg/ipa/ipa.exp --set runtestflags=gcc.dg/tree-prof/tree-prof.exp --set runtestflags=gcc.target/arm/arm.exp --set runtestflags=gfortran.dg/dg.exp --set runtestflags=libstdc++-dg/conformance.exp:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/artifact/artif…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/artifact/artif…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c
cd investigate-gcc-0cbf03689e3e7d9d6002b8e5d159ef3716d0404c
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/artifact/artif… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/artifact/artif… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/artifact/artif… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 0cbf03689e3e7d9d6002b8e5d159ef3716d0404c
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 32f7506bdc3956762bcc7dc84133fd7c3a00bb7b
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/artifact/artif…
Build log: https://ci.linaro.org/job/tcwg_gcc_check-bisect-master-arm/2/consoleText
Full commit (up to 1000 lines):
<cut>
commit 0cbf03689e3e7d9d6002b8e5d159ef3716d0404c
Author: Tobias Burnus <tobias(a)codesourcery.com>
Date: Mon Jul 26 14:20:46 2021 +0200
PR fortran/93308/93963/94327/94331/97046 problems raised by descriptor handling
Fortran: Fix attributes and bounds in ISO_Fortran_binding.
2021-07-26 José Rui Faustino de Sousa <jrfsousa(a)gmail.com>
Tobias Burnus <tobias(a)codesourcery.com>
PR fortran/93308
PR fortran/93963
PR fortran/94327
PR fortran/94331
PR fortran/97046
gcc/fortran/ChangeLog:
* trans-decl.c (convert_CFI_desc): Only copy out the descriptor
if necessary.
* trans-expr.c (gfc_conv_gfc_desc_to_cfi_desc): Updated attribute
handling which reflect a previous intermediate version of the
standard. Only copy out the descriptor if necessary.
libgfortran/ChangeLog:
* runtime/ISO_Fortran_binding.c (cfi_desc_to_gfc_desc): Add code
to verify the descriptor. Correct bounds calculation.
(gfc_desc_to_cfi_desc): Add code to verify the descriptor.
gcc/testsuite/ChangeLog:
* gfortran.dg/ISO_Fortran_binding_1.f90: Add pointer attribute,
this test is still erroneous but now it compiles.
* gfortran.dg/bind_c_array_params_2.f90: Update regex to match
code changes.
* gfortran.dg/PR93308.f90: New test.
* gfortran.dg/PR93963.f90: New test.
* gfortran.dg/PR94327.c: New test.
* gfortran.dg/PR94327.f90: New test.
* gfortran.dg/PR94331.c: New test.
* gfortran.dg/PR94331.f90: New test.
* gfortran.dg/PR97046.f90: New test.
---
gcc/fortran/trans-decl.c | 32 +--
gcc/fortran/trans-expr.c | 24 +-
.../gfortran.dg/ISO_Fortran_binding_1.f90 | 2 +-
gcc/testsuite/gfortran.dg/PR93308.f90 | 52 +++++
gcc/testsuite/gfortran.dg/PR93963.f90 | 150 ++++++++++++
gcc/testsuite/gfortran.dg/PR94327.c | 70 ++++++
gcc/testsuite/gfortran.dg/PR94327.f90 | 195 ++++++++++++++++
gcc/testsuite/gfortran.dg/PR94331.c | 73 ++++++
gcc/testsuite/gfortran.dg/PR94331.f90 | 252 +++++++++++++++++++++
gcc/testsuite/gfortran.dg/PR97046.f90 | 58 +++++
.../gfortran.dg/bind_c_array_params_2.f90 | 2 +-
libgfortran/runtime/ISO_Fortran_binding.c | 56 ++++-
12 files changed, 933 insertions(+), 33 deletions(-)
diff --git a/gcc/fortran/trans-decl.c b/gcc/fortran/trans-decl.c
index bf8783a35f8..784f7b61ce1 100644
--- a/gcc/fortran/trans-decl.c
+++ b/gcc/fortran/trans-decl.c
@@ -4539,22 +4539,28 @@ convert_CFI_desc (gfc_wrapped_block * block, gfc_symbol *sym)
gfc_add_expr_to_block (&outer_block, incoming);
incoming = gfc_finish_block (&outer_block);
-
/* Convert the gfc descriptor back to the CFI type before going
out of scope, if the CFI type was present at entry. */
- gfc_init_block (&outer_block);
- gfc_init_block (&tmpblock);
-
- tmp = gfc_build_addr_expr (ppvoid_type_node, CFI_desc_ptr);
- outgoing = build_call_expr_loc (input_location,
- gfor_fndecl_gfc_to_cfi, 2, tmp, gfc_desc_ptr);
- gfc_add_expr_to_block (&tmpblock, outgoing);
+ outgoing = NULL_TREE;
+ if ((sym->attr.pointer || sym->attr.allocatable)
+ && !sym->attr.value
+ && sym->attr.intent != INTENT_IN)
+ {
+ gfc_init_block (&outer_block);
+ gfc_init_block (&tmpblock);
- outgoing = build3_v (COND_EXPR, present,
- gfc_finish_block (&tmpblock),
- build_empty_stmt (input_location));
- gfc_add_expr_to_block (&outer_block, outgoing);
- outgoing = gfc_finish_block (&outer_block);
+ tmp = gfc_build_addr_expr (ppvoid_type_node, CFI_desc_ptr);
+ outgoing = build_call_expr_loc (input_location,
+ gfor_fndecl_gfc_to_cfi, 2,
+ tmp, gfc_desc_ptr);
+ gfc_add_expr_to_block (&tmpblock, outgoing);
+
+ outgoing = build3_v (COND_EXPR, present,
+ gfc_finish_block (&tmpblock),
+ build_empty_stmt (input_location));
+ gfc_add_expr_to_block (&outer_block, outgoing);
+ outgoing = gfc_finish_block (&outer_block);
+ }
/* Add the lot to the procedure init and finally blocks. */
gfc_add_init_cleanup (block, incoming, outgoing);
diff --git a/gcc/fortran/trans-expr.c b/gcc/fortran/trans-expr.c
index b18a9ec9799..c4291cce079 100644
--- a/gcc/fortran/trans-expr.c
+++ b/gcc/fortran/trans-expr.c
@@ -5502,13 +5502,12 @@ gfc_conv_gfc_desc_to_cfi_desc (gfc_se *parmse, gfc_expr *e, gfc_symbol *fsym)
attribute = 1;
}
- /* If the formal argument is assumed shape and neither a pointer nor
- allocatable, it is unconditionally CFI_attribute_other. */
- if (fsym->as->type == AS_ASSUMED_SHAPE
- && !fsym->attr.pointer && !fsym->attr.allocatable)
- cfi_attribute = 2;
+ if (fsym->attr.pointer)
+ cfi_attribute = 0;
+ else if (fsym->attr.allocatable)
+ cfi_attribute = 1;
else
- cfi_attribute = attribute;
+ cfi_attribute = 2;
if (e->rank != 0)
{
@@ -5616,10 +5615,15 @@ gfc_conv_gfc_desc_to_cfi_desc (gfc_se *parmse, gfc_expr *e, gfc_symbol *fsym)
gfc_prepend_expr_to_block (&parmse->post, tmp);
/* Transfer values back to gfc descriptor. */
- tmp = gfc_build_addr_expr (NULL_TREE, parmse->expr);
- tmp = build_call_expr_loc (input_location,
- gfor_fndecl_cfi_to_gfc, 2, gfc_desc_ptr, tmp);
- gfc_prepend_expr_to_block (&parmse->post, tmp);
+ if (cfi_attribute != 2 /* CFI_attribute_other. */
+ && !fsym->attr.value
+ && fsym->attr.intent != INTENT_IN)
+ {
+ tmp = gfc_build_addr_expr (NULL_TREE, parmse->expr);
+ tmp = build_call_expr_loc (input_location,
+ gfor_fndecl_cfi_to_gfc, 2, gfc_desc_ptr, tmp);
+ gfc_prepend_expr_to_block (&parmse->post, tmp);
+ }
/* Deal with an optional dummy being passed to an optional formal arg
by finishing the pre and post blocks and making their execution
diff --git a/gcc/testsuite/gfortran.dg/ISO_Fortran_binding_1.f90 b/gcc/testsuite/gfortran.dg/ISO_Fortran_binding_1.f90
index 102bc60310c..0cf3b2cb88c 100644
--- a/gcc/testsuite/gfortran.dg/ISO_Fortran_binding_1.f90
+++ b/gcc/testsuite/gfortran.dg/ISO_Fortran_binding_1.f90
@@ -39,7 +39,7 @@
USE, INTRINSIC :: ISO_C_BINDING
import
INTEGER(C_INT) :: err
- type (T), DIMENSION(..), intent(out) :: a
+ type (T), pointer, DIMENSION(..), intent(out) :: a
END FUNCTION c_establish
FUNCTION c_contiguous(a) BIND(C, NAME="contiguous_c") RESULT(err)
diff --git a/gcc/testsuite/gfortran.dg/PR93308.f90 b/gcc/testsuite/gfortran.dg/PR93308.f90
new file mode 100644
index 00000000000..ee116f961de
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR93308.f90
@@ -0,0 +1,52 @@
+! { dg-do run }
+!
+! Test the fix for PR94331
+!
+! Contributed by Robin Hogan <r.j.hogan(a)reading.ac.uk>
+!
+
+program test
+
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_float
+
+ implicit none
+
+ integer :: i
+ integer, parameter :: n = 11
+ real(kind=c_float), parameter :: u(*) = [(real(i, kind=c_float), i=1,n)]
+
+ real(kind=c_float), allocatable :: A(:)
+ real(kind=c_float) :: E(n)
+ integer(kind=c_int) :: l1, l2, l3
+
+ allocate(A, source=u)
+ l1 = lbound(A, 1)
+ call routine_bindc(A, l2) ! in gcc-9.2.1 this changes lbound of A...
+ l3 = lbound(A, 1)
+ if (l1 /= 1) stop 1
+ if (l1 /= l2) stop 2
+ if (l1 /= l3) stop 3
+ if (any(abs(A(1:n)-u)>0.0_c_float)) stop 4
+ deallocate(A)
+ !
+ E = u
+ l1 = lbound(E, 1)
+ call routine_bindc(E, l2) ! ...but does not change lbound of E
+ l3 = lbound(E, 1)
+ if (l1 /= 1) stop 5
+ if (l1 /= l2) stop 6
+ if (l1 /= l3) stop 7
+ if (any(abs(E(1:n)-u)>0.0_c_float)) stop 8
+
+contains
+
+ subroutine routine_bindc(v, l) bind(c)
+ real(kind=c_float), intent(inout) :: v(:)
+ integer(kind=c_int), intent(out) :: l
+
+ l = lbound(v, 1)
+ if (any(abs(v(1:n)-u)>0.0_c_float)) stop 9
+ end subroutine routine_bindc
+
+end program test
diff --git a/gcc/testsuite/gfortran.dg/PR93963.f90 b/gcc/testsuite/gfortran.dg/PR93963.f90
new file mode 100644
index 00000000000..4e1b06fd525
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR93963.f90
@@ -0,0 +1,150 @@
+! { dg-do run }
+!
+! Test the fix for PR93963
+!
+
+function rank_p(this) result(rnk) bind(c)
+ use, intrinsic :: iso_c_binding, only: c_int
+
+ implicit none
+
+ integer(kind=c_int), pointer, intent(in) :: this(..)
+ integer(kind=c_int) :: rnk
+
+ select rank(this)
+ rank(0)
+ rnk = 0
+ rank(1)
+ rnk = 1
+ rank(2)
+ rnk = 2
+ rank(3)
+ rnk = 3
+ rank(4)
+ rnk = 4
+ rank(5)
+ rnk = 5
+ rank(6)
+ rnk = 6
+ rank(7)
+ rnk = 7
+ rank(8)
+ rnk = 8
+ rank(9)
+ rnk = 9
+ rank(10)
+ rnk = 10
+ rank(11)
+ rnk = 11
+ rank(12)
+ rnk = 12
+ rank(13)
+ rnk = 13
+ rank(14)
+ rnk = 14
+ rank(15)
+ rnk = 15
+ rank default
+ rnk = -1000
+ end select
+ return
+end function rank_p
+
+function rank_a(this) result(rnk) bind(c)
+ use, intrinsic :: iso_c_binding, only: c_int
+
+ implicit none
+
+ integer(kind=c_int), allocatable, intent(in) :: this(..)
+ integer(kind=c_int) :: rnk
+
+ select rank(this)
+ rank(0)
+ rnk = 0
+ rank(1)
+ rnk = 1
+ rank(2)
+ rnk = 2
+ rank(3)
+ rnk = 3
+ rank(4)
+ rnk = 4
+ rank(5)
+ rnk = 5
+ rank(6)
+ rnk = 6
+ rank(7)
+ rnk = 7
+ rank(8)
+ rnk = 8
+ rank(9)
+ rnk = 9
+ rank(10)
+ rnk = 10
+ rank(11)
+ rnk = 11
+ rank(12)
+ rnk = 12
+ rank(13)
+ rnk = 13
+ rank(14)
+ rnk = 14
+ rank(15)
+ rnk = 15
+ rank default
+ rnk = -1000
+ end select
+ return
+end function rank_a
+
+program selr_p
+
+ use, intrinsic :: iso_c_binding, only: c_int
+
+ implicit none
+
+ interface
+ function rank_p(this) result(rnk) bind(c)
+ use, intrinsic :: iso_c_binding, only: c_int
+ integer(kind=c_int), pointer, intent(in) :: this(..)
+ integer(kind=c_int) :: rnk
+ end function rank_p
+ end interface
+
+ interface
+ function rank_a(this) result(rnk) bind(c)
+ use, intrinsic :: iso_c_binding, only: c_int
+ integer(kind=c_int), allocatable, intent(in) :: this(..)
+ integer(kind=c_int) :: rnk
+ end function rank_a
+ end interface
+
+ integer(kind=c_int), parameter :: siz = 7
+ integer(kind=c_int), parameter :: rnk = 1
+
+ integer(kind=c_int), pointer :: intp(:)
+ integer(kind=c_int), allocatable :: inta(:)
+ integer(kind=c_int) :: irnk
+
+ nullify(intp)
+ irnk = rank_p(intp)
+ if (irnk /= rnk) stop 1
+ if (irnk /= rank(intp)) stop 2
+ !
+ irnk = rank_a(inta)
+ if (irnk /= rnk) stop 3
+ if (irnk /= rank(inta)) stop 4
+ !
+ allocate(intp(siz))
+ irnk = rank_p(intp)
+ if (irnk /= rnk) stop 5
+ if (irnk /= rank(intp)) stop 6
+ deallocate(intp)
+ nullify(intp)
+ !
+ allocate(inta(siz))
+ if (irnk /= rnk) stop 7
+ if (irnk /= rank(inta)) stop 8
+ deallocate(inta)
+
+end program selr_p
diff --git a/gcc/testsuite/gfortran.dg/PR94327.c b/gcc/testsuite/gfortran.dg/PR94327.c
new file mode 100644
index 00000000000..6791c373546
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR94327.c
@@ -0,0 +1,70 @@
+/* Test the fix for PR94327. */
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+#include "../../../libgfortran/ISO_Fortran_binding.h"
+
+bool c_vrfy (const CFI_cdesc_t *restrict);
+
+char get_attr (const CFI_cdesc_t*restrict, bool);
+
+bool
+c_vrfy (const CFI_cdesc_t *restrict auxp)
+{
+ CFI_index_t i, lb, ub, ex;
+ int *ip = NULL;
+
+ assert (auxp);
+ assert (auxp->base_addr);
+ lb = auxp->dim[0].lower_bound;
+ ex = auxp->dim[0].extent;
+ ub = ex + lb - 1;
+ ip = (int*)auxp->base_addr;
+ for (i=0; i<ex; i++)
+ if (*ip++ != i+1)
+ return false;
+ for (i=lb; i<ub+1; i++)
+ {
+ ip = (int*)CFI_address(auxp, &i);
+ if (*ip != i-lb+1)
+ return false;
+ }
+ return true;
+}
+
+char
+get_attr (const CFI_cdesc_t *restrict auxp, bool alloc)
+{
+ char attr;
+
+ assert (auxp);
+ assert (auxp->elem_len == 4);
+ assert (auxp->rank == 1);
+ assert (auxp->type == CFI_type_int);
+ attr = '\0';
+ switch (auxp->attribute)
+ {
+ case CFI_attribute_pointer:
+ if (alloc && !c_vrfy (auxp))
+ break;
+ attr = 'p';
+ break;
+ case CFI_attribute_allocatable:
+ if (alloc && !c_vrfy (auxp))
+ break;
+ attr = 'a';
+ break;
+ case CFI_attribute_other:
+ assert (alloc);
+ if (!c_vrfy (auxp))
+ break;
+ attr = 'o';
+ break;
+ default:
+ break;
+ }
+ return attr;
+}
+
diff --git a/gcc/testsuite/gfortran.dg/PR94327.f90 b/gcc/testsuite/gfortran.dg/PR94327.f90
new file mode 100644
index 00000000000..3cb3ac3dda1
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR94327.f90
@@ -0,0 +1,195 @@
+! { dg-do run }
+! { dg-additional-sources PR94327.c }
+!
+! Test the fix for PR94327
+!
+
+program attr_p
+
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+
+ implicit none
+
+ integer :: i
+ integer, parameter :: n = 11
+ integer, parameter :: u(*) = [(i, i=1,n)]
+
+ interface
+ function attr_p_as(a, s) result(c) &
+ bind(c, name="get_attr")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+ implicit none
+ integer(kind=c_int), pointer, intent(in) :: a(:)
+ logical(kind=c_bool), value, intent(in) :: s
+ character(kind=c_char) :: c
+ end function attr_p_as
+ function attr_a_as(a, s) result(c) &
+ bind(c, name="get_attr")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+ implicit none
+ integer(kind=c_int), allocatable, intent(in) :: a(:)
+ logical(kind=c_bool), value, intent(in) :: s
+ character(kind=c_char) :: c
+ end function attr_a_as
+ function attr_o_as(a, s) result(c) &
+ bind(c, name="get_attr")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+ implicit none
+ integer(kind=c_int), intent(in) :: a(:)
+ logical(kind=c_bool), value, intent(in) :: s
+ character(kind=c_char) :: c
+ end function attr_o_as
+ function attr_p_ar(a, s) result(c) &
+ bind(c, name="get_attr")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+ implicit none
+ integer(kind=c_int), pointer, intent(in) :: a(..)
+ logical(kind=c_bool), value, intent(in) :: s
+ character(kind=c_char) :: c
+ end function attr_p_ar
+ function attr_a_ar(a, s) result(c) &
+ bind(c, name="get_attr")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+ implicit none
+ integer(kind=c_int), allocatable, intent(in) :: a(..)
+ logical(kind=c_bool), value, intent(in) :: s
+ character(kind=c_char) :: c
+ end function attr_a_ar
+ function attr_o_ar(a, s) result(c) &
+ bind(c, name="get_attr")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool, c_char
+ implicit none
+ integer(kind=c_int), intent(in) :: a(..)
+ logical(kind=c_bool), value, intent(in) :: s
+ character(kind=c_char) :: c
+ end function attr_o_ar
+ end interface
+
+ integer(kind=c_int), target :: a(n)
+ integer(kind=c_int), allocatable, target :: b(:)
+ integer(kind=c_int), pointer :: p(:)
+ character(kind=c_char) :: c
+
+ a = u
+ c = attr_p_as(a, .true._c_bool)
+ if(c/='p') stop 1
+ if(any(a/=u)) stop 2
+ !
+ a = u
+ c = attr_p_ar(a, .true._c_bool)
+ if(c/='p') stop 3
+ if(any(a/=u)) stop 4
+ !
+ a = u
+ c = attr_o_as(a, .true._c_bool)
+ if(c/='o') stop 5
+ if(any(a/=u)) stop 6
+ !
+ a = u
+ c = attr_o_ar(a, .true._c_bool)
+ if(c/='o') stop 7
+ if(any(a/=u)) stop 8
+ !
+ allocate(b, source=u)
+ c = attr_p_as(b, .true._c_bool)
+ if(c/='p') stop 9
+ if(.not.allocated(b)) stop 10
+ if(any(b/=u)) stop 11
+ !
+ deallocate(b)
+ allocate(b, source=u)
+ c = attr_p_ar(b, .true._c_bool)
+ if(c/='p') stop 12
+ if(.not.allocated(b)) stop 13
+ if(any(b/=u)) stop 14
+ !
+ deallocate(b)
+ allocate(b, source=u)
+ c = attr_a_as(b, .true._c_bool)
+ if(c/='a') stop 15
+ if(.not.allocated(b)) stop 16
+ if(any(b/=u)) stop 17
+ !
+ deallocate(b)
+ allocate(b, source=u)
+ c = attr_a_ar(b, .true._c_bool)
+ if(c/='a') stop 18
+ if(.not.allocated(b)) stop 19
+ if(any(b/=u)) stop 20
+ !
+ deallocate(b)
+ allocate(b, source=u)
+ c = attr_o_as(b, .true._c_bool)
+ if(c/='o') stop 21
+ if(.not.allocated(b)) stop 22
+ if(any(b/=u)) stop 23
+ !
+ deallocate(b)
+ allocate(b, source=u)
+ c = attr_o_ar(b, .true._c_bool)
+ if(c/='o') stop 24
+ if(.not.allocated(b)) stop 25
+ if(any(b/=u)) stop 26
+ !
+ deallocate(b)
+ c = attr_a_as(b, .false._c_bool)
+ if(c/='a') stop 27
+ if(allocated(b)) stop 28
+ !
+ c = attr_a_ar(b, .false._c_bool)
+ if(c/='a') stop 29
+ if(allocated(b)) stop 30
+ !
+ nullify(p)
+ p => a
+ c = attr_p_as(p, .true._c_bool)
+ if(c/='p') stop 31
+ if(.not.associated(p)) stop 32
+ if(.not.associated(p, a)) stop 33
+ if(any(p/=u)) stop 34
+ !
+ nullify(p)
+ p => a
+ c = attr_p_ar(p, .true._c_bool)
+ if(c/='p') stop 35
+ if(.not.associated(p)) stop 36
+ if(.not.associated(p, a)) stop 37
+ if(any(p/=u)) stop 38
+ !
+ nullify(p)
+ p => a
+ c = attr_o_as(p, .true._c_bool)
+ if(c/='o') stop 39
+ if(.not.associated(p)) stop 40
+ if(.not.associated(p, a)) stop 41
+ if(any(p/=u)) stop 42
+ !
+ nullify(p)
+ p => a
+ c = attr_o_ar(p, .true._c_bool)
+ if(c/='o') stop 43
+ if(.not.associated(p)) stop 44
+ if(.not.associated(p, a)) stop 45
+ if(any(p/=u)) stop 46
+ !
+ nullify(p)
+ c = attr_p_as(p, .false._c_bool)
+ if(c/='p') stop 47
+ if(associated(p)) stop 48
+ if(associated(p, a)) stop 49
+ !
+ nullify(p)
+ c = attr_p_ar(p, .false._c_bool)
+ if(c/='p') stop 50
+ if(associated(p)) stop 51
+ if(associated(p, a)) stop 52
+ stop
+
+end program attr_p
diff --git a/gcc/testsuite/gfortran.dg/PR94331.c b/gcc/testsuite/gfortran.dg/PR94331.c
new file mode 100644
index 00000000000..4e130515455
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR94331.c
@@ -0,0 +1,73 @@
+/* Test the fix for PR94331. */
+
+#include <assert.h>
+#include <stdbool.h>
+#include <stdlib.h>
+
+#include "../../../libgfortran/ISO_Fortran_binding.h"
+
+bool c_vrfy (const CFI_cdesc_t *restrict);
+
+bool check_bounds(const CFI_cdesc_t*restrict, const int, const int);
+
+bool
+c_vrfy (const CFI_cdesc_t *restrict auxp)
+{
+ CFI_index_t i, lb, ub, ex;
+ int *ip = NULL;
+
+ assert (auxp);
+ assert (auxp->base_addr);
+ lb = auxp->dim[0].lower_bound;
+ ex = auxp->dim[0].extent;
+ ub = ex + lb - 1;
+ ip = (int*)auxp->base_addr;
+ for (i=0; i<ex; i++)
+ if (*ip++ != i+1)
+ return false;
+ for (i=lb; i<ub+1; i++)
+ {
+ ip = (int*)CFI_address(auxp, &i);
+ if (*ip != i-lb+1)
+ return false;
+ }
+ return true;
+}
+
+bool
+check_bounds (const CFI_cdesc_t *restrict auxp, const int lb, const int ub)
+{
+ CFI_index_t ex = ub-lb+1;
+ size_t el;
+ bool is_ok = false;
+
+ assert (auxp);
+ el = auxp->elem_len;
+ assert (auxp->rank==1);
+ assert (auxp->type==CFI_type_int);
+ assert (auxp->dim[0].sm>0);
+ assert ((size_t)auxp->dim[0].sm==el);
+ if (auxp->dim[0].extent==ex
+ && auxp->dim[0].lower_bound==lb)
+ {
+ switch(auxp->attribute)
+ {
+ case CFI_attribute_pointer:
+ case CFI_attribute_allocatable:
+ if (!c_vrfy (auxp))
+ break;
+ is_ok = true;
+ break;
+ case CFI_attribute_other:
+ if (!c_vrfy (auxp))
+ break;
+ is_ok = (lb==0);
+ break;
+ default:
+ assert (false);
+ break;
+ }
+ }
+ return is_ok;
+}
+
diff --git a/gcc/testsuite/gfortran.dg/PR94331.f90 b/gcc/testsuite/gfortran.dg/PR94331.f90
new file mode 100644
index 00000000000..6185031afc5
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR94331.f90
@@ -0,0 +1,252 @@
+! { dg-do run }
+! { dg-additional-sources PR94331.c }
+!
+! Test the fix for PR94331
+!
+
+program main_p
+
+ use, intrinsic :: iso_c_binding, only: &
+ c_int
+
+ implicit none
+
+ integer :: i
+ integer, parameter :: ex = 11
+ integer, parameter :: lb = 11
+ integer, parameter :: ub = ex+lb-1
+ integer, parameter :: u(*) = [(i, i=1,ex)]
+
+ interface
+ function checkb_p_as(a, l, u) result(c) &
+ bind(c, name="check_bounds")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool
+ implicit none
+ integer(kind=c_int), pointer, intent(in) :: a(:)
+ integer(kind=c_int), value, intent(in) :: l
+ integer(kind=c_int), value, intent(in) :: u
+ logical(kind=c_bool) :: c
+ end function checkb_p_as
+ function checkb_a_as(a, l, u) result(c) &
+ bind(c, name="check_bounds")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool
+ implicit none
+ integer(kind=c_int), allocatable, intent(in) :: a(:)
+ integer(kind=c_int), value, intent(in) :: l
+ integer(kind=c_int), value, intent(in) :: u
+ logical(kind=c_bool) :: c
+ end function checkb_a_as
+ function checkb_o_as(a, l, u) result(c) &
+ bind(c, name="check_bounds")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool
+ implicit none
+ integer(kind=c_int), intent(in) :: a(:)
+ integer(kind=c_int), value, intent(in) :: l
+ integer(kind=c_int), value, intent(in) :: u
+ logical(kind=c_bool) :: c
+ end function checkb_o_as
+ function checkb_p_ar(a, l, u) result(c) &
+ bind(c, name="check_bounds")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool
+ implicit none
+ integer(kind=c_int), pointer, intent(in) :: a(..)
+ integer(kind=c_int), value, intent(in) :: l
+ integer(kind=c_int), value, intent(in) :: u
+ logical(kind=c_bool) :: c
+ end function checkb_p_ar
+ function checkb_a_ar(a, l, u) result(c) &
+ bind(c, name="check_bounds")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool
+ implicit none
+ integer(kind=c_int), allocatable, intent(in) :: a(..)
+ integer(kind=c_int), value, intent(in) :: l
+ integer(kind=c_int), value, intent(in) :: u
+ logical(kind=c_bool) :: c
+ end function checkb_a_ar
+ function checkb_o_ar(a, l, u) result(c) &
+ bind(c, name="check_bounds")
+ use, intrinsic :: iso_c_binding, only: &
+ c_int, c_bool
+ implicit none
+ integer(kind=c_int), intent(in) :: a(..)
+ integer(kind=c_int), value, intent(in) :: l
+ integer(kind=c_int), value, intent(in) :: u
+ logical(kind=c_bool) :: c
+ end function checkb_o_ar
+ end interface
+
+ integer(kind=c_int), target :: a(lb:ub)
+ integer(kind=c_int), allocatable, target :: b(:)
+ integer(kind=c_int), pointer :: p(:)
+
+ a = u
+ if(lbound(a,1)/=lb) stop 1
+ if(ubound(a,1)/=ub) stop 2
+ if(any(shape(a)/=[ex])) stop 3
+ if(.not.checkb_p_as(a, lb, ub)) stop 4
+ if(lbound(a,1)/=lb) stop 5
+ if(ubound(a,1)/=ub) stop 6
+ if(any(shape(a)/=[ex])) stop 7
+ if(any(a/=u)) stop 8
+ !
+ a = u
+ if(lbound(a,1)/=lb) stop 9
+ if(ubound(a,1)/=ub) stop 10
+ if(any(shape(a)/=[ex])) stop 11
+ if(.not.checkb_p_ar(a, lb, ub)) stop 12
+ if(lbound(a,1)/=lb) stop 13
+ if(ubound(a,1)/=ub) stop 14
+ if(any(shape(a)/=[ex])) stop 15
+ if(any(a/=u)) stop 16
+ !
+ a = u
+ if(lbound(a,1)/=lb) stop 17
+ if(ubound(a,1)/=ub) stop 18
+ if(any(shape(a)/=[ex])) stop 19
+ if(.not.checkb_o_as(a, 0, ex-1))stop 20
+ if(lbound(a,1)/=lb) stop 21
+ if(ubound(a,1)/=ub) stop 22
+ if(any(shape(a)/=[ex])) stop 23
+ if(any(a/=u)) stop 24
+ !
+ a = u
+ if(lbound(a,1)/=lb) stop 25
+ if(ubound(a,1)/=ub) stop 26
+ if(any(shape(a)/=[ex])) stop 27
+ if(.not.checkb_o_ar(a, 0, ex-1))stop 28
+ if(lbound(a,1)/=lb) stop 29
+ if(ubound(a,1)/=ub) stop 30
+ if(any(shape(a)/=[ex])) stop 31
+ if(any(a/=u)) stop 32
+ !
+ allocate(b(lb:ub), source=u)
+ if(lbound(b,1)/=lb) stop 33
+ if(ubound(b,1)/=ub) stop 34
+ if(any(shape(b)/=[ex])) stop 35
+ if(.not.checkb_p_as(b, lb, ub)) stop 36
+ if(.not.allocated(b)) stop 37
+ if(lbound(b,1)/=lb) stop 38
+ if(ubound(b,1)/=ub) stop 39
+ if(any(shape(b)/=[ex])) stop 40
+ if(any(b/=u)) stop 41
+ !
+ deallocate(b)
+ allocate(b(lb:ub), source=u)
+ if(lbound(b,1)/=lb) stop 42
+ if(ubound(b,1)/=ub) stop 43
+ if(any(shape(b)/=[ex])) stop 44
+ if(.not.checkb_p_ar(b, lb, ub)) stop 45
+ if(.not.allocated(b)) stop 46
+ if(lbound(b,1)/=lb) stop 47
+ if(ubound(b,1)/=ub) stop 48
+ if(any(shape(b)/=[ex])) stop 49
+ if(any(b/=u)) stop 50
+ !
+ deallocate(b)
+ allocate(b(lb:ub), source=u)
+ if(lbound(b,1)/=lb) stop 51
+ if(ubound(b,1)/=ub) stop 52
+ if(any(shape(b)/=[ex])) stop 53
+ if(.not.checkb_a_as(b, lb, ub)) stop 54
+ if(.not.allocated(b)) stop 55
+ if(lbound(b,1)/=lb) stop 56
+ if(ubound(b,1)/=ub) stop 57
+ if(any(shape(b)/=[ex])) stop 58
+ if(any(b/=u)) stop 59
+ !
+ deallocate(b)
+ allocate(b(lb:ub), source=u)
+ if(lbound(b,1)/=lb) stop 60
+ if(ubound(b,1)/=ub) stop 61
+ if(any(shape(b)/=[ex])) stop 62
+ if(.not.checkb_a_ar(b, lb, ub)) stop 63
+ if(.not.allocated(b)) stop 64
+ if(lbound(b,1)/=lb) stop 65
+ if(ubound(b,1)/=ub) stop 66
+ if(any(shape(b)/=[ex])) stop 67
+ if(any(b/=u)) stop 68
+ !
+ deallocate(b)
+ allocate(b(lb:ub), source=u)
+ if(lbound(b,1)/=lb) stop 69
+ if(ubound(b,1)/=ub) stop 70
+ if(any(shape(b)/=[ex])) stop 71
+ if(.not.checkb_o_as(b, 0, ex-1))stop 72
+ if(.not.allocated(b)) stop 73
+ if(lbound(b,1)/=lb) stop 74
+ if(ubound(b,1)/=ub) stop 75
+ if(any(shape(b)/=[ex])) stop 76
+ if(any(b/=u)) stop 77
+ !
+ deallocate(b)
+ allocate(b(lb:ub), source=u)
+ if(lbound(b,1)/=lb) stop 78
+ if(ubound(b,1)/=ub) stop 79
+ if(any(shape(b)/=[ex])) stop 80
+ if(.not.checkb_o_ar(b, 0, ex-1))stop 81
+ if(.not.allocated(b)) stop 82
+ if(lbound(b,1)/=lb) stop 83
+ if(ubound(b,1)/=ub) stop 84
+ if(any(shape(b)/=[ex])) stop 85
+ if(any(b/=u)) stop 86
+ deallocate(b)
+ !
+ p(lb:ub) => a
+ if(lbound(p,1)/=lb) stop 87
+ if(ubound(p,1)/=ub) stop 88
+ if(any(shape(p)/=[ex])) stop 89
+ if(.not.checkb_p_as(p, lb, ub)) stop 90
+ if(.not.associated(p)) stop 91
+ if(.not.associated(p, a)) stop 92
+ if(lbound(p,1)/=lb) stop 93
+ if(ubound(p,1)/=ub) stop 94
+ if(any(shape(p)/=[ex])) stop 95
+ if(any(p/=u)) stop 96
+ !
+ nullify(p)
+ p(lb:ub) => a
+ if(lbound(p,1)/=lb) stop 97
+ if(ubound(p,1)/=ub) stop 98
+ if(any(shape(p)/=[ex])) stop 99
+ if(.not.checkb_p_ar(p, lb, ub)) stop 100
+ if(.not.associated(p)) stop 101
+ if(.not.associated(p, a)) stop 102
+ if(lbound(p,1)/=lb) stop 103
+ if(ubound(p,1)/=ub) stop 104
+ if(any(shape(p)/=[ex])) stop 105
+ if(any(p/=u)) stop 106
+ !
+ nullify(p)
+ p(lb:ub) => a
+ if(lbound(p,1)/=lb) stop 107
+ if(ubound(p,1)/=ub) stop 108
+ if(any(shape(p)/=[ex])) stop 109
+ if(.not.checkb_o_as(p, 0, ex-1))stop 110
+ if(.not.associated(p)) stop 111
+ if(.not.associated(p, a)) stop 112
+ if(lbound(p,1)/=lb) stop 113
+ if(ubound(p,1)/=ub) stop 114
+ if(any(shape(p)/=[ex])) stop 115
+ if(any(p/=u)) stop 116
+ !
+ nullify(p)
+ p(lb:ub) => a
+ if(lbound(p,1)/=lb) stop 117
+ if(ubound(p,1)/=ub) stop 118
+ if(any(shape(p)/=[ex])) stop 119
+ if(.not.checkb_o_ar(p, 0, ex-1))stop 120
+ if(.not.associated(p)) stop 121
+ if(.not.associated(p, a)) stop 122
+ if(lbound(p,1)/=lb) stop 123
+ if(ubound(p,1)/=ub) stop 124
+ if(any(shape(p)/=[ex])) stop 125
+ if(any(p/=u)) stop 126
+ nullify(p)
+ stop
+
+end program main_p
diff --git a/gcc/testsuite/gfortran.dg/PR97046.f90 b/gcc/testsuite/gfortran.dg/PR97046.f90
new file mode 100644
index 00000000000..7d133a5ad70
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/PR97046.f90
@@ -0,0 +1,58 @@
+! { dg-do run }
+!
+! Test the fix for PR94331
+!
+! Contributed by Igor Gayday <igor.gayday(a)mu.edu>
</cut>
4 years, 1 month
- 1
- 0
[ACTIVITY] report week ending 6 Aug
by Peter Maydell
Progress:
* UM-2 [QEMU upstream maintainership]
+ Usual release work (rc2 now out) and code review
+ Continuing with systick timer refactoring. This has turned out a bit
more complicated than I expected: had to do a preliminary refactor
to move some stuff out of the NVIC device into the armv7m container;
also needed to add support in the Clock APIs for frequency multiply
and divide for the benefit of the stm32 SoCs which drive the systick
reference clock at 1/8 the speed of the main CPU clock
-- PMM
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/gnu-master-arm-spec2k6-O2 - Build # 17 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O2
Culprit:
<cut>
commit 2e96b5f14e4025691b57d2301d71aa6092ed44bc
Author: Aldy Hernandez <aldyh(a)redhat.com>
Date: Tue Jun 15 12:32:51 2021 +0200
Backwards jump threader rewrite with ranger.
This is a rewrite of the backwards threader with a ranger based solver.
The code is divided into two parts: the path solver in
gimple-range-path.*, and the path discovery bits in
tree-ssa-threadbackward.c.
The legacy code is still available with --param=threader-mode=legacy,
but will be removed shortly after.
gcc/ChangeLog:
* Makefile.in (tree-ssa-loop-im.o-warn): New.
* flag-types.h (enum threader_mode): New.
* params.opt: Add entry for --param=threader-mode.
* tree-ssa-threadbackward.c (THREADER_ITERATIVE_MODE): New.
(class back_threader): New.
(back_threader::back_threader): New.
(back_threader::~back_threader): New.
(back_threader::maybe_register_path): New.
(back_threader::find_taken_edge): New.
(back_threader::find_taken_edge_switch): New.
(back_threader::find_taken_edge_cond): New.
(back_threader::resolve_def): New.
(back_threader::resolve_phi): New.
(back_threader::find_paths_to_names): New.
(back_threader::find_paths): New.
(dump_path): New.
(debug): New.
(thread_jumps::find_jump_threads_backwards): Call ranger threader.
(thread_jumps::find_jump_threads_backwards_with_ranger): New.
(pass_thread_jumps::execute): Abstract out code...
(try_thread_blocks): ...here.
* tree-ssa-threadedge.c (jump_threader::thread_outgoing_edges):
Abstract out threading candidate code to...
(single_succ_to_potentially_threadable_block): ...here.
* tree-ssa-threadedge.h (single_succ_to_potentially_threadable_block):
New.
* tree-ssa-threadupdate.c (register_jump_thread): Return boolean.
* tree-ssa-threadupdate.h (class jump_thread_path_registry):
Return bool from register_jump_thread.
libgomp/ChangeLog:
* testsuite/libgomp.graphite/force-parallel-4.c: Adjust for
threader.
* testsuite/libgomp.graphite/force-parallel-8.c: Same.
gcc/testsuite/ChangeLog:
* g++.dg/debug/dwarf2/deallocator.C: Adjust for threader.
* gcc.c-torture/compile/pr83510.c: Same.
* dg.dg/analyzer/pr94851-2.c: Same.
* gcc.dg/loop-unswitch-2.c: Same.
* gcc.dg/old-style-asm-1.c: Same.
* gcc.dg/pr68317.c: Same.
* gcc.dg/pr97567-2.c: Same.
* gcc.dg/predict-9.c: Same.
* gcc.dg/shrink-wrap-loop.c: Same.
* gcc.dg/sibcall-1.c: Same.
* gcc.dg/tree-ssa/builtin-sprintf-3.c: Same.
* gcc.dg/tree-ssa/pr21001.c: Same.
* gcc.dg/tree-ssa/pr21294.c: Same.
* gcc.dg/tree-ssa/pr21417.c: Same.
* gcc.dg/tree-ssa/pr21458-2.c: Same.
* gcc.dg/tree-ssa/pr21563.c: Same.
* gcc.dg/tree-ssa/pr49039.c: Same.
* gcc.dg/tree-ssa/pr61839_1.c: Same.
* gcc.dg/tree-ssa/pr61839_3.c: Same.
* gcc.dg/tree-ssa/pr77445-2.c: Same.
* gcc.dg/tree-ssa/split-path-4.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-11.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-12.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-14.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-18.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-6.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-7.c: Same.
* gcc.dg/tree-ssa/ssa-fre-48.c: Same.
* gcc.dg/tree-ssa/ssa-thread-11.c: Same.
* gcc.dg/tree-ssa/ssa-thread-12.c: Same.
* gcc.dg/tree-ssa/ssa-thread-14.c: Same.
* gcc.dg/tree-ssa/vrp02.c: Same.
* gcc.dg/tree-ssa/vrp03.c: Same.
* gcc.dg/tree-ssa/vrp05.c: Same.
* gcc.dg/tree-ssa/vrp06.c: Same.
* gcc.dg/tree-ssa/vrp07.c: Same.
* gcc.dg/tree-ssa/vrp09.c: Same.
* gcc.dg/tree-ssa/vrp19.c: Same.
* gcc.dg/tree-ssa/vrp20.c: Same.
* gcc.dg/tree-ssa/vrp33.c: Same.
* gcc.dg/uninit-pred-9_b.c: Same.
* gcc.dg/uninit-pr61112.c: Same.
* gcc.dg/vect/bb-slp-16.c: Same.
* gcc.target/i386/avx2-vect-aggressive.c: Same.
* gcc.dg/tree-ssa/ranger-threader-1.c: New test.
* gcc.dg/tree-ssa/ranger-threader-2.c: New test.
* gcc.dg/tree-ssa/ranger-threader-3.c: New test.
* gcc.dg/tree-ssa/ranger-threader-4.c: New test.
* gcc.dg/tree-ssa/ranger-threader-5.c: New test.
</cut>
Results regressed to (for first_bad == 2e96b5f14e4025691b57d2301d71aa6092ed44bc)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2_marm artifacts/build-2e96b5f14e4025691b57d2301d71aa6092ed44bc/results_id:
1
# 445.gobmk,gobmk_base.default regressed by 103
# 445.gobmk,[.] fastlib regressed by 128
# 445.gobmk,[.] incremental_order_moves regressed by 127
from (for last_good == e63d76234d18cac731c4f3610d513bd8b39b5520)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2_marm artifacts/build-e63d76234d18cac731c4f3610d513bd8b39b5520/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of last_good: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O2/2943
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of first_bad: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O2/2932
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-2e96b5f14e4025691b57d2301d71aa6092ed44bc
cd investigate-gcc-2e96b5f14e4025691b57d2301d71aa6092ed44bc
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 2e96b5f14e4025691b57d2301d71aa6092ed44bc
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach e63d76234d18cac731c4f3610d513bd8b39b5520
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Full commit (up to 1000 lines):
<cut>
commit 2e96b5f14e4025691b57d2301d71aa6092ed44bc
Author: Aldy Hernandez <aldyh(a)redhat.com>
Date: Tue Jun 15 12:32:51 2021 +0200
Backwards jump threader rewrite with ranger.
This is a rewrite of the backwards threader with a ranger based solver.
The code is divided into two parts: the path solver in
gimple-range-path.*, and the path discovery bits in
tree-ssa-threadbackward.c.
The legacy code is still available with --param=threader-mode=legacy,
but will be removed shortly after.
gcc/ChangeLog:
* Makefile.in (tree-ssa-loop-im.o-warn): New.
* flag-types.h (enum threader_mode): New.
* params.opt: Add entry for --param=threader-mode.
* tree-ssa-threadbackward.c (THREADER_ITERATIVE_MODE): New.
(class back_threader): New.
(back_threader::back_threader): New.
(back_threader::~back_threader): New.
(back_threader::maybe_register_path): New.
(back_threader::find_taken_edge): New.
(back_threader::find_taken_edge_switch): New.
(back_threader::find_taken_edge_cond): New.
(back_threader::resolve_def): New.
(back_threader::resolve_phi): New.
(back_threader::find_paths_to_names): New.
(back_threader::find_paths): New.
(dump_path): New.
(debug): New.
(thread_jumps::find_jump_threads_backwards): Call ranger threader.
(thread_jumps::find_jump_threads_backwards_with_ranger): New.
(pass_thread_jumps::execute): Abstract out code...
(try_thread_blocks): ...here.
* tree-ssa-threadedge.c (jump_threader::thread_outgoing_edges):
Abstract out threading candidate code to...
(single_succ_to_potentially_threadable_block): ...here.
* tree-ssa-threadedge.h (single_succ_to_potentially_threadable_block):
New.
* tree-ssa-threadupdate.c (register_jump_thread): Return boolean.
* tree-ssa-threadupdate.h (class jump_thread_path_registry):
Return bool from register_jump_thread.
libgomp/ChangeLog:
* testsuite/libgomp.graphite/force-parallel-4.c: Adjust for
threader.
* testsuite/libgomp.graphite/force-parallel-8.c: Same.
gcc/testsuite/ChangeLog:
* g++.dg/debug/dwarf2/deallocator.C: Adjust for threader.
* gcc.c-torture/compile/pr83510.c: Same.
* dg.dg/analyzer/pr94851-2.c: Same.
* gcc.dg/loop-unswitch-2.c: Same.
* gcc.dg/old-style-asm-1.c: Same.
* gcc.dg/pr68317.c: Same.
* gcc.dg/pr97567-2.c: Same.
* gcc.dg/predict-9.c: Same.
* gcc.dg/shrink-wrap-loop.c: Same.
* gcc.dg/sibcall-1.c: Same.
* gcc.dg/tree-ssa/builtin-sprintf-3.c: Same.
* gcc.dg/tree-ssa/pr21001.c: Same.
* gcc.dg/tree-ssa/pr21294.c: Same.
* gcc.dg/tree-ssa/pr21417.c: Same.
* gcc.dg/tree-ssa/pr21458-2.c: Same.
* gcc.dg/tree-ssa/pr21563.c: Same.
* gcc.dg/tree-ssa/pr49039.c: Same.
* gcc.dg/tree-ssa/pr61839_1.c: Same.
* gcc.dg/tree-ssa/pr61839_3.c: Same.
* gcc.dg/tree-ssa/pr77445-2.c: Same.
* gcc.dg/tree-ssa/split-path-4.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-11.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-12.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-14.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-18.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-6.c: Same.
* gcc.dg/tree-ssa/ssa-dom-thread-7.c: Same.
* gcc.dg/tree-ssa/ssa-fre-48.c: Same.
* gcc.dg/tree-ssa/ssa-thread-11.c: Same.
* gcc.dg/tree-ssa/ssa-thread-12.c: Same.
* gcc.dg/tree-ssa/ssa-thread-14.c: Same.
* gcc.dg/tree-ssa/vrp02.c: Same.
* gcc.dg/tree-ssa/vrp03.c: Same.
* gcc.dg/tree-ssa/vrp05.c: Same.
* gcc.dg/tree-ssa/vrp06.c: Same.
* gcc.dg/tree-ssa/vrp07.c: Same.
* gcc.dg/tree-ssa/vrp09.c: Same.
* gcc.dg/tree-ssa/vrp19.c: Same.
* gcc.dg/tree-ssa/vrp20.c: Same.
* gcc.dg/tree-ssa/vrp33.c: Same.
* gcc.dg/uninit-pred-9_b.c: Same.
* gcc.dg/uninit-pr61112.c: Same.
* gcc.dg/vect/bb-slp-16.c: Same.
* gcc.target/i386/avx2-vect-aggressive.c: Same.
* gcc.dg/tree-ssa/ranger-threader-1.c: New test.
* gcc.dg/tree-ssa/ranger-threader-2.c: New test.
* gcc.dg/tree-ssa/ranger-threader-3.c: New test.
* gcc.dg/tree-ssa/ranger-threader-4.c: New test.
* gcc.dg/tree-ssa/ranger-threader-5.c: New test.
---
gcc/flag-types.h | 7 +
gcc/params.opt | 17 +
gcc/testsuite/g++.dg/debug/dwarf2/deallocator.C | 3 +-
gcc/testsuite/gcc.c-torture/compile/pr83510.c | 33 ++
gcc/testsuite/gcc.dg/analyzer/pr94851-2.c | 2 +-
gcc/testsuite/gcc.dg/loop-unswitch-2.c | 2 +-
gcc/testsuite/gcc.dg/old-style-asm-1.c | 5 +-
gcc/testsuite/gcc.dg/pr68317.c | 4 +-
gcc/testsuite/gcc.dg/pr97567-2.c | 2 +-
gcc/testsuite/gcc.dg/predict-9.c | 4 +-
gcc/testsuite/gcc.dg/shrink-wrap-loop.c | 53 +++
gcc/testsuite/gcc.dg/sibcall-1.c | 10 +
gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-3.c | 25 +-
gcc/testsuite/gcc.dg/tree-ssa/pr21001.c | 1 +
gcc/testsuite/gcc.dg/tree-ssa/pr21294.c | 1 +
gcc/testsuite/gcc.dg/tree-ssa/pr21417.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr21458-2.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr21563.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr49039.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr61839_1.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr61839_3.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-1.c | 20 +
gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-2.c | 39 ++
gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-3.c | 41 ++
gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-4.c | 83 ++++
gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-5.c | 80 ++++
gcc/testsuite/gcc.dg/tree-ssa/split-path-4.c | 4 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-11.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-12.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-14.c | 1 +
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c | 5 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c | 4 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c | 1 +
gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-48.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c | 1 +
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-14.c | 1 +
gcc/testsuite/gcc.dg/tree-ssa/vrp02.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp03.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp05.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp06.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp07.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp09.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp19.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp20.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/vrp33.c | 2 +-
gcc/testsuite/gcc.dg/uninit-pr61112.c | 6 +-
gcc/testsuite/gcc.dg/uninit-pred-9_b.c | 1 +
gcc/testsuite/gcc.dg/vect/bb-slp-16.c | 7 +
.../gcc.target/i386/avx2-vect-aggressive.c | 2 +-
gcc/tree-ssa-threadbackward.c | 476 ++++++++++++++++++++-
gcc/tree-ssa-threadedge.c | 20 +-
gcc/tree-ssa-threadedge.h | 1 +
gcc/tree-ssa-threadupdate.c | 12 +-
gcc/tree-ssa-threadupdate.h | 2 +-
.../testsuite/libgomp.graphite/force-parallel-4.c | 1 +
.../testsuite/libgomp.graphite/force-parallel-8.c | 2 +
58 files changed, 962 insertions(+), 57 deletions(-)
diff --git a/gcc/flag-types.h b/gcc/flag-types.h
index e43d1de490d..e39673f6716 100644
--- a/gcc/flag-types.h
+++ b/gcc/flag-types.h
@@ -454,6 +454,13 @@ enum evrp_mode
EVRP_MODE_RVRP_DEBUG = EVRP_MODE_RVRP_ONLY | EVRP_MODE_DEBUG
};
+/* Backwards threader mode. */
+enum threader_mode
+{
+ THREADER_MODE_LEGACY = 0,
+ THREADER_MODE_RANGER = 1
+};
+
/* Modes of OpenACC 'kernels' constructs handling. */
enum openacc_kernels
{
diff --git a/gcc/params.opt b/gcc/params.opt
index 92b003e38cb..f1f47b44215 100644
--- a/gcc/params.opt
+++ b/gcc/params.opt
@@ -1010,6 +1010,23 @@ Maximum depth of DFS walk used by modref escape analysis.
Common Joined UInteger Var(param_modref_max_escape_points) Init(256) Param Optimization
Maximum number of escape points tracked by modref per SSA-name.
+-param=threader-iterative=
+Common Joined UInteger Var(param_threader_iterative) Init(0) Param Optimization
+Run backwards threader in iterative mode.
+
+-param=threader-mode=
+Common Joined Var(param_threader_mode) Enum(threader_mode) Init(THREADER_MODE_RANGER) Param Optimization
+--param=threader-mode=[legacy|ranger] Specifies the mode the backwards threader should run in.
+
+Enum
+Name(threader_mode) Type(enum threader_mode) UnknownError(unknown threader mode %qs)
+
+EnumValue
+Enum(threader_mode) String(legacy) Value(THREADER_MODE_LEGACY)
+
+EnumValue
+Enum(threader_mode) String(ranger) Value(THREADER_MODE_RANGER)
+
-param=tm-max-aggregate-size=
Common Joined UInteger Var(param_tm_max_aggregate_size) Init(9) Param Optimization
Size in bytes after which thread-local aggregates should be instrumented with the logging functions instead of save/restore pairs.
diff --git a/gcc/testsuite/g++.dg/debug/dwarf2/deallocator.C b/gcc/testsuite/g++.dg/debug/dwarf2/deallocator.C
index d895e78e608..c1d387922ba 100644
--- a/gcc/testsuite/g++.dg/debug/dwarf2/deallocator.C
+++ b/gcc/testsuite/g++.dg/debug/dwarf2/deallocator.C
@@ -29,7 +29,7 @@ void foo(int i)
return;
}
}
- if (i)
+ if (i) // Threader makes everything after here disappear.
{
t test;
if (i == 10)
@@ -42,5 +42,4 @@ void foo(int i)
}
// { dg-final { scan-assembler "deallocator.C:29" } }
// { dg-final { scan-assembler "deallocator.C:24" } }
-// { dg-final { scan-assembler "deallocator.C:34" } }
// { dg-final { scan-assembler "deallocator.C:21" } }
diff --git a/gcc/testsuite/gcc.c-torture/compile/pr83510.c b/gcc/testsuite/gcc.c-torture/compile/pr83510.c
index 907dd80ccd7..fc932e57f3a 100644
--- a/gcc/testsuite/gcc.c-torture/compile/pr83510.c
+++ b/gcc/testsuite/gcc.c-torture/compile/pr83510.c
@@ -3,6 +3,39 @@
(PR tree-optimization/83510). */
/* { dg-options "-Warray-bounds" } */
+/* { dg-xfail-if "" { "*-*-*" } { "-Os" } } */
+
+
+/* This test is XFAILed because thread1 threads a switch statement
+ such that the various cases have been split into different
+ independent blocks. One of these blocks exposes an arr[i_27]
+ which is later propagated by VRP to be arr[10]. This is an
+ invalid access, but the array bounds code doesn't know it is an
+ unreachable path.
+
+ However, it is not until dom2 that we "know" that the value of the
+ switch index is such that the path to arr[10] is unreachable. For
+ that matter, it is not until dom3 that we remove the unreachable
+ path.
+
+
+ See:
+ https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83510
+ https://gcc.gnu.org/bugzilla/show_bug.cgi?id=83312
+
+ It's not until here that ranger "knows" that the path is
+ unreachable:
+
+ thread1
+ vrp1 <-- array bounds checking
+ dce2
+ stdarg
+ cdce
+ cselim
+ copyprop
+ ifcombine
+ mergephi3 <-- too late
+*/
extern int get_flag (void);
diff --git a/gcc/testsuite/gcc.dg/analyzer/pr94851-2.c b/gcc/testsuite/gcc.dg/analyzer/pr94851-2.c
index b837451b27a..0acf48810c1 100644
--- a/gcc/testsuite/gcc.dg/analyzer/pr94851-2.c
+++ b/gcc/testsuite/gcc.dg/analyzer/pr94851-2.c
@@ -45,7 +45,7 @@ int pamark(void) {
if (curbp->b_amark == (AMARK *)NULL)
curbp->b_amark = p;
else
- last->m_next = p; /* { dg-warning "dereference of NULL 'last'" } */
+ last->m_next = p; /* { dg-warning "dereference of NULL 'last'" "deref" { xfail *-*-* } } */
}
p->m_name = (char)c; /* { dg-bogus "leak of 'p'" "bogus leak" } */
diff --git a/gcc/testsuite/gcc.dg/loop-unswitch-2.c b/gcc/testsuite/gcc.dg/loop-unswitch-2.c
index f8d314e34de..0931f6e71c3 100644
--- a/gcc/testsuite/gcc.dg/loop-unswitch-2.c
+++ b/gcc/testsuite/gcc.dg/loop-unswitch-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -funswitch-loops -fdump-tree-unswitch-details" } */
+/* { dg-options "-O2 -funswitch-loops -fdump-tree-unswitch-details -fdisable-tree-thread2 -fdisable-tree-thread3" } */
void foo (float **a, float **b, float *c, int n, int m, int l)
{
diff --git a/gcc/testsuite/gcc.dg/old-style-asm-1.c b/gcc/testsuite/gcc.dg/old-style-asm-1.c
index 8af007795a7..f9406ff0a26 100644
--- a/gcc/testsuite/gcc.dg/old-style-asm-1.c
+++ b/gcc/testsuite/gcc.dg/old-style-asm-1.c
@@ -1,6 +1,9 @@
/* PR inline-asm/8832 */
/* { dg-do compile } */
-/* { dg-options "-O2 -dP" } */
+/* { dg-options "-O2 -dP -fdisable-tree-ethread -fdisable-tree-thread1 -fdisable-tree-thread2 -fdisable-tree-thread3 -fdisable-tree-thread4" } */
+
+/* Note: Threader will duplicate BBs and replace one conditional branch by an
+ unconditional one. */
/* Verify that GCC doesn't optimize
old style asm instructions. */
diff --git a/gcc/testsuite/gcc.dg/pr68317.c b/gcc/testsuite/gcc.dg/pr68317.c
index 891d12954ba..bd053a7522b 100644
--- a/gcc/testsuite/gcc.dg/pr68317.c
+++ b/gcc/testsuite/gcc.dg/pr68317.c
@@ -1,5 +1,7 @@
/* { dg-do compile } */
-/* { dg-options "-O2" } */
+/* { dg-options "-O2 -fdisable-tree-ethread" } */
+
+/* Note: Threader will collapse loop. */
typedef int int32_t __attribute__((mode (__SI__)));
diff --git a/gcc/testsuite/gcc.dg/pr97567-2.c b/gcc/testsuite/gcc.dg/pr97567-2.c
index dee31c6dc01..c3ead54eaa8 100644
--- a/gcc/testsuite/gcc.dg/pr97567-2.c
+++ b/gcc/testsuite/gcc.dg/pr97567-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile} */
-/* { dg-options "-O2 -fdump-tree-evrp" } */
+/* { dg-options "-O2 -fdump-tree-evrp -fdisable-tree-ethread" } */
char a[2];
diff --git a/gcc/testsuite/gcc.dg/predict-9.c b/gcc/testsuite/gcc.dg/predict-9.c
index f491c511bd9..cb68a218a93 100644
--- a/gcc/testsuite/gcc.dg/predict-9.c
+++ b/gcc/testsuite/gcc.dg/predict-9.c
@@ -1,5 +1,7 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-profile_estimate -fno-finite-loops" } */
+/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-profile_estimate -fno-finite-loops -fdisable-tree-ethread" } */
+
+/* Note: Threader causes removal of for loop. */
extern int global;
extern int global2;
diff --git a/gcc/testsuite/gcc.dg/shrink-wrap-loop.c b/gcc/testsuite/gcc.dg/shrink-wrap-loop.c
index 52dfc2790ed..ba872fa23f6 100644
--- a/gcc/testsuite/gcc.dg/shrink-wrap-loop.c
+++ b/gcc/testsuite/gcc.dg/shrink-wrap-loop.c
@@ -1,5 +1,58 @@
/* { dg-do compile { target { { { i?86-*-* x86_64-*-* } && lp64 } || { arm_thumb2 } } } } */
/* { dg-options "-O2 -fdump-rtl-pro_and_epilogue" } */
+// { dg-additional-options "-fdisable-tree-ethread" }
+
+/*
+Our new threader is threading things a bit too early, and causing the
+testcase in gcc.dg/shrink-wrap-loop.c to fail.
+
+ The gist is this BB inside a loop:
+
+ <bb 6> :
+ # p_2 = PHI <p2_6(D)(2), p_12(5)>
+ if (p_2 != 0B)
+ goto <bb 3>; [INV]
+ else
+ goto <bb 7>; [INV]
+
+Our threader can move this check outside of the loop (good). This is
+done before branch probabilities are calculated and causes the probs
+to be calculated as:
+
+<bb 2> [local count: 216361238]:
+ if (p2_6(D) != 0B)
+ goto <bb 7>; [54.59%]
+ else
+ goto <bb 6>; [45.41%]
+
+Logically this seems correct to me. A simple check outside of a loop
+should slightly but not overwhelmingly favor a non-zero value.
+
+Interestingly however, the old threader couldn't get this, but the IL
+ended up identical, albeit with different probabilities. What happens
+is that, because the old code could not thread this, the p2 != 0 check
+would remain inside the loop and probs would be calculated thusly:
+
+ <bb 6> [local count: 1073741824]:
+ # p_2 = PHI <p2_6(D)(2), p_12(5)>
+ if (p_2 != 0B)
+ goto <bb 3>; [94.50%]
+ else
+ goto <bb 7>; [5.50%]
+
+Then when the loop header copying pass ("ch") shuffled things around,
+the IL would end up identical to my early threader code, but with the
+probabilities would remain as 94.5/5.5.
+
+The above discrepancy causes the RTL ifcvt pass to generate different
+code, and by the time we get to the shrink wrapping pass, things look
+sufficiently different such that the legacy code can actually shrink
+wrap, whereas our new code does not.
+
+IMO, if the loop-ch pass moves conditionals outside of a loop, the
+probabilities should be adjusted, but that does mean the shrink wrap
+won't happen for this contrived testcase.
+ */
int foo (int *p1, int *p2);
diff --git a/gcc/testsuite/gcc.dg/sibcall-1.c b/gcc/testsuite/gcc.dg/sibcall-1.c
index e8a95513d9e..367ee4374e1 100644
--- a/gcc/testsuite/gcc.dg/sibcall-1.c
+++ b/gcc/testsuite/gcc.dg/sibcall-1.c
@@ -7,6 +7,9 @@
/* { dg-do run } */
/* { dg-options "-O2 -foptimize-sibling-calls" } */
+/* See note in recurser_void() as to why we disable threading. */
+/* { dg-additional-options "-fdisable-tree-thread1" } */
+
/* The option -foptimize-sibling-calls is the default, but serves as
marker. Self-recursion tail calls are optimized for all targets,
regardless of presence of sibcall patterns. */
@@ -26,6 +29,13 @@ int main ()
void
recurser_void (int n)
{
+ /* In some architectures like ppc64*, jump threading may thread
+ paths such that there are two calls into track(), one for
+ track(0) and one for track(7). The track(7) call can be
+ transformed into a jump instead of a call, which means that
+ different calls into track() may end up with a different
+ &stackpos. This is the reason we disable jump threading for this
+ test. */
if (n == 0 || n == 7)
track (n);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-3.c b/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-3.c
index fae2a1b73ea..ec55f267318 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-3.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/builtin-sprintf-3.c
@@ -15,7 +15,7 @@ extern void string_lt_0_fail ();
extern void string_eq_0_fail ();
extern void string_gt_0_fail ();
-void test_string (char *d, const char *s)
+void test_string_eq_min (char *d, const char *s)
{
int n = __builtin_sprintf (d, "%-s", s);
@@ -23,13 +23,36 @@ void test_string (char *d, const char *s)
or INT_MAX. (This is a white box test based on knowing that
the optimization computes its own values of the two constants.) */
if (n == INT_MIN) string_eq_min_fail ();
+}
+
+void test_string_eq_max (char *d, const char *s)
+{
+ int n = __builtin_sprintf (d, "%-s", s);
+
if (n == INT_MAX) string_eq_max_fail ();
+}
+
+void test_string_lt_0 (char *d, const char *s)
+{
+ int n = __builtin_sprintf (d, "%-s", s);
/* The return value could be negative when strlen(s) is in excess
of 4095 (the maximum number of bytes a single directive is required
to handle). */
if (n < 0) string_lt_0_fail ();
+}
+
+void test_string_eq_0 (char *d, const char *s)
+{
+ int n = __builtin_sprintf (d, "%-s", s);
+
if (n == 0) string_eq_0_fail ();
+}
+
+void test_string_gt_0 (char *d, const char *s)
+{
+ int n = __builtin_sprintf (d, "%-s", s);
+
if (n > 0) string_gt_0_fail ();
}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21001.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21001.c
index 719360a015f..4ea5f21addf 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21001.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21001.c
@@ -6,6 +6,7 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fno-tree-dominator-opts -fno-tree-fre -fdisable-tree-evrp -fdump-tree-vrp1-details" } */
+/* { dg-additional-options "-fdisable-tree-ethread -fdisable-tree-thread1" } */
int
foo (int a)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21294.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21294.c
index cc7d4cdf338..b9edabc6234 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21294.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21294.c
@@ -5,6 +5,7 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fno-tree-dominator-opts -fdisable-tree-evrp -fdump-tree-vrp1-details" } */
+/* { dg-additional-options "-fdisable-tree-ethread -fdisable-tree-thread1" } */
struct f {
int i;
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21417.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21417.c
index 484511978a1..fc14af4e662 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21417.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21417.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-thread4-details" } */
+/* { dg-options "-O2 -fdisable-tree-thread3 -fdump-tree-thread4-details" } */
struct tree_common
{
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21458-2.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21458-2.c
index 2aee42f4c05..f8d7353fc0e 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21458-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21458-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-evrp-details" } */
+/* { dg-options "-O2 -fdump-tree-evrp-details -fdisable-tree-ethread" } */
extern void g (void);
extern void bar (int);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr21563.c b/gcc/testsuite/gcc.dg/tree-ssa/pr21563.c
index 9c67a3acb46..72dce83ce37 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr21563.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr21563.c
@@ -2,7 +2,7 @@
Make sure VRP folds the second "if" statement. */
/* { dg-do compile } */
-/* { dg-options "-O2 -fno-tree-dominator-opts -fdisable-tree-evrp -fdump-tree-vrp1-details" } */
+/* { dg-options "-O2 -fno-tree-dominator-opts -fdisable-tree-evrp -fdump-tree-vrp1-details -fdisable-tree-ethread -fdisable-tree-thread1" } */
int
foo (int a)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr49039.c b/gcc/testsuite/gcc.dg/tree-ssa/pr49039.c
index 4bc0a8175a0..a2044d012cc 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr49039.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr49039.c
@@ -1,6 +1,6 @@
/* PR tree-optimization/49039 */
/* { dg-do compile } */
-/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-vrp1" } */
+/* { dg-options "-O2 -fdisable-tree-evrp -fdump-tree-vrp1 -fdisable-tree-ethread -fdisable-tree-thread1" } */
extern void bar (void);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr61839_1.c b/gcc/testsuite/gcc.dg/tree-ssa/pr61839_1.c
index d44c7dc1882..ddc53fbfbcc 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr61839_1.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr61839_1.c
@@ -1,6 +1,6 @@
/* PR tree-optimization/61839. */
/* { dg-do run } */
-/* { dg-options "-O2 -fdump-tree-vrp1 -fdisable-tree-evrp -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fdump-tree-vrp1 -fdisable-tree-evrp -fdump-tree-optimized -fdisable-tree-ethread -fdisable-tree-thread1" } */
/* { dg-require-effective-target int32plus } */
__attribute__ ((noinline))
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr61839_3.c b/gcc/testsuite/gcc.dg/tree-ssa/pr61839_3.c
index 5ceb0738bde..cc322d6e703 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr61839_3.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr61839_3.c
@@ -1,6 +1,6 @@
/* PR tree-optimization/61839. */
/* { dg-do run } */
-/* { dg-options "-O2 -fdump-tree-vrp1 -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fdump-tree-vrp1 -fdump-tree-optimized -fdisable-tree-ethread -fdisable-tree-thread1" } */
__attribute__ ((noinline))
int foo (int a, unsigned b)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c b/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
index cf74e156109..f9fc212f49e 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/pr77445-2.c
@@ -124,7 +124,7 @@ enum STATES FMS( u8 **in , u32 *transitions) {
to change decisions in switch expansion which in turn can expose new
jump threading opportunities. Skip the later tests on aarch64. */
/* { dg-final { scan-tree-dump "Jumps threaded: 1\[1-9\]" "thread1" } } */
-/* { dg-final { scan-tree-dump-times "Invalid sum" 3 "thread1" } } */
+/* { dg-final { scan-tree-dump-times "Invalid sum" 4 "thread1" } } */
/* { dg-final { scan-tree-dump-not "optimizing for size" "thread1" } } */
/* { dg-final { scan-tree-dump-not "optimizing for size" "thread2" } } */
/* { dg-final { scan-tree-dump-not "optimizing for size" "thread3" { target { ! aarch64*-*-* } } } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-1.c b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-1.c
new file mode 100644
index 00000000000..c3ccb5d5b7e
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-1.c
@@ -0,0 +1,20 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-thread1-details --param logical-op-non-short-circuit=1" } */
+
+// Copied from ssa-dom-thread-11.c
+
+static int *bb_ticks;
+extern void frob (void);
+void
+mark_target_live_regs (int b, int block, int bb_tick)
+{
+ if (b == block && b != -1 && bb_tick == bb_ticks[b])
+ return;
+ if (b != -1)
+ frob ();
+}
+
+/* When the first two conditionals in the first IF are true, but
+ the third conditional is false, then there's a jump threading
+ opportunity to bypass the second IF statement. */
+/* { dg-final { scan-tree-dump-times "Registering.*jump thread" 1 "thread1"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-2.c b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-2.c
new file mode 100644
index 00000000000..d2689b6c788
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-2.c
@@ -0,0 +1,39 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-thread2-details -w" } */
+
+// Copied from ssa-dom-thread-12.c.
+
+typedef long unsigned int size_t;
+union tree_node;
+typedef union tree_node *tree;
+typedef union gimple_statement_d *gimple;
+typedef const union gimple_statement_d *const_gimple;
+union gimple_statement_d
+{
+ unsigned num_ops;
+ tree exp;
+};
+
+unsigned int x;
+static inline tree
+gimple_op (const_gimple gs, unsigned i)
+{
+ if (!(i < gs->num_ops))
+ abort ();
+ return gs->exp;
+}
+
+unsigned char
+scan_function (gimple stmt)
+{
+ unsigned i;
+ for (i = 0; i < stmt->num_ops - 3 ; i++)
+ gimple_call_arg (stmt, i);
+ gimple_op (stmt, 1);
+}
+
+/* The test which bypasses the loop is simplified prior to DOM to check
+ that stmt->num_ops - 3 != 0. When that test is false, we can derive
+ a value for stmt->num_ops. That in turn allows us to thread the jump
+ for the conditional at the start of the call to gimple_op. */
+/* { dg-final { scan-tree-dump-times "Registering.*jump thread" 1 "thread2"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-3.c b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-3.c
new file mode 100644
index 00000000000..79ec067e68a
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-3.c
@@ -0,0 +1,41 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fdump-tree-ethread-details -w --param logical-op-non-short-circuit=1" } */
+
+// Copied from ssa-dom-thread-14.c
+
+enum optab_methods
+{
+ OPTAB_DIRECT,
+ OPTAB_LIB,
+ OPTAB_WIDEN,
+ OPTAB_LIB_WIDEN,
+ OPTAB_MUST_WIDEN
+};
+struct optab_d { };
+typedef struct optab_d *optab;
+void
+expand_shift_1 (int code, int unsignedp, int rotate,
+ optab lshift_optab, optab rshift_arith_optab)
+{
+ int left = (code == 42 || code == 0xde);
+ int attempt;
+ enum optab_methods methods;
+ if (attempt == 0)
+ methods = OPTAB_DIRECT;
+ else if (attempt == 1)
+ methods = OPTAB_WIDEN;
+ if ((!unsignedp || (!left && methods == OPTAB_WIDEN)))
+ {
+ enum optab_methods methods1 = methods;
+ if (unsignedp)
+ methods1 = OPTAB_MUST_WIDEN;
+ expand_binop (left ? lshift_optab : rshift_arith_optab,
+ unsignedp, methods1);
+ }
+}
+
+/* When UNSIGNEDP is true, LEFT is false and METHOD == OPTAB_WIDEN
+ we will enter the TRUE arm of the conditional and we can thread
+ the test to compute the first first argument of the expand_binop
+ call if we look backwards through the boolean logicals. */
+/* { dg-final { scan-tree-dump-times "Registering.*jump thread" 1 "ethread"} } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-4.c b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-4.c
new file mode 100644
index 00000000000..e8d1cfc03ac
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-4.c
@@ -0,0 +1,83 @@
+/* { dg-do compile } */
+/* { dg-additional-options "-O2 -fdump-tree-vrp-details -fdump-tree-thread1-details --param logical-op-non-short-circuit=1" } */
+/* { dg-final { scan-tree-dump-times "Registering FSM jump" 8 "thread1" } } */
+
+/* Copied from ssa-thread-14. */
+
+void foo (void);
+void bar (void);
+void blah (void);
+
+/* One jump threaded here. */
+
+void
+baz_1 (int a, int b, int c)
+{
+ if (a && b)
+ foo ();
+ if (!b && c)
+ bar ();
+}
+
+/* One jump threaded here. */
+
+void
+baz_2 (int a, int b, int c)
+{
+ if (a && b)
+ foo ();
+ if (b || c)
+ bar ();
+}
+
+/* One jump threaded here. */
+
+void
+baz_3 (int a, int b, int c)
+{
+ if (a && b > 10)
+ foo ();
+ if (b < 5 && c)
+ bar ();
+}
+
+/* Two jumps threaded here. */
+
+void
+baz_4 (int a, int b, int c)
+{
+ if (a && b)
+ {
+ foo ();
+ if (c)
+ bar ();
+ }
+ if (b && c)
+ blah ();
+}
+
+/* Two jumps threaded here. */
+
+void
+baz_5 (int a, int b, int c)
+{
+ if (a && b)
+ {
+ foo ();
+ if (c)
+ bar ();
+ }
+ if (!b || !c)
+ blah ();
+}
+
+/* One jump threaded here. */
+
+void
+baz_6 (int a, int b, int c)
+{
+ if (a == 39 && b == 41)
+ foo ();
+ if (c == 12 || b == 41)
+ bar ();
+}
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-5.c b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-5.c
new file mode 100644
index 00000000000..b7ca99a0152
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ranger-threader-5.c
@@ -0,0 +1,80 @@
+// { dg-do compile }
+// { dg-options "-fgimple -O2 -fdump-tree-thread1-details" }
+
+/* This tests that we can thread BB4->BB999 coming in through the
+ following path:
+
+ latch many insns
+ | |
+ V V
+ 6 -> 7 -> 3 -> 4 -> 999
+
+ The ranger based threader cannot thread this because BB4 has too
+ many instructions so it gives up looking back. However, if we were
+ able to looking further, we would notice that a profitable path
+ passing through the loop latch (BB7) exists.
+
+ That is, 3->4->N in isolation is not profitable, but 6->7->3->4->N is.
+
+ It is not clear whether handling this case in the backwards
+ threader is profitable, as it would increase the search space
+ considerably. The test is being added to note a regression from
+ the old backward threader code.
+
+ This test has been distilled from libphobos/src/std/net/isemail.d.
+
+ The ranger threader stops at the 3->4 subpath with: "did not thread
+ around loop and would copy too many statements". */
+
+
+extern void bar();
+extern int random();
+
+int __GIMPLE (ssa,startwith("thread1"))
+foo (int key)
+{
+ int context;
+ int _1454;
+
+ __BB(2):
+ goto __BB3;
+
+ // Loop header.
+ __BB(3):
+ context_448 = __PHI (__BB2: 0, __BB7: context_450);
+ if (key_5(D) > 0)
+ goto __BB999;
+ else
+ goto __BB4;
+
+ __BB(4):
+ bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar();
+ bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar();
+ bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar();
+ bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar();
+ bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar();
+ bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar(); bar();
+ switch (context_448) {default: L5; case 0: L999; }
+
+ __BB(5):
+ L5:
+ goto __BB6;
+
+ __BB(6):
+ context_450 = __PHI (__BB5: 0);
+ _1454 = random ();
+ if (_1454 > 0)
+ goto __BB999;
+ else
+ goto __BB7;
+
+ // Loop latch.
+ __BB(7):
+ goto __BB3;
+
+ __BB(999):
+ L999:
+ return 5;
+}
+
+// { dg-final { scan-tree-dump-times "Registering.*jump thread.*incoming edge; \\(6, 7\\) \\(7, 3\\) \\(3, 4\\) \\(4, 999\\) nocopy" 1 "thread1" { xfail *-*-* } } }
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/split-path-4.c b/gcc/testsuite/gcc.dg/tree-ssa/split-path-4.c
index dac931c18d0..8ef7646282c 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/split-path-4.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/split-path-4.c
@@ -1,5 +1,7 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fsplit-paths -fdump-tree-split-paths-details -w" } */
+/* { dg-options "-O2 -fsplit-paths -fdump-tree-split-paths-details -w -fdisable-tree-thread1 -fdisable-tree-thread2" } */
+
+/* Note: Threader causes the infinite loop in val & 1 sooner. */
powi_cost (long n)
{
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-11.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-11.c
index 5f90613263d..856ab389439 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-11.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-11.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-dom2-details --param logical-op-non-short-circuit=1" } */
+/* { dg-options "-O2 -fdump-tree-dom2-details --param logical-op-non-short-circuit=1 -fdisable-tree-thread1 -fdisable-tree-thread2" } */
static int *bb_ticks;
extern void frob (void);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-12.c
index 63bd12a06a4..bad5e0a782d 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-12.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-12.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-dom2-details -w" } */
+/* { dg-options "-O2 -fdump-tree-dom2-details -w -fdisable-tree-thread2" } */
typedef long unsigned int size_t;
union tree_node;
typedef union tree_node *tree;
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-14.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-14.c
index 4e6a911506e..3bc4b3795cb 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-14.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-14.c
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-dom2-details -w --param logical-op-non-short-circuit=1" } */
+/* { dg-additional-options "-fdisable-tree-thread1 -fdisable-tree-ethread -fdisable-tree-thread2" } */
enum optab_methods
{
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c
index d4759b8903b..03872e7a02f 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-18.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-vrp1-details -fdump-tree-dom2-details -std=gnu89 --param logical-op-non-short-circuit=0" } */
+/* { dg-options "-O2 -fdump-tree-vrp1-details -fdump-tree-thread1-details -std=gnu89 --param logical-op-non-short-circuit=0" } */
#include "ssa-dom-thread-4.c"
@@ -21,4 +21,5 @@
condition.
All the cases are picked up by VRP1 as jump threads. */
-/* { dg-final { scan-tree-dump-times "Threaded" 4 "vrp1" } } */
+/* { dg-final { scan-tree-dump-times "Registering FSM jump" 6 "thread1" } } */
+/* { dg-final { scan-tree-dump-times "Threaded" 2 "vrp1" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
index 16a9ef4e28a..c7bf867b084 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-6.c
@@ -34,8 +34,8 @@
SWITCH_BB -> BBx -> BBy -> BBz -> PHI
We now know the value of the switch index at PHI. */
-/* { dg-final { scan-tree-dump-times "FSM" 6 "thread1" } } */
-/* { dg-final { scan-tree-dump-times "FSM" 1 "thread2" } } */
+/* { dg-final { scan-tree-dump-times "Registering FSM jump" 6 "thread1" } } */
+/* { dg-final { scan-tree-dump-times "Registering FSM jump" 1 "thread2" } } */
int sum0, sum1, sum2, sum3;
int foo (char *s, char **ret)
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
index bad5bc1d003..1c2d12aa9ea 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-dom-thread-7.c
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-thread1-stats -fdump-tree-thread2-stats -fdump-tree-dom2-stats -fdump-tree-thread3-stats -fdump-tree-dom3-stats -fdump-tree-vrp2-stats -fno-guess-branch-probability" } */
+/* { dg-additional-options "--param=threader-mode=legacy" } */
/* Here we have the same issue as was commented in ssa-dom-thread-6.c.
The PHI coming into the threader has a lot more constants, so the
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-48.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-48.c
index b3d610204da..5e74c78e7b0 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-48.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-fre-48.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O -fdump-tree-fre1-details" } */
+/* { dg-options "-O -fdump-tree-fre1-details -fdisable-tree-ethread" } */
int foo (int i)
{
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c
index 67e1e89ecd3..672a54e07db 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-11.c
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-options "-O2 -fdump-tree-vrp2-details --param logical-op-non-short-circuit=1" } */
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 20 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit 6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093
Author: Richard Sandiford <richard.sandiford(a)arm.com>
Date: Thu Oct 31 17:16:31 2019 +0000
[AArch64] Fix build for non-default languages
The SVE PCS support broke go, D and Ada because those languages don't
call TARGET_INIT_BUILTINS. We therefore ended up trying to get the
TYPE_MAIN_VARIANT of a null __SVBool_t.
We shouldn't really need to apply TYPE_MAIN_VARIANT there anyway,
since the ABI-defined types are (and need to be) their own main
variants. This patch asserts for that instead.
2019-10-31 Richard Sandiford <richard.sandiford(a)arm.com>
gcc/
* config/aarch64/aarch64-sve-builtins.cc (register_builtin_types):
Assert that the type we store in abi_vector_types is its own
main variant.
(svbool_type_p): Don't apply TYPE_MAIN_VARIANT here.
From-SVN: r277680
</cut>
Results regressed to (for first_bad == 6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093/results_id:
1
# 458.sjeng,[.] setup_attackers regressed by 111
# 458.sjeng,[.] search regressed by 215
from (for last_good == aaa80941e042d18dcd5add6e7bb28cb392767a39)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O2 artifacts/build-aaa80941e042d18dcd5add6e7bb28cb392767a39/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/2854
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/2851
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093
cd investigate-gcc-6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach aaa80941e042d18dcd5add6e7bb28cb392767a39
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit 6ff0cdebb1bc281ba2374f3ecdbe358c4fa74093
Author: Richard Sandiford <richard.sandiford(a)arm.com>
Date: Thu Oct 31 17:16:31 2019 +0000
[AArch64] Fix build for non-default languages
The SVE PCS support broke go, D and Ada because those languages don't
call TARGET_INIT_BUILTINS. We therefore ended up trying to get the
TYPE_MAIN_VARIANT of a null __SVBool_t.
We shouldn't really need to apply TYPE_MAIN_VARIANT there anyway,
since the ABI-defined types are (and need to be) their own main
variants. This patch asserts for that instead.
2019-10-31 Richard Sandiford <richard.sandiford(a)arm.com>
gcc/
* config/aarch64/aarch64-sve-builtins.cc (register_builtin_types):
Assert that the type we store in abi_vector_types is its own
main variant.
(svbool_type_p): Don't apply TYPE_MAIN_VARIANT here.
From-SVN: r277680
---
gcc/ChangeLog | 7 +++++++
gcc/config/aarch64/aarch64-sve-builtins.cc | 4 ++--
2 files changed, 9 insertions(+), 2 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 66b7a142251..affa74cdd25 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,10 @@
+2019-10-31 Richard Sandiford <richard.sandiford(a)arm.com>
+
+ * config/aarch64/aarch64-sve-builtins.cc (register_builtin_types):
+ Assert that the type we store in abi_vector_types is its own
+ main variant.
+ (svbool_type_p): Don't apply TYPE_MAIN_VARIANT here.
+
2019-10-31 Richard Earnshaw <rearnsha(a)arm.com>
* config/arm/arm.c (arm_legitimize_address): Don't form negative offsets
diff --git a/gcc/config/aarch64/aarch64-sve-builtins.cc b/gcc/config/aarch64/aarch64-sve-builtins.cc
index 70d7b1a165d..424f64adfef 100644
--- a/gcc/config/aarch64/aarch64-sve-builtins.cc
+++ b/gcc/config/aarch64/aarch64-sve-builtins.cc
@@ -2993,6 +2993,7 @@ register_builtin_types ()
BITS_PER_SVE_VECTOR));
}
vectype = build_distinct_type_copy (vectype);
+ gcc_assert (vectype == TYPE_MAIN_VARIANT (vectype));
SET_TYPE_STRUCTURAL_EQUALITY (vectype);
TYPE_ARTIFICIAL (vectype) = 1;
abi_vector_types[i] = vectype;
@@ -3235,8 +3236,7 @@ bool
svbool_type_p (const_tree type)
{
tree abi_type = abi_vector_types[VECTOR_TYPE_svbool_t];
- return (type != error_mark_node
- && TYPE_MAIN_VARIANT (type) == TYPE_MAIN_VARIANT (abi_type));
+ return type != error_mark_node && TYPE_MAIN_VARIANT (type) == abi_type;
}
/* If TYPE is a built-in type defined by the SVE ABI, return the mangled name,
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/gnu-release-arm-stable-allyesconfig - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/gnu-release-arm-stable-allyesconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/gnu-release-arm-stable-allyesconfig
Culprit:
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
</cut>
Results regressed to (for first_bad == 341db343768bc44f3512facc464021730d64071c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
19543
# First few build errors in logs:
# 00:19:53 drivers/power/supply/ab8500_fg.c:3061:39: error: ‘np’ undeclared (first use in this function); did you mean ‘up’?
# 00:19:53 make[3]: *** [drivers/power/supply/ab8500_fg.o] Error 1
# 00:21:11 make[2]: *** [drivers/power/supply] Error 2
# 00:21:11 make[1]: *** [drivers/power] Error 2
# 00:28:45 make: *** [drivers] Error 2
from (for last_good == dc72a15859b2e604abb8a4bff123fbac8a0be92a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1:
-5
# build_abe qemu:
-2
# linux_n_obj:
19631
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-341db343768bc44f3512facc464021730d64071c
cd investigate-linux-341db343768bc44f3512facc464021730d64071c
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 341db343768bc44f3512facc464021730d64071c
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dc72a15859b2e604abb8a4bff123fbac8a0be92a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all…
Build log: https://ci.linaro.org/job/tcwg_kernel-gnu-bisect-gnu-release-arm-stable-all…
Full commit (up to 1000 lines):
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/power/supply/ab8500-bm.h | 4 +
drivers/power/supply/ab8500_btemp.c | 118 +++++-------
drivers/power/supply/ab8500_charger.c | 339 +++++++++++++++++++--------------
drivers/power/supply/ab8500_fg.c | 136 +++++++------
drivers/power/supply/abx500_chargalg.c | 116 ++++++-----
5 files changed, 379 insertions(+), 334 deletions(-)
diff --git a/drivers/power/supply/ab8500-bm.h b/drivers/power/supply/ab8500-bm.h
index 41c69a4f2a1f..012595a9d269 100644
--- a/drivers/power/supply/ab8500-bm.h
+++ b/drivers/power/supply/ab8500-bm.h
@@ -730,4 +730,8 @@ int ab8500_bm_of_probe(struct device *dev,
struct device_node *np,
struct abx500_bm_data *bm);
+extern struct platform_driver ab8500_fg_driver;
+extern struct platform_driver ab8500_btemp_driver;
+extern struct platform_driver abx500_chargalg_driver;
+
#endif /* _AB8500_CHARGER_H_ */
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index fdfcd59fc43e..3598b5a748e7 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/slab.h>
@@ -932,26 +933,6 @@ static int __maybe_unused ab8500_btemp_suspend(struct device *dev)
return 0;
}
-static int ab8500_btemp_remove(struct platform_device *pdev)
-{
- struct ab8500_btemp *di = platform_get_drvdata(pdev);
- int i, irq;
-
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
-
- /* Delete the work queue */
- destroy_workqueue(di->btemp_wq);
-
- flush_scheduled_work();
- power_supply_unregister(di->btemp_psy);
-
- return 0;
-}
-
static char *supply_interface[] = {
"ab8500_chargalg",
"ab8500_fg",
@@ -966,6 +947,40 @@ static const struct power_supply_desc ab8500_btemp_desc = {
.external_power_changed = ab8500_btemp_external_power_changed,
};
+static int ab8500_btemp_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for the btemp */
+ di->btemp_wq =
+ alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
+ if (di->btemp_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Kick off periodic temperature measurements */
+ ab8500_btemp_periodic(di, true);
+
+ return 0;
+}
+
+static void ab8500_btemp_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Delete the work queue */
+ destroy_workqueue(di->btemp_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_btemp_component_ops = {
+ .bind = ab8500_btemp_bind,
+ .unbind = ab8500_btemp_unbind,
+};
+
static int ab8500_btemp_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -1011,14 +1026,6 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
psy_cfg.num_supplicants = ARRAY_SIZE(supply_interface);
psy_cfg.drv_data = di;
- /* Create a work queue for the btemp */
- di->btemp_wq =
- alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
- if (di->btemp_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for measuring temperature periodically */
INIT_DEFERRABLE_WORK(&di->btemp_periodic_work,
ab8500_btemp_periodic_work);
@@ -1031,7 +1038,7 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
AB8500_BTEMP_HIGH_TH, &val);
if (ret < 0) {
dev_err(dev, "%s ab8500 read failed\n", __func__);
- goto free_btemp_wq;
+ return ret;
}
switch (val) {
case BTEMP_HIGH_TH_57_0:
@@ -1050,30 +1057,28 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
}
/* Register BTEMP power supply class */
- di->btemp_psy = power_supply_register(dev, &ab8500_btemp_desc,
- &psy_cfg);
+ di->btemp_psy = devm_power_supply_register(dev, &ab8500_btemp_desc,
+ &psy_cfg);
if (IS_ERR(di->btemp_psy)) {
dev_err(dev, "failed to register BTEMP psy\n");
- ret = PTR_ERR(di->btemp_psy);
- goto free_btemp_wq;
+ return PTR_ERR(di->btemp_psy);
}
/* Register interrupts */
for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_btemp_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_btemp_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_btemp_irq[i].name, di);
if (ret) {
dev_err(dev, "failed to request %s IRQ %d: %d\n"
, ab8500_btemp_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_btemp_irq[i].name, irq, ret);
@@ -1081,23 +1086,16 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, di);
- /* Kick off periodic temperature measurements */
- ab8500_btemp_periodic(di, true);
list_add_tail(&di->node, &ab8500_btemp_list);
- return ret;
+ return component_add(dev, &ab8500_btemp_component_ops);
+}
-free_irq:
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_btemp_remove(struct platform_device *pdev)
+{
+ component_del(&pdev->dev, &ab8500_btemp_component_ops);
- power_supply_unregister(di->btemp_psy);
-free_btemp_wq:
- destroy_workqueue(di->btemp_wq);
- return ret;
+ return 0;
}
static SIMPLE_DEV_PM_OPS(ab8500_btemp_pm_ops, ab8500_btemp_suspend, ab8500_btemp_resume);
@@ -1107,7 +1105,7 @@ static const struct of_device_id ab8500_btemp_match[] = {
{ },
};
-static struct platform_driver ab8500_btemp_driver = {
+struct platform_driver ab8500_btemp_driver = {
.probe = ab8500_btemp_probe,
.remove = ab8500_btemp_remove,
.driver = {
@@ -1116,20 +1114,6 @@ static struct platform_driver ab8500_btemp_driver = {
.pm = &ab8500_btemp_pm_ops,
},
};
-
-static int __init ab8500_btemp_init(void)
-{
- return platform_driver_register(&ab8500_btemp_driver);
-}
-
-static void __exit ab8500_btemp_exit(void)
-{
- platform_driver_unregister(&ab8500_btemp_driver);
-}
-
-device_initcall(ab8500_btemp_init);
-module_exit(ab8500_btemp_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski, Arun R Murthy");
MODULE_ALIAS("platform:ab8500-btemp");
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index a9be10eb2c22..af32cfae9f19 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/notifier.h>
@@ -3276,10 +3277,74 @@ static struct notifier_block charger_nb = {
.notifier_call = ab8500_external_charger_prepare,
};
-static int ab8500_charger_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_chargalg",
+ "ab8500_fg",
+ "ab8500_btemp",
+};
+
+static const struct power_supply_desc ab8500_ac_chg_desc = {
+ .name = "ab8500_ac",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = ab8500_charger_ac_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
+ .get_property = ab8500_charger_ac_get_property,
+};
+
+static const struct power_supply_desc ab8500_usb_chg_desc = {
+ .name = "ab8500_usb",
+ .type = POWER_SUPPLY_TYPE_USB,
+ .properties = ab8500_charger_usb_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
+ .get_property = ab8500_charger_usb_get_property,
+};
+
+static int ab8500_charger_bind(struct device *dev)
{
- struct ab8500_charger *di = platform_get_drvdata(pdev);
- int i, irq, ret;
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ch_stat;
+ int ret;
+
+ /* Create a work queue for the charger */
+ di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
+ WQ_MEM_RECLAIM);
+ if (di->charger_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ ch_stat = ab8500_charger_detect_chargers(di, false);
+
+ if (ch_stat & AC_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->ac_charger_attached_work,
+ HZ);
+ }
+ if (ch_stat & USB_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->usb_charger_attached_work,
+ HZ);
+ di->vbus_detected = true;
+ di->vbus_detected_start = true;
+ queue_work(di->charger_wq,
+ &di->detect_usb_type_work);
+ }
+
+ ret = component_bind_all(dev, di);
+ if (ret) {
+ dev_err(dev, "can't bind component devices\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static void ab8500_charger_unbind(struct device *dev)
+{
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ret;
/* Disable AC charging */
ab8500_charger_ac_en(&di->ac_chg, false, 0, 0);
@@ -3287,68 +3352,47 @@ static int ab8500_charger_remove(struct platform_device *pdev)
/* Disable USB charging */
ab8500_charger_usb_en(&di->usb_chg, false, 0, 0);
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
-
/* Backup battery voltage and current disable */
ret = abx500_mask_and_set_register_interruptible(di->dev,
AB8500_RTC, AB8500_RTC_CTRL_REG, RTC_BUP_CH_ENA, 0);
if (ret < 0)
dev_err(di->dev, "%s mask and set failed\n", __func__);
- usb_unregister_notifier(di->usb_phy, &di->nb);
- usb_put_phy(di->usb_phy);
-
/* Delete the work queue */
destroy_workqueue(di->charger_wq);
- /* Unregister external charger enable notifier */
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_unregister(
- &charger_notifier_list, &charger_nb);
-
flush_scheduled_work();
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-
- if (di->ac_chg.enabled && !di->ac_chg.external)
- power_supply_unregister(di->ac_chg.psy);
- return 0;
+ /* Unbind fg, btemp, algorithm */
+ component_unbind_all(dev, di);
}
-static char *supply_interface[] = {
- "ab8500_chargalg",
- "ab8500_fg",
- "ab8500_btemp",
+static const struct component_master_ops ab8500_charger_comp_ops = {
+ .bind = ab8500_charger_bind,
+ .unbind = ab8500_charger_unbind,
};
-static const struct power_supply_desc ab8500_ac_chg_desc = {
- .name = "ab8500_ac",
- .type = POWER_SUPPLY_TYPE_MAINS,
- .properties = ab8500_charger_ac_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
- .get_property = ab8500_charger_ac_get_property,
+static struct platform_driver *const ab8500_charger_component_drivers[] = {
+ &ab8500_fg_driver,
+ &ab8500_btemp_driver,
+ &abx500_chargalg_driver,
};
-static const struct power_supply_desc ab8500_usb_chg_desc = {
- .name = "ab8500_usb",
- .type = POWER_SUPPLY_TYPE_USB,
- .properties = ab8500_charger_usb_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
- .get_property = ab8500_charger_usb_get_property,
-};
+static int ab8500_charger_compare_dev(struct device *dev, void *data)
+{
+ return dev == data;
+}
static int ab8500_charger_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct component_match *match = NULL;
struct power_supply_config ac_psy_cfg = {}, usb_psy_cfg = {};
struct ab8500_charger *di;
- int irq, i, charger_status, ret = 0, ch_stat;
- struct device *dev = &pdev->dev;
+ int charger_status;
+ int i, irq;
+ int ret;
di = devm_kzalloc(dev, sizeof(*di), GFP_KERNEL);
if (!di)
@@ -3393,6 +3437,38 @@ static int ab8500_charger_probe(struct platform_device *pdev)
return ret;
}
+ /*
+ * VDD ADC supply needs to be enabled from this driver when there
+ * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
+ * interrupts during charging
+ */
+ di->regu = devm_regulator_get(dev, "vddadc");
+ if (IS_ERR(di->regu)) {
+ ret = PTR_ERR(di->regu);
+ dev_err(dev, "failed to get vddadc regulator\n");
+ return ret;
+ }
+
+ /* Request interrupts */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
+ irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+ if (irq < 0)
+ return irq;
+
+ ret = devm_request_threaded_irq(dev,
+ irq, NULL, ab8500_charger_irq[i].isr,
+ IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
+ ab8500_charger_irq[i].name, di);
+
+ if (ret != 0) {
+ dev_err(dev, "failed to request %s IRQ %d: %d\n"
+ , ab8500_charger_irq[i].name, irq, ret);
+ return ret;
+ }
+ dev_dbg(dev, "Requested %s IRQ %d: %d\n",
+ ab8500_charger_irq[i].name, irq, ret);
+ }
+
/* initialize lock */
spin_lock_init(&di->usb_state.usb_lock);
mutex_init(&di->usb_ipt_crnt_lock);
@@ -3422,11 +3498,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->ac_chg.enabled = di->bm->ac_enabled;
di->ac_chg.external = false;
- /*notifier for external charger enabling*/
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_register(
- &charger_notifier_list, &charger_nb);
-
/* USB supply */
/* ux500_charger sub-class */
di->usb_chg.ops.enable = &ab8500_charger_usb_en;
@@ -3442,14 +3513,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->usb_chg.external = false;
di->usb_state.usb_current = -1;
- /* Create a work queue for the charger */
- di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
- WQ_MEM_RECLAIM);
- if (di->charger_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
mutex_init(&di->charger_attached_mutex);
/* Init work for HW failure check */
@@ -3500,63 +3563,36 @@ static int ab8500_charger_probe(struct platform_device *pdev)
INIT_WORK(&di->check_usb_thermal_prot_work,
ab8500_charger_check_usb_thermal_prot_work);
- /*
- * VDD ADC supply needs to be enabled from this driver when there
- * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
- * interrupts during charging
- */
- di->regu = devm_regulator_get(dev, "vddadc");
- if (IS_ERR(di->regu)) {
- ret = PTR_ERR(di->regu);
- dev_err(dev, "failed to get vddadc regulator\n");
- goto free_charger_wq;
- }
-
/* Initialize OVV, and other registers */
ret = ab8500_charger_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize ABB registers\n");
- goto free_charger_wq;
+ return ret;
}
/* Register AC charger class */
if (di->ac_chg.enabled) {
- di->ac_chg.psy = power_supply_register(dev,
+ di->ac_chg.psy = devm_power_supply_register(dev,
&ab8500_ac_chg_desc,
&ac_psy_cfg);
if (IS_ERR(di->ac_chg.psy)) {
dev_err(dev, "failed to register AC charger\n");
- ret = PTR_ERR(di->ac_chg.psy);
- goto free_charger_wq;
+ return PTR_ERR(di->ac_chg.psy);
}
}
/* Register USB charger class */
if (di->usb_chg.enabled) {
- di->usb_chg.psy = power_supply_register(dev,
+ di->usb_chg.psy = devm_power_supply_register(dev,
&ab8500_usb_chg_desc,
&usb_psy_cfg);
if (IS_ERR(di->usb_chg.psy)) {
dev_err(dev, "failed to register USB charger\n");
- ret = PTR_ERR(di->usb_chg.psy);
- goto free_ac;
+ return PTR_ERR(di->usb_chg.psy);
}
}
- di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
- if (IS_ERR_OR_NULL(di->usb_phy)) {
- dev_err(dev, "failed to get usb transceiver\n");
- ret = -EINVAL;
- goto free_usb;
- }
- di->nb.notifier_call = ab8500_charger_usb_notifier_call;
- ret = usb_register_notifier(di->usb_phy, &di->nb);
- if (ret) {
- dev_err(dev, "failed to register usb notifier\n");
- goto put_usb_phy;
- }
-
/* Identify the connected charger types during startup */
charger_status = ab8500_charger_detect_chargers(di, true);
if (charger_status & AC_PW_CONN) {
@@ -3566,78 +3602,86 @@ static int ab8500_charger_probe(struct platform_device *pdev)
sysfs_notify(&di->ac_chg.psy->dev.kobj, NULL, "present");
}
- if (charger_status & USB_PW_CONN) {
- di->vbus_detected = true;
- di->vbus_detected_start = true;
- queue_work(di->charger_wq,
- &di->detect_usb_type_work);
- }
-
- /* Register interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ platform_set_drvdata(pdev, di);
- ret = request_threaded_irq(irq, NULL, ab8500_charger_irq[i].isr,
- IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
- ab8500_charger_irq[i].name, di);
+ /* Create something that will match the subdrivers when we bind */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_component_drivers); i++) {
+ struct device_driver *drv = &ab8500_charger_component_drivers[i]->driver;
+ struct device *p = NULL, *d;
- if (ret != 0) {
- dev_err(dev, "failed to request %s IRQ %d: %d\n"
- , ab8500_charger_irq[i].name, irq, ret);
- goto free_irq;
+ while ((d = platform_find_device_by_driver(p, drv))) {
+ put_device(p);
+ component_match_add(dev, &match,
+ ab8500_charger_compare_dev, d);
+ p = d;
}
- dev_dbg(dev, "Requested %s IRQ %d: %d\n",
- ab8500_charger_irq[i].name, irq, ret);
+ put_device(p);
+ }
+ if (!match) {
+ dev_err(dev, "no matching components\n");
+ return -ENODEV;
+ }
+ if (IS_ERR(match)) {
+ dev_err(dev, "could not create component match\n");
+ return PTR_ERR(match);
}
- platform_set_drvdata(pdev, di);
+ /* Notifier for external charger enabling */
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_register(
+ &charger_notifier_list, &charger_nb);
- mutex_lock(&di->charger_attached_mutex);
- ch_stat = ab8500_charger_detect_chargers(di, false);
-
- if ((ch_stat & AC_PW_CONN) == AC_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->ac_charger_attached_work,
- HZ);
+ di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
+ if (IS_ERR_OR_NULL(di->usb_phy)) {
+ dev_err(dev, "failed to get usb transceiver\n");
+ ret = -EINVAL;
+ goto out_charger_notifier;
}
- if ((ch_stat & USB_PW_CONN) == USB_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->usb_charger_attached_work,
- HZ);
+ di->nb.notifier_call = ab8500_charger_usb_notifier_call;
+ ret = usb_register_notifier(di->usb_phy, &di->nb);
+ if (ret) {
+ dev_err(dev, "failed to register usb notifier\n");
+ goto put_usb_phy;
}
- mutex_unlock(&di->charger_attached_mutex);
- return ret;
+ ret = component_master_add_with_match(&pdev->dev,
+ &ab8500_charger_comp_ops,
+ match);
+ if (ret) {
+ dev_err(dev, "failed to add component master\n");
+ goto free_notifier;
+ }
-free_irq:
- usb_unregister_notifier(di->usb_phy, &di->nb);
+ return 0;
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
+free_notifier:
+ usb_unregister_notifier(di->usb_phy, &di->nb);
put_usb_phy:
usb_put_phy(di->usb_phy);
-free_usb:
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-free_ac:
- if (di->ac_chg.enabled)
- power_supply_unregister(di->ac_chg.psy);
-free_charger_wq:
- destroy_workqueue(di->charger_wq);
+out_charger_notifier:
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
return ret;
}
+static int ab8500_charger_remove(struct platform_device *pdev)
+{
+ struct ab8500_charger *di = platform_get_drvdata(pdev);
+
+ component_master_del(&pdev->dev, &ab8500_charger_comp_ops);
+
+ usb_unregister_notifier(di->usb_phy, &di->nb);
+ usb_put_phy(di->usb_phy);
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
+
+ return 0;
+}
+
static SIMPLE_DEV_PM_OPS(ab8500_charger_pm_ops, ab8500_charger_suspend, ab8500_charger_resume);
static const struct of_device_id ab8500_charger_match[] = {
@@ -3657,15 +3701,24 @@ static struct platform_driver ab8500_charger_driver = {
static int __init ab8500_charger_init(void)
{
+ int ret;
+
+ ret = platform_register_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
+ if (ret)
+ return ret;
+
return platform_driver_register(&ab8500_charger_driver);
}
static void __exit ab8500_charger_exit(void)
{
+ platform_unregister_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
platform_driver_unregister(&ab8500_charger_driver);
}
-subsys_initcall_sync(ab8500_charger_init);
+module_init(ab8500_charger_init);
module_exit(ab8500_charger_exit);
MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index 0c7c01a0d979..acf0f2471c0b 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/component.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
@@ -2980,27 +2981,6 @@ static int __maybe_unused ab8500_fg_suspend(struct device *dev)
return 0;
}
-static int ab8500_fg_remove(struct platform_device *pdev)
-{
- int ret = 0;
- struct ab8500_fg *di = platform_get_drvdata(pdev);
-
- list_del(&di->node);
-
- /* Disable coulomb counter */
- ret = ab8500_fg_coulomb_counter(di, false);
- if (ret)
- dev_err(di->dev, "failed to disable coulomb counter\n");
-
- destroy_workqueue(di->fg_wq);
- ab8500_fg_sysfs_exit(di);
-
- flush_scheduled_work();
- ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
- return ret;
-}
-
/* ab8500 fg driver interrupts and their respective isr */
static struct ab8500_fg_interrupts ab8500_fg_irq[] = {
{"NCONV_ACCU", ab8500_fg_cc_convend_handler},
@@ -3024,11 +3004,50 @@ static const struct power_supply_desc ab8500_fg_desc = {
.external_power_changed = ab8500_fg_external_power_changed,
};
+static int ab8500_fg_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for running the FG algorithm */
+ di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
+ if (di->fg_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Start the coulomb counter */
+ ab8500_fg_coulomb_counter(di, true);
+ /* Run the FG algorithm */
+ queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+
+ return 0;
+}
+
+static void ab8500_fg_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+ int ret;
+
+ /* Disable coulomb counter */
+ ret = ab8500_fg_coulomb_counter(di, false);
+ if (ret)
+ dev_err(dev, "failed to disable coulomb counter\n");
+
+ destroy_workqueue(di->fg_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_fg_component_ops = {
+ .bind = ab8500_fg_bind,
+ .unbind = ab8500_fg_unbind,
+};
+
static int ab8500_fg_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
- struct power_supply_config psy_cfg = {};
struct device *dev = &pdev->dev;
+ struct power_supply_config psy_cfg = {};
struct ab8500_fg *di;
int i, irq;
int ret = 0;
@@ -3074,13 +3093,6 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INIT);
- /* Create a work queue for running the FG algorithm */
- di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
- if (di->fg_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for running the fg algorithm instantly */
INIT_WORK(&di->fg_work, ab8500_fg_instant_work);
@@ -3113,7 +3125,7 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize registers\n");
- goto free_inst_curr_wq;
+ return ret;
}
/* Consider battery unknown until we're informed otherwise */
@@ -3121,15 +3133,13 @@ static int ab8500_fg_probe(struct platform_device *pdev)
di->flags.batt_id_received = false;
/* Register FG power supply class */
- di->fg_psy = power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
+ di->fg_psy = devm_power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
if (IS_ERR(di->fg_psy)) {
dev_err(dev, "failed to register FG psy\n");
- ret = PTR_ERR(di->fg_psy);
- goto free_inst_curr_wq;
+ return PTR_ERR(di->fg_psy);
}
di->fg_samples = SEC_TO_SAMPLE(di->bm->fg_params->init_timer);
- ab8500_fg_coulomb_counter(di, true);
/*
* Initialize completion used to notify completion and start
@@ -3141,19 +3151,18 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Register primary interrupt handlers */
for (i = 0; i < ARRAY_SIZE(ab8500_fg_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_fg_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_fg_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_fg_irq[i].name, di);
if (ret != 0) {
dev_err(dev, "failed to request %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
@@ -3168,14 +3177,14 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_sysfs_init(di);
if (ret) {
dev_err(dev, "failed to create sysfs entry\n");
- goto free_irq;
+ return ret;
}
ret = ab8500_fg_sysfs_psy_create_attrs(di);
if (ret) {
dev_err(dev, "failed to create FG psy\n");
ab8500_fg_sysfs_exit(di);
- goto free_irq;
+ return ret;
}
/* Calibrate the fg first time */
@@ -3185,24 +3194,21 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Use room temp as default value until we get an update from driver. */
di->bat_temp = 210;
- /* Run the FG algorithm */
- queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
-
list_add_tail(&di->node, &ab8500_fg_list);
- return ret;
+ return component_add(dev, &ab8500_fg_component_ops);
+}
-free_irq:
- /* We also have to free all registered irqs */
- while (--i >= 0) {
- /* Last assignment of i from primary interrupt handlers */
- irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_fg_remove(struct platform_device *pdev)
+{
+ int ret = 0;
+ struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+ component_del(&pdev->dev, &ab8500_fg_component_ops);
+ list_del(&di->node);
+ ab8500_fg_sysfs_exit(di);
+ ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
-free_inst_curr_wq:
- destroy_workqueue(di->fg_wq);
return ret;
}
@@ -3213,7 +3219,7 @@ static const struct of_device_id ab8500_fg_match[] = {
{ },
};
-static struct platform_driver ab8500_fg_driver = {
+struct platform_driver ab8500_fg_driver = {
.probe = ab8500_fg_probe,
.remove = ab8500_fg_remove,
.driver = {
@@ -3222,20 +3228,6 @@ static struct platform_driver ab8500_fg_driver = {
.pm = &ab8500_fg_pm_ops,
},
};
-
-static int __init ab8500_fg_init(void)
-{
- return platform_driver_register(&ab8500_fg_driver);
-}
-
-static void __exit ab8500_fg_exit(void)
-{
- platform_driver_unregister(&ab8500_fg_driver);
-}
-
-subsys_initcall_sync(ab8500_fg_init);
-module_exit(ab8500_fg_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski");
MODULE_ALIAS("platform:ab8500-fg");
diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c
index f5b792243727..599684ce0e4b 100644
--- a/drivers/power/supply/abx500_chargalg.c
+++ b/drivers/power/supply/abx500_chargalg.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
@@ -1943,13 +1944,44 @@ static int __maybe_unused abx500_chargalg_suspend(struct device *dev)
return 0;
}
-static int abx500_chargalg_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_fg",
+};
+
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gnu/gnu-master-aarch64-check_gcc - Build # 2 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gnu/gnu-master-aarch64-check_gcc. So far, this commit has regressed CI configurations:
- tcwg_gnu/gnu-master-aarch64-check_gcc
Culprit:
<cut>
commit 261d5a4a459bd49942e53bc83334ccc7154a09d5
Author: Jonathan Wakely <jwakely(a)redhat.com>
Date: Thu Jul 22 14:48:27 2021 +0100
libstdc++: Reduce header dependencies on <array> and <utility>
This refactoring reduces the memory usage and compilation time to parse
a number of headers that depend on std::pair, std::tuple or std::array.
Previously the headers for these class templates were all intertwined,
due to the common dependency on std::tuple_size, std::tuple_element and
their std::get overloads. This decouples the headers by moving some
parts of <utility> into a new <bits/utility.h> header. This means that
<array> and <tuple> no longer need to include the whole of <utility>,
and <tuple> no longer needs to include <array>.
This decoupling benefits headers such as <thread> and <scoped_allocator>
which only need std::tuple, and so no longer have to parse std::array.
Some other headers such as <any>, <optional> and <variant> no longer
need to include <utility> just for the std::in_place tag types, so
do not have to parse the std::pair definitions.
Removing direct uses of <utility> also means that the std::rel_ops
namespace is not transitively declared by other headers.
Signed-off-by: Jonathan Wakely <jwakely(a)redhat.com>
libstdc++-v3/ChangeLog:
* include/Makefile.am: Add bits/utility.h header.
* include/Makefile.in: Regenerate.
* include/bits/utility.h: New file.
* include/std/utility (tuple_size, tuple_element): Move
to new header.
* include/std/type_traits (__is_tuple_like_impl<tuple<T...>>):
Move to <tuple>.
(_Index_tuple, _Build_index_tuple, integer_sequence): Likewise.
(in_place_t, in_place_index_t, in_place_type_t): Likewise.
* include/bits/ranges_util.h: Include new header instead of
<utility>.
* include/bits/stl_pair.h (tuple_size, tuple_element): Move
partial specializations for std::pair here.
(get): Move overloads for std::pair here.
* include/std/any: Include new header instead of <utility>.
* include/std/array: Likewise.
* include/std/memory_resource: Likewise.
* include/std/optional: Likewise.
* include/std/variant: Likewise.
* include/std/tuple: Likewise.
(__is_tuple_like_impl<tuple<T...>>): Move here.
(get) Declare overloads for std::array.
* include/std/version (__cpp_lib_tuples_by_type): Change type
to long.
* testsuite/20_util/optional/84601.cc: Include <utility>.
* testsuite/20_util/specialized_algorithms/uninitialized_fill/constrained.cc:
Likewise.
* testsuite/23_containers/array/tuple_interface/get_neg.cc:
Adjust dg-error line numbers.
* testsuite/std/ranges/access/cbegin.cc: Include <utility>.
* testsuite/std/ranges/access/cend.cc: Likewise.
* testsuite/std/ranges/access/end.cc: Likewise.
* testsuite/std/ranges/single_view.cc: Likewise.
</cut>
Results regressed to (for first_bad == 261d5a4a459bd49942e53bc83334ccc7154a09d5)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=g++.dg/dg.exp:
1
# Getting actual results from build directory /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/libstdc++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/gfortran.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/libitm.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/libgomp.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/libatomic.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/g++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_5/artifacts/build-261d5a4a459bd49942e53bc83334ccc7154a09d5/sumfiles/gcc.sum
# Manifest: gcc-compare-results/contrib/testsuite-management/flaky/gnu-master-aarch64-check_gcc.xfail
# Getting actual results from build directory base-artifacts/sumfiles
# base-artifacts/sumfiles/libstdc++.sum
# base-artifacts/sumfiles/gfortran.sum
# base-artifacts/sumfiles/libitm.sum
# base-artifacts/sumfiles/libgomp.sum
# base-artifacts/sumfiles/libatomic.sum
# base-artifacts/sumfiles/g++.sum
# base-artifacts/sumfiles/gcc.sum
#
#
# Unexpected results in this build (new failures)
# === g++ tests ===
#
# Running g++.dg/dg.exp ...
# FAIL: g++.dg/pr71655.C (test for excess errors)
# === gcc tests ===
# FAIL: g++.dg/pr71655.C (test for excess errors)
#
# === Results Summary ===
from (for last_good == fcc7c6369f7fbf293f502d3d207a90b76cc2c62f)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=g++.dg/dg.exp:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/ar…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/ar…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-261d5a4a459bd49942e53bc83334ccc7154a09d5
cd investigate-gcc-261d5a4a459bd49942e53bc83334ccc7154a09d5
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/ar… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/ar… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/ar… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 261d5a4a459bd49942e53bc83334ccc7154a09d5
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach fcc7c6369f7fbf293f502d3d207a90b76cc2c62f
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/ar…
Build log: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/2/co…
Full commit (up to 1000 lines):
<cut>
commit 261d5a4a459bd49942e53bc83334ccc7154a09d5
Author: Jonathan Wakely <jwakely(a)redhat.com>
Date: Thu Jul 22 14:48:27 2021 +0100
libstdc++: Reduce header dependencies on <array> and <utility>
This refactoring reduces the memory usage and compilation time to parse
a number of headers that depend on std::pair, std::tuple or std::array.
Previously the headers for these class templates were all intertwined,
due to the common dependency on std::tuple_size, std::tuple_element and
their std::get overloads. This decouples the headers by moving some
parts of <utility> into a new <bits/utility.h> header. This means that
<array> and <tuple> no longer need to include the whole of <utility>,
and <tuple> no longer needs to include <array>.
This decoupling benefits headers such as <thread> and <scoped_allocator>
which only need std::tuple, and so no longer have to parse std::array.
Some other headers such as <any>, <optional> and <variant> no longer
need to include <utility> just for the std::in_place tag types, so
do not have to parse the std::pair definitions.
Removing direct uses of <utility> also means that the std::rel_ops
namespace is not transitively declared by other headers.
Signed-off-by: Jonathan Wakely <jwakely(a)redhat.com>
libstdc++-v3/ChangeLog:
* include/Makefile.am: Add bits/utility.h header.
* include/Makefile.in: Regenerate.
* include/bits/utility.h: New file.
* include/std/utility (tuple_size, tuple_element): Move
to new header.
* include/std/type_traits (__is_tuple_like_impl<tuple<T...>>):
Move to <tuple>.
(_Index_tuple, _Build_index_tuple, integer_sequence): Likewise.
(in_place_t, in_place_index_t, in_place_type_t): Likewise.
* include/bits/ranges_util.h: Include new header instead of
<utility>.
* include/bits/stl_pair.h (tuple_size, tuple_element): Move
partial specializations for std::pair here.
(get): Move overloads for std::pair here.
* include/std/any: Include new header instead of <utility>.
* include/std/array: Likewise.
* include/std/memory_resource: Likewise.
* include/std/optional: Likewise.
* include/std/variant: Likewise.
* include/std/tuple: Likewise.
(__is_tuple_like_impl<tuple<T...>>): Move here.
(get) Declare overloads for std::array.
* include/std/version (__cpp_lib_tuples_by_type): Change type
to long.
* testsuite/20_util/optional/84601.cc: Include <utility>.
* testsuite/20_util/specialized_algorithms/uninitialized_fill/constrained.cc:
Likewise.
* testsuite/23_containers/array/tuple_interface/get_neg.cc:
Adjust dg-error line numbers.
* testsuite/std/ranges/access/cbegin.cc: Include <utility>.
* testsuite/std/ranges/access/cend.cc: Likewise.
* testsuite/std/ranges/access/end.cc: Likewise.
* testsuite/std/ranges/single_view.cc: Likewise.
---
libstdc++-v3/include/Makefile.am | 1 +
libstdc++-v3/include/Makefile.in | 1 +
libstdc++-v3/include/bits/ranges_util.h | 1 +
libstdc++-v3/include/bits/stl_pair.h | 155 ++++++++++-
libstdc++-v3/include/bits/utility.h | 205 ++++++++++++++
libstdc++-v3/include/std/any | 3 +-
libstdc++-v3/include/std/array | 30 +-
libstdc++-v3/include/std/memory_resource | 6 +-
libstdc++-v3/include/std/optional | 4 +-
libstdc++-v3/include/std/tuple | 36 ++-
libstdc++-v3/include/std/type_traits | 7 -
libstdc++-v3/include/std/utility | 308 +--------------------
libstdc++-v3/include/std/variant | 6 +-
libstdc++-v3/include/std/version | 2 +-
libstdc++-v3/testsuite/20_util/optional/84601.cc | 1 +
.../uninitialized_fill/constrained.cc | 1 +
.../23_containers/array/tuple_interface/get_neg.cc | 6 +-
libstdc++-v3/testsuite/std/ranges/access/cbegin.cc | 1 +
libstdc++-v3/testsuite/std/ranges/access/cend.cc | 1 +
libstdc++-v3/testsuite/std/ranges/access/end.cc | 1 +
libstdc++-v3/testsuite/std/ranges/single_view.cc | 1 +
21 files changed, 433 insertions(+), 344 deletions(-)
diff --git a/libstdc++-v3/include/Makefile.am b/libstdc++-v3/include/Makefile.am
index 40a41ef2a1c..99eec558116 100644
--- a/libstdc++-v3/include/Makefile.am
+++ b/libstdc++-v3/include/Makefile.am
@@ -233,6 +233,7 @@ bits_headers = \
${bits_srcdir}/unordered_set.h \
${bits_srcdir}/uses_allocator.h \
${bits_srcdir}/uses_allocator_args.h \
+ ${bits_srcdir}/utility.h \
${bits_srcdir}/valarray_array.h \
${bits_srcdir}/valarray_array.tcc \
${bits_srcdir}/valarray_before.h \
diff --git a/libstdc++-v3/include/Makefile.in b/libstdc++-v3/include/Makefile.in
index fcd2b5b2d40..7e668b86bbb 100644
--- a/libstdc++-v3/include/Makefile.in
+++ b/libstdc++-v3/include/Makefile.in
@@ -583,6 +583,7 @@ bits_headers = \
${bits_srcdir}/unordered_set.h \
${bits_srcdir}/uses_allocator.h \
${bits_srcdir}/uses_allocator_args.h \
+ ${bits_srcdir}/utility.h \
${bits_srcdir}/valarray_array.h \
${bits_srcdir}/valarray_array.tcc \
${bits_srcdir}/valarray_before.h \
diff --git a/libstdc++-v3/include/bits/ranges_util.h b/libstdc++-v3/include/bits/ranges_util.h
index 9a07079ac13..0ca203dd4b0 100644
--- a/libstdc++-v3/include/bits/ranges_util.h
+++ b/libstdc++-v3/include/bits/ranges_util.h
@@ -32,6 +32,7 @@
#if __cplusplus > 201703L
# include <bits/ranges_base.h>
+# include <bits/utility.h>
#ifdef __cpp_lib_ranges
namespace std _GLIBCXX_VISIBILITY(default)
diff --git a/libstdc++-v3/include/bits/stl_pair.h b/libstdc++-v3/include/bits/stl_pair.h
index c89f377fddc..329485ce3b2 100644
--- a/libstdc++-v3/include/bits/stl_pair.h
+++ b/libstdc++-v3/include/bits/stl_pair.h
@@ -56,12 +56,12 @@
#ifndef _STL_PAIR_H
#define _STL_PAIR_H 1
-#include <bits/move.h> // for std::move / std::forward, and std::swap
-
#if __cplusplus >= 201103L
-# include <type_traits> // for std::__decay_and_strip, std::is_reference_v
+# include <type_traits> // for std::__decay_and_strip
+# include <bits/move.h> // for std::move / std::forward, and std::swap
+# include <bits/utility.h> // for std::tuple_element, std::tuple_size
#endif
-#if __cplusplus > 201703L
+#if __cplusplus >= 202002L
# include <compare>
# define __cpp_lib_constexpr_utility 201811L
#endif
@@ -752,6 +752,153 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
/// @}
+#if __cplusplus >= 201103L
+ // Various functions which give std::pair a tuple-like interface.
+
+ template<typename _T1, typename _T2>
+ struct __is_tuple_like_impl<pair<_T1, _T2>> : true_type
+ { };
+
+ /// Partial specialization for std::pair
+ template<class _Tp1, class _Tp2>
+ struct tuple_size<pair<_Tp1, _Tp2>>
+ : public integral_constant<size_t, 2> { };
+
+ /// Partial specialization for std::pair
+ template<class _Tp1, class _Tp2>
+ struct tuple_element<0, pair<_Tp1, _Tp2>>
+ { typedef _Tp1 type; };
+
+ /// Partial specialization for std::pair
+ template<class _Tp1, class _Tp2>
+ struct tuple_element<1, pair<_Tp1, _Tp2>>
+ { typedef _Tp2 type; };
+
+ /// @cond undocumented
+ template<size_t _Int>
+ struct __pair_get;
+
+ template<>
+ struct __pair_get<0>
+ {
+ template<typename _Tp1, typename _Tp2>
+ static constexpr _Tp1&
+ __get(pair<_Tp1, _Tp2>& __pair) noexcept
+ { return __pair.first; }
+
+ template<typename _Tp1, typename _Tp2>
+ static constexpr _Tp1&&
+ __move_get(pair<_Tp1, _Tp2>&& __pair) noexcept
+ { return std::forward<_Tp1>(__pair.first); }
+
+ template<typename _Tp1, typename _Tp2>
+ static constexpr const _Tp1&
+ __const_get(const pair<_Tp1, _Tp2>& __pair) noexcept
+ { return __pair.first; }
+
+ template<typename _Tp1, typename _Tp2>
+ static constexpr const _Tp1&&
+ __const_move_get(const pair<_Tp1, _Tp2>&& __pair) noexcept
+ { return std::forward<const _Tp1>(__pair.first); }
+ };
+
+ template<>
+ struct __pair_get<1>
+ {
+ template<typename _Tp1, typename _Tp2>
+ static constexpr _Tp2&
+ __get(pair<_Tp1, _Tp2>& __pair) noexcept
+ { return __pair.second; }
+
+ template<typename _Tp1, typename _Tp2>
+ static constexpr _Tp2&&
+ __move_get(pair<_Tp1, _Tp2>&& __pair) noexcept
+ { return std::forward<_Tp2>(__pair.second); }
+
+ template<typename _Tp1, typename _Tp2>
+ static constexpr const _Tp2&
+ __const_get(const pair<_Tp1, _Tp2>& __pair) noexcept
+ { return __pair.second; }
+
+ template<typename _Tp1, typename _Tp2>
+ static constexpr const _Tp2&&
+ __const_move_get(const pair<_Tp1, _Tp2>&& __pair) noexcept
+ { return std::forward<const _Tp2>(__pair.second); }
+ };
+ /// @endcond
+
+ /** @{
+ * std::get overloads for accessing members of std::pair
+ */
+
+ template<size_t _Int, class _Tp1, class _Tp2>
+ constexpr typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&
+ get(pair<_Tp1, _Tp2>& __in) noexcept
+ { return __pair_get<_Int>::__get(__in); }
+
+ template<size_t _Int, class _Tp1, class _Tp2>
+ constexpr typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&&
+ get(pair<_Tp1, _Tp2>&& __in) noexcept
+ { return __pair_get<_Int>::__move_get(std::move(__in)); }
+
+ template<size_t _Int, class _Tp1, class _Tp2>
+ constexpr const typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&
+ get(const pair<_Tp1, _Tp2>& __in) noexcept
+ { return __pair_get<_Int>::__const_get(__in); }
+
+ template<size_t _Int, class _Tp1, class _Tp2>
+ constexpr const typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&&
+ get(const pair<_Tp1, _Tp2>&& __in) noexcept
+ { return __pair_get<_Int>::__const_move_get(std::move(__in)); }
+
+#if __cplusplus >= 201402L
+
+#define __cpp_lib_tuples_by_type 201304L
+
+ template <typename _Tp, typename _Up>
+ constexpr _Tp&
+ get(pair<_Tp, _Up>& __p) noexcept
+ { return __p.first; }
+
+ template <typename _Tp, typename _Up>
+ constexpr const _Tp&
+ get(const pair<_Tp, _Up>& __p) noexcept
+ { return __p.first; }
+
+ template <typename _Tp, typename _Up>
+ constexpr _Tp&&
+ get(pair<_Tp, _Up>&& __p) noexcept
+ { return std::move(__p.first); }
+
+ template <typename _Tp, typename _Up>
+ constexpr const _Tp&&
+ get(const pair<_Tp, _Up>&& __p) noexcept
+ { return std::move(__p.first); }
+
+ template <typename _Tp, typename _Up>
+ constexpr _Tp&
+ get(pair<_Up, _Tp>& __p) noexcept
+ { return __p.second; }
+
+ template <typename _Tp, typename _Up>
+ constexpr const _Tp&
+ get(const pair<_Up, _Tp>& __p) noexcept
+ { return __p.second; }
+
+ template <typename _Tp, typename _Up>
+ constexpr _Tp&&
+ get(pair<_Up, _Tp>&& __p) noexcept
+ { return std::move(__p.second); }
+
+ template <typename _Tp, typename _Up>
+ constexpr const _Tp&&
+ get(const pair<_Up, _Tp>&& __p) noexcept
+ { return std::move(__p.second); }
+
+#endif // C++14
+ /// @}
+#endif // C++11
+
_GLIBCXX_END_NAMESPACE_VERSION
} // namespace std
diff --git a/libstdc++-v3/include/bits/utility.h b/libstdc++-v3/include/bits/utility.h
new file mode 100644
index 00000000000..96d350874d9
--- /dev/null
+++ b/libstdc++-v3/include/bits/utility.h
@@ -0,0 +1,205 @@
+// Utilities used throughout the library -*- C++ -*-
+
+// Copyright (C) 2004-2021 Free Software Foundation, Inc.
+//
+// This file is part of the GNU ISO C++ Library. This library is free
+// software; you can redistribute it and/or modify it under the
+// terms of the GNU General Public License as published by the
+// Free Software Foundation; either version 3, or (at your option)
+// any later version.
+
+// This library is distributed in the hope that it will be useful,
+// but WITHOUT ANY WARRANTY; without even the implied warranty of
+// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
+// GNU General Public License for more details.
+
+// Under Section 7 of GPL version 3, you are granted additional
+// permissions described in the GCC Runtime Library Exception, version
+// 3.1, as published by the Free Software Foundation.
+
+// You should have received a copy of the GNU General Public License and
+// a copy of the GCC Runtime Library Exception along with this program;
+// see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
+// <http://www.gnu.org/licenses/>.
+
+/** @file include/bits/utility.h
+ * This is an internal header file, included by other library headers.
+ * Do not attempt to use it directly. @headername{utility}
+ *
+ * This file contains the parts of `<utility>` needed by other headers,
+ * so they don't need to include the whole of `<utility>`.
+ */
+
+#ifndef _GLIBCXX_UTILITY_H
+#define _GLIBCXX_UTILITY_H 1
+
+#pragma GCC system_header
+
+#if __cplusplus >= 201103L
+
+#include <type_traits>
+#include <bits/move.h>
+
+namespace std _GLIBCXX_VISIBILITY(default)
+{
+_GLIBCXX_BEGIN_NAMESPACE_VERSION
+
+ /// Finds the size of a given tuple type.
+ template<typename _Tp>
+ struct tuple_size;
+
+ // _GLIBCXX_RESOLVE_LIB_DEFECTS
+ // 2313. tuple_size should always derive from integral_constant<size_t, N>
+ // 2770. tuple_size<const T> specialization is not SFINAE compatible
+
+ template<typename _Tp,
+ typename _Up = typename remove_cv<_Tp>::type,
+ typename = typename enable_if<is_same<_Tp, _Up>::value>::type,
+ size_t = tuple_size<_Tp>::value>
+ using __enable_if_has_tuple_size = _Tp;
+
+ template<typename _Tp>
+ struct tuple_size<const __enable_if_has_tuple_size<_Tp>>
+ : public tuple_size<_Tp> { };
+
+ template<typename _Tp>
+ struct tuple_size<volatile __enable_if_has_tuple_size<_Tp>>
+ : public tuple_size<_Tp> { };
+
+ template<typename _Tp>
+ struct tuple_size<const volatile __enable_if_has_tuple_size<_Tp>>
+ : public tuple_size<_Tp> { };
+
+ /// Gives the type of the ith element of a given tuple type.
+ template<size_t __i, typename _Tp>
+ struct tuple_element;
+
+ // Duplicate of C++14's tuple_element_t for internal use in C++11 mode
+ template<size_t __i, typename _Tp>
+ using __tuple_element_t = typename tuple_element<__i, _Tp>::type;
+
+ template<size_t __i, typename _Tp>
+ struct tuple_element<__i, const _Tp>
+ {
+ typedef typename add_const<__tuple_element_t<__i, _Tp>>::type type;
+ };
+
+ template<size_t __i, typename _Tp>
+ struct tuple_element<__i, volatile _Tp>
+ {
+ typedef typename add_volatile<__tuple_element_t<__i, _Tp>>::type type;
+ };
+
+ template<size_t __i, typename _Tp>
+ struct tuple_element<__i, const volatile _Tp>
+ {
+ typedef typename add_cv<__tuple_element_t<__i, _Tp>>::type type;
+ };
+
+#if __cplusplus >= 201402L
+// The standard says this macro and alias template should be in <tuple>
+// but we define them here, to be available in <utility> and <array> too.
+#define __cpp_lib_tuple_element_t 201402L
+
+ template<size_t __i, typename _Tp>
+ using tuple_element_t = typename tuple_element<__i, _Tp>::type;
+#endif // C++14
+
+ // Stores a tuple of indices. Used by tuple and pair, and by bind() to
+ // extract the elements in a tuple.
+ template<size_t... _Indexes> struct _Index_tuple { };
+
+ // Builds an _Index_tuple<0, 1, 2, ..., _Num-1>.
+ template<size_t _Num>
+ struct _Build_index_tuple
+ {
+#if __has_builtin(__make_integer_seq)
+ template<typename, size_t... _Indices>
+ using _IdxTuple = _Index_tuple<_Indices...>;
+
+ // Clang defines __make_integer_seq for this purpose.
+ using __type = __make_integer_seq<_IdxTuple, size_t, _Num>;
+#else
+ // For GCC and other compilers, use __integer_pack instead.
+ using __type = _Index_tuple<__integer_pack(_Num)...>;
+#endif
+ };
+
+#if __cplusplus >= 201402L
+
+#define __cpp_lib_integer_sequence 201304L
+
+ /// Class template integer_sequence
+ template<typename _Tp, _Tp... _Idx>
+ struct integer_sequence
+ {
+ typedef _Tp value_type;
+ static constexpr size_t size() noexcept { return sizeof...(_Idx); }
+ };
+
+ /// Alias template make_integer_sequence
+ template<typename _Tp, _Tp _Num>
+ using make_integer_sequence
+#if __has_builtin(__make_integer_seq)
+ = __make_integer_seq<integer_sequence, _Tp, _Num>;
+#else
+ = integer_sequence<_Tp, __integer_pack(_Num)...>;
+#endif
+
+ /// Alias template index_sequence
+ template<size_t... _Idx>
+ using index_sequence = integer_sequence<size_t, _Idx...>;
+
+ /// Alias template make_index_sequence
+ template<size_t _Num>
+ using make_index_sequence = make_integer_sequence<size_t, _Num>;
+
+ /// Alias template index_sequence_for
+ template<typename... _Types>
+ using index_sequence_for = make_index_sequence<sizeof...(_Types)>;
+
+#if __cplusplus >= 201703L
+
+ //
+ struct in_place_t {
+ explicit in_place_t() = default;
+ };
+
+ inline constexpr in_place_t in_place{};
+
+ template<typename _Tp> struct in_place_type_t
+ {
+ explicit in_place_type_t() = default;
+ };
+
+ template<typename _Tp>
+ inline constexpr in_place_type_t<_Tp> in_place_type{};
+
+ template<size_t _Idx> struct in_place_index_t
+ {
+ explicit in_place_index_t() = default;
+ };
+
+ template<size_t _Idx>
+ inline constexpr in_place_index_t<_Idx> in_place_index{};
+
+ template<typename>
+ struct __is_in_place_type_impl : false_type
+ { };
+
+ template<typename _Tp>
+ struct __is_in_place_type_impl<in_place_type_t<_Tp>> : true_type
+ { };
+
+ template<typename _Tp>
+ struct __is_in_place_type
+ : public __is_in_place_type_impl<_Tp>
+ { };
+#endif // C++17
+#endif // C++14
+
+_GLIBCXX_END_NAMESPACE_VERSION
+} // namespace
+
+#endif // C++11
+#endif /* _GLIBCXX_UTILITY_H */
diff --git a/libstdc++-v3/include/std/any b/libstdc++-v3/include/std/any
index a6995b79c43..1fce95730ea 100644
--- a/libstdc++-v3/include/std/any
+++ b/libstdc++-v3/include/std/any
@@ -33,10 +33,11 @@
#if __cplusplus >= 201703L
+#include <initializer_list>
#include <typeinfo>
#include <new>
-#include <utility>
#include <type_traits>
+#include <bits/utility.h> // in_place_type_t
namespace std _GLIBCXX_VISIBILITY(default)
{
diff --git a/libstdc++-v3/include/std/array b/libstdc++-v3/include/std/array
index 0c6f33e3276..ea8d3cb5f2e 100644
--- a/libstdc++-v3/include/std/array
+++ b/libstdc++-v3/include/std/array
@@ -35,10 +35,14 @@
# include <bits/c++0x_warning.h>
#else
-#include <utility>
+#include <compare>
+#include <initializer_list>
+
+#include <type_traits>
#include <bits/functexcept.h>
#include <bits/stl_algobase.h>
-#include <bits/range_access.h>
+#include <bits/range_access.h> // std::begin, std::end etc.
+#include <bits/utility.h> // std::index_sequence, std::tuple_size
#include <debug/assertions.h>
namespace std _GLIBCXX_VISIBILITY(default)
@@ -428,28 +432,20 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
// Tuple interface to class template array.
- /// tuple_size
- template<typename _Tp>
- struct tuple_size;
-
/// Partial specialization for std::array
- template<typename _Tp, std::size_t _Nm>
+ template<typename _Tp, size_t _Nm>
struct tuple_size<array<_Tp, _Nm>>
- : public integral_constant<std::size_t, _Nm> { };
-
- /// tuple_element
- template<std::size_t _Int, typename _Tp>
- struct tuple_element;
+ : public integral_constant<size_t, _Nm> { };
/// Partial specialization for std::array
- template<std::size_t _Int, typename _Tp, std::size_t _Nm>
- struct tuple_element<_Int, array<_Tp, _Nm>>
+ template<size_t _Ind, typename _Tp, size_t _Nm>
+ struct tuple_element<_Ind, array<_Tp, _Nm>>
{
- static_assert(_Int < _Nm, "index is out of bounds");
- typedef _Tp type;
+ static_assert(_Ind < _Nm, "array index is in range");
+ using type = _Tp;
};
- template<typename _Tp, std::size_t _Nm>
+ template<typename _Tp, size_t _Nm>
struct __is_tuple_like_impl<array<_Tp, _Nm>> : true_type
{ };
diff --git a/libstdc++-v3/include/std/memory_resource b/libstdc++-v3/include/std/memory_resource
index df4e806f814..cdc5e5d98b1 100644
--- a/libstdc++-v3/include/std/memory_resource
+++ b/libstdc++-v3/include/std/memory_resource
@@ -38,13 +38,13 @@
#include <shared_mutex> // shared_mutex
#include <bits/align.h> // align
#include <bits/functexcept.h> // __throw_bad_array_new_length
-#include <bits/uses_allocator.h> // __use_alloc
+#include <bits/uses_allocator.h> // allocator_arg_t, __use_alloc
#include <bits/uses_allocator_args.h> // uninitialized_construct_using_alloc
#include <ext/numeric_traits.h>
#include <debug/assertions.h>
#if ! __cpp_lib_make_obj_using_allocator
-# include <utility> // pair, index_sequence
+# include <bits/utility.h> // index_sequence
# include <tuple> // tuple, forward_as_tuple
#endif
@@ -338,10 +338,10 @@ namespace pmr
{ return _M_resource; }
private:
+#if ! __cpp_lib_make_obj_using_allocator
using __uses_alloc1_ = __uses_alloc1<polymorphic_allocator>;
using __uses_alloc2_ = __uses_alloc2<polymorphic_allocator>;
-#if ! __cpp_lib_make_obj_using_allocator
template<typename _Ind, typename... _Args>
static tuple<_Args&&...>
_S_construct_p(__uses_alloc0, _Ind, tuple<_Args...>& __t)
diff --git a/libstdc++-v3/include/std/optional b/libstdc++-v3/include/std/optional
index 0a67ce24bbd..df9ed0736b3 100644
--- a/libstdc++-v3/include/std/optional
+++ b/libstdc++-v3/include/std/optional
@@ -33,14 +33,14 @@
#if __cplusplus >= 201703L
-#include <utility>
#include <type_traits>
#include <exception>
#include <new>
#include <initializer_list>
+#include <bits/enable_special_members.h>
#include <bits/exception_defines.h>
#include <bits/functional_hash.h>
-#include <bits/enable_special_members.h>
+#include <bits/utility.h> // in_place_t
#if __cplusplus > 201703L
# include <compare>
#endif
diff --git a/libstdc++-v3/include/std/tuple b/libstdc++-v3/include/std/tuple
index 8ee0d2f1ef5..1292aee45c0 100644
--- a/libstdc++-v3/include/std/tuple
+++ b/libstdc++-v3/include/std/tuple
@@ -35,10 +35,10 @@
# include <bits/c++0x_warning.h>
#else
-#include <utility>
-#include <array>
-#include <bits/uses_allocator.h>
-#include <bits/invoke.h>
+#include <bits/stl_pair.h> // for std::pair
+#include <bits/uses_allocator.h> // for std::allocator_arg_t
+#include <bits/utility.h> // for std::get, std::tuple_size etc.
+#include <bits/invoke.h> // for std::__invoke
#if __cplusplus > 201703L
# include <compare>
# define __cpp_lib_constexpr_tuple 201811L
@@ -1415,7 +1415,7 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
#if __cplusplus >= 201402L
-#define __cpp_lib_tuples_by_type 201304
+#define __cpp_lib_tuples_by_type 201304L
// Return the index of _Tp in _Types, if it occurs exactly once.
// Otherwise, return sizeof...(_Types).
@@ -1613,6 +1613,28 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
forward_as_tuple(_Elements&&... __args) noexcept
{ return tuple<_Elements&&...>(std::forward<_Elements>(__args)...); }
+ // Declarations of std::array and its std::get overloads, so that
+ // std::tuple_cat can use them if <tuple> is included before <array>.
+
+ template<typename _Tp, size_t _Nm> struct array;
+
+ template<size_t _Int, typename _Tp, size_t _Nm>
+ constexpr _Tp&
+ get(array<_Tp, _Nm>&) noexcept;
+
+ template<size_t _Int, typename _Tp, size_t _Nm>
+ constexpr _Tp&&
+ get(array<_Tp, _Nm>&&) noexcept;
+
+ template<size_t _Int, typename _Tp, size_t _Nm>
+ constexpr const _Tp&
+ get(const array<_Tp, _Nm>&) noexcept;
+
+ template<size_t _Int, typename _Tp, size_t _Nm>
+ constexpr const _Tp&&
+ get(const array<_Tp, _Nm>&&) noexcept;
+
+
template<size_t, typename, typename, size_t>
struct __make_tuple_impl;
@@ -1721,6 +1743,10 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
}
};
+ template<typename... _Tps>
+ struct __is_tuple_like_impl<tuple<_Tps...>> : true_type
+ { };
+
/// tuple_cat
template<typename... _Tpls, typename = typename
enable_if<__and_<__is_tuple_like<_Tpls>...>::value>::type>
diff --git a/libstdc++-v3/include/std/type_traits b/libstdc++-v3/include/std/type_traits
index 15ec83a06b8..0d821f9c074 100644
--- a/libstdc++-v3/include/std/type_traits
+++ b/libstdc++-v3/include/std/type_traits
@@ -41,9 +41,6 @@ namespace std _GLIBCXX_VISIBILITY(default)
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION
- template<typename... _Elements>
- class tuple;
-
template<typename _Tp>
class reference_wrapper;
@@ -2680,10 +2677,6 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
struct __is_tuple_like_impl : false_type
{ };
- template<typename... _Tps>
- struct __is_tuple_like_impl<tuple<_Tps...>> : true_type
- { };
-
// Internal type trait that allows us to sfinae-protect tuple_cat.
template<typename _Tp>
struct __is_tuple_like
diff --git a/libstdc++-v3/include/std/utility b/libstdc++-v3/include/std/utility
index 3e68f682e00..c2697f87dc5 100644
--- a/libstdc++-v3/include/std/utility
+++ b/libstdc++-v3/include/std/utility
@@ -60,9 +60,8 @@
/**
* @defgroup utilities Utilities
*
- * Components deemed generally useful. Includes pair, tuple,
- * forward/move helpers, ratio, function object, metaprogramming and
- * type traits, time, date, and memory functions.
+ * Basic function and class templates used with the rest of the library.
+ * Includes pair, swap, forward/move helpers, declval, integer_sequence.
*/
#include <bits/c++config.h>
@@ -71,218 +70,21 @@
#if __cplusplus >= 201103L
+#include <initializer_list>
#include <type_traits>
#include <bits/move.h>
-#include <initializer_list>
+#include <bits/utility.h>
-#if __cplusplus > 201703L
-#include <ext/numeric_traits.h>
+#if __cplusplus >= 202002L
+#include <ext/numeric_traits.h> // __is_standard_integer, __int_traits
#endif
namespace std _GLIBCXX_VISIBILITY(default)
{
_GLIBCXX_BEGIN_NAMESPACE_VERSION
- /// Finds the size of a given tuple type.
- template<typename _Tp>
- struct tuple_size;
-
- // _GLIBCXX_RESOLVE_LIB_DEFECTS
- // 2313. tuple_size should always derive from integral_constant<size_t, N>
- // 2770. tuple_size<const T> specialization is not SFINAE compatible
-
- template<typename _Tp,
- typename _Up = typename remove_cv<_Tp>::type,
- typename = typename enable_if<is_same<_Tp, _Up>::value>::type,
- size_t = tuple_size<_Tp>::value>
- using __enable_if_has_tuple_size = _Tp;
-
- template<typename _Tp>
- struct tuple_size<const __enable_if_has_tuple_size<_Tp>>
- : public tuple_size<_Tp> { };
-
- template<typename _Tp>
- struct tuple_size<volatile __enable_if_has_tuple_size<_Tp>>
- : public tuple_size<_Tp> { };
-
- template<typename _Tp>
- struct tuple_size<const volatile __enable_if_has_tuple_size<_Tp>>
- : public tuple_size<_Tp> { };
-
- /// Gives the type of the ith element of a given tuple type.
- template<size_t __i, typename _Tp>
- struct tuple_element;
-
- // Duplicate of C++14's tuple_element_t for internal use in C++11 mode
- template<size_t __i, typename _Tp>
- using __tuple_element_t = typename tuple_element<__i, _Tp>::type;
-
- template<size_t __i, typename _Tp>
- struct tuple_element<__i, const _Tp>
- {
- typedef typename add_const<__tuple_element_t<__i, _Tp>>::type type;
- };
-
- template<size_t __i, typename _Tp>
- struct tuple_element<__i, volatile _Tp>
- {
- typedef typename add_volatile<__tuple_element_t<__i, _Tp>>::type type;
- };
-
- template<size_t __i, typename _Tp>
- struct tuple_element<__i, const volatile _Tp>
- {
- typedef typename add_cv<__tuple_element_t<__i, _Tp>>::type type;
- };
-
-#if __cplusplus >= 201402L
-// The standard says this macro and alias template should be in <tuple>
-// but we define them here, to be available when the partial specializations
-// of tuple_element<pair<T,U>> and tuple_element<array<T,N>> are defined.
-#define __cpp_lib_tuple_element_t 201402L
-
- template<size_t __i, typename _Tp>
- using tuple_element_t = typename tuple_element<__i, _Tp>::type;
-#endif
-
- // Various functions which give std::pair a tuple-like interface.
-
- /// Partial specialization for std::pair
- template<typename _T1, typename _T2>
- struct __is_tuple_like_impl<pair<_T1, _T2>> : true_type
- { };
-
- /// Partial specialization for std::pair
- template<class _Tp1, class _Tp2>
- struct tuple_size<pair<_Tp1, _Tp2>>
- : public integral_constant<size_t, 2> { };
-
- /// Partial specialization for std::pair
- template<class _Tp1, class _Tp2>
- struct tuple_element<0, pair<_Tp1, _Tp2>>
- { typedef _Tp1 type; };
-
- /// Partial specialization for std::pair
- template<class _Tp1, class _Tp2>
- struct tuple_element<1, pair<_Tp1, _Tp2>>
- { typedef _Tp2 type; };
-
- template<size_t _Int>
- struct __pair_get;
-
- template<>
- struct __pair_get<0>
- {
- template<typename _Tp1, typename _Tp2>
- static constexpr _Tp1&
- __get(pair<_Tp1, _Tp2>& __pair) noexcept
- { return __pair.first; }
-
- template<typename _Tp1, typename _Tp2>
- static constexpr _Tp1&&
- __move_get(pair<_Tp1, _Tp2>&& __pair) noexcept
- { return std::forward<_Tp1>(__pair.first); }
-
- template<typename _Tp1, typename _Tp2>
- static constexpr const _Tp1&
- __const_get(const pair<_Tp1, _Tp2>& __pair) noexcept
- { return __pair.first; }
-
- template<typename _Tp1, typename _Tp2>
- static constexpr const _Tp1&&
- __const_move_get(const pair<_Tp1, _Tp2>&& __pair) noexcept
- { return std::forward<const _Tp1>(__pair.first); }
- };
-
- template<>
- struct __pair_get<1>
- {
- template<typename _Tp1, typename _Tp2>
- static constexpr _Tp2&
- __get(pair<_Tp1, _Tp2>& __pair) noexcept
- { return __pair.second; }
-
- template<typename _Tp1, typename _Tp2>
- static constexpr _Tp2&&
- __move_get(pair<_Tp1, _Tp2>&& __pair) noexcept
- { return std::forward<_Tp2>(__pair.second); }
-
- template<typename _Tp1, typename _Tp2>
- static constexpr const _Tp2&
- __const_get(const pair<_Tp1, _Tp2>& __pair) noexcept
- { return __pair.second; }
-
- template<typename _Tp1, typename _Tp2>
- static constexpr const _Tp2&&
- __const_move_get(const pair<_Tp1, _Tp2>&& __pair) noexcept
- { return std::forward<const _Tp2>(__pair.second); }
- };
-
- template<size_t _Int, class _Tp1, class _Tp2>
- constexpr typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&
- get(pair<_Tp1, _Tp2>& __in) noexcept
- { return __pair_get<_Int>::__get(__in); }
-
- template<size_t _Int, class _Tp1, class _Tp2>
- constexpr typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&&
- get(pair<_Tp1, _Tp2>&& __in) noexcept
- { return __pair_get<_Int>::__move_get(std::move(__in)); }
-
- template<size_t _Int, class _Tp1, class _Tp2>
- constexpr const typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&
- get(const pair<_Tp1, _Tp2>& __in) noexcept
- { return __pair_get<_Int>::__const_get(__in); }
-
- template<size_t _Int, class _Tp1, class _Tp2>
- constexpr const typename tuple_element<_Int, pair<_Tp1, _Tp2>>::type&&
- get(const pair<_Tp1, _Tp2>&& __in) noexcept
- { return __pair_get<_Int>::__const_move_get(std::move(__in)); }
-
#if __cplusplus >= 201402L
-
-#define __cpp_lib_tuples_by_type 201304
-
- template <typename _Tp, typename _Up>
- constexpr _Tp&
- get(pair<_Tp, _Up>& __p) noexcept
- { return __p.first; }
-
- template <typename _Tp, typename _Up>
- constexpr const _Tp&
- get(const pair<_Tp, _Up>& __p) noexcept
- { return __p.first; }
-
- template <typename _Tp, typename _Up>
- constexpr _Tp&&
- get(pair<_Tp, _Up>&& __p) noexcept
- { return std::move(__p.first); }
-
- template <typename _Tp, typename _Up>
- constexpr const _Tp&&
- get(const pair<_Tp, _Up>&& __p) noexcept
- { return std::move(__p.first); }
-
- template <typename _Tp, typename _Up>
- constexpr _Tp&
- get(pair<_Up, _Tp>& __p) noexcept
- { return __p.second; }
-
- template <typename _Tp, typename _Up>
- constexpr const _Tp&
- get(const pair<_Up, _Tp>& __p) noexcept
- { return __p.second; }
-
- template <typename _Tp, typename _Up>
- constexpr _Tp&&
- get(pair<_Up, _Tp>&& __p) noexcept
- { return std::move(__p.second); }
-
- template <typename _Tp, typename _Up>
- constexpr const _Tp&&
- get(const pair<_Up, _Tp>&& __p) noexcept
- { return std::move(__p.second); }
-
-#define __cpp_lib_exchange_function 201304
+#define __cpp_lib_exchange_function 201304L
/// Assign @p __new_val to @p __obj and return its previous value.
template <typename _Tp, typename _Up = _Tp>
@@ -291,100 +93,9 @@ _GLIBCXX_BEGIN_NAMESPACE_VERSION
exchange(_Tp& __obj, _Up&& __new_val)
{ return std::__exchange(__obj, std::forward<_Up>(__new_val)); }
-#endif // C++14
-
- // Stores a tuple of indices. Used by tuple and pair, and by bind() to
- // extract the elements in a tuple.
- template<size_t... _Indexes> struct _Index_tuple { };
-
- // Builds an _Index_tuple<0, 1, 2, ..., _Num-1>.
- template<size_t _Num>
- struct _Build_index_tuple
- {
-#if __has_builtin(__make_integer_seq)
- template<typename, size_t... _Indices>
- using _IdxTuple = _Index_tuple<_Indices...>;
-
- // Clang defines __make_integer_seq for this purpose.
- using __type = __make_integer_seq<_IdxTuple, size_t, _Num>;
-#else
- // For GCC and other compilers, use __integer_pack instead.
- using __type = _Index_tuple<__integer_pack(_Num)...>;
-#endif
- };
-
-#if __cplusplus >= 201402L
-
-#define __cpp_lib_integer_sequence 201304
-
- /// Class template integer_sequence
- template<typename _Tp, _Tp... _Idx>
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3 - Build # 12 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3
Culprit:
<cut>
commit 0fb299072c5b26396ab84002445570f296be44b3
Author: Jez Ng <jezng(a)fb.com>
Date: Sun Jul 11 21:34:31 2021 -0400
[lld-macho][nfc] Fix YAML input in compact-unwind-sym-relocs.s
* Adjust strsize so llvm-objdump doesn't complain about it extending
past the end of file
* Remove symbol that was referencing a deleted section
* Adjust n_sect of the remaining `_main` symbol to point at the right
section
</cut>
Results regressed to (for first_bad == 0fb299072c5b26396ab84002445570f296be44b3)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-0fb299072c5b26396ab84002445570f296be44b3/results_id:
1
# 433.milc,milc_base.default regressed by 105
# 433.milc,[.] mult_su3_mat_vec regressed by 132
from (for last_good == a7b7b5dfe5a931a76cbe8410e5a9f55beea73c8e)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -- -O3 artifacts/build-a7b7b5dfe5a931a76cbe8410e5a9f55beea73c8e/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/2801
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3/2794
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-0fb299072c5b26396ab84002445570f296be44b3
cd investigate-llvm-0fb299072c5b26396ab84002445570f296be44b3
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 0fb299072c5b26396ab84002445570f296be44b3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach a7b7b5dfe5a931a76cbe8410e5a9f55beea73c8e
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 0fb299072c5b26396ab84002445570f296be44b3
Author: Jez Ng <jezng(a)fb.com>
Date: Sun Jul 11 21:34:31 2021 -0400
[lld-macho][nfc] Fix YAML input in compact-unwind-sym-relocs.s
* Adjust strsize so llvm-objdump doesn't complain about it extending
past the end of file
* Remove symbol that was referencing a deleted section
* Adjust n_sect of the remaining `_main` symbol to point at the right
section
---
lld/test/MachO/compact-unwind-sym-relocs.s | 11 +++--------
1 file changed, 3 insertions(+), 8 deletions(-)
diff --git a/lld/test/MachO/compact-unwind-sym-relocs.s b/lld/test/MachO/compact-unwind-sym-relocs.s
index e87c3330841a..ff0896fd0daf 100644
--- a/lld/test/MachO/compact-unwind-sym-relocs.s
+++ b/lld/test/MachO/compact-unwind-sym-relocs.s
@@ -76,7 +76,7 @@ LoadCommands:
content: '0000000000000000010000000000020200000000000000000000000000000000'
relocations:
- address: 0x00000000
- symbolnum: 1
+ symbolnum: 0
pcrel: false
length: 3
extern: true
@@ -86,16 +86,11 @@ LoadCommands:
- cmd: LC_SYMTAB
cmdsize: 24
symoff: 520
- nsyms: 2
+ nsyms: 1
stroff: 552
- strsize: 24
+ strsize: 8
LinkEditData:
NameList:
- - n_strx: 8
- n_type: 0x0E
- n_sect: 2
- n_desc: 0
- n_value: 8
- n_strx: 2
n_type: 0x0F
n_sect: 1
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-master-arm-stable-allyesconfig - Build # 9 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-master-arm-stable-allyesconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-master-arm-stable-allyesconfig
Culprit:
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
</cut>
Results regressed to (for first_bad == 341db343768bc44f3512facc464021730d64071c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
19634
# First few build errors in logs:
# 00:03:00 drivers/power/supply/ab8500_fg.c:3061:32: error: use of undeclared identifier 'np'
# 00:03:00 make[3]: *** [scripts/Makefile.build:273: drivers/power/supply/ab8500_fg.o] Error 1
# 00:03:05 make[2]: *** [scripts/Makefile.build:516: drivers/power/supply] Error 2
# 00:03:05 make[1]: *** [scripts/Makefile.build:516: drivers/power] Error 2
# 00:03:54 make: *** [Makefile:1847: drivers] Error 2
from (for last_good == dc72a15859b2e604abb8a4bff123fbac8a0be92a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
19722
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-341db343768bc44f3512facc464021730d64071c
cd investigate-linux-341db343768bc44f3512facc464021730d64071c
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 341db343768bc44f3512facc464021730d64071c
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dc72a15859b2e604abb8a4bff123fbac8a0be92a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-master-arm-stable-al…
Full commit (up to 1000 lines):
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/power/supply/ab8500-bm.h | 4 +
drivers/power/supply/ab8500_btemp.c | 118 +++++-------
drivers/power/supply/ab8500_charger.c | 339 +++++++++++++++++++--------------
drivers/power/supply/ab8500_fg.c | 136 +++++++------
drivers/power/supply/abx500_chargalg.c | 116 ++++++-----
5 files changed, 379 insertions(+), 334 deletions(-)
diff --git a/drivers/power/supply/ab8500-bm.h b/drivers/power/supply/ab8500-bm.h
index 41c69a4f2a1f..012595a9d269 100644
--- a/drivers/power/supply/ab8500-bm.h
+++ b/drivers/power/supply/ab8500-bm.h
@@ -730,4 +730,8 @@ int ab8500_bm_of_probe(struct device *dev,
struct device_node *np,
struct abx500_bm_data *bm);
+extern struct platform_driver ab8500_fg_driver;
+extern struct platform_driver ab8500_btemp_driver;
+extern struct platform_driver abx500_chargalg_driver;
+
#endif /* _AB8500_CHARGER_H_ */
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index fdfcd59fc43e..3598b5a748e7 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/slab.h>
@@ -932,26 +933,6 @@ static int __maybe_unused ab8500_btemp_suspend(struct device *dev)
return 0;
}
-static int ab8500_btemp_remove(struct platform_device *pdev)
-{
- struct ab8500_btemp *di = platform_get_drvdata(pdev);
- int i, irq;
-
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
-
- /* Delete the work queue */
- destroy_workqueue(di->btemp_wq);
-
- flush_scheduled_work();
- power_supply_unregister(di->btemp_psy);
-
- return 0;
-}
-
static char *supply_interface[] = {
"ab8500_chargalg",
"ab8500_fg",
@@ -966,6 +947,40 @@ static const struct power_supply_desc ab8500_btemp_desc = {
.external_power_changed = ab8500_btemp_external_power_changed,
};
+static int ab8500_btemp_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for the btemp */
+ di->btemp_wq =
+ alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
+ if (di->btemp_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Kick off periodic temperature measurements */
+ ab8500_btemp_periodic(di, true);
+
+ return 0;
+}
+
+static void ab8500_btemp_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Delete the work queue */
+ destroy_workqueue(di->btemp_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_btemp_component_ops = {
+ .bind = ab8500_btemp_bind,
+ .unbind = ab8500_btemp_unbind,
+};
+
static int ab8500_btemp_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -1011,14 +1026,6 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
psy_cfg.num_supplicants = ARRAY_SIZE(supply_interface);
psy_cfg.drv_data = di;
- /* Create a work queue for the btemp */
- di->btemp_wq =
- alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
- if (di->btemp_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for measuring temperature periodically */
INIT_DEFERRABLE_WORK(&di->btemp_periodic_work,
ab8500_btemp_periodic_work);
@@ -1031,7 +1038,7 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
AB8500_BTEMP_HIGH_TH, &val);
if (ret < 0) {
dev_err(dev, "%s ab8500 read failed\n", __func__);
- goto free_btemp_wq;
+ return ret;
}
switch (val) {
case BTEMP_HIGH_TH_57_0:
@@ -1050,30 +1057,28 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
}
/* Register BTEMP power supply class */
- di->btemp_psy = power_supply_register(dev, &ab8500_btemp_desc,
- &psy_cfg);
+ di->btemp_psy = devm_power_supply_register(dev, &ab8500_btemp_desc,
+ &psy_cfg);
if (IS_ERR(di->btemp_psy)) {
dev_err(dev, "failed to register BTEMP psy\n");
- ret = PTR_ERR(di->btemp_psy);
- goto free_btemp_wq;
+ return PTR_ERR(di->btemp_psy);
}
/* Register interrupts */
for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_btemp_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_btemp_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_btemp_irq[i].name, di);
if (ret) {
dev_err(dev, "failed to request %s IRQ %d: %d\n"
, ab8500_btemp_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_btemp_irq[i].name, irq, ret);
@@ -1081,23 +1086,16 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, di);
- /* Kick off periodic temperature measurements */
- ab8500_btemp_periodic(di, true);
list_add_tail(&di->node, &ab8500_btemp_list);
- return ret;
+ return component_add(dev, &ab8500_btemp_component_ops);
+}
-free_irq:
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_btemp_remove(struct platform_device *pdev)
+{
+ component_del(&pdev->dev, &ab8500_btemp_component_ops);
- power_supply_unregister(di->btemp_psy);
-free_btemp_wq:
- destroy_workqueue(di->btemp_wq);
- return ret;
+ return 0;
}
static SIMPLE_DEV_PM_OPS(ab8500_btemp_pm_ops, ab8500_btemp_suspend, ab8500_btemp_resume);
@@ -1107,7 +1105,7 @@ static const struct of_device_id ab8500_btemp_match[] = {
{ },
};
-static struct platform_driver ab8500_btemp_driver = {
+struct platform_driver ab8500_btemp_driver = {
.probe = ab8500_btemp_probe,
.remove = ab8500_btemp_remove,
.driver = {
@@ -1116,20 +1114,6 @@ static struct platform_driver ab8500_btemp_driver = {
.pm = &ab8500_btemp_pm_ops,
},
};
-
-static int __init ab8500_btemp_init(void)
-{
- return platform_driver_register(&ab8500_btemp_driver);
-}
-
-static void __exit ab8500_btemp_exit(void)
-{
- platform_driver_unregister(&ab8500_btemp_driver);
-}
-
-device_initcall(ab8500_btemp_init);
-module_exit(ab8500_btemp_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski, Arun R Murthy");
MODULE_ALIAS("platform:ab8500-btemp");
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index a9be10eb2c22..af32cfae9f19 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/notifier.h>
@@ -3276,10 +3277,74 @@ static struct notifier_block charger_nb = {
.notifier_call = ab8500_external_charger_prepare,
};
-static int ab8500_charger_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_chargalg",
+ "ab8500_fg",
+ "ab8500_btemp",
+};
+
+static const struct power_supply_desc ab8500_ac_chg_desc = {
+ .name = "ab8500_ac",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = ab8500_charger_ac_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
+ .get_property = ab8500_charger_ac_get_property,
+};
+
+static const struct power_supply_desc ab8500_usb_chg_desc = {
+ .name = "ab8500_usb",
+ .type = POWER_SUPPLY_TYPE_USB,
+ .properties = ab8500_charger_usb_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
+ .get_property = ab8500_charger_usb_get_property,
+};
+
+static int ab8500_charger_bind(struct device *dev)
{
- struct ab8500_charger *di = platform_get_drvdata(pdev);
- int i, irq, ret;
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ch_stat;
+ int ret;
+
+ /* Create a work queue for the charger */
+ di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
+ WQ_MEM_RECLAIM);
+ if (di->charger_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ ch_stat = ab8500_charger_detect_chargers(di, false);
+
+ if (ch_stat & AC_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->ac_charger_attached_work,
+ HZ);
+ }
+ if (ch_stat & USB_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->usb_charger_attached_work,
+ HZ);
+ di->vbus_detected = true;
+ di->vbus_detected_start = true;
+ queue_work(di->charger_wq,
+ &di->detect_usb_type_work);
+ }
+
+ ret = component_bind_all(dev, di);
+ if (ret) {
+ dev_err(dev, "can't bind component devices\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static void ab8500_charger_unbind(struct device *dev)
+{
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ret;
/* Disable AC charging */
ab8500_charger_ac_en(&di->ac_chg, false, 0, 0);
@@ -3287,68 +3352,47 @@ static int ab8500_charger_remove(struct platform_device *pdev)
/* Disable USB charging */
ab8500_charger_usb_en(&di->usb_chg, false, 0, 0);
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
-
/* Backup battery voltage and current disable */
ret = abx500_mask_and_set_register_interruptible(di->dev,
AB8500_RTC, AB8500_RTC_CTRL_REG, RTC_BUP_CH_ENA, 0);
if (ret < 0)
dev_err(di->dev, "%s mask and set failed\n", __func__);
- usb_unregister_notifier(di->usb_phy, &di->nb);
- usb_put_phy(di->usb_phy);
-
/* Delete the work queue */
destroy_workqueue(di->charger_wq);
- /* Unregister external charger enable notifier */
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_unregister(
- &charger_notifier_list, &charger_nb);
-
flush_scheduled_work();
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-
- if (di->ac_chg.enabled && !di->ac_chg.external)
- power_supply_unregister(di->ac_chg.psy);
- return 0;
+ /* Unbind fg, btemp, algorithm */
+ component_unbind_all(dev, di);
}
-static char *supply_interface[] = {
- "ab8500_chargalg",
- "ab8500_fg",
- "ab8500_btemp",
+static const struct component_master_ops ab8500_charger_comp_ops = {
+ .bind = ab8500_charger_bind,
+ .unbind = ab8500_charger_unbind,
};
-static const struct power_supply_desc ab8500_ac_chg_desc = {
- .name = "ab8500_ac",
- .type = POWER_SUPPLY_TYPE_MAINS,
- .properties = ab8500_charger_ac_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
- .get_property = ab8500_charger_ac_get_property,
+static struct platform_driver *const ab8500_charger_component_drivers[] = {
+ &ab8500_fg_driver,
+ &ab8500_btemp_driver,
+ &abx500_chargalg_driver,
};
-static const struct power_supply_desc ab8500_usb_chg_desc = {
- .name = "ab8500_usb",
- .type = POWER_SUPPLY_TYPE_USB,
- .properties = ab8500_charger_usb_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
- .get_property = ab8500_charger_usb_get_property,
-};
+static int ab8500_charger_compare_dev(struct device *dev, void *data)
+{
+ return dev == data;
+}
static int ab8500_charger_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct component_match *match = NULL;
struct power_supply_config ac_psy_cfg = {}, usb_psy_cfg = {};
struct ab8500_charger *di;
- int irq, i, charger_status, ret = 0, ch_stat;
- struct device *dev = &pdev->dev;
+ int charger_status;
+ int i, irq;
+ int ret;
di = devm_kzalloc(dev, sizeof(*di), GFP_KERNEL);
if (!di)
@@ -3393,6 +3437,38 @@ static int ab8500_charger_probe(struct platform_device *pdev)
return ret;
}
+ /*
+ * VDD ADC supply needs to be enabled from this driver when there
+ * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
+ * interrupts during charging
+ */
+ di->regu = devm_regulator_get(dev, "vddadc");
+ if (IS_ERR(di->regu)) {
+ ret = PTR_ERR(di->regu);
+ dev_err(dev, "failed to get vddadc regulator\n");
+ return ret;
+ }
+
+ /* Request interrupts */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
+ irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+ if (irq < 0)
+ return irq;
+
+ ret = devm_request_threaded_irq(dev,
+ irq, NULL, ab8500_charger_irq[i].isr,
+ IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
+ ab8500_charger_irq[i].name, di);
+
+ if (ret != 0) {
+ dev_err(dev, "failed to request %s IRQ %d: %d\n"
+ , ab8500_charger_irq[i].name, irq, ret);
+ return ret;
+ }
+ dev_dbg(dev, "Requested %s IRQ %d: %d\n",
+ ab8500_charger_irq[i].name, irq, ret);
+ }
+
/* initialize lock */
spin_lock_init(&di->usb_state.usb_lock);
mutex_init(&di->usb_ipt_crnt_lock);
@@ -3422,11 +3498,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->ac_chg.enabled = di->bm->ac_enabled;
di->ac_chg.external = false;
- /*notifier for external charger enabling*/
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_register(
- &charger_notifier_list, &charger_nb);
-
/* USB supply */
/* ux500_charger sub-class */
di->usb_chg.ops.enable = &ab8500_charger_usb_en;
@@ -3442,14 +3513,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->usb_chg.external = false;
di->usb_state.usb_current = -1;
- /* Create a work queue for the charger */
- di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
- WQ_MEM_RECLAIM);
- if (di->charger_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
mutex_init(&di->charger_attached_mutex);
/* Init work for HW failure check */
@@ -3500,63 +3563,36 @@ static int ab8500_charger_probe(struct platform_device *pdev)
INIT_WORK(&di->check_usb_thermal_prot_work,
ab8500_charger_check_usb_thermal_prot_work);
- /*
- * VDD ADC supply needs to be enabled from this driver when there
- * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
- * interrupts during charging
- */
- di->regu = devm_regulator_get(dev, "vddadc");
- if (IS_ERR(di->regu)) {
- ret = PTR_ERR(di->regu);
- dev_err(dev, "failed to get vddadc regulator\n");
- goto free_charger_wq;
- }
-
/* Initialize OVV, and other registers */
ret = ab8500_charger_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize ABB registers\n");
- goto free_charger_wq;
+ return ret;
}
/* Register AC charger class */
if (di->ac_chg.enabled) {
- di->ac_chg.psy = power_supply_register(dev,
+ di->ac_chg.psy = devm_power_supply_register(dev,
&ab8500_ac_chg_desc,
&ac_psy_cfg);
if (IS_ERR(di->ac_chg.psy)) {
dev_err(dev, "failed to register AC charger\n");
- ret = PTR_ERR(di->ac_chg.psy);
- goto free_charger_wq;
+ return PTR_ERR(di->ac_chg.psy);
}
}
/* Register USB charger class */
if (di->usb_chg.enabled) {
- di->usb_chg.psy = power_supply_register(dev,
+ di->usb_chg.psy = devm_power_supply_register(dev,
&ab8500_usb_chg_desc,
&usb_psy_cfg);
if (IS_ERR(di->usb_chg.psy)) {
dev_err(dev, "failed to register USB charger\n");
- ret = PTR_ERR(di->usb_chg.psy);
- goto free_ac;
+ return PTR_ERR(di->usb_chg.psy);
}
}
- di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
- if (IS_ERR_OR_NULL(di->usb_phy)) {
- dev_err(dev, "failed to get usb transceiver\n");
- ret = -EINVAL;
- goto free_usb;
- }
- di->nb.notifier_call = ab8500_charger_usb_notifier_call;
- ret = usb_register_notifier(di->usb_phy, &di->nb);
- if (ret) {
- dev_err(dev, "failed to register usb notifier\n");
- goto put_usb_phy;
- }
-
/* Identify the connected charger types during startup */
charger_status = ab8500_charger_detect_chargers(di, true);
if (charger_status & AC_PW_CONN) {
@@ -3566,78 +3602,86 @@ static int ab8500_charger_probe(struct platform_device *pdev)
sysfs_notify(&di->ac_chg.psy->dev.kobj, NULL, "present");
}
- if (charger_status & USB_PW_CONN) {
- di->vbus_detected = true;
- di->vbus_detected_start = true;
- queue_work(di->charger_wq,
- &di->detect_usb_type_work);
- }
-
- /* Register interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ platform_set_drvdata(pdev, di);
- ret = request_threaded_irq(irq, NULL, ab8500_charger_irq[i].isr,
- IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
- ab8500_charger_irq[i].name, di);
+ /* Create something that will match the subdrivers when we bind */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_component_drivers); i++) {
+ struct device_driver *drv = &ab8500_charger_component_drivers[i]->driver;
+ struct device *p = NULL, *d;
- if (ret != 0) {
- dev_err(dev, "failed to request %s IRQ %d: %d\n"
- , ab8500_charger_irq[i].name, irq, ret);
- goto free_irq;
+ while ((d = platform_find_device_by_driver(p, drv))) {
+ put_device(p);
+ component_match_add(dev, &match,
+ ab8500_charger_compare_dev, d);
+ p = d;
}
- dev_dbg(dev, "Requested %s IRQ %d: %d\n",
- ab8500_charger_irq[i].name, irq, ret);
+ put_device(p);
+ }
+ if (!match) {
+ dev_err(dev, "no matching components\n");
+ return -ENODEV;
+ }
+ if (IS_ERR(match)) {
+ dev_err(dev, "could not create component match\n");
+ return PTR_ERR(match);
}
- platform_set_drvdata(pdev, di);
+ /* Notifier for external charger enabling */
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_register(
+ &charger_notifier_list, &charger_nb);
- mutex_lock(&di->charger_attached_mutex);
- ch_stat = ab8500_charger_detect_chargers(di, false);
-
- if ((ch_stat & AC_PW_CONN) == AC_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->ac_charger_attached_work,
- HZ);
+ di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
+ if (IS_ERR_OR_NULL(di->usb_phy)) {
+ dev_err(dev, "failed to get usb transceiver\n");
+ ret = -EINVAL;
+ goto out_charger_notifier;
}
- if ((ch_stat & USB_PW_CONN) == USB_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->usb_charger_attached_work,
- HZ);
+ di->nb.notifier_call = ab8500_charger_usb_notifier_call;
+ ret = usb_register_notifier(di->usb_phy, &di->nb);
+ if (ret) {
+ dev_err(dev, "failed to register usb notifier\n");
+ goto put_usb_phy;
}
- mutex_unlock(&di->charger_attached_mutex);
- return ret;
+ ret = component_master_add_with_match(&pdev->dev,
+ &ab8500_charger_comp_ops,
+ match);
+ if (ret) {
+ dev_err(dev, "failed to add component master\n");
+ goto free_notifier;
+ }
-free_irq:
- usb_unregister_notifier(di->usb_phy, &di->nb);
+ return 0;
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
+free_notifier:
+ usb_unregister_notifier(di->usb_phy, &di->nb);
put_usb_phy:
usb_put_phy(di->usb_phy);
-free_usb:
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-free_ac:
- if (di->ac_chg.enabled)
- power_supply_unregister(di->ac_chg.psy);
-free_charger_wq:
- destroy_workqueue(di->charger_wq);
+out_charger_notifier:
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
return ret;
}
+static int ab8500_charger_remove(struct platform_device *pdev)
+{
+ struct ab8500_charger *di = platform_get_drvdata(pdev);
+
+ component_master_del(&pdev->dev, &ab8500_charger_comp_ops);
+
+ usb_unregister_notifier(di->usb_phy, &di->nb);
+ usb_put_phy(di->usb_phy);
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
+
+ return 0;
+}
+
static SIMPLE_DEV_PM_OPS(ab8500_charger_pm_ops, ab8500_charger_suspend, ab8500_charger_resume);
static const struct of_device_id ab8500_charger_match[] = {
@@ -3657,15 +3701,24 @@ static struct platform_driver ab8500_charger_driver = {
static int __init ab8500_charger_init(void)
{
+ int ret;
+
+ ret = platform_register_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
+ if (ret)
+ return ret;
+
return platform_driver_register(&ab8500_charger_driver);
}
static void __exit ab8500_charger_exit(void)
{
+ platform_unregister_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
platform_driver_unregister(&ab8500_charger_driver);
}
-subsys_initcall_sync(ab8500_charger_init);
+module_init(ab8500_charger_init);
module_exit(ab8500_charger_exit);
MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index 0c7c01a0d979..acf0f2471c0b 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/component.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
@@ -2980,27 +2981,6 @@ static int __maybe_unused ab8500_fg_suspend(struct device *dev)
return 0;
}
-static int ab8500_fg_remove(struct platform_device *pdev)
-{
- int ret = 0;
- struct ab8500_fg *di = platform_get_drvdata(pdev);
-
- list_del(&di->node);
-
- /* Disable coulomb counter */
- ret = ab8500_fg_coulomb_counter(di, false);
- if (ret)
- dev_err(di->dev, "failed to disable coulomb counter\n");
-
- destroy_workqueue(di->fg_wq);
- ab8500_fg_sysfs_exit(di);
-
- flush_scheduled_work();
- ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
- return ret;
-}
-
/* ab8500 fg driver interrupts and their respective isr */
static struct ab8500_fg_interrupts ab8500_fg_irq[] = {
{"NCONV_ACCU", ab8500_fg_cc_convend_handler},
@@ -3024,11 +3004,50 @@ static const struct power_supply_desc ab8500_fg_desc = {
.external_power_changed = ab8500_fg_external_power_changed,
};
+static int ab8500_fg_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for running the FG algorithm */
+ di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
+ if (di->fg_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Start the coulomb counter */
+ ab8500_fg_coulomb_counter(di, true);
+ /* Run the FG algorithm */
+ queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+
+ return 0;
+}
+
+static void ab8500_fg_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+ int ret;
+
+ /* Disable coulomb counter */
+ ret = ab8500_fg_coulomb_counter(di, false);
+ if (ret)
+ dev_err(dev, "failed to disable coulomb counter\n");
+
+ destroy_workqueue(di->fg_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_fg_component_ops = {
+ .bind = ab8500_fg_bind,
+ .unbind = ab8500_fg_unbind,
+};
+
static int ab8500_fg_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
- struct power_supply_config psy_cfg = {};
struct device *dev = &pdev->dev;
+ struct power_supply_config psy_cfg = {};
struct ab8500_fg *di;
int i, irq;
int ret = 0;
@@ -3074,13 +3093,6 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INIT);
- /* Create a work queue for running the FG algorithm */
- di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
- if (di->fg_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for running the fg algorithm instantly */
INIT_WORK(&di->fg_work, ab8500_fg_instant_work);
@@ -3113,7 +3125,7 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize registers\n");
- goto free_inst_curr_wq;
+ return ret;
}
/* Consider battery unknown until we're informed otherwise */
@@ -3121,15 +3133,13 @@ static int ab8500_fg_probe(struct platform_device *pdev)
di->flags.batt_id_received = false;
/* Register FG power supply class */
- di->fg_psy = power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
+ di->fg_psy = devm_power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
if (IS_ERR(di->fg_psy)) {
dev_err(dev, "failed to register FG psy\n");
- ret = PTR_ERR(di->fg_psy);
- goto free_inst_curr_wq;
+ return PTR_ERR(di->fg_psy);
}
di->fg_samples = SEC_TO_SAMPLE(di->bm->fg_params->init_timer);
- ab8500_fg_coulomb_counter(di, true);
/*
* Initialize completion used to notify completion and start
@@ -3141,19 +3151,18 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Register primary interrupt handlers */
for (i = 0; i < ARRAY_SIZE(ab8500_fg_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_fg_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_fg_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_fg_irq[i].name, di);
if (ret != 0) {
dev_err(dev, "failed to request %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
@@ -3168,14 +3177,14 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_sysfs_init(di);
if (ret) {
dev_err(dev, "failed to create sysfs entry\n");
- goto free_irq;
+ return ret;
}
ret = ab8500_fg_sysfs_psy_create_attrs(di);
if (ret) {
dev_err(dev, "failed to create FG psy\n");
ab8500_fg_sysfs_exit(di);
- goto free_irq;
+ return ret;
}
/* Calibrate the fg first time */
@@ -3185,24 +3194,21 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Use room temp as default value until we get an update from driver. */
di->bat_temp = 210;
- /* Run the FG algorithm */
- queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
-
list_add_tail(&di->node, &ab8500_fg_list);
- return ret;
+ return component_add(dev, &ab8500_fg_component_ops);
+}
-free_irq:
- /* We also have to free all registered irqs */
- while (--i >= 0) {
- /* Last assignment of i from primary interrupt handlers */
- irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_fg_remove(struct platform_device *pdev)
+{
+ int ret = 0;
+ struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+ component_del(&pdev->dev, &ab8500_fg_component_ops);
+ list_del(&di->node);
+ ab8500_fg_sysfs_exit(di);
+ ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
-free_inst_curr_wq:
- destroy_workqueue(di->fg_wq);
return ret;
}
@@ -3213,7 +3219,7 @@ static const struct of_device_id ab8500_fg_match[] = {
{ },
};
-static struct platform_driver ab8500_fg_driver = {
+struct platform_driver ab8500_fg_driver = {
.probe = ab8500_fg_probe,
.remove = ab8500_fg_remove,
.driver = {
@@ -3222,20 +3228,6 @@ static struct platform_driver ab8500_fg_driver = {
.pm = &ab8500_fg_pm_ops,
},
};
-
-static int __init ab8500_fg_init(void)
-{
- return platform_driver_register(&ab8500_fg_driver);
-}
-
-static void __exit ab8500_fg_exit(void)
-{
- platform_driver_unregister(&ab8500_fg_driver);
-}
-
-subsys_initcall_sync(ab8500_fg_init);
-module_exit(ab8500_fg_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski");
MODULE_ALIAS("platform:ab8500-fg");
diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c
index f5b792243727..599684ce0e4b 100644
--- a/drivers/power/supply/abx500_chargalg.c
+++ b/drivers/power/supply/abx500_chargalg.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
@@ -1943,13 +1944,44 @@ static int __maybe_unused abx500_chargalg_suspend(struct device *dev)
return 0;
}
-static int abx500_chargalg_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_fg",
+};
+
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3_LTO - Build # 26 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit 45b7cf995551a0c0743e5d69f611bba7e4072ddf
Author: Sam Clegg <sbc(a)chromium.org>
Date: Wed May 12 16:48:34 2021 -0700
[lld][WebAssembly] Enable string tail merging in debug sections
This is a followup to https://reviews.llvm.org/D97657 which
applied string tail merging to data segments.
Fixes: https://bugs.llvm.org/show_bug.cgi?id=48828
Differential Revision: https://reviews.llvm.org/D102436
</cut>
Results regressed to (for first_bad == 45b7cf995551a0c0743e5d69f611bba7e4072ddf)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO -- artifacts/build-45b7cf995551a0c0743e5d69f611bba7e4072ddf/results_id:
1
# 433.milc,milc_base.default regressed by 104
from (for last_good == 8dd5ef01ef13e402784bba47f7a24175f5f00325)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO -- artifacts/build-8dd5ef01ef13e402784bba47f7a24175f5f00325/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3_LTO/2681
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3_LTO/2637
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-45b7cf995551a0c0743e5d69f611bba7e4072ddf
cd investigate-llvm-45b7cf995551a0c0743e5d69f611bba7e4072ddf
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 45b7cf995551a0c0743e5d69f611bba7e4072ddf
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 8dd5ef01ef13e402784bba47f7a24175f5f00325
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 45b7cf995551a0c0743e5d69f611bba7e4072ddf
Author: Sam Clegg <sbc(a)chromium.org>
Date: Wed May 12 16:48:34 2021 -0700
[lld][WebAssembly] Enable string tail merging in debug sections
This is a followup to https://reviews.llvm.org/D97657 which
applied string tail merging to data segments.
Fixes: https://bugs.llvm.org/show_bug.cgi?id=48828
Differential Revision: https://reviews.llvm.org/D102436
---
lld/test/wasm/Inputs/merge-string-debug2.s | 4 +++
lld/test/wasm/merge-string-debug.s | 22 ++++++++++++++
lld/wasm/Driver.cpp | 6 +++-
lld/wasm/InputChunks.cpp | 16 +++++-----
lld/wasm/InputChunks.h | 49 +++++++++++++++++-------------
lld/wasm/InputFiles.cpp | 23 +++++++++++---
lld/wasm/InputFiles.h | 4 +--
lld/wasm/OutputSections.cpp | 38 ++++++++++++++++++++---
lld/wasm/OutputSections.h | 5 +--
lld/wasm/OutputSegment.cpp | 7 ++---
lld/wasm/Symbols.cpp | 2 +-
lld/wasm/Symbols.h | 4 +--
lld/wasm/Writer.cpp | 4 +--
llvm/include/llvm/MC/MCContext.h | 5 +--
llvm/lib/MC/MCObjectFileInfo.cpp | 11 ++++---
15 files changed, 143 insertions(+), 57 deletions(-)
diff --git a/lld/test/wasm/Inputs/merge-string-debug2.s b/lld/test/wasm/Inputs/merge-string-debug2.s
new file mode 100644
index 000000000000..1f4979056ac8
--- /dev/null
+++ b/lld/test/wasm/Inputs/merge-string-debug2.s
@@ -0,0 +1,4 @@
+.section .debug_str,"S",@
+ .asciz "clang version 13.0.0"
+ .asciz "bar"
+ .asciz "foo"
diff --git a/lld/test/wasm/merge-string-debug.s b/lld/test/wasm/merge-string-debug.s
new file mode 100644
index 000000000000..4a663501959f
--- /dev/null
+++ b/lld/test/wasm/merge-string-debug.s
@@ -0,0 +1,22 @@
+# RUN: llvm-mc -filetype=obj -triple=wasm32-unknown-unknown %s -o %t.o
+# RUN: llvm-mc -filetype=obj -triple=wasm32-unknown-unknown %p/Inputs/merge-string-debug2.s -o %t2.o
+
+# RUN: wasm-ld %t.o %t2.o -o %t.wasm --no-entry
+# RUN: llvm-readobj -x .debug_str %t.wasm | FileCheck %s --check-prefixes CHECK,CHECK-O1
+
+# RUN: wasm-ld -O0 %t.o %t2.o -o %tO0.wasm --no-entry
+# RUN: llvm-readobj -x .debug_str %tO0.wasm | FileCheck %s --check-prefixes CHECK,CHECK-O0
+
+.section .debug_str,"S",@
+ .asciz "clang version 13.0.0"
+ .asciz "foobar"
+
+# CHECK: Hex dump of section '.debug_str':
+
+# CHECK-O0: 0x00000000 636c616e 67207665 7273696f 6e203133 clang version 13
+# CHECK-O0: 0x00000010 2e302e30 00666f6f 62617200 636c616e .0.0.foobar.clan
+# CHECK-O0: 0x00000020 67207665 7273696f 6e203133 2e302e30 g version 13.0.0
+# CHECK-O0: 0x00000030 00626172 00666f6f 00 .bar.foo.
+
+# CHECK-O1: 0x00000000 666f6f62 61720066 6f6f0063 6c616e67 foobar.foo.clang
+# CHECK-O1: 0x00000010 20766572 73696f6e 2031332e 302e3000 version 13.0.0.
diff --git a/lld/wasm/Driver.cpp b/lld/wasm/Driver.cpp
index 6fec9d5b2278..9b01a84f7812 100644
--- a/lld/wasm/Driver.cpp
+++ b/lld/wasm/Driver.cpp
@@ -796,7 +796,7 @@ static void wrapSymbols(ArrayRef<WrappedSymbol> wrapped) {
}
static void splitSections() {
- // splitIntoPieces needs to be called on each MergeInputSection
+ // splitIntoPieces needs to be called on each MergeInputChunk
// before calling finalizeContents().
LLVM_DEBUG(llvm::dbgs() << "splitSections\n");
parallelForEach(symtab->objectFiles, [](ObjFile *file) {
@@ -804,6 +804,10 @@ static void splitSections() {
if (auto *s = dyn_cast<MergeInputChunk>(seg))
s->splitIntoPieces();
}
+ for (InputChunk *sec : file->customSections) {
+ if (auto *s = dyn_cast<MergeInputChunk>(sec))
+ s->splitIntoPieces();
+ }
});
}
diff --git a/lld/wasm/InputChunks.cpp b/lld/wasm/InputChunks.cpp
index b7d1aa25e9c8..279cd41d1ff2 100644
--- a/lld/wasm/InputChunks.cpp
+++ b/lld/wasm/InputChunks.cpp
@@ -328,24 +328,24 @@ void InputFunction::writeCompressed(uint8_t *buf) const {
LLVM_DEBUG(dbgs() << " total: " << (buf + chunkSize - orig) << "\n");
}
-uint64_t InputChunk::getOffset(uint64_t offset) const {
- return outSecOff + offset;
-}
-
-uint64_t InputChunk::getSegmentOffset(uint64_t offset) const {
+uint64_t InputChunk::getChunkOffset(uint64_t offset) const {
if (const auto *ms = dyn_cast<MergeInputChunk>(this)) {
- LLVM_DEBUG(dbgs() << "getSegmentOffset(merged): " << getName() << "\n");
+ LLVM_DEBUG(dbgs() << "getChunkOffset(merged): " << getName() << "\n");
LLVM_DEBUG(dbgs() << "offset: " << offset << "\n");
LLVM_DEBUG(dbgs() << "parentOffset: " << ms->getParentOffset(offset)
<< "\n");
assert(ms->parent);
- return ms->parent->getSegmentOffset(ms->getParentOffset(offset));
+ return ms->parent->getChunkOffset(ms->getParentOffset(offset));
}
return outputSegmentOffset + offset;
}
+uint64_t InputChunk::getOffset(uint64_t offset) const {
+ return outSecOff + getChunkOffset(offset);
+}
+
uint64_t InputChunk::getVA(uint64_t offset) const {
- return (outputSeg ? outputSeg->startVA : 0) + getSegmentOffset(offset);
+ return (outputSeg ? outputSeg->startVA : 0) + getChunkOffset(offset);
}
// Generate code to apply relocations to the data section at runtime.
diff --git a/lld/wasm/InputChunks.h b/lld/wasm/InputChunks.h
index 47ed7ccaadcb..f1174d937ad3 100644
--- a/lld/wasm/InputChunks.h
+++ b/lld/wasm/InputChunks.h
@@ -43,7 +43,7 @@ public:
MergedChunk,
Function,
SyntheticFunction,
- Section
+ Section,
};
StringRef name;
@@ -62,12 +62,15 @@ public:
ArrayRef<WasmRelocation> getRelocations() const { return relocations; }
void setRelocations(ArrayRef<WasmRelocation> rs) { relocations = rs; }
- // Translate an offset in the input section to an offset in the output
+ // Translate an offset into the input chunk to an offset in the output
// section.
uint64_t getOffset(uint64_t offset) const;
- // For data segments, translate and offset into the input segment into
- // an offset into the output segment
- uint64_t getSegmentOffset(uint64_t offset) const;
+ // Translate an offset into the input chunk into an offset into the output
+ // chunk. For data segments (InputSegment) this will return and offset into
+ // the output segment. For MergeInputChunk, this will return an offset into
+ // the parent merged chunk. For other chunk types this is no-op and we just
+ // return unmodified offset.
+ uint64_t getChunkOffset(uint64_t offset) const;
uint64_t getVA(uint64_t offset = 0) const;
uint32_t getComdat() const { return comdat; }
@@ -132,22 +135,19 @@ protected:
// each global variable.
class InputSegment : public InputChunk {
public:
- InputSegment(const WasmSegment *seg, ObjFile *f)
- : InputChunk(f, InputChunk::DataSegment, seg->Data.Name,
- seg->Data.Alignment, seg->Data.LinkingFlags),
+ InputSegment(const WasmSegment &seg, ObjFile *f)
+ : InputChunk(f, InputChunk::DataSegment, seg.Data.Name,
+ seg.Data.Alignment, seg.Data.LinkingFlags),
segment(seg) {
- rawData = segment->Data.Content;
- comdat = segment->Data.Comdat;
- inputSectionOffset = segment->SectionOffset;
+ rawData = segment.Data.Content;
+ comdat = segment.Data.Comdat;
+ inputSectionOffset = segment.SectionOffset;
}
- InputSegment(StringRef name, uint32_t alignment, uint32_t flags)
- : InputChunk(nullptr, InputChunk::DataSegment, name, alignment, flags) {}
-
static bool classof(const InputChunk *c) { return c->kind() == DataSegment; }
protected:
- const WasmSegment *segment = nullptr;
+ const WasmSegment &segment;
};
class SyntheticMergedChunk;
@@ -174,12 +174,19 @@ static_assert(sizeof(SectionPiece) == 16, "SectionPiece is too big");
// This corresponds segments marked as WASM_SEG_FLAG_STRINGS.
class MergeInputChunk : public InputChunk {
public:
- MergeInputChunk(const WasmSegment *seg, ObjFile *f)
- : InputChunk(f, Merge, seg->Data.Name, seg->Data.Alignment,
- seg->Data.LinkingFlags) {
- rawData = seg->Data.Content;
- comdat = seg->Data.Comdat;
- inputSectionOffset = seg->SectionOffset;
+ MergeInputChunk(const WasmSegment &seg, ObjFile *f)
+ : InputChunk(f, Merge, seg.Data.Name, seg.Data.Alignment,
+ seg.Data.LinkingFlags) {
+ rawData = seg.Data.Content;
+ comdat = seg.Data.Comdat;
+ inputSectionOffset = seg.SectionOffset;
+ }
+
+ MergeInputChunk(const WasmSection &s, ObjFile *f)
+ : InputChunk(f, Merge, s.Name, 0, llvm::wasm::WASM_SEG_FLAG_STRINGS) {
+ assert(s.Type == llvm::wasm::WASM_SEC_CUSTOM);
+ comdat = s.Comdat;
+ rawData = s.Content;
}
static bool classof(const InputChunk *s) { return s->kind() == Merge; }
diff --git a/lld/wasm/InputFiles.cpp b/lld/wasm/InputFiles.cpp
index c65b05109c3d..7fd9215f1171 100644
--- a/lld/wasm/InputFiles.cpp
+++ b/lld/wasm/InputFiles.cpp
@@ -360,6 +360,17 @@ void ObjFile::addLegacyIndirectFunctionTableIfNeeded(
config->legacyFunctionTable = true;
}
+static bool shouldMerge(const WasmSection &sec) {
+ if (config->optimize == 0)
+ return false;
+ // Sadly we don't have section attributes yet for custom sections, so we
+ // currently go by the name alone.
+ // TODO(sbc): Add ability for wasm sections to carry flags so we don't
+ // need to use names here.
+ return sec.Name.startswith(".debug_str") ||
+ sec.Name.startswith(".debug_line_str");
+}
+
static bool shouldMerge(const WasmSegment &seg) {
// As of now we only support merging strings, and only with single byte
// alignment (2^0).
@@ -445,7 +456,11 @@ void ObjFile::parse(bool ignoreComdats) {
assert(!dataSection);
dataSection = §ion;
} else if (section.Type == WASM_SEC_CUSTOM) {
- auto *customSec = make<InputSection>(section, this);
+ InputChunk *customSec;
+ if (shouldMerge(section))
+ customSec = make<MergeInputChunk>(section, this);
+ else
+ customSec = make<InputSection>(section, this);
customSec->discarded = isExcludedByComdat(customSec);
customSections.emplace_back(customSec);
customSections.back()->setRelocations(section.Relocations);
@@ -466,9 +481,9 @@ void ObjFile::parse(bool ignoreComdats) {
for (const WasmSegment &s : wasmObj->dataSegments()) {
InputChunk *seg;
if (shouldMerge(s)) {
- seg = make<MergeInputChunk>(&s, this);
+ seg = make<MergeInputChunk>(s, this);
} else
- seg = make<InputSegment>(&s, this);
+ seg = make<InputSegment>(s, this);
seg->discarded = isExcludedByComdat(seg);
segments.emplace_back(seg);
@@ -585,7 +600,7 @@ Symbol *ObjFile::createDefined(const WasmSymbol &sym) {
return symtab->addDefinedGlobal(name, flags, this, global);
}
case WASM_SYMBOL_TYPE_SECTION: {
- InputSection *section = customSectionsByIndex[sym.Info.ElementIndex];
+ InputChunk *section = customSectionsByIndex[sym.Info.ElementIndex];
assert(sym.isBindingLocal());
// Need to return null if discarded here? data and func only do that when
// binding is not local.
diff --git a/lld/wasm/InputFiles.h b/lld/wasm/InputFiles.h
index b720b889adcc..49337bd0eb33 100644
--- a/lld/wasm/InputFiles.h
+++ b/lld/wasm/InputFiles.h
@@ -141,8 +141,8 @@ public:
std::vector<InputGlobal *> globals;
std::vector<InputEvent *> events;
std::vector<InputTable *> tables;
- std::vector<InputSection *> customSections;
- llvm::DenseMap<uint32_t, InputSection *> customSectionsByIndex;
+ std::vector<InputChunk *> customSections;
+ llvm::DenseMap<uint32_t, InputChunk *> customSectionsByIndex;
Symbol *getSymbol(uint32_t index) const { return symbols[index]; }
FunctionSymbol *getFunctionSymbol(uint32_t index) const;
diff --git a/lld/wasm/OutputSections.cpp b/lld/wasm/OutputSections.cpp
index 780c8e4b2776..e39c3331641a 100644
--- a/lld/wasm/OutputSections.cpp
+++ b/lld/wasm/OutputSections.cpp
@@ -12,6 +12,7 @@
#include "OutputSegment.h"
#include "WriterUtils.h"
#include "lld/Common/ErrorHandler.h"
+#include "lld/Common/Memory.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/Parallel.h"
@@ -234,13 +235,42 @@ bool DataSection::isNeeded() const {
return false;
}
+// Lots of duplication here with OutputSegment::finalizeInputSegments
+void CustomSection::finalizeInputSections() {
+ SyntheticMergedChunk *mergedSection = nullptr;
+ std::vector<InputChunk *> newSections;
+
+ for (InputChunk *s : inputSections) {
+ MergeInputChunk *ms = dyn_cast<MergeInputChunk>(s);
+ if (!ms) {
+ newSections.push_back(s);
+ continue;
+ }
+
+ if (!mergedSection) {
+ mergedSection =
+ make<SyntheticMergedChunk>(name, 0, WASM_SEG_FLAG_STRINGS);
+ newSections.push_back(mergedSection);
+ }
+ mergedSection->addMergeChunk(ms);
+ }
+
+ if (!mergedSection)
+ return;
+
+ mergedSection->finalizeContents();
+ inputSections = newSections;
+}
+
void CustomSection::finalizeContents() {
+ finalizeInputSections();
+
raw_string_ostream os(nameData);
encodeULEB128(name.size(), os);
os << name;
os.flush();
- for (InputSection *section : inputSections) {
+ for (InputChunk *section : inputSections) {
assert(!section->discarded);
section->outputSec = this;
section->outSecOff = payloadSize;
@@ -264,19 +294,19 @@ void CustomSection::writeTo(uint8_t *buf) {
buf += nameData.size();
// Write custom sections payload
- for (const InputSection *section : inputSections)
+ for (const InputChunk *section : inputSections)
section->writeTo(buf);
}
uint32_t CustomSection::getNumRelocations() const {
uint32_t count = 0;
- for (const InputSection *inputSect : inputSections)
+ for (const InputChunk *inputSect : inputSections)
count += inputSect->getNumRelocations();
return count;
}
void CustomSection::writeRelocations(raw_ostream &os) const {
- for (const InputSection *s : inputSections)
+ for (const InputChunk *s : inputSections)
s->writeRelocations(os);
}
diff --git a/lld/wasm/OutputSections.h b/lld/wasm/OutputSections.h
index 444116dac7d8..c3becf6ec240 100644
--- a/lld/wasm/OutputSections.h
+++ b/lld/wasm/OutputSections.h
@@ -111,7 +111,7 @@ protected:
// separately and are instead synthesized by the linker.
class CustomSection : public OutputSection {
public:
- CustomSection(std::string name, ArrayRef<InputSection *> inputSections)
+ CustomSection(std::string name, ArrayRef<InputChunk *> inputSections)
: OutputSection(llvm::wasm::WASM_SEC_CUSTOM, name),
inputSections(inputSections) {}
@@ -128,8 +128,9 @@ public:
void finalizeContents() override;
protected:
+ void finalizeInputSections();
size_t payloadSize = 0;
- ArrayRef<InputSection *> inputSections;
+ std::vector<InputChunk *> inputSections;
std::string nameData;
};
diff --git a/lld/wasm/OutputSegment.cpp b/lld/wasm/OutputSegment.cpp
index bf3e40c968a0..c09d5c30a0f6 100644
--- a/lld/wasm/OutputSegment.cpp
+++ b/lld/wasm/OutputSegment.cpp
@@ -55,16 +55,15 @@ void OutputSegment::finalizeInputSegments() {
return seg->flags == ms->flags && seg->alignment == ms->alignment;
});
if (i == mergedSegments.end()) {
- LLVM_DEBUG(llvm::dbgs() << "new merge section: " << name
+ LLVM_DEBUG(llvm::dbgs() << "new merge segment: " << name
<< " alignment=" << ms->alignment << "\n");
- SyntheticMergedChunk *syn =
- make<SyntheticMergedChunk>(name, ms->alignment, ms->flags);
+ auto *syn = make<SyntheticMergedChunk>(name, ms->alignment, ms->flags);
syn->outputSeg = this;
mergedSegments.push_back(syn);
i = std::prev(mergedSegments.end());
newSegments.push_back(syn);
} else {
- LLVM_DEBUG(llvm::dbgs() << "adding to merge section: " << name << "\n");
+ LLVM_DEBUG(llvm::dbgs() << "adding to merge segment: " << name << "\n");
}
(*i)->addMergeChunk(ms);
}
diff --git a/lld/wasm/Symbols.cpp b/lld/wasm/Symbols.cpp
index 24b7e10dc559..6d960b4cf7e6 100644
--- a/lld/wasm/Symbols.cpp
+++ b/lld/wasm/Symbols.cpp
@@ -301,7 +301,7 @@ void DefinedData::setVA(uint64_t value_) {
uint64_t DefinedData::getOutputSegmentOffset() const {
LLVM_DEBUG(dbgs() << "getOutputSegmentOffset: " << getName() << "\n");
- return segment->getSegmentOffset(value);
+ return segment->getChunkOffset(value);
}
uint64_t DefinedData::getOutputSegmentIndex() const {
diff --git a/lld/wasm/Symbols.h b/lld/wasm/Symbols.h
index ff6eb0ae7ccb..0c557530236d 100644
--- a/lld/wasm/Symbols.h
+++ b/lld/wasm/Symbols.h
@@ -254,14 +254,14 @@ public:
class SectionSymbol : public Symbol {
public:
- SectionSymbol(uint32_t flags, const InputSection *s, InputFile *f = nullptr)
+ SectionSymbol(uint32_t flags, const InputChunk *s, InputFile *f = nullptr)
: Symbol("", SectionKind, flags, f), section(s) {}
static bool classof(const Symbol *s) { return s->kind() == SectionKind; }
const OutputSectionSymbol *getOutputSectionSymbol() const;
- const InputSection *section;
+ const InputChunk *section;
};
class DataSymbol : public Symbol {
diff --git a/lld/wasm/Writer.cpp b/lld/wasm/Writer.cpp
index 055972560b81..1705c205eca4 100644
--- a/lld/wasm/Writer.cpp
+++ b/lld/wasm/Writer.cpp
@@ -100,7 +100,7 @@ private:
uint64_t fileSize = 0;
std::vector<WasmInitEntry> initFunctions;
- llvm::StringMap<std::vector<InputSection *>> customSectionMapping;
+ llvm::StringMap<std::vector<InputChunk *>> customSectionMapping;
// Stable storage for command export wrapper function name strings.
std::list<std::string> commandExportWrapperNames;
@@ -121,7 +121,7 @@ void Writer::calculateCustomSections() {
log("calculateCustomSections");
bool stripDebug = config->stripDebug || config->stripAll;
for (ObjFile *file : symtab->objectFiles) {
- for (InputSection *section : file->customSections) {
+ for (InputChunk *section : file->customSections) {
// Exclude COMDAT sections that are not selected for inclusion
if (section->discarded)
continue;
diff --git a/llvm/include/llvm/MC/MCContext.h b/llvm/include/llvm/MC/MCContext.h
index c531aa851d1e..100befc48ecb 100644
--- a/llvm/include/llvm/MC/MCContext.h
+++ b/llvm/include/llvm/MC/MCContext.h
@@ -610,8 +610,9 @@ namespace llvm {
getAssociativeCOFFSection(MCSectionCOFF *Sec, const MCSymbol *KeySym,
unsigned UniqueID = GenericSectionID);
- MCSectionWasm *getWasmSection(const Twine &Section, SectionKind K) {
- return getWasmSection(Section, K, 0, nullptr);
+ MCSectionWasm *getWasmSection(const Twine &Section, SectionKind K,
+ unsigned Flags = 0) {
+ return getWasmSection(Section, K, Flags, nullptr);
}
MCSectionWasm *getWasmSection(const Twine &Section, SectionKind K,
diff --git a/llvm/lib/MC/MCObjectFileInfo.cpp b/llvm/lib/MC/MCObjectFileInfo.cpp
index 92091ffcb746..1a448f040b3b 100644
--- a/llvm/lib/MC/MCObjectFileInfo.cpp
+++ b/llvm/lib/MC/MCObjectFileInfo.cpp
@@ -11,6 +11,7 @@
#include "llvm/ADT/Triple.h"
#include "llvm/BinaryFormat/COFF.h"
#include "llvm/BinaryFormat/ELF.h"
+#include "llvm/BinaryFormat/Wasm.h"
#include "llvm/MC/MCAsmInfo.h"
#include "llvm/MC/MCContext.h"
#include "llvm/MC/MCSection.h"
@@ -791,9 +792,10 @@ void MCObjectFileInfo::initWasmMCObjectFileInfo(const Triple &T) {
DwarfLineSection =
Ctx->getWasmSection(".debug_line", SectionKind::getMetadata());
DwarfLineStrSection =
- Ctx->getWasmSection(".debug_line_str", SectionKind::getMetadata());
- DwarfStrSection =
- Ctx->getWasmSection(".debug_str", SectionKind::getMetadata());
+ Ctx->getWasmSection(".debug_line_str", SectionKind::getMetadata(),
+ wasm::WASM_SEG_FLAG_STRINGS);
+ DwarfStrSection = Ctx->getWasmSection(
+ ".debug_str", SectionKind::getMetadata(), wasm::WASM_SEG_FLAG_STRINGS);
DwarfLocSection =
Ctx->getWasmSection(".debug_loc", SectionKind::getMetadata());
DwarfAbbrevSection =
@@ -836,7 +838,8 @@ void MCObjectFileInfo::initWasmMCObjectFileInfo(const Triple &T) {
DwarfAbbrevDWOSection =
Ctx->getWasmSection(".debug_abbrev.dwo", SectionKind::getMetadata());
DwarfStrDWOSection =
- Ctx->getWasmSection(".debug_str.dwo", SectionKind::getMetadata());
+ Ctx->getWasmSection(".debug_str.dwo", SectionKind::getMetadata(),
+ wasm::WASM_SEG_FLAG_STRINGS);
DwarfLineDWOSection =
Ctx->getWasmSection(".debug_line.dwo", SectionKind::getMetadata());
DwarfLocDWOSection =
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-arm-next-allmodconfig - Build # 30 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-arm-next-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-release-arm-next-allmodconfig
Culprit:
<cut>
commit 3d463dd5023b5a58b3c37207d65eeb5acbac2be3
Author: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Date: Thu Jul 29 12:40:19 2021 +0200
nfc: fdp: constify several pointers
Several functions do not modify pointed data so arguments and local
variables can be const for correctness and safety. This allows also
making file-scope nci_core_get_config_otp_ram_version array const.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
</cut>
Results regressed to (for first_bad == 3d463dd5023b5a58b3c37207d65eeb5acbac2be3)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
21699
# First few build errors in logs:
# 00:02:22 drivers/nfc/fdp/fdp.c:116:60: error: passing 'const char *' to parameter of type '__u8 *' (aka 'unsigned char *') discards qualifiers [-Werror,-Wincompatible-pointer-types-discards-qualifiers]
# 00:02:22 make[3]: *** [drivers/nfc/fdp/fdp.o] Error 1
# 00:02:23 make[2]: *** [drivers/nfc/fdp] Error 2
# 00:02:45 make[1]: *** [drivers/nfc] Error 2
# 00:05:31 make: *** [drivers] Error 2
from (for last_good == c3e26b6dc1b4e3e8f57be4f004b1f2a410c5c468)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29761
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Configuration details:
rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#cb16362…"
Reproduce builds:
<cut>
mkdir investigate-linux-3d463dd5023b5a58b3c37207d65eeb5acbac2be3
cd investigate-linux-3d463dd5023b5a58b3c37207d65eeb5acbac2be3
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 3d463dd5023b5a58b3c37207d65eeb5acbac2be3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c3e26b6dc1b4e3e8f57be4f004b1f2a410c5c468
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Full commit (up to 1000 lines):
<cut>
commit 3d463dd5023b5a58b3c37207d65eeb5acbac2be3
Author: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Date: Thu Jul 29 12:40:19 2021 +0200
nfc: fdp: constify several pointers
Several functions do not modify pointed data so arguments and local
variables can be const for correctness and safety. This allows also
making file-scope nci_core_get_config_otp_ram_version array const.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
---
drivers/nfc/fdp/fdp.c | 18 +++++++++---------
drivers/nfc/fdp/fdp.h | 2 +-
drivers/nfc/fdp/i2c.c | 6 +++---
3 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index 3f5fba922c4d..c6b3334f24c9 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -52,7 +52,7 @@ struct fdp_nci_info {
u32 limited_otp_version;
u8 key_index;
- u8 *fw_vsc_cfg;
+ const u8 *fw_vsc_cfg;
u8 clock_type;
u32 clock_freq;
@@ -65,7 +65,7 @@ struct fdp_nci_info {
wait_queue_head_t setup_wq;
};
-static u8 nci_core_get_config_otp_ram_version[5] = {
+static const u8 nci_core_get_config_otp_ram_version[5] = {
0x04,
NCI_PARAM_ID_FW_RAM_VERSION,
NCI_PARAM_ID_FW_OTP_VERSION,
@@ -111,7 +111,7 @@ static inline int fdp_nci_patch_cmd(struct nci_dev *ndev, u8 type)
}
static inline int fdp_nci_set_production_data(struct nci_dev *ndev, u8 len,
- char *data)
+ const char *data)
{
return nci_prop_cmd(ndev, NCI_OP_PROP_SET_PDATA_OID, len, data);
}
@@ -236,7 +236,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
static int fdp_nci_open(struct nci_dev *ndev)
{
- struct fdp_nci_info *info = nci_get_drvdata(ndev);
+ const struct fdp_nci_info *info = nci_get_drvdata(ndev);
return info->phy_ops->enable(info->phy);
}
@@ -260,7 +260,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
{
struct fdp_nci_info *info = nci_get_drvdata(ndev);
struct device *dev = &info->phy->i2c_dev->dev;
- u8 *data;
+ const u8 *data;
int r;
r = request_firmware(&info->ram_patch, FDP_RAM_PATCH_NAME, dev);
@@ -269,7 +269,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
return r;
}
- data = (u8 *) info->ram_patch->data;
+ data = info->ram_patch->data;
info->ram_patch_version =
data[FDP_FW_HEADER_SIZE] |
(data[FDP_FW_HEADER_SIZE + 1] << 8) |
@@ -610,9 +610,9 @@ static int fdp_nci_core_get_config_rsp_packet(struct nci_dev *ndev,
{
struct fdp_nci_info *info = nci_get_drvdata(ndev);
struct device *dev = &info->phy->i2c_dev->dev;
- struct nci_core_get_config_rsp *rsp = (void *) skb->data;
+ const struct nci_core_get_config_rsp *rsp = (void *) skb->data;
unsigned int i;
- u8 *p;
+ const u8 *p;
if (rsp->status == NCI_STATUS_OK) {
@@ -691,7 +691,7 @@ static const struct nci_ops nci_ops = {
int fdp_nci_probe(struct fdp_i2c_phy *phy, const struct nfc_phy_ops *phy_ops,
struct nci_dev **ndevp, int tx_headroom,
int tx_tailroom, u8 clock_type, u32 clock_freq,
- u8 *fw_vsc_cfg)
+ const u8 *fw_vsc_cfg)
{
struct device *dev = &phy->i2c_dev->dev;
struct fdp_nci_info *info;
diff --git a/drivers/nfc/fdp/fdp.h b/drivers/nfc/fdp/fdp.h
index dc048d4b977e..2e9161a4d7bf 100644
--- a/drivers/nfc/fdp/fdp.h
+++ b/drivers/nfc/fdp/fdp.h
@@ -23,7 +23,7 @@ struct fdp_i2c_phy {
int fdp_nci_probe(struct fdp_i2c_phy *phy, const struct nfc_phy_ops *phy_ops,
struct nci_dev **ndev, int tx_headroom, int tx_tailroom,
- u8 clock_type, u32 clock_freq, u8 *fw_vsc_cfg);
+ u8 clock_type, u32 clock_freq, const u8 *fw_vsc_cfg);
void fdp_nci_remove(struct nci_dev *ndev);
#endif /* __LOCAL_FDP_H_ */
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 98e1876c9468..051c43a2a52f 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -36,7 +36,7 @@
print_hex_dump(KERN_DEBUG, prefix": ", DUMP_PREFIX_OFFSET, \
16, 1, (skb)->data, (skb)->len, 0)
-static void fdp_nci_i2c_reset(struct fdp_i2c_phy *phy)
+static void fdp_nci_i2c_reset(const struct fdp_i2c_phy *phy)
{
/* Reset RST/WakeUP for at least 100 micro-second */
gpiod_set_value_cansleep(phy->power_gpio, FDP_POWER_OFF);
@@ -47,7 +47,7 @@ static void fdp_nci_i2c_reset(struct fdp_i2c_phy *phy)
static int fdp_nci_i2c_enable(void *phy_id)
{
- struct fdp_i2c_phy *phy = phy_id;
+ const struct fdp_i2c_phy *phy = phy_id;
fdp_nci_i2c_reset(phy);
@@ -56,7 +56,7 @@ static int fdp_nci_i2c_enable(void *phy_id)
static void fdp_nci_i2c_disable(void *phy_id)
{
- struct fdp_i2c_phy *phy = phy_id;
+ const struct fdp_i2c_phy *phy = phy_id;
fdp_nci_i2c_reset(phy);
}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-release-aarch64-spec2k6-O2 - Build # 17 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
</cut>
Results regressed to (for first_bad == 0b92cf305dcf34387a8e2564e55ca8948df3b47a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2 -- artifacts/build-0b92cf305dcf34387a8e2564e55ca8948df3b47a/results_id:
1
# 483.xalancbmk,Xalan_base.default regressed by 103
# 447.dealII,[.] _ZSt18_Rb_tree_incrementPKSt18_Rb_tree_node_ba regressed by 1239
from (for last_good == 7552c36afa1f9058bb39f336ae84f019621885a0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2 -- artifacts/build-7552c36afa1f9058bb39f336ae84f019621885a0/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/2646
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-release-aarch64-spec2k6-O2/2640
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
cd investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 0b92cf305dcf34387a8e2564e55ca8948df3b47a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 7552c36afa1f9058bb39f336ae84f019621885a0
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
---
gcc/ChangeLog | 8 ++++++++
gcc/doc/invoke.texi | 8 ++++++++
gcc/ipa-inline.c | 22 ++++++++++++++--------
gcc/params.def | 6 +++++-
gcc/testsuite/ChangeLog | 9 +++++++++
gcc/testsuite/g++.dg/tree-ssa/pr61034.C | 2 +-
gcc/testsuite/g++.dg/tree-ssa/pr8781.C | 2 +-
gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C | 2 +-
gcc/testsuite/gcc.dg/ipa/pr63416.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c | 2 +-
gcc/testsuite/gcc.dg/vect/pr66142.c | 2 +-
11 files changed, 50 insertions(+), 15 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index bb4de20ab16..b4c4292c299 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * doc/invoke.texi (early-inlining-insns-O2): Document.
+ (early-inlining-insns): Update.
+ * params.def (early-inlining-insns-O2): New bound.
+ (early-inlining-insns): Update docs.
+ * ipa-inline.c (want_early_inline_function_p): Use new bound.
+
2019-10-01 Oleg Endo <olegendo(a)gcc.gnu.org>
PR target/88562
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 83016a5a8ee..4281ee7c614 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -11291,9 +11291,17 @@ recursion depth can be guessed from the probability that function recurses
via a given call expression. This parameter limits inlining only to call
expressions whose probability exceeds the given threshold (in percents).
+@item early-inlining-insns-O2
+Specify growth that the early inliner can make. In effect it increases
+the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O1} or @option{-O2}
+optimization levels.
+
@item early-inlining-insns
Specify growth that the early inliner can make. In effect it increases
the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O3} or @option{-Ofast}
+optimization levels.
@item max-early-inliner-iterations
Limit of iterations of the early inliner. This basically bounds
diff --git a/gcc/ipa-inline.c b/gcc/ipa-inline.c
index b62d280eb25..c8689c7d9a8 100644
--- a/gcc/ipa-inline.c
+++ b/gcc/ipa-inline.c
@@ -641,6 +641,10 @@ want_early_inline_function_p (struct cgraph_edge *e)
{
int growth = estimate_edge_growth (e);
int n;
+ int early_inlining_insns = opt_for_fn (e->caller->decl, optimize) >= 3
+ ? PARAM_VALUE (PARAM_EARLY_INLINING_INSNS)
+ : PARAM_VALUE (PARAM_EARLY_INLINING_INSNS_O2);
+
if (growth <= PARAM_VALUE (PARAM_MAX_INLINE_INSNS_SIZE))
;
@@ -654,26 +658,28 @@ want_early_inline_function_p (struct cgraph_edge *e)
growth);
want_inline = false;
}
- else if (growth > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ else if (growth > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns\n",
- e->caller, callee,
- growth);
+ "growth %i exceeds --param early-inlining-insns%s\n",
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
else if ((n = num_calls (callee)) != 0
- && growth * (n + 1) > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ && growth * (n + 1) > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns "
+ "growth %i exceeds --param early-inlining-insns%s "
"divided by number of calls\n",
- e->caller, callee,
- growth);
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
}
diff --git a/gcc/params.def b/gcc/params.def
index d2d957fc6b1..0acf29b6c4d 100644
--- a/gcc/params.def
+++ b/gcc/params.def
@@ -233,8 +233,12 @@ DEFPARAM(PARAM_IPCP_UNIT_GROWTH,
10, 0, 0)
DEFPARAM(PARAM_EARLY_INLINING_INSNS,
"early-inlining-insns",
- "Maximal estimated growth of function body caused by early inlining of single call.",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O3 and -Ofast.",
14, 0, 0)
+DEFPARAM(PARAM_EARLY_INLINING_INSNS_O2,
+ "early-inlining-insns-O2",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O1 and -O2.",
+ 6, 0, 0)
DEFPARAM(PARAM_LARGE_STACK_FRAME,
"large-stack-frame",
"The size of stack frame to be considered large.",
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index df6105f3d13..0dcaf4b6292 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
+ * g++.dg/tree-ssa/pr8781.C: Likewise.
+ * g++.dg/warn/Wstringop-truncation-1.C: Likewise.
+ * gcc.dg/ipa/pr63416.c: likewise.
+ * gcc.dg/vect/pr66142.c: Likewise.
+ * gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
+
2019-10-01 Jakub Jelinek <jakub(a)redhat.com>
PR c++/91925
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
index 870b2372166..2e3dfecacb4 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
@@ -1,5 +1,5 @@
// { dg-do compile }
-// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks" }
+// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks --param early-inlining-insns-O2=14" }
#define assume(x) if(!(x))__builtin_unreachable()
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
index 1f115b2b26d..5bc1ef03520 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1" } */
+/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1 --param early-inlining-insns-O2=14" } */
int f();
diff --git a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
index 83066019772..49dde0a65ba 100644
--- a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
+++ b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
@@ -1,7 +1,7 @@
/* PR/tree-optimization/84480 - bogus -Wstringop-truncation despite
assignment with an inlined string literal
{ dg-do compile }
- { dg-options "-O2 -Wstringop-truncation" } */
+ { dg-options "-O2 -Wstringop-truncation --param early-inlining-insns-O2=14" } */
#include <string.h>
diff --git a/gcc/testsuite/gcc.dg/ipa/pr63416.c b/gcc/testsuite/gcc.dg/ipa/pr63416.c
index b5374c51fe9..5873954fba3 100644
--- a/gcc/testsuite/gcc.dg/ipa/pr63416.c
+++ b/gcc/testsuite/gcc.dg/ipa/pr63416.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fdump-tree-optimized --param early-inlining-insns-O2=14" } */
#define _UNUSED_ __attribute__((__unused__))
typedef int TEST_F30 (int *v);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
index 67526762f2c..216de23d791 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
@@ -56,7 +56,7 @@ bmp_iter_and_compl (bitmap_iterator * bi, unsigned *bit_no)
}
extern int VEC_int_base_length (VEC_int_base *);
-bitmap
+inline bitmap
compute_idf (bitmap def_blocks, bitmap_head * dfs)
{
bitmap_iterator bi;
diff --git a/gcc/testsuite/gcc.dg/vect/pr66142.c b/gcc/testsuite/gcc.dg/vect/pr66142.c
index 8c79f290767..a0316f1f01e 100644
--- a/gcc/testsuite/gcc.dg/vect/pr66142.c
+++ b/gcc/testsuite/gcc.dg/vect/pr66142.c
@@ -1,6 +1,6 @@
/* PR middle-end/66142 */
/* { dg-do compile } */
-/* { dg-additional-options "-ffast-math -fopenmp-simd" } */
+/* { dg-additional-options "-ffast-math -fopenmp-simd --param early-inlining-insns-O2=14" } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
struct A { float x, y; };
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/gnu-master-arm-spec2k6-O3 - Build # 37 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tk1/gnu-master-arm-spec2k6-O3
Culprit:
<cut>
commit 5b759cdcb7f863520346e5bf63fcf1d3746c2cc3
Author: Jason Merrill <jason(a)redhat.com>
Date: Sat Jul 10 05:45:02 2021 -0400
c++: pretty-print TYPE_PACK_EXPANSION better
gcc/cp/ChangeLog:
* ptree.c (cxx_print_type) [TYPE_PACK_EXPANSION]: Also print
PACK_EXPANSION_PATTERN.
</cut>
Results regressed to (for first_bad == 5b759cdcb7f863520346e5bf63fcf1d3746c2cc3)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O3_marm artifacts/build-5b759cdcb7f863520346e5bf63fcf1d3746c2cc3/results_id:
1
# 483.xalancbmk,[.] _ZN11xercesc_2_510ValueStore13isDuplicateOf regressed by 111
from (for last_good == 4c4249b71de3b15ba1e176ce90a57fb7bc54b917)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -- -O3_marm artifacts/build-4c4249b71de3b15ba1e176ce90a57fb7bc54b917/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of last_good: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O3/2632
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Results ID of first_bad: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-master-arm-spec2k6-O3/2639
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-5b759cdcb7f863520346e5bf63fcf1d3746c2cc3
cd investigate-gcc-5b759cdcb7f863520346e5bf63fcf1d3746c2cc3
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 5b759cdcb7f863520346e5bf63fcf1d3746c2cc3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 4c4249b71de3b15ba1e176ce90a57fb7bc54b917
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-master-ar…
Full commit (up to 1000 lines):
<cut>
commit 5b759cdcb7f863520346e5bf63fcf1d3746c2cc3
Author: Jason Merrill <jason(a)redhat.com>
Date: Sat Jul 10 05:45:02 2021 -0400
c++: pretty-print TYPE_PACK_EXPANSION better
gcc/cp/ChangeLog:
* ptree.c (cxx_print_type) [TYPE_PACK_EXPANSION]: Also print
PACK_EXPANSION_PATTERN.
---
gcc/cp/ptree.c | 1 +
1 file changed, 1 insertion(+)
diff --git a/gcc/cp/ptree.c b/gcc/cp/ptree.c
index 33b73fb24b6..7f140f5f06b 100644
--- a/gcc/cp/ptree.c
+++ b/gcc/cp/ptree.c
@@ -171,6 +171,7 @@ cxx_print_type (FILE *file, tree node, int indent)
return;
case TYPE_PACK_EXPANSION:
+ print_node (file, "pattern", PACK_EXPANSION_PATTERN (node), indent + 4);
print_node (file, "args", PACK_EXPANSION_EXTRA_ARGS (node), indent + 4);
return;
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-arm-stable-allyesconfig - Build # 4 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-arm-stable-allyesconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-release-arm-stable-allyesconfig
Culprit:
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
</cut>
Results regressed to (for first_bad == 341db343768bc44f3512facc464021730d64071c)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
19634
# First few build errors in logs:
# 00:03:07 drivers/power/supply/ab8500_fg.c:3061:32: error: use of undeclared identifier 'np'
# 00:03:08 make[3]: *** [drivers/power/supply/ab8500_fg.o] Error 1
# 00:03:10 make[2]: *** [drivers/power/supply] Error 2
# 00:03:10 make[1]: *** [drivers/power] Error 2
# 00:04:05 make: *** [drivers] Error 2
from (for last_good == dc72a15859b2e604abb8a4bff123fbac8a0be92a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
19722
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-linux-341db343768bc44f3512facc464021730d64071c
cd investigate-linux-341db343768bc44f3512facc464021730d64071c
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 341db343768bc44f3512facc464021730d64071c
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach dc72a15859b2e604abb8a4bff123fbac8a0be92a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-stable-a…
Full commit (up to 1000 lines):
<cut>
commit 341db343768bc44f3512facc464021730d64071c
Author: Linus Walleij <linus.walleij(a)linaro.org>
Date: Sun May 23 00:50:39 2021 +0200
power: supply: ab8500: Move to componentized binding
[ Upstream commit 1c1f13a006ed0d71bb5664c8b7e3e77a28da3beb ]
The driver has problems with the different components of
the charging code racing with each other to probe().
This results in all four subdrivers populating battery
information to ascertain that it is populated for their
own needs for example.
Fix this by using component probing and thus expressing
to the kernel that these are dependent components.
The probes can happen in any order and will only acquire
resources such as state container, regulators and
interrupts and initialize the data structures, but no
execution happens until the .bind() callback is called.
The charging driver is the main component and binds
first, then bind in order the three subcomponents:
ab8500-fg, ab8500-btemp and ab8500-chargalg.
Do some housekeeping while we are moving the code around.
Like use devm_* for IRQs so as to cut down on some
boilerplate.
Signed-off-by: Linus Walleij <linus.walleij(a)linaro.org>
Signed-off-by: Sebastian Reichel <sebastian.reichel(a)collabora.com>
Signed-off-by: Sasha Levin <sashal(a)kernel.org>
---
drivers/power/supply/ab8500-bm.h | 4 +
drivers/power/supply/ab8500_btemp.c | 118 +++++-------
drivers/power/supply/ab8500_charger.c | 339 +++++++++++++++++++--------------
drivers/power/supply/ab8500_fg.c | 136 +++++++------
drivers/power/supply/abx500_chargalg.c | 116 ++++++-----
5 files changed, 379 insertions(+), 334 deletions(-)
diff --git a/drivers/power/supply/ab8500-bm.h b/drivers/power/supply/ab8500-bm.h
index 41c69a4f2a1f..012595a9d269 100644
--- a/drivers/power/supply/ab8500-bm.h
+++ b/drivers/power/supply/ab8500-bm.h
@@ -730,4 +730,8 @@ int ab8500_bm_of_probe(struct device *dev,
struct device_node *np,
struct abx500_bm_data *bm);
+extern struct platform_driver ab8500_fg_driver;
+extern struct platform_driver ab8500_btemp_driver;
+extern struct platform_driver abx500_chargalg_driver;
+
#endif /* _AB8500_CHARGER_H_ */
diff --git a/drivers/power/supply/ab8500_btemp.c b/drivers/power/supply/ab8500_btemp.c
index fdfcd59fc43e..3598b5a748e7 100644
--- a/drivers/power/supply/ab8500_btemp.c
+++ b/drivers/power/supply/ab8500_btemp.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/slab.h>
@@ -932,26 +933,6 @@ static int __maybe_unused ab8500_btemp_suspend(struct device *dev)
return 0;
}
-static int ab8500_btemp_remove(struct platform_device *pdev)
-{
- struct ab8500_btemp *di = platform_get_drvdata(pdev);
- int i, irq;
-
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
-
- /* Delete the work queue */
- destroy_workqueue(di->btemp_wq);
-
- flush_scheduled_work();
- power_supply_unregister(di->btemp_psy);
-
- return 0;
-}
-
static char *supply_interface[] = {
"ab8500_chargalg",
"ab8500_fg",
@@ -966,6 +947,40 @@ static const struct power_supply_desc ab8500_btemp_desc = {
.external_power_changed = ab8500_btemp_external_power_changed,
};
+static int ab8500_btemp_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for the btemp */
+ di->btemp_wq =
+ alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
+ if (di->btemp_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Kick off periodic temperature measurements */
+ ab8500_btemp_periodic(di, true);
+
+ return 0;
+}
+
+static void ab8500_btemp_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_btemp *di = dev_get_drvdata(dev);
+
+ /* Delete the work queue */
+ destroy_workqueue(di->btemp_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_btemp_component_ops = {
+ .bind = ab8500_btemp_bind,
+ .unbind = ab8500_btemp_unbind,
+};
+
static int ab8500_btemp_probe(struct platform_device *pdev)
{
struct device_node *np = pdev->dev.of_node;
@@ -1011,14 +1026,6 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
psy_cfg.num_supplicants = ARRAY_SIZE(supply_interface);
psy_cfg.drv_data = di;
- /* Create a work queue for the btemp */
- di->btemp_wq =
- alloc_workqueue("ab8500_btemp_wq", WQ_MEM_RECLAIM, 0);
- if (di->btemp_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for measuring temperature periodically */
INIT_DEFERRABLE_WORK(&di->btemp_periodic_work,
ab8500_btemp_periodic_work);
@@ -1031,7 +1038,7 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
AB8500_BTEMP_HIGH_TH, &val);
if (ret < 0) {
dev_err(dev, "%s ab8500 read failed\n", __func__);
- goto free_btemp_wq;
+ return ret;
}
switch (val) {
case BTEMP_HIGH_TH_57_0:
@@ -1050,30 +1057,28 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
}
/* Register BTEMP power supply class */
- di->btemp_psy = power_supply_register(dev, &ab8500_btemp_desc,
- &psy_cfg);
+ di->btemp_psy = devm_power_supply_register(dev, &ab8500_btemp_desc,
+ &psy_cfg);
if (IS_ERR(di->btemp_psy)) {
dev_err(dev, "failed to register BTEMP psy\n");
- ret = PTR_ERR(di->btemp_psy);
- goto free_btemp_wq;
+ return PTR_ERR(di->btemp_psy);
}
/* Register interrupts */
for (i = 0; i < ARRAY_SIZE(ab8500_btemp_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_btemp_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_btemp_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_btemp_irq[i].name, di);
if (ret) {
dev_err(dev, "failed to request %s IRQ %d: %d\n"
, ab8500_btemp_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_btemp_irq[i].name, irq, ret);
@@ -1081,23 +1086,16 @@ static int ab8500_btemp_probe(struct platform_device *pdev)
platform_set_drvdata(pdev, di);
- /* Kick off periodic temperature measurements */
- ab8500_btemp_periodic(di, true);
list_add_tail(&di->node, &ab8500_btemp_list);
- return ret;
+ return component_add(dev, &ab8500_btemp_component_ops);
+}
-free_irq:
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_btemp_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_btemp_remove(struct platform_device *pdev)
+{
+ component_del(&pdev->dev, &ab8500_btemp_component_ops);
- power_supply_unregister(di->btemp_psy);
-free_btemp_wq:
- destroy_workqueue(di->btemp_wq);
- return ret;
+ return 0;
}
static SIMPLE_DEV_PM_OPS(ab8500_btemp_pm_ops, ab8500_btemp_suspend, ab8500_btemp_resume);
@@ -1107,7 +1105,7 @@ static const struct of_device_id ab8500_btemp_match[] = {
{ },
};
-static struct platform_driver ab8500_btemp_driver = {
+struct platform_driver ab8500_btemp_driver = {
.probe = ab8500_btemp_probe,
.remove = ab8500_btemp_remove,
.driver = {
@@ -1116,20 +1114,6 @@ static struct platform_driver ab8500_btemp_driver = {
.pm = &ab8500_btemp_pm_ops,
},
};
-
-static int __init ab8500_btemp_init(void)
-{
- return platform_driver_register(&ab8500_btemp_driver);
-}
-
-static void __exit ab8500_btemp_exit(void)
-{
- platform_driver_unregister(&ab8500_btemp_driver);
-}
-
-device_initcall(ab8500_btemp_init);
-module_exit(ab8500_btemp_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski, Arun R Murthy");
MODULE_ALIAS("platform:ab8500-btemp");
diff --git a/drivers/power/supply/ab8500_charger.c b/drivers/power/supply/ab8500_charger.c
index a9be10eb2c22..af32cfae9f19 100644
--- a/drivers/power/supply/ab8500_charger.c
+++ b/drivers/power/supply/ab8500_charger.c
@@ -13,6 +13,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
#include <linux/notifier.h>
@@ -3276,10 +3277,74 @@ static struct notifier_block charger_nb = {
.notifier_call = ab8500_external_charger_prepare,
};
-static int ab8500_charger_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_chargalg",
+ "ab8500_fg",
+ "ab8500_btemp",
+};
+
+static const struct power_supply_desc ab8500_ac_chg_desc = {
+ .name = "ab8500_ac",
+ .type = POWER_SUPPLY_TYPE_MAINS,
+ .properties = ab8500_charger_ac_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
+ .get_property = ab8500_charger_ac_get_property,
+};
+
+static const struct power_supply_desc ab8500_usb_chg_desc = {
+ .name = "ab8500_usb",
+ .type = POWER_SUPPLY_TYPE_USB,
+ .properties = ab8500_charger_usb_props,
+ .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
+ .get_property = ab8500_charger_usb_get_property,
+};
+
+static int ab8500_charger_bind(struct device *dev)
{
- struct ab8500_charger *di = platform_get_drvdata(pdev);
- int i, irq, ret;
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ch_stat;
+ int ret;
+
+ /* Create a work queue for the charger */
+ di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
+ WQ_MEM_RECLAIM);
+ if (di->charger_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ ch_stat = ab8500_charger_detect_chargers(di, false);
+
+ if (ch_stat & AC_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->ac_charger_attached_work,
+ HZ);
+ }
+ if (ch_stat & USB_PW_CONN) {
+ if (is_ab8500(di->parent))
+ queue_delayed_work(di->charger_wq,
+ &di->usb_charger_attached_work,
+ HZ);
+ di->vbus_detected = true;
+ di->vbus_detected_start = true;
+ queue_work(di->charger_wq,
+ &di->detect_usb_type_work);
+ }
+
+ ret = component_bind_all(dev, di);
+ if (ret) {
+ dev_err(dev, "can't bind component devices\n");
+ return ret;
+ }
+
+ return 0;
+}
+
+static void ab8500_charger_unbind(struct device *dev)
+{
+ struct ab8500_charger *di = dev_get_drvdata(dev);
+ int ret;
/* Disable AC charging */
ab8500_charger_ac_en(&di->ac_chg, false, 0, 0);
@@ -3287,68 +3352,47 @@ static int ab8500_charger_remove(struct platform_device *pdev)
/* Disable USB charging */
ab8500_charger_usb_en(&di->usb_chg, false, 0, 0);
- /* Disable interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
-
/* Backup battery voltage and current disable */
ret = abx500_mask_and_set_register_interruptible(di->dev,
AB8500_RTC, AB8500_RTC_CTRL_REG, RTC_BUP_CH_ENA, 0);
if (ret < 0)
dev_err(di->dev, "%s mask and set failed\n", __func__);
- usb_unregister_notifier(di->usb_phy, &di->nb);
- usb_put_phy(di->usb_phy);
-
/* Delete the work queue */
destroy_workqueue(di->charger_wq);
- /* Unregister external charger enable notifier */
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_unregister(
- &charger_notifier_list, &charger_nb);
-
flush_scheduled_work();
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-
- if (di->ac_chg.enabled && !di->ac_chg.external)
- power_supply_unregister(di->ac_chg.psy);
- return 0;
+ /* Unbind fg, btemp, algorithm */
+ component_unbind_all(dev, di);
}
-static char *supply_interface[] = {
- "ab8500_chargalg",
- "ab8500_fg",
- "ab8500_btemp",
+static const struct component_master_ops ab8500_charger_comp_ops = {
+ .bind = ab8500_charger_bind,
+ .unbind = ab8500_charger_unbind,
};
-static const struct power_supply_desc ab8500_ac_chg_desc = {
- .name = "ab8500_ac",
- .type = POWER_SUPPLY_TYPE_MAINS,
- .properties = ab8500_charger_ac_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_ac_props),
- .get_property = ab8500_charger_ac_get_property,
+static struct platform_driver *const ab8500_charger_component_drivers[] = {
+ &ab8500_fg_driver,
+ &ab8500_btemp_driver,
+ &abx500_chargalg_driver,
};
-static const struct power_supply_desc ab8500_usb_chg_desc = {
- .name = "ab8500_usb",
- .type = POWER_SUPPLY_TYPE_USB,
- .properties = ab8500_charger_usb_props,
- .num_properties = ARRAY_SIZE(ab8500_charger_usb_props),
- .get_property = ab8500_charger_usb_get_property,
-};
+static int ab8500_charger_compare_dev(struct device *dev, void *data)
+{
+ return dev == data;
+}
static int ab8500_charger_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
+ struct device *dev = &pdev->dev;
+ struct device_node *np = dev->of_node;
+ struct component_match *match = NULL;
struct power_supply_config ac_psy_cfg = {}, usb_psy_cfg = {};
struct ab8500_charger *di;
- int irq, i, charger_status, ret = 0, ch_stat;
- struct device *dev = &pdev->dev;
+ int charger_status;
+ int i, irq;
+ int ret;
di = devm_kzalloc(dev, sizeof(*di), GFP_KERNEL);
if (!di)
@@ -3393,6 +3437,38 @@ static int ab8500_charger_probe(struct platform_device *pdev)
return ret;
}
+ /*
+ * VDD ADC supply needs to be enabled from this driver when there
+ * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
+ * interrupts during charging
+ */
+ di->regu = devm_regulator_get(dev, "vddadc");
+ if (IS_ERR(di->regu)) {
+ ret = PTR_ERR(di->regu);
+ dev_err(dev, "failed to get vddadc regulator\n");
+ return ret;
+ }
+
+ /* Request interrupts */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
+ irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
+ if (irq < 0)
+ return irq;
+
+ ret = devm_request_threaded_irq(dev,
+ irq, NULL, ab8500_charger_irq[i].isr,
+ IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
+ ab8500_charger_irq[i].name, di);
+
+ if (ret != 0) {
+ dev_err(dev, "failed to request %s IRQ %d: %d\n"
+ , ab8500_charger_irq[i].name, irq, ret);
+ return ret;
+ }
+ dev_dbg(dev, "Requested %s IRQ %d: %d\n",
+ ab8500_charger_irq[i].name, irq, ret);
+ }
+
/* initialize lock */
spin_lock_init(&di->usb_state.usb_lock);
mutex_init(&di->usb_ipt_crnt_lock);
@@ -3422,11 +3498,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->ac_chg.enabled = di->bm->ac_enabled;
di->ac_chg.external = false;
- /*notifier for external charger enabling*/
- if (!di->ac_chg.enabled)
- blocking_notifier_chain_register(
- &charger_notifier_list, &charger_nb);
-
/* USB supply */
/* ux500_charger sub-class */
di->usb_chg.ops.enable = &ab8500_charger_usb_en;
@@ -3442,14 +3513,6 @@ static int ab8500_charger_probe(struct platform_device *pdev)
di->usb_chg.external = false;
di->usb_state.usb_current = -1;
- /* Create a work queue for the charger */
- di->charger_wq = alloc_ordered_workqueue("ab8500_charger_wq",
- WQ_MEM_RECLAIM);
- if (di->charger_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
mutex_init(&di->charger_attached_mutex);
/* Init work for HW failure check */
@@ -3500,63 +3563,36 @@ static int ab8500_charger_probe(struct platform_device *pdev)
INIT_WORK(&di->check_usb_thermal_prot_work,
ab8500_charger_check_usb_thermal_prot_work);
- /*
- * VDD ADC supply needs to be enabled from this driver when there
- * is a charger connected to avoid erroneous BTEMP_HIGH/LOW
- * interrupts during charging
- */
- di->regu = devm_regulator_get(dev, "vddadc");
- if (IS_ERR(di->regu)) {
- ret = PTR_ERR(di->regu);
- dev_err(dev, "failed to get vddadc regulator\n");
- goto free_charger_wq;
- }
-
/* Initialize OVV, and other registers */
ret = ab8500_charger_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize ABB registers\n");
- goto free_charger_wq;
+ return ret;
}
/* Register AC charger class */
if (di->ac_chg.enabled) {
- di->ac_chg.psy = power_supply_register(dev,
+ di->ac_chg.psy = devm_power_supply_register(dev,
&ab8500_ac_chg_desc,
&ac_psy_cfg);
if (IS_ERR(di->ac_chg.psy)) {
dev_err(dev, "failed to register AC charger\n");
- ret = PTR_ERR(di->ac_chg.psy);
- goto free_charger_wq;
+ return PTR_ERR(di->ac_chg.psy);
}
}
/* Register USB charger class */
if (di->usb_chg.enabled) {
- di->usb_chg.psy = power_supply_register(dev,
+ di->usb_chg.psy = devm_power_supply_register(dev,
&ab8500_usb_chg_desc,
&usb_psy_cfg);
if (IS_ERR(di->usb_chg.psy)) {
dev_err(dev, "failed to register USB charger\n");
- ret = PTR_ERR(di->usb_chg.psy);
- goto free_ac;
+ return PTR_ERR(di->usb_chg.psy);
}
}
- di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
- if (IS_ERR_OR_NULL(di->usb_phy)) {
- dev_err(dev, "failed to get usb transceiver\n");
- ret = -EINVAL;
- goto free_usb;
- }
- di->nb.notifier_call = ab8500_charger_usb_notifier_call;
- ret = usb_register_notifier(di->usb_phy, &di->nb);
- if (ret) {
- dev_err(dev, "failed to register usb notifier\n");
- goto put_usb_phy;
- }
-
/* Identify the connected charger types during startup */
charger_status = ab8500_charger_detect_chargers(di, true);
if (charger_status & AC_PW_CONN) {
@@ -3566,78 +3602,86 @@ static int ab8500_charger_probe(struct platform_device *pdev)
sysfs_notify(&di->ac_chg.psy->dev.kobj, NULL, "present");
}
- if (charger_status & USB_PW_CONN) {
- di->vbus_detected = true;
- di->vbus_detected_start = true;
- queue_work(di->charger_wq,
- &di->detect_usb_type_work);
- }
-
- /* Register interrupts */
- for (i = 0; i < ARRAY_SIZE(ab8500_charger_irq); i++) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ platform_set_drvdata(pdev, di);
- ret = request_threaded_irq(irq, NULL, ab8500_charger_irq[i].isr,
- IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
- ab8500_charger_irq[i].name, di);
+ /* Create something that will match the subdrivers when we bind */
+ for (i = 0; i < ARRAY_SIZE(ab8500_charger_component_drivers); i++) {
+ struct device_driver *drv = &ab8500_charger_component_drivers[i]->driver;
+ struct device *p = NULL, *d;
- if (ret != 0) {
- dev_err(dev, "failed to request %s IRQ %d: %d\n"
- , ab8500_charger_irq[i].name, irq, ret);
- goto free_irq;
+ while ((d = platform_find_device_by_driver(p, drv))) {
+ put_device(p);
+ component_match_add(dev, &match,
+ ab8500_charger_compare_dev, d);
+ p = d;
}
- dev_dbg(dev, "Requested %s IRQ %d: %d\n",
- ab8500_charger_irq[i].name, irq, ret);
+ put_device(p);
+ }
+ if (!match) {
+ dev_err(dev, "no matching components\n");
+ return -ENODEV;
+ }
+ if (IS_ERR(match)) {
+ dev_err(dev, "could not create component match\n");
+ return PTR_ERR(match);
}
- platform_set_drvdata(pdev, di);
+ /* Notifier for external charger enabling */
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_register(
+ &charger_notifier_list, &charger_nb);
- mutex_lock(&di->charger_attached_mutex);
- ch_stat = ab8500_charger_detect_chargers(di, false);
-
- if ((ch_stat & AC_PW_CONN) == AC_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->ac_charger_attached_work,
- HZ);
+ di->usb_phy = usb_get_phy(USB_PHY_TYPE_USB2);
+ if (IS_ERR_OR_NULL(di->usb_phy)) {
+ dev_err(dev, "failed to get usb transceiver\n");
+ ret = -EINVAL;
+ goto out_charger_notifier;
}
- if ((ch_stat & USB_PW_CONN) == USB_PW_CONN) {
- if (is_ab8500(di->parent))
- queue_delayed_work(di->charger_wq,
- &di->usb_charger_attached_work,
- HZ);
+ di->nb.notifier_call = ab8500_charger_usb_notifier_call;
+ ret = usb_register_notifier(di->usb_phy, &di->nb);
+ if (ret) {
+ dev_err(dev, "failed to register usb notifier\n");
+ goto put_usb_phy;
}
- mutex_unlock(&di->charger_attached_mutex);
- return ret;
+ ret = component_master_add_with_match(&pdev->dev,
+ &ab8500_charger_comp_ops,
+ match);
+ if (ret) {
+ dev_err(dev, "failed to add component master\n");
+ goto free_notifier;
+ }
-free_irq:
- usb_unregister_notifier(di->usb_phy, &di->nb);
+ return 0;
- /* We also have to free all successfully registered irqs */
- for (i = i - 1; i >= 0; i--) {
- irq = platform_get_irq_byname(pdev, ab8500_charger_irq[i].name);
- free_irq(irq, di);
- }
+free_notifier:
+ usb_unregister_notifier(di->usb_phy, &di->nb);
put_usb_phy:
usb_put_phy(di->usb_phy);
-free_usb:
- if (di->usb_chg.enabled)
- power_supply_unregister(di->usb_chg.psy);
-free_ac:
- if (di->ac_chg.enabled)
- power_supply_unregister(di->ac_chg.psy);
-free_charger_wq:
- destroy_workqueue(di->charger_wq);
+out_charger_notifier:
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
return ret;
}
+static int ab8500_charger_remove(struct platform_device *pdev)
+{
+ struct ab8500_charger *di = platform_get_drvdata(pdev);
+
+ component_master_del(&pdev->dev, &ab8500_charger_comp_ops);
+
+ usb_unregister_notifier(di->usb_phy, &di->nb);
+ usb_put_phy(di->usb_phy);
+ if (!di->ac_chg.enabled)
+ blocking_notifier_chain_unregister(
+ &charger_notifier_list, &charger_nb);
+
+ return 0;
+}
+
static SIMPLE_DEV_PM_OPS(ab8500_charger_pm_ops, ab8500_charger_suspend, ab8500_charger_resume);
static const struct of_device_id ab8500_charger_match[] = {
@@ -3657,15 +3701,24 @@ static struct platform_driver ab8500_charger_driver = {
static int __init ab8500_charger_init(void)
{
+ int ret;
+
+ ret = platform_register_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
+ if (ret)
+ return ret;
+
return platform_driver_register(&ab8500_charger_driver);
}
static void __exit ab8500_charger_exit(void)
{
+ platform_unregister_drivers(ab8500_charger_component_drivers,
+ ARRAY_SIZE(ab8500_charger_component_drivers));
platform_driver_unregister(&ab8500_charger_driver);
}
-subsys_initcall_sync(ab8500_charger_init);
+module_init(ab8500_charger_init);
module_exit(ab8500_charger_exit);
MODULE_LICENSE("GPL v2");
diff --git a/drivers/power/supply/ab8500_fg.c b/drivers/power/supply/ab8500_fg.c
index 0c7c01a0d979..acf0f2471c0b 100644
--- a/drivers/power/supply/ab8500_fg.c
+++ b/drivers/power/supply/ab8500_fg.c
@@ -17,6 +17,7 @@
#include <linux/init.h>
#include <linux/module.h>
+#include <linux/component.h>
#include <linux/device.h>
#include <linux/interrupt.h>
#include <linux/platform_device.h>
@@ -2980,27 +2981,6 @@ static int __maybe_unused ab8500_fg_suspend(struct device *dev)
return 0;
}
-static int ab8500_fg_remove(struct platform_device *pdev)
-{
- int ret = 0;
- struct ab8500_fg *di = platform_get_drvdata(pdev);
-
- list_del(&di->node);
-
- /* Disable coulomb counter */
- ret = ab8500_fg_coulomb_counter(di, false);
- if (ret)
- dev_err(di->dev, "failed to disable coulomb counter\n");
-
- destroy_workqueue(di->fg_wq);
- ab8500_fg_sysfs_exit(di);
-
- flush_scheduled_work();
- ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
- return ret;
-}
-
/* ab8500 fg driver interrupts and their respective isr */
static struct ab8500_fg_interrupts ab8500_fg_irq[] = {
{"NCONV_ACCU", ab8500_fg_cc_convend_handler},
@@ -3024,11 +3004,50 @@ static const struct power_supply_desc ab8500_fg_desc = {
.external_power_changed = ab8500_fg_external_power_changed,
};
+static int ab8500_fg_bind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+
+ /* Create a work queue for running the FG algorithm */
+ di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
+ if (di->fg_wq == NULL) {
+ dev_err(dev, "failed to create work queue\n");
+ return -ENOMEM;
+ }
+
+ /* Start the coulomb counter */
+ ab8500_fg_coulomb_counter(di, true);
+ /* Run the FG algorithm */
+ queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
+
+ return 0;
+}
+
+static void ab8500_fg_unbind(struct device *dev, struct device *master,
+ void *data)
+{
+ struct ab8500_fg *di = dev_get_drvdata(dev);
+ int ret;
+
+ /* Disable coulomb counter */
+ ret = ab8500_fg_coulomb_counter(di, false);
+ if (ret)
+ dev_err(dev, "failed to disable coulomb counter\n");
+
+ destroy_workqueue(di->fg_wq);
+ flush_scheduled_work();
+}
+
+static const struct component_ops ab8500_fg_component_ops = {
+ .bind = ab8500_fg_bind,
+ .unbind = ab8500_fg_unbind,
+};
+
static int ab8500_fg_probe(struct platform_device *pdev)
{
- struct device_node *np = pdev->dev.of_node;
- struct power_supply_config psy_cfg = {};
struct device *dev = &pdev->dev;
+ struct power_supply_config psy_cfg = {};
struct ab8500_fg *di;
int i, irq;
int ret = 0;
@@ -3074,13 +3093,6 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ab8500_fg_charge_state_to(di, AB8500_FG_CHARGE_INIT);
ab8500_fg_discharge_state_to(di, AB8500_FG_DISCHARGE_INIT);
- /* Create a work queue for running the FG algorithm */
- di->fg_wq = alloc_ordered_workqueue("ab8500_fg_wq", WQ_MEM_RECLAIM);
- if (di->fg_wq == NULL) {
- dev_err(dev, "failed to create work queue\n");
- return -ENOMEM;
- }
-
/* Init work for running the fg algorithm instantly */
INIT_WORK(&di->fg_work, ab8500_fg_instant_work);
@@ -3113,7 +3125,7 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_init_hw_registers(di);
if (ret) {
dev_err(dev, "failed to initialize registers\n");
- goto free_inst_curr_wq;
+ return ret;
}
/* Consider battery unknown until we're informed otherwise */
@@ -3121,15 +3133,13 @@ static int ab8500_fg_probe(struct platform_device *pdev)
di->flags.batt_id_received = false;
/* Register FG power supply class */
- di->fg_psy = power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
+ di->fg_psy = devm_power_supply_register(dev, &ab8500_fg_desc, &psy_cfg);
if (IS_ERR(di->fg_psy)) {
dev_err(dev, "failed to register FG psy\n");
- ret = PTR_ERR(di->fg_psy);
- goto free_inst_curr_wq;
+ return PTR_ERR(di->fg_psy);
}
di->fg_samples = SEC_TO_SAMPLE(di->bm->fg_params->init_timer);
- ab8500_fg_coulomb_counter(di, true);
/*
* Initialize completion used to notify completion and start
@@ -3141,19 +3151,18 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Register primary interrupt handlers */
for (i = 0; i < ARRAY_SIZE(ab8500_fg_irq); i++) {
irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- if (irq < 0) {
- ret = irq;
- goto free_irq;
- }
+ if (irq < 0)
+ return irq;
- ret = request_threaded_irq(irq, NULL, ab8500_fg_irq[i].isr,
+ ret = devm_request_threaded_irq(dev, irq, NULL,
+ ab8500_fg_irq[i].isr,
IRQF_SHARED | IRQF_NO_SUSPEND | IRQF_ONESHOT,
ab8500_fg_irq[i].name, di);
if (ret != 0) {
dev_err(dev, "failed to request %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
- goto free_irq;
+ return ret;
}
dev_dbg(dev, "Requested %s IRQ %d: %d\n",
ab8500_fg_irq[i].name, irq, ret);
@@ -3168,14 +3177,14 @@ static int ab8500_fg_probe(struct platform_device *pdev)
ret = ab8500_fg_sysfs_init(di);
if (ret) {
dev_err(dev, "failed to create sysfs entry\n");
- goto free_irq;
+ return ret;
}
ret = ab8500_fg_sysfs_psy_create_attrs(di);
if (ret) {
dev_err(dev, "failed to create FG psy\n");
ab8500_fg_sysfs_exit(di);
- goto free_irq;
+ return ret;
}
/* Calibrate the fg first time */
@@ -3185,24 +3194,21 @@ static int ab8500_fg_probe(struct platform_device *pdev)
/* Use room temp as default value until we get an update from driver. */
di->bat_temp = 210;
- /* Run the FG algorithm */
- queue_delayed_work(di->fg_wq, &di->fg_periodic_work, 0);
-
list_add_tail(&di->node, &ab8500_fg_list);
- return ret;
+ return component_add(dev, &ab8500_fg_component_ops);
+}
-free_irq:
- /* We also have to free all registered irqs */
- while (--i >= 0) {
- /* Last assignment of i from primary interrupt handlers */
- irq = platform_get_irq_byname(pdev, ab8500_fg_irq[i].name);
- free_irq(irq, di);
- }
+static int ab8500_fg_remove(struct platform_device *pdev)
+{
+ int ret = 0;
+ struct ab8500_fg *di = platform_get_drvdata(pdev);
+
+ component_del(&pdev->dev, &ab8500_fg_component_ops);
+ list_del(&di->node);
+ ab8500_fg_sysfs_exit(di);
+ ab8500_fg_sysfs_psy_remove_attrs(di);
- power_supply_unregister(di->fg_psy);
-free_inst_curr_wq:
- destroy_workqueue(di->fg_wq);
return ret;
}
@@ -3213,7 +3219,7 @@ static const struct of_device_id ab8500_fg_match[] = {
{ },
};
-static struct platform_driver ab8500_fg_driver = {
+struct platform_driver ab8500_fg_driver = {
.probe = ab8500_fg_probe,
.remove = ab8500_fg_remove,
.driver = {
@@ -3222,20 +3228,6 @@ static struct platform_driver ab8500_fg_driver = {
.pm = &ab8500_fg_pm_ops,
},
};
-
-static int __init ab8500_fg_init(void)
-{
- return platform_driver_register(&ab8500_fg_driver);
-}
-
-static void __exit ab8500_fg_exit(void)
-{
- platform_driver_unregister(&ab8500_fg_driver);
-}
-
-subsys_initcall_sync(ab8500_fg_init);
-module_exit(ab8500_fg_exit);
-
MODULE_LICENSE("GPL v2");
MODULE_AUTHOR("Johan Palsson, Karl Komierowski");
MODULE_ALIAS("platform:ab8500-fg");
diff --git a/drivers/power/supply/abx500_chargalg.c b/drivers/power/supply/abx500_chargalg.c
index f5b792243727..599684ce0e4b 100644
--- a/drivers/power/supply/abx500_chargalg.c
+++ b/drivers/power/supply/abx500_chargalg.c
@@ -15,6 +15,7 @@
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
+#include <linux/component.h>
#include <linux/hrtimer.h>
#include <linux/interrupt.h>
#include <linux/delay.h>
@@ -1943,13 +1944,44 @@ static int __maybe_unused abx500_chargalg_suspend(struct device *dev)
return 0;
}
-static int abx500_chargalg_remove(struct platform_device *pdev)
+static char *supply_interface[] = {
+ "ab8500_fg",
+};
+
</cut>
4 years, 1 month
- 4
- 3
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-aarch64-next-allmodconfig - Build # 26 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-aarch64-next-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-release-aarch64-next-allmodconfig
Culprit:
<cut>
commit 3d463dd5023b5a58b3c37207d65eeb5acbac2be3
Author: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Date: Thu Jul 29 12:40:19 2021 +0200
nfc: fdp: constify several pointers
Several functions do not modify pointed data so arguments and local
variables can be const for correctness and safety. This allows also
making file-scope nci_core_get_config_otp_ram_version array const.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
</cut>
Results regressed to (for first_bad == 3d463dd5023b5a58b3c37207d65eeb5acbac2be3)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
21802
# First few build errors in logs:
# 00:03:45 drivers/nfc/fdp/fdp.c:116:60: error: passing 'const char *' to parameter of type '__u8 *' (aka 'unsigned char *') discards qualifiers [-Werror,-Wincompatible-pointer-types-discards-qualifiers]
# 00:03:45 make[3]: *** [drivers/nfc/fdp/fdp.o] Error 1
# 00:03:49 make[2]: *** [drivers/nfc/fdp] Error 2
# 00:04:01 make[1]: *** [drivers/nfc] Error 2
# 00:09:25 make: *** [drivers] Error 2
from (for last_good == c3e26b6dc1b4e3e8f57be4f004b1f2a410c5c468)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29857
# linux build successful:
all
# linux boot successful:
boot
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next…
Configuration details:
rr[linux_git]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git#cb16362…"
Reproduce builds:
<cut>
mkdir investigate-linux-3d463dd5023b5a58b3c37207d65eeb5acbac2be3
cd investigate-linux-3d463dd5023b5a58b3c37207d65eeb5acbac2be3
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 3d463dd5023b5a58b3c37207d65eeb5acbac2be3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach c3e26b6dc1b4e3e8f57be4f004b1f2a410c5c468
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-aarch64-next…
Full commit (up to 1000 lines):
<cut>
commit 3d463dd5023b5a58b3c37207d65eeb5acbac2be3
Author: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Date: Thu Jul 29 12:40:19 2021 +0200
nfc: fdp: constify several pointers
Several functions do not modify pointed data so arguments and local
variables can be const for correctness and safety. This allows also
making file-scope nci_core_get_config_otp_ram_version array const.
Signed-off-by: Krzysztof Kozlowski <krzysztof.kozlowski(a)canonical.com>
Signed-off-by: David S. Miller <davem(a)davemloft.net>
---
drivers/nfc/fdp/fdp.c | 18 +++++++++---------
drivers/nfc/fdp/fdp.h | 2 +-
drivers/nfc/fdp/i2c.c | 6 +++---
3 files changed, 13 insertions(+), 13 deletions(-)
diff --git a/drivers/nfc/fdp/fdp.c b/drivers/nfc/fdp/fdp.c
index 3f5fba922c4d..c6b3334f24c9 100644
--- a/drivers/nfc/fdp/fdp.c
+++ b/drivers/nfc/fdp/fdp.c
@@ -52,7 +52,7 @@ struct fdp_nci_info {
u32 limited_otp_version;
u8 key_index;
- u8 *fw_vsc_cfg;
+ const u8 *fw_vsc_cfg;
u8 clock_type;
u32 clock_freq;
@@ -65,7 +65,7 @@ struct fdp_nci_info {
wait_queue_head_t setup_wq;
};
-static u8 nci_core_get_config_otp_ram_version[5] = {
+static const u8 nci_core_get_config_otp_ram_version[5] = {
0x04,
NCI_PARAM_ID_FW_RAM_VERSION,
NCI_PARAM_ID_FW_OTP_VERSION,
@@ -111,7 +111,7 @@ static inline int fdp_nci_patch_cmd(struct nci_dev *ndev, u8 type)
}
static inline int fdp_nci_set_production_data(struct nci_dev *ndev, u8 len,
- char *data)
+ const char *data)
{
return nci_prop_cmd(ndev, NCI_OP_PROP_SET_PDATA_OID, len, data);
}
@@ -236,7 +236,7 @@ static int fdp_nci_send_patch(struct nci_dev *ndev, u8 conn_id, u8 type)
static int fdp_nci_open(struct nci_dev *ndev)
{
- struct fdp_nci_info *info = nci_get_drvdata(ndev);
+ const struct fdp_nci_info *info = nci_get_drvdata(ndev);
return info->phy_ops->enable(info->phy);
}
@@ -260,7 +260,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
{
struct fdp_nci_info *info = nci_get_drvdata(ndev);
struct device *dev = &info->phy->i2c_dev->dev;
- u8 *data;
+ const u8 *data;
int r;
r = request_firmware(&info->ram_patch, FDP_RAM_PATCH_NAME, dev);
@@ -269,7 +269,7 @@ static int fdp_nci_request_firmware(struct nci_dev *ndev)
return r;
}
- data = (u8 *) info->ram_patch->data;
+ data = info->ram_patch->data;
info->ram_patch_version =
data[FDP_FW_HEADER_SIZE] |
(data[FDP_FW_HEADER_SIZE + 1] << 8) |
@@ -610,9 +610,9 @@ static int fdp_nci_core_get_config_rsp_packet(struct nci_dev *ndev,
{
struct fdp_nci_info *info = nci_get_drvdata(ndev);
struct device *dev = &info->phy->i2c_dev->dev;
- struct nci_core_get_config_rsp *rsp = (void *) skb->data;
+ const struct nci_core_get_config_rsp *rsp = (void *) skb->data;
unsigned int i;
- u8 *p;
+ const u8 *p;
if (rsp->status == NCI_STATUS_OK) {
@@ -691,7 +691,7 @@ static const struct nci_ops nci_ops = {
int fdp_nci_probe(struct fdp_i2c_phy *phy, const struct nfc_phy_ops *phy_ops,
struct nci_dev **ndevp, int tx_headroom,
int tx_tailroom, u8 clock_type, u32 clock_freq,
- u8 *fw_vsc_cfg)
+ const u8 *fw_vsc_cfg)
{
struct device *dev = &phy->i2c_dev->dev;
struct fdp_nci_info *info;
diff --git a/drivers/nfc/fdp/fdp.h b/drivers/nfc/fdp/fdp.h
index dc048d4b977e..2e9161a4d7bf 100644
--- a/drivers/nfc/fdp/fdp.h
+++ b/drivers/nfc/fdp/fdp.h
@@ -23,7 +23,7 @@ struct fdp_i2c_phy {
int fdp_nci_probe(struct fdp_i2c_phy *phy, const struct nfc_phy_ops *phy_ops,
struct nci_dev **ndev, int tx_headroom, int tx_tailroom,
- u8 clock_type, u32 clock_freq, u8 *fw_vsc_cfg);
+ u8 clock_type, u32 clock_freq, const u8 *fw_vsc_cfg);
void fdp_nci_remove(struct nci_dev *ndev);
#endif /* __LOCAL_FDP_H_ */
diff --git a/drivers/nfc/fdp/i2c.c b/drivers/nfc/fdp/i2c.c
index 98e1876c9468..051c43a2a52f 100644
--- a/drivers/nfc/fdp/i2c.c
+++ b/drivers/nfc/fdp/i2c.c
@@ -36,7 +36,7 @@
print_hex_dump(KERN_DEBUG, prefix": ", DUMP_PREFIX_OFFSET, \
16, 1, (skb)->data, (skb)->len, 0)
-static void fdp_nci_i2c_reset(struct fdp_i2c_phy *phy)
+static void fdp_nci_i2c_reset(const struct fdp_i2c_phy *phy)
{
/* Reset RST/WakeUP for at least 100 micro-second */
gpiod_set_value_cansleep(phy->power_gpio, FDP_POWER_OFF);
@@ -47,7 +47,7 @@ static void fdp_nci_i2c_reset(struct fdp_i2c_phy *phy)
static int fdp_nci_i2c_enable(void *phy_id)
{
- struct fdp_i2c_phy *phy = phy_id;
+ const struct fdp_i2c_phy *phy = phy_id;
fdp_nci_i2c_reset(phy);
@@ -56,7 +56,7 @@ static int fdp_nci_i2c_enable(void *phy_id)
static void fdp_nci_i2c_disable(void *phy_id)
{
- struct fdp_i2c_phy *phy = phy_id;
+ const struct fdp_i2c_phy *phy = phy_id;
fdp_nci_i2c_reset(phy);
}
</cut>
4 years, 1 month
- 3
- 2
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3_LTO - Build # 25 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit 5a9b25e15b4f9707245bb9d1ab56ab99b725505a
Author: Sam Clegg <sbc(a)chromium.org>
Date: Fri May 14 16:25:04 2021 -0700
[lld][WebAssembly] Refactor input chunk class hierarchy. NFC
The main motivation for this refactor is to remove the subclass
relationship between the InputSegment and MergeInputSegment and
SyntenticMergedInputSegment so that we can use the merging classes for
debug sections which are not data segments.
In the process of refactoring I also remove all the virtual functions
from the class hierarchy and try to reuse techniques used in the ELF
linker (see `lld/ELF/InputSections.h`).
Differential Revision: https://reviews.llvm.org/D102546
</cut>
Results regressed to (for first_bad == 5a9b25e15b4f9707245bb9d1ab56ab99b725505a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO -- artifacts/build-5a9b25e15b4f9707245bb9d1ab56ab99b725505a/results_id:
1
# 462.libquantum,libquantum_base.default regressed by 113
from (for last_good == ed9d70781bbd1dc858b9f6913729fcc49a1e4bdf)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO -- artifacts/build-ed9d70781bbd1dc858b9f6913729fcc49a1e4bdf/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3_LTO/2499
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3_LTO/2539
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-5a9b25e15b4f9707245bb9d1ab56ab99b725505a
cd investigate-llvm-5a9b25e15b4f9707245bb9d1ab56ab99b725505a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 5a9b25e15b4f9707245bb9d1ab56ab99b725505a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach ed9d70781bbd1dc858b9f6913729fcc49a1e4bdf
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 5a9b25e15b4f9707245bb9d1ab56ab99b725505a
Author: Sam Clegg <sbc(a)chromium.org>
Date: Fri May 14 16:25:04 2021 -0700
[lld][WebAssembly] Refactor input chunk class hierarchy. NFC
The main motivation for this refactor is to remove the subclass
relationship between the InputSegment and MergeInputSegment and
SyntenticMergedInputSegment so that we can use the merging classes for
debug sections which are not data segments.
In the process of refactoring I also remove all the virtual functions
from the class hierarchy and try to reuse techniques used in the ELF
linker (see `lld/ELF/InputSections.h`).
Differential Revision: https://reviews.llvm.org/D102546
---
lld/wasm/Driver.cpp | 4 +-
lld/wasm/InputChunks.cpp | 99 ++++++++++------
lld/wasm/InputChunks.h | 254 +++++++++++++++++++----------------------
lld/wasm/InputFiles.cpp | 6 +-
lld/wasm/InputFiles.h | 2 +-
lld/wasm/OutputSections.cpp | 2 +-
lld/wasm/OutputSegment.cpp | 27 +++--
lld/wasm/OutputSegment.h | 4 +-
lld/wasm/SymbolTable.cpp | 2 +-
lld/wasm/SymbolTable.h | 3 +-
lld/wasm/Symbols.cpp | 6 +-
lld/wasm/Symbols.h | 6 +-
lld/wasm/SyntheticSections.cpp | 2 +-
lld/wasm/Writer.cpp | 10 +-
14 files changed, 214 insertions(+), 213 deletions(-)
diff --git a/lld/wasm/Driver.cpp b/lld/wasm/Driver.cpp
index a0ba04c4fa1e..6fec9d5b2278 100644
--- a/lld/wasm/Driver.cpp
+++ b/lld/wasm/Driver.cpp
@@ -800,8 +800,8 @@ static void splitSections() {
// before calling finalizeContents().
LLVM_DEBUG(llvm::dbgs() << "splitSections\n");
parallelForEach(symtab->objectFiles, [](ObjFile *file) {
- for (InputSegment *seg : file->segments) {
- if (auto *s = dyn_cast<MergeInputSegment>(seg))
+ for (InputChunk *seg : file->segments) {
+ if (auto *s = dyn_cast<MergeInputChunk>(seg))
s->splitIntoPieces();
}
});
diff --git a/lld/wasm/InputChunks.cpp b/lld/wasm/InputChunks.cpp
index f73e3362ae8e..b7d1aa25e9c8 100644
--- a/lld/wasm/InputChunks.cpp
+++ b/lld/wasm/InputChunks.cpp
@@ -57,8 +57,37 @@ StringRef InputChunk::getComdatName() const {
return file->getWasmObj()->linkingData().Comdats[index];
}
+uint32_t InputChunk::getSize() const {
+ if (const auto *ms = dyn_cast<SyntheticMergedChunk>(this))
+ return ms->builder.getSize();
+
+ if (const auto *f = dyn_cast<InputFunction>(this)) {
+ if (config->compressRelocations && f->file) {
+ return f->getCompressedSize();
+ }
+ }
+
+ return data().size();
+}
+
+uint32_t InputChunk::getInputSize() const {
+ if (const auto *f = dyn_cast<InputFunction>(this))
+ return f->function->Size;
+ return getSize();
+}
+
// Copy this input chunk to an mmap'ed output file and apply relocations.
void InputChunk::writeTo(uint8_t *buf) const {
+ if (const auto *f = dyn_cast<InputFunction>(this)) {
+ if (file && config->compressRelocations)
+ return f->writeCompressed(buf);
+ } else if (const auto *ms = dyn_cast<SyntheticMergedChunk>(this)) {
+ ms->builder.write(buf + outSecOff);
+ // Apply relocations
+ ms->relocate(buf + outSecOff);
+ return;
+ }
+
// Copy contents
memcpy(buf + outSecOff, data().data(), data().size());
@@ -73,7 +102,7 @@ void InputChunk::relocate(uint8_t *buf) const {
LLVM_DEBUG(dbgs() << "applying relocations: " << toString(this)
<< " count=" << relocations.size() << "\n");
int32_t inputSectionOffset = getInputSectionOffset();
- auto tombstone = getTombstone();
+ uint64_t tombstone = getTombstone();
for (const WasmRelocation &rel : relocations) {
uint8_t *loc = buf + rel.Offset - inputSectionOffset;
@@ -149,6 +178,14 @@ void InputChunk::writeRelocations(raw_ostream &os) const {
}
}
+uint64_t InputChunk::getTombstone() const {
+ if (const auto *s = dyn_cast<InputSection>(this)) {
+ return s->tombstoneValue;
+ }
+
+ return 0;
+}
+
void InputFunction::setFunctionIndex(uint32_t index) {
LLVM_DEBUG(dbgs() << "InputFunction::setFunctionIndex: " << getName()
<< " -> " << index << "\n");
@@ -235,7 +272,7 @@ void InputFunction::calculateSize() {
uint32_t start = getInputSectionOffset();
uint32_t end = start + function->Size;
- auto tombstone = getTombstone();
+ uint64_t tombstone = getTombstone();
uint32_t lastRelocEnd = start + functionSizeLength;
for (const WasmRelocation &rel : relocations) {
@@ -259,10 +296,7 @@ void InputFunction::calculateSize() {
// Override the default writeTo method so that we can (optionally) write the
// compressed version of the function.
-void InputFunction::writeTo(uint8_t *buf) const {
- if (!file || !config->compressRelocations)
- return InputChunk::writeTo(buf);
-
+void InputFunction::writeCompressed(uint8_t *buf) const {
buf += outSecOff;
uint8_t *orig = buf;
(void)orig;
@@ -270,7 +304,7 @@ void InputFunction::writeTo(uint8_t *buf) const {
const uint8_t *secStart = file->codeSection->Content.data();
const uint8_t *funcStart = secStart + getInputSectionOffset();
const uint8_t *end = funcStart + function->Size;
- auto tombstone = getTombstone();
+ uint64_t tombstone = getTombstone();
uint32_t count;
decodeULEB128(funcStart, &count);
funcStart += count;
@@ -294,26 +328,30 @@ void InputFunction::writeTo(uint8_t *buf) const {
LLVM_DEBUG(dbgs() << " total: " << (buf + chunkSize - orig) << "\n");
}
-uint64_t InputSegment::getOffset(uint64_t offset) const {
- if (const MergeInputSegment *ms = dyn_cast<MergeInputSegment>(this)) {
- LLVM_DEBUG(dbgs() << "getOffset(merged): " << getName() << "\n");
+uint64_t InputChunk::getOffset(uint64_t offset) const {
+ return outSecOff + offset;
+}
+
+uint64_t InputChunk::getSegmentOffset(uint64_t offset) const {
+ if (const auto *ms = dyn_cast<MergeInputChunk>(this)) {
+ LLVM_DEBUG(dbgs() << "getSegmentOffset(merged): " << getName() << "\n");
LLVM_DEBUG(dbgs() << "offset: " << offset << "\n");
LLVM_DEBUG(dbgs() << "parentOffset: " << ms->getParentOffset(offset)
<< "\n");
assert(ms->parent);
- return ms->parent->getOffset(ms->getParentOffset(offset));
+ return ms->parent->getSegmentOffset(ms->getParentOffset(offset));
}
return outputSegmentOffset + offset;
}
-uint64_t InputSegment::getVA(uint64_t offset) const {
- return (outputSeg ? outputSeg->startVA : 0) + getOffset(offset);
+uint64_t InputChunk::getVA(uint64_t offset) const {
+ return (outputSeg ? outputSeg->startVA : 0) + getSegmentOffset(offset);
}
// Generate code to apply relocations to the data section at runtime.
// This is only called when generating shared libaries (PIC) where address are
// not known at static link time.
-void InputSegment::generateRelocationCode(raw_ostream &os) const {
+void InputChunk::generateRelocationCode(raw_ostream &os) const {
LLVM_DEBUG(dbgs() << "generating runtime relocations: " << getName()
<< " count=" << relocations.size() << "\n");
@@ -324,7 +362,7 @@ void InputSegment::generateRelocationCode(raw_ostream &os) const {
? WASM_OPCODE_I64_ADD
: WASM_OPCODE_I32_ADD;
- auto tombstone = getTombstone();
+ uint64_t tombstone = getTombstone();
// TODO(sbc): Encode the relocations in the data section and write a loop
// here to apply them.
for (const WasmRelocation &rel : relocations) {
@@ -382,7 +420,7 @@ void InputSegment::generateRelocationCode(raw_ostream &os) const {
// Split WASM_SEG_FLAG_STRINGS section. Such a section is a sequence of
// null-terminated strings.
-void MergeInputSegment::splitStrings(ArrayRef<uint8_t> data) {
+void MergeInputChunk::splitStrings(ArrayRef<uint8_t> data) {
LLVM_DEBUG(llvm::dbgs() << "splitStrings\n");
size_t off = 0;
StringRef s = toStringRef(data);
@@ -405,15 +443,15 @@ void MergeInputSegment::splitStrings(ArrayRef<uint8_t> data) {
//
// Note that this function is called from parallelForEach. This must be
// thread-safe (i.e. no memory allocation from the pools).
-void MergeInputSegment::splitIntoPieces() {
+void MergeInputChunk::splitIntoPieces() {
assert(pieces.empty());
// As of now we only support WASM_SEG_FLAG_STRINGS but in the future we
// could add other types of splitting (see ELF's splitIntoPieces).
- assert(segment->Data.LinkingFlags & WASM_SEG_FLAG_STRINGS);
+ assert(flags & WASM_SEG_FLAG_STRINGS);
splitStrings(data());
}
-SegmentPiece *MergeInputSegment::getSegmentPiece(uint64_t offset) {
+SectionPiece *MergeInputChunk::getSectionPiece(uint64_t offset) {
if (this->data().size() <= offset)
fatal(toString(this) + ": offset is outside the section");
@@ -421,36 +459,25 @@ SegmentPiece *MergeInputSegment::getSegmentPiece(uint64_t offset) {
// In that case we need to do a binary search of the original section piece
// vector.
auto it = partition_point(
- pieces, [=](SegmentPiece p) { return p.inputOff <= offset; });
+ pieces, [=](SectionPiece p) { return p.inputOff <= offset; });
return &it[-1];
}
// Returns the offset in an output section for a given input offset.
// Because contents of a mergeable section is not contiguous in output,
// it is not just an addition to a base output offset.
-uint64_t MergeInputSegment::getParentOffset(uint64_t offset) const {
+uint64_t MergeInputChunk::getParentOffset(uint64_t offset) const {
// If Offset is not at beginning of a section piece, it is not in the map.
// In that case we need to search from the original section piece vector.
- const SegmentPiece *piece = getSegmentPiece(offset);
+ const SectionPiece *piece = getSectionPiece(offset);
uint64_t addend = offset - piece->inputOff;
return piece->outputOff + addend;
}
-uint32_t SyntheticMergedDataSegment::getSize() const {
- return builder.getSize();
-}
-
-void SyntheticMergedDataSegment::writeTo(uint8_t *buf) const {
- builder.write(buf + outSecOff);
-
- // Apply relocations
- relocate(buf + outSecOff);
-}
-
-void SyntheticMergedDataSegment::finalizeContents() {
+void SyntheticMergedChunk::finalizeContents() {
// Add all string pieces to the string table builder to create section
// contents.
- for (MergeInputSegment *sec : segments)
+ for (MergeInputChunk *sec : chunks)
for (size_t i = 0, e = sec->pieces.size(); i != e; ++i)
if (sec->pieces[i].live)
builder.add(sec->getData(i));
@@ -461,7 +488,7 @@ void SyntheticMergedDataSegment::finalizeContents() {
// finalize() fixed tail-optimized strings, so we can now get
// offsets of strings. Get an offset for each string and save it
// to a corresponding SectionPiece for easy access.
- for (MergeInputSegment *sec : segments)
+ for (MergeInputChunk *sec : chunks)
for (size_t i = 0, e = sec->pieces.size(); i != e; ++i)
if (sec->pieces[i].live)
sec->pieces[i].outputOff = builder.getOffset(sec->getData(i));
diff --git a/lld/wasm/InputChunks.h b/lld/wasm/InputChunks.h
index 5bf96df695d5..47ed7ccaadcb 100644
--- a/lld/wasm/InputChunks.h
+++ b/lld/wasm/InputChunks.h
@@ -40,40 +40,68 @@ public:
enum Kind {
DataSegment,
Merge,
- MergedSegment,
+ MergedChunk,
Function,
SyntheticFunction,
Section
};
- Kind kind() const { return sectionKind; }
+ StringRef name;
+ StringRef debugName;
+
+ StringRef getName() const { return name; }
+ StringRef getDebugName() const { return debugName; }
+ Kind kind() const { return (Kind)sectionKind; }
- virtual uint32_t getSize() const { return data().size(); }
- virtual uint32_t getInputSize() const { return getSize(); };
+ uint32_t getSize() const;
+ uint32_t getInputSize() const;
- virtual void writeTo(uint8_t *buf) const;
+ void writeTo(uint8_t *buf) const;
void relocate(uint8_t *buf) const;
ArrayRef<WasmRelocation> getRelocations() const { return relocations; }
void setRelocations(ArrayRef<WasmRelocation> rs) { relocations = rs; }
- uint64_t getOffset(uint64_t offset) const { return outSecOff + offset; }
- virtual StringRef getName() const = 0;
- virtual StringRef getDebugName() const = 0;
- virtual uint32_t getComdat() const = 0;
+ // Translate an offset in the input section to an offset in the output
+ // section.
+ uint64_t getOffset(uint64_t offset) const;
+ // For data segments, translate and offset into the input segment into
+ // an offset into the output segment
+ uint64_t getSegmentOffset(uint64_t offset) const;
+ uint64_t getVA(uint64_t offset = 0) const;
+
+ uint32_t getComdat() const { return comdat; }
StringRef getComdatName() const;
- virtual uint32_t getInputSectionOffset() const = 0;
+ uint32_t getInputSectionOffset() const { return inputSectionOffset; }
size_t getNumRelocations() const { return relocations.size(); }
void writeRelocations(llvm::raw_ostream &os) const;
+ void generateRelocationCode(raw_ostream &os) const;
+
+ bool isTLS() const {
+ // Older object files don't include WASM_SEG_FLAG_TLS and instead
+ // relied on the naming convention.
+ return flags & llvm::wasm::WASM_SEG_FLAG_TLS || name.startswith(".tdata") ||
+ name.startswith(".tbss");
+ }
ObjFile *file;
OutputSection *outputSec = nullptr;
+ uint32_t comdat = UINT32_MAX;
+ uint32_t inputSectionOffset = 0;
+ uint32_t alignment;
+ uint32_t flags;
+
+ // Only applies to data segments.
+ uint32_t outputSegmentOffset = 0;
+ const OutputSegment *outputSeg = nullptr;
// After assignAddresses is called, this represents the offset from
// the beginning of the output section this chunk was assigned to.
int32_t outSecOff = 0;
+ uint8_t sectionKind : 3;
+
// Signals that the section is part of the output. The garbage collector,
// and COMDAT handling can set a sections' Live bit.
// If GC is disabled, all sections start out as live by default.
@@ -83,14 +111,15 @@ public:
unsigned discarded : 1;
protected:
- InputChunk(ObjFile *f, Kind k)
- : file(f), live(!config->gcSections), discarded(false), sectionKind(k) {}
- virtual ~InputChunk() = default;
- virtual ArrayRef<uint8_t> data() const = 0;
- virtual uint64_t getTombstone() const { return 0; }
+ InputChunk(ObjFile *f, Kind k, StringRef name, uint32_t alignment = 0,
+ uint32_t flags = 0)
+ : name(name), file(f), alignment(alignment), flags(flags), sectionKind(k),
+ live(!config->gcSections), discarded(false) {}
+ ArrayRef<uint8_t> data() const { return rawData; }
+ uint64_t getTombstone() const;
ArrayRef<WasmRelocation> relocations;
- Kind sectionKind;
+ ArrayRef<uint8_t> rawData;
};
// Represents a WebAssembly data segment which can be included as part of
@@ -104,64 +133,34 @@ protected:
class InputSegment : public InputChunk {
public:
InputSegment(const WasmSegment *seg, ObjFile *f)
- : InputChunk(f, InputChunk::DataSegment), segment(seg) {
- alignment = segment->Data.Alignment;
- flags = segment->Data.LinkingFlags;
- }
-
- InputSegment(uint32_t alignment, uint32_t flags)
- : InputChunk(nullptr, InputChunk::DataSegment), alignment(alignment),
- flags(flags) {}
-
- static bool classof(const InputChunk *c) {
- return c->kind() == DataSegment || c->kind() == Merge ||
- c->kind() == MergedSegment;
- }
-
- void generateRelocationCode(raw_ostream &os) const;
-
- StringRef getName() const override { return segment->Data.Name; }
- StringRef getDebugName() const override { return StringRef(); }
- uint32_t getComdat() const override { return segment->Data.Comdat; }
- uint32_t getInputSectionOffset() const override {
- return segment->SectionOffset;
+ : InputChunk(f, InputChunk::DataSegment, seg->Data.Name,
+ seg->Data.Alignment, seg->Data.LinkingFlags),
+ segment(seg) {
+ rawData = segment->Data.Content;
+ comdat = segment->Data.Comdat;
+ inputSectionOffset = segment->SectionOffset;
}
- // Translate an offset in the input section to an offset in the output
- // section.
- uint64_t getOffset(uint64_t offset) const;
-
- uint64_t getVA(uint64_t offset = 0) const;
-
- bool isTLS() const {
- // Older object files don't include WASM_SEG_FLAG_TLS and instead
- // relied on the naming convention.
- return flags & llvm::wasm::WASM_SEG_FLAG_TLS ||
- getName().startswith(".tdata") || getName().startswith(".tbss");
- }
+ InputSegment(StringRef name, uint32_t alignment, uint32_t flags)
+ : InputChunk(nullptr, InputChunk::DataSegment, name, alignment, flags) {}
- const OutputSegment *outputSeg = nullptr;
- uint32_t outputSegmentOffset = 0;
- uint32_t alignment = 0;
- uint32_t flags = 0;
+ static bool classof(const InputChunk *c) { return c->kind() == DataSegment; }
protected:
- ArrayRef<uint8_t> data() const override { return segment->Data.Content; }
-
const WasmSegment *segment = nullptr;
};
-class SyntheticMergedDataSegment;
+class SyntheticMergedChunk;
// Merge segment handling copied from lld/ELF/InputSection.h. Keep in sync
// where possible.
-// SegmentPiece represents a piece of splittable segment contents.
+// SectionPiece represents a piece of splittable segment contents.
// We allocate a lot of these and binary search on them. This means that they
// have to be as compact as possible, which is why we don't store the size (can
// be found by looking at the next one).
-struct SegmentPiece {
- SegmentPiece(size_t off, uint32_t hash, bool live)
+struct SectionPiece {
+ SectionPiece(size_t off, uint32_t hash, bool live)
: inputOff(off), live(live || !config->gcSections), hash(hash >> 1) {}
uint32_t inputOff;
@@ -170,13 +169,17 @@ struct SegmentPiece {
uint64_t outputOff = 0;
};
-static_assert(sizeof(SegmentPiece) == 16, "SectionPiece is too big");
+static_assert(sizeof(SectionPiece) == 16, "SectionPiece is too big");
// This corresponds segments marked as WASM_SEG_FLAG_STRINGS.
-class MergeInputSegment : public InputSegment {
+class MergeInputChunk : public InputChunk {
public:
- MergeInputSegment(const WasmSegment *seg, ObjFile *f) : InputSegment(seg, f) {
- sectionKind = Merge;
+ MergeInputChunk(const WasmSegment *seg, ObjFile *f)
+ : InputChunk(f, Merge, seg->Data.Name, seg->Data.Alignment,
+ seg->Data.LinkingFlags) {
+ rawData = seg->Data.Content;
+ comdat = seg->Data.Comdat;
+ inputSectionOffset = seg->SectionOffset;
}
static bool classof(const InputChunk *s) { return s->kind() == Merge; }
@@ -188,7 +191,7 @@ public:
// Splittable sections are handled as a sequence of data
// rather than a single large blob of data.
- std::vector<SegmentPiece> pieces;
+ std::vector<SectionPiece> pieces;
// Returns I'th piece's data. This function is very hot when
// string merging is enabled, so we want to inline.
@@ -201,52 +204,43 @@ public:
}
// Returns the SectionPiece at a given input section offset.
- SegmentPiece *getSegmentPiece(uint64_t offset);
- const SegmentPiece *getSegmentPiece(uint64_t offset) const {
- return const_cast<MergeInputSegment *>(this)->getSegmentPiece(offset);
+ SectionPiece *getSectionPiece(uint64_t offset);
+ const SectionPiece *getSectionPiece(uint64_t offset) const {
+ return const_cast<MergeInputChunk *>(this)->getSectionPiece(offset);
}
- SyntheticMergedDataSegment *parent = nullptr;
+ SyntheticMergedChunk *parent = nullptr;
private:
void splitStrings(ArrayRef<uint8_t> a);
};
-// SyntheticMergedDataSegment is a class that allows us to put mergeable
+// SyntheticMergedChunk is a class that allows us to put mergeable
// sections with different attributes in a single output sections. To do that we
-// put them into SyntheticMergedDataSegment synthetic input sections which are
+// put them into SyntheticMergedChunk synthetic input sections which are
// attached to regular output sections.
-class SyntheticMergedDataSegment : public InputSegment {
+class SyntheticMergedChunk : public InputChunk {
public:
- SyntheticMergedDataSegment(StringRef name, uint32_t alignment, uint32_t flags)
- : InputSegment(alignment, flags), name(name),
- builder(llvm::StringTableBuilder::RAW, 1ULL << alignment) {
- sectionKind = InputChunk::MergedSegment;
- }
+ SyntheticMergedChunk(StringRef name, uint32_t alignment, uint32_t flags)
+ : InputChunk(nullptr, InputChunk::MergedChunk, name, alignment, flags),
+ builder(llvm::StringTableBuilder::RAW, 1ULL << alignment) {}
static bool classof(const InputChunk *c) {
- return c->kind() == InputChunk::MergedSegment;
+ return c->kind() == InputChunk::MergedChunk;
}
- uint32_t getSize() const override;
-
- StringRef getName() const override { return name; }
-
- uint32_t getComdat() const override { return segments[0]->getComdat(); }
-
- void writeTo(uint8_t *buf) const override;
-
- void addMergeSegment(MergeInputSegment *ms) {
+ void addMergeChunk(MergeInputChunk *ms) {
+ comdat = ms->getComdat();
ms->parent = this;
- segments.push_back(ms);
+ chunks.push_back(ms);
}
void finalizeContents();
-protected:
- std::vector<MergeInputSegment *> segments;
- StringRef name;
llvm::StringTableBuilder builder;
+
+protected:
+ std::vector<MergeInputChunk *> chunks;
};
// Represents a single wasm function within and input file. These are
@@ -254,44 +248,39 @@ protected:
class InputFunction : public InputChunk {
public:
InputFunction(const WasmSignature &s, const WasmFunction *func, ObjFile *f)
- : InputChunk(f, InputChunk::Function), signature(s), function(func),
- exportName(func && func->ExportName.hasValue()
- ? (*func->ExportName).str()
- : llvm::Optional<std::string>()) {}
+ : InputChunk(f, InputChunk::Function, func->SymbolName), signature(s),
+ function(func), exportName(func && func->ExportName.hasValue()
+ ? (*func->ExportName).str()
+ : llvm::Optional<std::string>()) {
+ inputSectionOffset = function->CodeSectionOffset;
+ rawData =
+ file->codeSection->Content.slice(inputSectionOffset, function->Size);
+ debugName = function->DebugName;
+ comdat = function->Comdat;
+ }
+
+ InputFunction(StringRef name, const WasmSignature &s)
+ : InputChunk(nullptr, InputChunk::Function, name), signature(s) {}
static bool classof(const InputChunk *c) {
return c->kind() == InputChunk::Function ||
c->kind() == InputChunk::SyntheticFunction;
}
- void writeTo(uint8_t *buf) const override;
- StringRef getName() const override { return function->SymbolName; }
- StringRef getDebugName() const override { return function->DebugName; }
llvm::Optional<StringRef> getExportName() const {
return exportName.hasValue() ? llvm::Optional<StringRef>(*exportName)
: llvm::Optional<StringRef>();
}
void setExportName(std::string exportName) { this->exportName = exportName; }
- uint32_t getComdat() const override { return function->Comdat; }
uint32_t getFunctionInputOffset() const { return getInputSectionOffset(); }
uint32_t getFunctionCodeOffset() const { return function->CodeOffset; }
- uint32_t getSize() const override {
- if (config->compressRelocations && file) {
- assert(compressedSize);
- return compressedSize;
- }
- return data().size();
- }
- uint32_t getInputSize() const override { return function->Size; }
uint32_t getFunctionIndex() const { return functionIndex.getValue(); }
bool hasFunctionIndex() const { return functionIndex.hasValue(); }
void setFunctionIndex(uint32_t index);
- uint32_t getInputSectionOffset() const override {
- return function->CodeSectionOffset;
- }
uint32_t getTableIndex() const { return tableIndex.getValue(); }
bool hasTableIndex() const { return tableIndex.hasValue(); }
void setTableIndex(uint32_t index);
+ void writeCompressed(uint8_t *buf) const;
// The size of a given input function can depend on the values of the
// LEB relocations within it. This finalizeContents method is called after
@@ -301,14 +290,14 @@ public:
const WasmSignature &signature;
-protected:
- ArrayRef<uint8_t> data() const override {
- assert(!config->compressRelocations);
- return file->codeSection->Content.slice(getInputSectionOffset(),
- function->Size);
+ uint32_t getCompressedSize() const {
+ assert(compressedSize);
+ return compressedSize;
}
const WasmFunction *function;
+
+protected:
llvm::Optional<std::string> exportName;
llvm::Optional<uint32_t> functionIndex;
llvm::Optional<uint32_t> tableIndex;
@@ -320,51 +309,38 @@ class SyntheticFunction : public InputFunction {
public:
SyntheticFunction(const WasmSignature &s, StringRef name,
StringRef debugName = {})
- : InputFunction(s, nullptr, nullptr), name(name), debugName(debugName) {
+ : InputFunction(name, s) {
sectionKind = InputChunk::SyntheticFunction;
+ this->debugName = debugName;
}
static bool classof(const InputChunk *c) {
return c->kind() == InputChunk::SyntheticFunction;
}
- StringRef getName() const override { return name; }
- StringRef getDebugName() const override { return debugName; }
- uint32_t getComdat() const override { return UINT32_MAX; }
-
- void setBody(ArrayRef<uint8_t> body_) { body = body_; }
-
-protected:
- ArrayRef<uint8_t> data() const override { return body; }
-
- StringRef name;
- StringRef debugName;
- ArrayRef<uint8_t> body;
+ void setBody(ArrayRef<uint8_t> body) { rawData = body; }
};
// Represents a single Wasm Section within an input file.
class InputSection : public InputChunk {
public:
InputSection(const WasmSection &s, ObjFile *f)
- : InputChunk(f, InputChunk::Section), section(s), tombstoneValue(getTombstoneForSection(s.Name)) {
+ : InputChunk(f, InputChunk::Section, s.Name),
+ tombstoneValue(getTombstoneForSection(s.Name)), section(s) {
assert(section.Type == llvm::wasm::WASM_SEC_CUSTOM);
+ comdat = section.Comdat;
+ rawData = section.Content;
}
- StringRef getName() const override { return section.Name; }
- StringRef getDebugName() const override { return StringRef(); }
- uint32_t getComdat() const override { return section.Comdat; }
+ static bool classof(const InputChunk *c) {
+ return c->kind() == InputChunk::Section;
+ }
-protected:
- ArrayRef<uint8_t> data() const override { return section.Content; }
+ const uint64_t tombstoneValue;
- // Offset within the input section. This is only zero since this chunk
- // type represents an entire input section, not part of one.
- uint32_t getInputSectionOffset() const override { return 0; }
- uint64_t getTombstone() const override { return tombstoneValue; }
+protected:
static uint64_t getTombstoneForSection(StringRef name);
-
const WasmSection §ion;
- const uint64_t tombstoneValue;
};
} // namespace wasm
diff --git a/lld/wasm/InputFiles.cpp b/lld/wasm/InputFiles.cpp
index 2cb5d59286e3..c65b05109c3d 100644
--- a/lld/wasm/InputFiles.cpp
+++ b/lld/wasm/InputFiles.cpp
@@ -464,9 +464,9 @@ void ObjFile::parse(bool ignoreComdats) {
// Populate `Segments`.
for (const WasmSegment &s : wasmObj->dataSegments()) {
- InputSegment *seg;
+ InputChunk *seg;
if (shouldMerge(s)) {
- seg = make<MergeInputSegment>(&s, this);
+ seg = make<MergeInputChunk>(&s, this);
} else
seg = make<InputSegment>(&s, this);
seg->discarded = isExcludedByComdat(seg);
@@ -568,7 +568,7 @@ Symbol *ObjFile::createDefined(const WasmSymbol &sym) {
return symtab->addDefinedFunction(name, flags, this, func);
}
case WASM_SYMBOL_TYPE_DATA: {
- InputSegment *seg = segments[sym.Info.DataRef.Segment];
+ InputChunk *seg = segments[sym.Info.DataRef.Segment];
auto offset = sym.Info.DataRef.Offset;
auto size = sym.Info.DataRef.Size;
if (sym.isBindingLocal())
diff --git a/lld/wasm/InputFiles.h b/lld/wasm/InputFiles.h
index dab44cd6830c..b720b889adcc 100644
--- a/lld/wasm/InputFiles.h
+++ b/lld/wasm/InputFiles.h
@@ -136,7 +136,7 @@ public:
std::vector<uint32_t> tableEntries;
std::vector<uint32_t> tableEntriesRel;
std::vector<bool> keptComdats;
- std::vector<InputSegment *> segments;
+ std::vector<InputChunk *> segments;
std::vector<InputFunction *> functions;
std::vector<InputGlobal *> globals;
std::vector<InputEvent *> events;
diff --git a/lld/wasm/OutputSections.cpp b/lld/wasm/OutputSections.cpp
index 6d91708d326a..780c8e4b2776 100644
--- a/lld/wasm/OutputSections.cpp
+++ b/lld/wasm/OutputSections.cpp
@@ -178,7 +178,7 @@ void DataSection::finalizeContents() {
log("Data segment: size=" + Twine(segment->size) + ", startVA=" +
Twine::utohexstr(segment->startVA) + ", name=" + segment->name);
- for (InputSegment *inputSeg : segment->inputSegments) {
+ for (InputChunk *inputSeg : segment->inputSegments) {
inputSeg->outputSec = this;
inputSeg->outSecOff = segment->sectionOffset + segment->header.size() +
inputSeg->outputSegmentOffset;
diff --git a/lld/wasm/OutputSegment.cpp b/lld/wasm/OutputSegment.cpp
index 899308e87c94..bf3e40c968a0 100644
--- a/lld/wasm/OutputSegment.cpp
+++ b/lld/wasm/OutputSegment.cpp
@@ -19,7 +19,7 @@ namespace lld {
namespace wasm {
-void OutputSegment::addInputSegment(InputSegment *inSeg) {
+void OutputSegment::addInputSegment(InputChunk *inSeg) {
alignment = std::max(alignment, inSeg->alignment);
inputSegments.push_back(inSeg);
size = llvm::alignTo(size, 1ULL << inSeg->alignment);
@@ -33,16 +33,16 @@ void OutputSegment::addInputSegment(InputSegment *inSeg) {
// This function scans over the input segments.
//
-// It removes MergeInputSegments from the input section array and adds
+// It removes MergeInputChunks from the input section array and adds
// new synthetic sections at the location of the first input section
// that it replaces. It then finalizes each synthetic section in order
// to compute an output offset for each piece of each input section.
void OutputSegment::finalizeInputSegments() {
LLVM_DEBUG(llvm::dbgs() << "finalizeInputSegments: " << name << "\n");
- std::vector<SyntheticMergedDataSegment *> mergedSegments;
- std::vector<InputSegment *> newSegments;
- for (InputSegment *s : inputSegments) {
- MergeInputSegment *ms = dyn_cast<MergeInputSegment>(s);
+ std::vector<SyntheticMergedChunk *> mergedSegments;
+ std::vector<InputChunk *> newSegments;
+ for (InputChunk *s : inputSegments) {
+ MergeInputChunk *ms = dyn_cast<MergeInputChunk>(s);
if (!ms) {
newSegments.push_back(s);
continue;
@@ -51,15 +51,14 @@ void OutputSegment::finalizeInputSegments() {
// A segment should not make it here unless its alive
assert(ms->live);
- auto i =
- llvm::find_if(mergedSegments, [=](SyntheticMergedDataSegment *seg) {
- return seg->flags == ms->flags && seg->alignment == ms->alignment;
- });
+ auto i = llvm::find_if(mergedSegments, [=](SyntheticMergedChunk *seg) {
+ return seg->flags == ms->flags && seg->alignment == ms->alignment;
+ });
if (i == mergedSegments.end()) {
LLVM_DEBUG(llvm::dbgs() << "new merge section: " << name
<< " alignment=" << ms->alignment << "\n");
- SyntheticMergedDataSegment *syn =
- make<SyntheticMergedDataSegment>(name, ms->alignment, ms->flags);
+ SyntheticMergedChunk *syn =
+ make<SyntheticMergedChunk>(name, ms->alignment, ms->flags);
syn->outputSeg = this;
mergedSegments.push_back(syn);
i = std::prev(mergedSegments.end());
@@ -67,7 +66,7 @@ void OutputSegment::finalizeInputSegments() {
} else {
LLVM_DEBUG(llvm::dbgs() << "adding to merge section: " << name << "\n");
}
- (*i)->addMergeSegment(ms);
+ (*i)->addMergeChunk(ms);
}
for (auto *ms : mergedSegments)
@@ -75,7 +74,7 @@ void OutputSegment::finalizeInputSegments() {
inputSegments = newSegments;
size = 0;
- for (InputSegment *seg : inputSegments) {
+ for (InputChunk *seg : inputSegments) {
size = llvm::alignTo(size, 1ULL << seg->alignment);
LLVM_DEBUG(llvm::dbgs() << "outputSegmentOffset set: " << seg->getName()
<< " -> " << size << "\n");
diff --git a/lld/wasm/OutputSegment.h b/lld/wasm/OutputSegment.h
index 10e28a4a8836..1d5cf9145241 100644
--- a/lld/wasm/OutputSegment.h
+++ b/lld/wasm/OutputSegment.h
@@ -22,7 +22,7 @@ class OutputSegment {
public:
OutputSegment(StringRef n) : name(n) {}
- void addInputSegment(InputSegment *inSeg);
+ void addInputSegment(InputChunk *inSeg);
void finalizeInputSegments();
bool isTLS() const { return name == ".tdata"; }
@@ -35,7 +35,7 @@ public:
uint32_t sectionOffset = 0;
uint32_t alignment = 0;
uint64_t startVA = 0;
- std::vector<InputSegment *> inputSegments;
+ std::vector<InputChunk *> inputSegments;
// Sum of the size of the all the input segments
uint32_t size = 0;
diff --git a/lld/wasm/SymbolTable.cpp b/lld/wasm/SymbolTable.cpp
index 56438c7b5d99..7e794a1bd431 100644
--- a/lld/wasm/SymbolTable.cpp
+++ b/lld/wasm/SymbolTable.cpp
@@ -365,7 +365,7 @@ Symbol *SymbolTable::addDefinedFunction(StringRef name, uint32_t flags,
}
Symbol *SymbolTable::addDefinedData(StringRef name, uint32_t flags,
- InputFile *file, InputSegment *segment,
+ InputFile *file, InputChunk *segment,
uint64_t address, uint64_t size) {
LLVM_DEBUG(dbgs() << "addDefinedData:" << name << " addr:" << address
<< "\n");
diff --git a/lld/wasm/SymbolTable.h b/lld/wasm/SymbolTable.h
index 36c776be30f5..bee18ce9c6bd 100644
--- a/lld/wasm/SymbolTable.h
+++ b/lld/wasm/SymbolTable.h
@@ -54,8 +54,7 @@ public:
Symbol *addDefinedFunction(StringRef name, uint32_t flags, InputFile *file,
InputFunction *function);
Symbol *addDefinedData(StringRef name, uint32_t flags, InputFile *file,
- InputSegment *segment, uint64_t address,
- uint64_t size);
+ InputChunk *segment, uint64_t address, uint64_t size);
Symbol *addDefinedGlobal(StringRef name, uint32_t flags, InputFile *file,
InputGlobal *g);
Symbol *addDefinedEvent(StringRef name, uint32_t flags, InputFile *file,
diff --git a/lld/wasm/Symbols.cpp b/lld/wasm/Symbols.cpp
index 00fe754e3eaa..24b7e10dc559 100644
--- a/lld/wasm/Symbols.cpp
+++ b/lld/wasm/Symbols.cpp
@@ -160,8 +160,8 @@ void Symbol::markLive() {
// (splittable) sections, each piece of data has independent liveness bit.
// So we explicitly tell it which offset is in use.
if (auto *d = dyn_cast<DefinedData>(this)) {
- if (auto *ms = dyn_cast<MergeInputSegment>(c)) {
- ms->getSegmentPiece(d->value)->live = true;
+ if (auto *ms = dyn_cast<MergeInputChunk>(c)) {
+ ms->getSectionPiece(d->value)->live = true;
}
}
c->live = true;
@@ -301,7 +301,7 @@ void DefinedData::setVA(uint64_t value_) {
uint64_t DefinedData::getOutputSegmentOffset() const {
LLVM_DEBUG(dbgs() << "getOutputSegmentOffset: " << getName() << "\n");
- return segment->getOffset(value);
+ return segment->getSegmentOffset(value);
}
uint64_t DefinedData::getOutputSegmentIndex() const {
diff --git a/lld/wasm/Symbols.h b/lld/wasm/Symbols.h
index 8bc3be0d2247..ff6eb0ae7ccb 100644
--- a/lld/wasm/Symbols.h
+++ b/lld/wasm/Symbols.h
@@ -278,8 +278,8 @@ protected:
class DefinedData : public DataSymbol {
public:
// Constructor for regular data symbols originating from input files.
- DefinedData(StringRef name, uint32_t flags, InputFile *f,
- InputSegment *segment, uint64_t value, uint64_t size)
+ DefinedData(StringRef name, uint32_t flags, InputFile *f, InputChunk *segment,
+ uint64_t value, uint64_t size)
: DataSymbol(name, DefinedDataKind, flags, f), segment(segment),
value(value), size(size) {}
@@ -298,7 +298,7 @@ public:
uint64_t getOutputSegmentIndex() const;
uint64_t getSize() const { return size; }
- InputSegment *segment = nullptr;
+ InputChunk *segment = nullptr;
uint64_t value = 0;
protected:
diff --git a/lld/wasm/SyntheticSections.cpp b/lld/wasm/SyntheticSections.cpp
index 4439761df9f9..b10ecc04b4b2 100644
--- a/lld/wasm/SyntheticSections.cpp
+++ b/lld/wasm/SyntheticSections.cpp
@@ -569,7 +569,7 @@ void LinkingSection::writeBody() {
continue;
StringRef comdat = inputSegments[0]->getComdatName();
#ifndef NDEBUG
- for (const InputSegment *isec : inputSegments)
+ for (const InputChunk *isec : inputSegments)
assert(isec->getComdatName() == comdat);
#endif
if (!comdat.empty())
diff --git a/lld/wasm/Writer.cpp b/lld/wasm/Writer.cpp
index 08149bc605a2..055972560b81 100644
--- a/lld/wasm/Writer.cpp
+++ b/lld/wasm/Writer.cpp
@@ -460,7 +460,7 @@ void Writer::populateTargetFeatures() {
}
// Find TLS data segments
- auto isTLS = [](InputSegment *segment) {
+ auto isTLS = [](InputChunk *segment) {
return segment->live && segment->isTLS();
};
tlsUsed = tlsUsed ||
@@ -816,7 +816,7 @@ void Writer::assignIndexes() {
out.tableSec->assignIndexes();
}
-static StringRef getOutputDataSegmentName(const InputSegment &seg) {
+static StringRef getOutputDataSegmentName(const InputChunk &seg) {
// We always merge .tbss and .tdata into a single TLS segment so all TLS
// symbols are be relative to single __tls_base.
if (seg.isTLS())
@@ -852,7 +852,7 @@ OutputSegment *Writer::createOutputSegment(StringRef name) {
void Writer::createOutputSegments() {
for (ObjFile *file : symtab->objectFiles) {
- for (InputSegment *segment : file->segments) {
+ for (InputChunk *segment : file->segments) {
if (!segment->live)
continue;
StringRef name = getOutputDataSegmentName(*segment);
@@ -919,7 +919,7 @@ void Writer::combineOutputSegments() {
combined->initFlags = WASM_DATA_SEGMENT_IS_PASSIVE;
}
bool first = true;
- for (InputSegment *inSeg : s->inputSegments) {
+ for (InputChunk *inSeg : s->inputSegments) {
if (first)
inSeg->alignment = std::max(inSeg->alignment, s->alignment);
first = false;
@@ -1201,7 +1201,7 @@ void Writer::createApplyDataRelocationsFunction() {
raw_string_ostream os(bodyContent);
writeUleb128(os, 0, "num locals");
for (const OutputSegment *seg : segments)
- for (const InputSegment *inSeg : seg->inputSegments)
+ for (const InputChunk *inSeg : seg->inputSegments)
inSeg->generateRelocationCode(os);
writeU8(os, WASM_OPCODE_END, "END");
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_apm/gnu-release-aarch64-spec2k6-Os_LTO - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_apm/gnu-release-aarch64-spec2k6-Os_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_apm/gnu-release-aarch64-spec2k6-Os_LTO
Culprit:
<cut>
commit ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4
Author: Martin Jambor <mjambor(a)suse.cz>
Date: Fri Sep 20 00:25:04 2019 +0200
New IPA-SRA
2019-09-20 Martin Jambor <mjambor(a)suse.cz>
* coretypes.h (cgraph_edge): Declare.
* ipa-param-manipulation.c: Rewrite.
* ipa-param-manipulation.h: Likewise.
* Makefile.in (GTFILES): Added ipa-param-manipulation.h and ipa-sra.c.
(OBJS): Added ipa-sra.o.
* cgraph.h (ipa_replace_map): Removed fields old_tree, replace_p
and ref_p, added fields param_adjustments and performed_splits.
(struct cgraph_clone_info): Remove ags_to_skip and
combined_args_to_skip, new field param_adjustments.
(cgraph_node::create_clone): Changed parameters to use
ipa_param_adjustments.
(cgraph_node::create_virtual_clone): Likewise.
(cgraph_node::create_virtual_clone_with_body): Likewise.
(tree_function_versioning): Likewise.
(cgraph_build_function_type_skip_args): Removed.
* cgraph.c (cgraph_edge::redirect_call_stmt_to_callee): Convert to
using ipa_param_adjustments.
(clone_of_p): Likewise.
* cgraphclones.c (cgraph_build_function_type_skip_args): Removed.
(build_function_decl_skip_args): Likewise.
(duplicate_thunk_for_node): Adjust parameters using
ipa_param_body_adjustments, copy param_adjustments instead of
args_to_skip.
(cgraph_node::create_clone): Convert to using ipa_param_adjustments.
(cgraph_node::create_virtual_clone): Likewise.
(cgraph_node::create_version_clone_with_body): Likewise.
(cgraph_materialize_clone): Likewise.
(symbol_table::materialize_all_clones): Likewise.
* ipa-fnsummary.c (ipa_fn_summary_t::duplicate): Simplify
ipa_replace_map check.
* ipa-cp.c (get_replacement_map): Do not initialize removed fields.
(initialize_node_lattices): Make aware that some parameters might have
already been removed.
(want_remove_some_param_p): New function.
(create_specialized_node): Convert to using ipa_param_adjustments and
deal with possibly pre-existing adjustments.
* lto-cgraph.c (output_cgraph_opt_summary_p): Likewise.
(output_node_opt_summary): Do not stream removed fields. Stream
parameter adjustments instead of argumetns to skip.
(input_node_opt_summary): Likewise.
(input_node_opt_summary): Likewise.
* lto-section-in.c (lto_section_name): Added ipa-sra section.
* lto-streamer.h (lto_section_type): Likewise.
* tree-inline.h (copy_body_data): New fields killed_new_ssa_names and
param_body_adjs.
(copy_decl_to_var): Declare.
* tree-inline.c (update_clone_info): Do not remap old_tree.
(remap_gimple_stmt): Use ipa_param_body_adjustments to modify gimple
statements, walk all extra generated statements and remap their
operands.
(redirect_all_calls): Add killed SSA names to a hash set.
(remap_ssa_name): Do not remap killed SSA names.
(copy_arguments_for_versioning): Renames to copy_arguments_nochange,
half of functionality moved to ipa_param_body_adjustments.
(copy_decl_to_var): Make exported.
(copy_body): Destroy killed_new_ssa_names hash set.
(expand_call_inline): Remap performed splits.
(update_clone_info): Likewise.
(tree_function_versioning): Simplify tree_map processing. Updated to
accept ipa_param_adjustments and use ipa_param_body_adjustments.
* omp-simd-clone.c (simd_clone_vector_of_formal_parm_types): Adjust
for the new interface.
(simd_clone_clauses_extract): Likewise, make args an auto_vec.
(simd_clone_compute_base_data_type): Likewise.
(simd_clone_init_simd_arrays): Adjust for the new interface.
(simd_clone_adjust_argument_types): Likewise.
(struct modify_stmt_info): Likewise.
(ipa_simd_modify_stmt_ops): Likewise.
(ipa_simd_modify_function_body): Likewise.
(simd_clone_adjust): Likewise.
* tree-sra.c: Removed IPA-SRA. Include tree-sra.h.
(type_internals_preclude_sra_p): Make public.
* tree-sra.h: New file.
* ipa-inline-transform.c (save_inline_function_body): Update to
refelct new tree_function_versioning signature.
* ipa-prop.c (adjust_agg_replacement_values): Use a helper from
ipa_param_adjustments to get current parameter indices.
(ipcp_modif_dom_walker::before_dom_children): Likewise.
(ipcp_update_bits): Likewise.
(ipcp_update_vr): Likewise.
* ipa-split.c (split_function): Convert to using ipa_param_adjustments.
* ipa-sra.c: New file.
* multiple_target.c (create_target_clone): Update to reflet new type
of create_version_clone_with_body.
* trans-mem.c (ipa_tm_create_version): Update to reflect new type of
tree_function_versioning.
(modify_function): Update to reflect new type of
tree_function_versioning.
* params.def (PARAM_IPA_SRA_MAX_REPLACEMENTS): New.
* passes.def: Remove old IPA-SRA and add new one.
* tree-pass.h (make_pass_early_ipa_sra): Remove declaration.
(make_pass_ipa_sra): Declare.
* dbgcnt.def: Remove eipa_sra. Added ipa_sra_params and
ipa_sra_retvalues.
* doc/invoke.texi (ipa-sra-max-replacements): New.
testsuite/
* g++.dg/ipa/pr81248.C: Adjust dg-options and dump-scan.
* gcc.dg/ipa/ipa-sra-1.c: Likewise.
* gcc.dg/ipa/ipa-sra-10.c: Likewise.
* gcc.dg/ipa/ipa-sra-11.c: Likewise.
* gcc.dg/ipa/ipa-sra-3.c: Likewise.
* gcc.dg/ipa/ipa-sra-4.c: Likewise.
* gcc.dg/ipa/ipa-sra-5.c: Likewise.
* gcc.dg/ipa/ipacost-2.c: Disable ipa-sra.
* gcc.dg/ipa/ipcp-agg-9.c: Likewise.
* gcc.dg/ipa/pr78121.c: Adjust scan pattern.
* gcc.dg/ipa/vrp1.c: Likewise.
* gcc.dg/ipa/vrp2.c: Likewise.
* gcc.dg/ipa/vrp3.c: Likewise.
* gcc.dg/ipa/vrp7.c: Likewise.
* gcc.dg/ipa/vrp8.c: Likewise.
* gcc.dg/noreorder.c: use noipa attribute instead of noinline.
* gcc.dg/ipa/20040703-wpa.c: New test.
* gcc.dg/ipa/ipa-sra-12.c: New test.
* gcc.dg/ipa/ipa-sra-13.c: Likewise.
* gcc.dg/ipa/ipa-sra-14.c: Likewise.
* gcc.dg/ipa/ipa-sra-15.c: Likewise.
* gcc.dg/ipa/ipa-sra-16.c: Likewise.
* gcc.dg/ipa/ipa-sra-17.c: Likewise.
* gcc.dg/ipa/ipa-sra-18.c: Likewise.
* gcc.dg/ipa/ipa-sra-19.c: Likewise.
* gcc.dg/ipa/ipa-sra-20.c: Likewise.
* gcc.dg/ipa/ipa-sra-21.c: Likewise.
* gcc.dg/ipa/ipa-sra-22.c: Likewise.
* gcc.dg/sso/ipa-sra-1.c: Likewise.
* g++.dg/ipa/ipa-sra-2.C: Likewise.
* g++.dg/ipa/ipa-sra-3.C: Likewise.
* gcc.dg/tree-ssa/ipa-cp-1.c: Make return value used.
* g++.dg/ipa/devirt-19.C: Add missing return, add -fipa-cp-clone
option.
* g++.dg/lto/devirt-19_0.C: Add -fipa-cp-clone option.
* gcc.dg/ipa/ipa-sra-2.c: Removed.
* gcc.dg/ipa/ipa-sra-6.c: Likewise.
From-SVN: r275982
</cut>
Results regressed to (for first_bad == ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -Os_LTO -- artifacts/build-ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4/results_id:
1
# 450.soplex,soplex_base.default regressed by 103
from (for last_good == 6889a3acfeed47265886676c6d43b04ef799fb82)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -Os_LTO -- artifacts/build-6889a3acfeed47265886676c6d43b04ef799fb82/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a…
Results ID of last_good: apm_64/tcwg_bmk_gnu_apm/bisect-gnu-release-aarch64-spec2k6-Os_LTO/2526
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a…
Results ID of first_bad: apm_64/tcwg_bmk_gnu_apm/bisect-gnu-release-aarch64-spec2k6-Os_LTO/2531
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4
cd investigate-gcc-ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 6889a3acfeed47265886676c6d43b04ef799fb82
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_apm-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit ff6686d2e5f797d6c6a36ad14a7084bc1dc350e4
Author: Martin Jambor <mjambor(a)suse.cz>
Date: Fri Sep 20 00:25:04 2019 +0200
New IPA-SRA
2019-09-20 Martin Jambor <mjambor(a)suse.cz>
* coretypes.h (cgraph_edge): Declare.
* ipa-param-manipulation.c: Rewrite.
* ipa-param-manipulation.h: Likewise.
* Makefile.in (GTFILES): Added ipa-param-manipulation.h and ipa-sra.c.
(OBJS): Added ipa-sra.o.
* cgraph.h (ipa_replace_map): Removed fields old_tree, replace_p
and ref_p, added fields param_adjustments and performed_splits.
(struct cgraph_clone_info): Remove ags_to_skip and
combined_args_to_skip, new field param_adjustments.
(cgraph_node::create_clone): Changed parameters to use
ipa_param_adjustments.
(cgraph_node::create_virtual_clone): Likewise.
(cgraph_node::create_virtual_clone_with_body): Likewise.
(tree_function_versioning): Likewise.
(cgraph_build_function_type_skip_args): Removed.
* cgraph.c (cgraph_edge::redirect_call_stmt_to_callee): Convert to
using ipa_param_adjustments.
(clone_of_p): Likewise.
* cgraphclones.c (cgraph_build_function_type_skip_args): Removed.
(build_function_decl_skip_args): Likewise.
(duplicate_thunk_for_node): Adjust parameters using
ipa_param_body_adjustments, copy param_adjustments instead of
args_to_skip.
(cgraph_node::create_clone): Convert to using ipa_param_adjustments.
(cgraph_node::create_virtual_clone): Likewise.
(cgraph_node::create_version_clone_with_body): Likewise.
(cgraph_materialize_clone): Likewise.
(symbol_table::materialize_all_clones): Likewise.
* ipa-fnsummary.c (ipa_fn_summary_t::duplicate): Simplify
ipa_replace_map check.
* ipa-cp.c (get_replacement_map): Do not initialize removed fields.
(initialize_node_lattices): Make aware that some parameters might have
already been removed.
(want_remove_some_param_p): New function.
(create_specialized_node): Convert to using ipa_param_adjustments and
deal with possibly pre-existing adjustments.
* lto-cgraph.c (output_cgraph_opt_summary_p): Likewise.
(output_node_opt_summary): Do not stream removed fields. Stream
parameter adjustments instead of argumetns to skip.
(input_node_opt_summary): Likewise.
(input_node_opt_summary): Likewise.
* lto-section-in.c (lto_section_name): Added ipa-sra section.
* lto-streamer.h (lto_section_type): Likewise.
* tree-inline.h (copy_body_data): New fields killed_new_ssa_names and
param_body_adjs.
(copy_decl_to_var): Declare.
* tree-inline.c (update_clone_info): Do not remap old_tree.
(remap_gimple_stmt): Use ipa_param_body_adjustments to modify gimple
statements, walk all extra generated statements and remap their
operands.
(redirect_all_calls): Add killed SSA names to a hash set.
(remap_ssa_name): Do not remap killed SSA names.
(copy_arguments_for_versioning): Renames to copy_arguments_nochange,
half of functionality moved to ipa_param_body_adjustments.
(copy_decl_to_var): Make exported.
(copy_body): Destroy killed_new_ssa_names hash set.
(expand_call_inline): Remap performed splits.
(update_clone_info): Likewise.
(tree_function_versioning): Simplify tree_map processing. Updated to
accept ipa_param_adjustments and use ipa_param_body_adjustments.
* omp-simd-clone.c (simd_clone_vector_of_formal_parm_types): Adjust
for the new interface.
(simd_clone_clauses_extract): Likewise, make args an auto_vec.
(simd_clone_compute_base_data_type): Likewise.
(simd_clone_init_simd_arrays): Adjust for the new interface.
(simd_clone_adjust_argument_types): Likewise.
(struct modify_stmt_info): Likewise.
(ipa_simd_modify_stmt_ops): Likewise.
(ipa_simd_modify_function_body): Likewise.
(simd_clone_adjust): Likewise.
* tree-sra.c: Removed IPA-SRA. Include tree-sra.h.
(type_internals_preclude_sra_p): Make public.
* tree-sra.h: New file.
* ipa-inline-transform.c (save_inline_function_body): Update to
refelct new tree_function_versioning signature.
* ipa-prop.c (adjust_agg_replacement_values): Use a helper from
ipa_param_adjustments to get current parameter indices.
(ipcp_modif_dom_walker::before_dom_children): Likewise.
(ipcp_update_bits): Likewise.
(ipcp_update_vr): Likewise.
* ipa-split.c (split_function): Convert to using ipa_param_adjustments.
* ipa-sra.c: New file.
* multiple_target.c (create_target_clone): Update to reflet new type
of create_version_clone_with_body.
* trans-mem.c (ipa_tm_create_version): Update to reflect new type of
tree_function_versioning.
(modify_function): Update to reflect new type of
tree_function_versioning.
* params.def (PARAM_IPA_SRA_MAX_REPLACEMENTS): New.
* passes.def: Remove old IPA-SRA and add new one.
* tree-pass.h (make_pass_early_ipa_sra): Remove declaration.
(make_pass_ipa_sra): Declare.
* dbgcnt.def: Remove eipa_sra. Added ipa_sra_params and
ipa_sra_retvalues.
* doc/invoke.texi (ipa-sra-max-replacements): New.
testsuite/
* g++.dg/ipa/pr81248.C: Adjust dg-options and dump-scan.
* gcc.dg/ipa/ipa-sra-1.c: Likewise.
* gcc.dg/ipa/ipa-sra-10.c: Likewise.
* gcc.dg/ipa/ipa-sra-11.c: Likewise.
* gcc.dg/ipa/ipa-sra-3.c: Likewise.
* gcc.dg/ipa/ipa-sra-4.c: Likewise.
* gcc.dg/ipa/ipa-sra-5.c: Likewise.
* gcc.dg/ipa/ipacost-2.c: Disable ipa-sra.
* gcc.dg/ipa/ipcp-agg-9.c: Likewise.
* gcc.dg/ipa/pr78121.c: Adjust scan pattern.
* gcc.dg/ipa/vrp1.c: Likewise.
* gcc.dg/ipa/vrp2.c: Likewise.
* gcc.dg/ipa/vrp3.c: Likewise.
* gcc.dg/ipa/vrp7.c: Likewise.
* gcc.dg/ipa/vrp8.c: Likewise.
* gcc.dg/noreorder.c: use noipa attribute instead of noinline.
* gcc.dg/ipa/20040703-wpa.c: New test.
* gcc.dg/ipa/ipa-sra-12.c: New test.
* gcc.dg/ipa/ipa-sra-13.c: Likewise.
* gcc.dg/ipa/ipa-sra-14.c: Likewise.
* gcc.dg/ipa/ipa-sra-15.c: Likewise.
* gcc.dg/ipa/ipa-sra-16.c: Likewise.
* gcc.dg/ipa/ipa-sra-17.c: Likewise.
* gcc.dg/ipa/ipa-sra-18.c: Likewise.
* gcc.dg/ipa/ipa-sra-19.c: Likewise.
* gcc.dg/ipa/ipa-sra-20.c: Likewise.
* gcc.dg/ipa/ipa-sra-21.c: Likewise.
* gcc.dg/ipa/ipa-sra-22.c: Likewise.
* gcc.dg/sso/ipa-sra-1.c: Likewise.
* g++.dg/ipa/ipa-sra-2.C: Likewise.
* g++.dg/ipa/ipa-sra-3.C: Likewise.
* gcc.dg/tree-ssa/ipa-cp-1.c: Make return value used.
* g++.dg/ipa/devirt-19.C: Add missing return, add -fipa-cp-clone
option.
* g++.dg/lto/devirt-19_0.C: Add -fipa-cp-clone option.
* gcc.dg/ipa/ipa-sra-2.c: Removed.
* gcc.dg/ipa/ipa-sra-6.c: Likewise.
From-SVN: r275982
---
gcc/ChangeLog | 98 +
gcc/Makefile.in | 3 +-
gcc/cgraph.c | 127 +-
gcc/cgraph.h | 45 +-
gcc/cgraphclones.c | 213 +-
gcc/coretypes.h | 1 +
gcc/dbgcnt.def | 3 +-
gcc/doc/invoke.texi | 5 +
gcc/ipa-cp.c | 172 +-
gcc/ipa-fnsummary.c | 4 +-
gcc/ipa-inline-transform.c | 3 +-
gcc/ipa-param-manipulation.c | 2093 +++++++++++----
gcc/ipa-param-manipulation.h | 449 +++-
gcc/ipa-prop.c | 103 +-
gcc/ipa-split.c | 32 +-
gcc/ipa-sra.c | 4049 ++++++++++++++++++++++++++++++
gcc/lto-cgraph.c | 121 +-
gcc/lto-section-in.c | 3 +-
gcc/lto-streamer.h | 1 +
gcc/multiple_target.c | 5 +-
gcc/omp-simd-clone.c | 229 +-
gcc/params.def | 7 +
gcc/passes.def | 2 +-
gcc/testsuite/ChangeLog | 40 +
gcc/testsuite/g++.dg/ipa/devirt-19.C | 5 +-
gcc/testsuite/g++.dg/ipa/ipa-sra-1.C | 46 +
gcc/testsuite/g++.dg/ipa/ipa-sra-2.C | 19 +
gcc/testsuite/g++.dg/ipa/ipa-sra-3.C | 9 +
gcc/testsuite/g++.dg/ipa/pr81248.C | 4 +-
gcc/testsuite/g++.dg/lto/devirt-19_0.C | 2 +-
gcc/testsuite/gcc.dg/ipa/20040703-wpa.c | 151 ++
gcc/testsuite/gcc.dg/ipa/ipa-sra-1.c | 4 +-
gcc/testsuite/gcc.dg/ipa/ipa-sra-10.c | 4 +-
gcc/testsuite/gcc.dg/ipa/ipa-sra-11.c | 6 +-
gcc/testsuite/gcc.dg/ipa/ipa-sra-12.c | 50 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-13.c | 49 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-14.c | 60 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-15.c | 61 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-16.c | 74 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-17.c | 102 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-18.c | 49 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-19.c | 31 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-2.c | 51 -
gcc/testsuite/gcc.dg/ipa/ipa-sra-20.c | 38 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-21.c | 33 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-22.c | 56 +
gcc/testsuite/gcc.dg/ipa/ipa-sra-3.c | 7 +-
gcc/testsuite/gcc.dg/ipa/ipa-sra-4.c | 8 +-
gcc/testsuite/gcc.dg/ipa/ipa-sra-5.c | 4 +-
gcc/testsuite/gcc.dg/ipa/ipa-sra-6.c | 33 -
gcc/testsuite/gcc.dg/ipa/ipacost-2.c | 4 +-
gcc/testsuite/gcc.dg/ipa/ipcp-agg-9.c | 2 +-
gcc/testsuite/gcc.dg/ipa/pr78121.c | 2 +-
gcc/testsuite/gcc.dg/ipa/vrp1.c | 4 +-
gcc/testsuite/gcc.dg/ipa/vrp2.c | 4 +-
gcc/testsuite/gcc.dg/ipa/vrp3.c | 2 +-
gcc/testsuite/gcc.dg/ipa/vrp7.c | 2 +-
gcc/testsuite/gcc.dg/ipa/vrp8.c | 2 +-
gcc/testsuite/gcc.dg/noreorder.c | 6 +-
gcc/testsuite/gcc.dg/sso/ipa-sra-1.c | 57 +
gcc/testsuite/gcc.dg/tree-ssa/ipa-cp-1.c | 2 +-
gcc/trans-mem.c | 3 +-
gcc/tree-inline.c | 385 ++-
gcc/tree-inline.h | 10 +
gcc/tree-pass.h | 2 +-
gcc/tree-sra.c | 1859 +-------------
gcc/tree-sra.h | 31 +
67 files changed, 7998 insertions(+), 3143 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 9dfb64643c1..6f34d1a90c4 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,101 @@
+2019-09-20 Martin Jambor <mjambor(a)suse.cz>
+
+ * coretypes.h (cgraph_edge): Declare.
+ * ipa-param-manipulation.c: Rewrite.
+ * ipa-param-manipulation.h: Likewise.
+ * Makefile.in (GTFILES): Added ipa-param-manipulation.h and ipa-sra.c.
+ (OBJS): Added ipa-sra.o.
+ * cgraph.h (ipa_replace_map): Removed fields old_tree, replace_p
+ and ref_p, added fields param_adjustments and performed_splits.
+ (struct cgraph_clone_info): Remove ags_to_skip and
+ combined_args_to_skip, new field param_adjustments.
+ (cgraph_node::create_clone): Changed parameters to use
+ ipa_param_adjustments.
+ (cgraph_node::create_virtual_clone): Likewise.
+ (cgraph_node::create_virtual_clone_with_body): Likewise.
+ (tree_function_versioning): Likewise.
+ (cgraph_build_function_type_skip_args): Removed.
+ * cgraph.c (cgraph_edge::redirect_call_stmt_to_callee): Convert to
+ using ipa_param_adjustments.
+ (clone_of_p): Likewise.
+ * cgraphclones.c (cgraph_build_function_type_skip_args): Removed.
+ (build_function_decl_skip_args): Likewise.
+ (duplicate_thunk_for_node): Adjust parameters using
+ ipa_param_body_adjustments, copy param_adjustments instead of
+ args_to_skip.
+ (cgraph_node::create_clone): Convert to using ipa_param_adjustments.
+ (cgraph_node::create_virtual_clone): Likewise.
+ (cgraph_node::create_version_clone_with_body): Likewise.
+ (cgraph_materialize_clone): Likewise.
+ (symbol_table::materialize_all_clones): Likewise.
+ * ipa-fnsummary.c (ipa_fn_summary_t::duplicate): Simplify
+ ipa_replace_map check.
+ * ipa-cp.c (get_replacement_map): Do not initialize removed fields.
+ (initialize_node_lattices): Make aware that some parameters might have
+ already been removed.
+ (want_remove_some_param_p): New function.
+ (create_specialized_node): Convert to using ipa_param_adjustments and
+ deal with possibly pre-existing adjustments.
+ * lto-cgraph.c (output_cgraph_opt_summary_p): Likewise.
+ (output_node_opt_summary): Do not stream removed fields. Stream
+ parameter adjustments instead of argumetns to skip.
+ (input_node_opt_summary): Likewise.
+ (input_node_opt_summary): Likewise.
+ * lto-section-in.c (lto_section_name): Added ipa-sra section.
+ * lto-streamer.h (lto_section_type): Likewise.
+ * tree-inline.h (copy_body_data): New fields killed_new_ssa_names and
+ param_body_adjs.
+ (copy_decl_to_var): Declare.
+ * tree-inline.c (update_clone_info): Do not remap old_tree.
+ (remap_gimple_stmt): Use ipa_param_body_adjustments to modify gimple
+ statements, walk all extra generated statements and remap their
+ operands.
+ (redirect_all_calls): Add killed SSA names to a hash set.
+ (remap_ssa_name): Do not remap killed SSA names.
+ (copy_arguments_for_versioning): Renames to copy_arguments_nochange,
+ half of functionality moved to ipa_param_body_adjustments.
+ (copy_decl_to_var): Make exported.
+ (copy_body): Destroy killed_new_ssa_names hash set.
+ (expand_call_inline): Remap performed splits.
+ (update_clone_info): Likewise.
+ (tree_function_versioning): Simplify tree_map processing. Updated to
+ accept ipa_param_adjustments and use ipa_param_body_adjustments.
+ * omp-simd-clone.c (simd_clone_vector_of_formal_parm_types): Adjust
+ for the new interface.
+ (simd_clone_clauses_extract): Likewise, make args an auto_vec.
+ (simd_clone_compute_base_data_type): Likewise.
+ (simd_clone_init_simd_arrays): Adjust for the new interface.
+ (simd_clone_adjust_argument_types): Likewise.
+ (struct modify_stmt_info): Likewise.
+ (ipa_simd_modify_stmt_ops): Likewise.
+ (ipa_simd_modify_function_body): Likewise.
+ (simd_clone_adjust): Likewise.
+ * tree-sra.c: Removed IPA-SRA. Include tree-sra.h.
+ (type_internals_preclude_sra_p): Make public.
+ * tree-sra.h: New file.
+ * ipa-inline-transform.c (save_inline_function_body): Update to
+ refelct new tree_function_versioning signature.
+ * ipa-prop.c (adjust_agg_replacement_values): Use a helper from
+ ipa_param_adjustments to get current parameter indices.
+ (ipcp_modif_dom_walker::before_dom_children): Likewise.
+ (ipcp_update_bits): Likewise.
+ (ipcp_update_vr): Likewise.
+ * ipa-split.c (split_function): Convert to using ipa_param_adjustments.
+ * ipa-sra.c: New file.
+ * multiple_target.c (create_target_clone): Update to reflet new type
+ of create_version_clone_with_body.
+ * trans-mem.c (ipa_tm_create_version): Update to reflect new type of
+ tree_function_versioning.
+ (modify_function): Update to reflect new type of
+ tree_function_versioning.
+ * params.def (PARAM_IPA_SRA_MAX_REPLACEMENTS): New.
+ * passes.def: Remove old IPA-SRA and add new one.
+ * tree-pass.h (make_pass_early_ipa_sra): Remove declaration.
+ (make_pass_ipa_sra): Declare.
+ * dbgcnt.def: Remove eipa_sra. Added ipa_sra_params and
+ ipa_sra_retvalues.
+ * doc/invoke.texi (ipa-sra-max-replacements): New.
+
2019-09-19 Martin Sebor <msebor(a)redhat.com>
PR middle-end/91631
diff --git a/gcc/Makefile.in b/gcc/Makefile.in
index 152df9fa9b3..2cf0c79c977 100644
--- a/gcc/Makefile.in
+++ b/gcc/Makefile.in
@@ -1368,6 +1368,7 @@ OBJS = \
init-regs.o \
internal-fn.o \
ipa-cp.o \
+ ipa-sra.o \
ipa-devirt.o \
ipa-fnsummary.o \
ipa-polymorphic-call.o \
@@ -2527,7 +2528,7 @@ GTFILES = $(CPPLIB_H) $(srcdir)/input.h $(srcdir)/coretypes.h \
$(srcdir)/reload.h $(srcdir)/caller-save.c $(srcdir)/symtab.c \
$(srcdir)/alias.c $(srcdir)/bitmap.c $(srcdir)/cselib.c $(srcdir)/cgraph.c \
$(srcdir)/ipa-prop.c $(srcdir)/ipa-cp.c $(srcdir)/ipa-utils.h \
- $(srcdir)/dbxout.c \
+ $(srcdir)/ipa-param-manipulation.h $(srcdir)/ipa-sra.c $(srcdir)/dbxout.c \
$(srcdir)/signop.h \
$(srcdir)/dwarf2out.h \
$(srcdir)/dwarf2asm.c \
diff --git a/gcc/cgraph.c b/gcc/cgraph.c
index 843891e9e56..331b363c175 100644
--- a/gcc/cgraph.c
+++ b/gcc/cgraph.c
@@ -1342,7 +1342,7 @@ cgraph_edge::redirect_call_stmt_to_callee (void)
if (flag_checking && decl)
{
cgraph_node *node = cgraph_node::get (decl);
- gcc_assert (!node || !node->clone.combined_args_to_skip);
+ gcc_assert (!node || !node->clone.param_adjustments);
}
if (symtab->dump_file)
@@ -1350,25 +1350,36 @@ cgraph_edge::redirect_call_stmt_to_callee (void)
fprintf (symtab->dump_file, "updating call of %s -> %s: ",
e->caller->dump_name (), e->callee->dump_name ());
print_gimple_stmt (symtab->dump_file, e->call_stmt, 0, dump_flags);
- if (e->callee->clone.combined_args_to_skip)
+ if (e->callee->clone.param_adjustments)
+ e->callee->clone.param_adjustments->dump (symtab->dump_file);
+ unsigned performed_len
+ = vec_safe_length (e->caller->clone.performed_splits);
+ if (performed_len > 0)
+ fprintf (symtab->dump_file, "Performed splits records:\n");
+ for (unsigned i = 0; i < performed_len; i++)
{
- fprintf (symtab->dump_file, " combined args to skip: ");
- dump_bitmap (symtab->dump_file,
- e->callee->clone.combined_args_to_skip);
+ ipa_param_performed_split *sm
+ = &(*e->caller->clone.performed_splits)[i];
+ print_node_brief (symtab->dump_file, " dummy_decl: ", sm->dummy_decl,
+ TDF_UID);
+ fprintf (symtab->dump_file, ", unit_offset: %u\n", sm->unit_offset);
}
}
- if (e->callee->clone.combined_args_to_skip)
+ if (ipa_param_adjustments *padjs = e->callee->clone.param_adjustments)
{
- int lp_nr;
+ /* We need to defer cleaning EH info on the new statement to
+ fixup-cfg. We may not have dominator information at this point
+ and thus would end up with unreachable blocks and have no way
+ to communicate that we need to run CFG cleanup then. */
+ int lp_nr = lookup_stmt_eh_lp (e->call_stmt);
+ if (lp_nr != 0)
+ remove_stmt_from_eh_lp (e->call_stmt);
- new_stmt = e->call_stmt;
- if (e->callee->clone.combined_args_to_skip)
- new_stmt
- = gimple_call_copy_skip_args (new_stmt,
- e->callee->clone.combined_args_to_skip);
tree old_fntype = gimple_call_fntype (e->call_stmt);
- gimple_call_set_fndecl (new_stmt, e->callee->decl);
+ new_stmt = padjs->modify_call (e->call_stmt,
+ e->caller->clone.performed_splits,
+ e->callee->decl, false);
cgraph_node *origin = e->callee;
while (origin->clone_of)
origin = origin->clone_of;
@@ -1379,92 +1390,12 @@ cgraph_edge::redirect_call_stmt_to_callee (void)
gimple_call_set_fntype (new_stmt, TREE_TYPE (e->callee->decl));
else
{
- bitmap skip = e->callee->clone.combined_args_to_skip;
- tree t = cgraph_build_function_type_skip_args (old_fntype, skip,
- false);
- gimple_call_set_fntype (new_stmt, t);
- }
-
- if (gimple_vdef (new_stmt)
- && TREE_CODE (gimple_vdef (new_stmt)) == SSA_NAME)
- SSA_NAME_DEF_STMT (gimple_vdef (new_stmt)) = new_stmt;
-
- gsi = gsi_for_stmt (e->call_stmt);
-
- /* For optimized away parameters, add on the caller side
- before the call
- DEBUG D#X => parm_Y(D)
- stmts and associate D#X with parm in decl_debug_args_lookup
- vector to say for debug info that if parameter parm had been passed,
- it would have value parm_Y(D). */
- if (e->callee->clone.combined_args_to_skip && MAY_HAVE_DEBUG_BIND_STMTS)
- {
- vec<tree, va_gc> **debug_args
- = decl_debug_args_lookup (e->callee->decl);
- tree old_decl = gimple_call_fndecl (e->call_stmt);
- if (debug_args && old_decl)
- {
- tree parm;
- unsigned i = 0, num;
- unsigned len = vec_safe_length (*debug_args);
- unsigned nargs = gimple_call_num_args (e->call_stmt);
- for (parm = DECL_ARGUMENTS (old_decl), num = 0;
- parm && num < nargs;
- parm = DECL_CHAIN (parm), num++)
- if (bitmap_bit_p (e->callee->clone.combined_args_to_skip, num)
- && is_gimple_reg (parm))
- {
- unsigned last = i;
-
- while (i < len && (**debug_args)[i] != DECL_ORIGIN (parm))
- i += 2;
- if (i >= len)
- {
- i = 0;
- while (i < last
- && (**debug_args)[i] != DECL_ORIGIN (parm))
- i += 2;
- if (i >= last)
- continue;
- }
- tree ddecl = (**debug_args)[i + 1];
- tree arg = gimple_call_arg (e->call_stmt, num);
- if (!useless_type_conversion_p (TREE_TYPE (ddecl),
- TREE_TYPE (arg)))
- {
- tree rhs1;
- if (!fold_convertible_p (TREE_TYPE (ddecl), arg))
- continue;
- if (TREE_CODE (arg) == SSA_NAME
- && gimple_assign_cast_p (SSA_NAME_DEF_STMT (arg))
- && (rhs1
- = gimple_assign_rhs1 (SSA_NAME_DEF_STMT (arg)))
- && useless_type_conversion_p (TREE_TYPE (ddecl),
- TREE_TYPE (rhs1)))
- arg = rhs1;
- else
- arg = fold_convert (TREE_TYPE (ddecl), arg);
- }
-
- gimple *def_temp
- = gimple_build_debug_bind (ddecl, unshare_expr (arg),
- e->call_stmt);
- gsi_insert_before (&gsi, def_temp, GSI_SAME_STMT);
- }
- }
+ tree new_fntype = padjs->build_new_function_type (old_fntype, true);
+ gimple_call_set_fntype (new_stmt, new_fntype);
}
- gsi_replace (&gsi, new_stmt, false);
- /* We need to defer cleaning EH info on the new statement to
- fixup-cfg. We may not have dominator information at this point
- and thus would end up with unreachable blocks and have no way
- to communicate that we need to run CFG cleanup then. */
- lp_nr = lookup_stmt_eh_lp (e->call_stmt);
if (lp_nr != 0)
- {
- remove_stmt_from_eh_lp (e->call_stmt);
- add_stmt_to_eh_lp (new_stmt, lp_nr);
- }
+ add_stmt_to_eh_lp (new_stmt, lp_nr);
}
else
{
@@ -3014,8 +2945,8 @@ clone_of_p (cgraph_node *node, cgraph_node *node2)
return true;
node = node->callees->callee->ultimate_alias_target ();
- if (!node2->clone.args_to_skip
- || !bitmap_bit_p (node2->clone.args_to_skip, 0))
+ if (!node2->clone.param_adjustments
+ || node2->clone.param_adjustments->first_param_intact_p ())
return false;
if (node2->former_clone_of == node->decl)
return true;
diff --git a/gcc/cgraph.h b/gcc/cgraph.h
index 4c54210123a..1da6cab54b0 100644
--- a/gcc/cgraph.h
+++ b/gcc/cgraph.h
@@ -24,6 +24,7 @@ along with GCC; see the file COPYING3. If not see
#include "profile-count.h"
#include "ipa-ref.h"
#include "plugin-api.h"
+#include "ipa-param-manipulation.h"
extern void debuginfo_early_init (void);
extern void debuginfo_init (void);
@@ -740,23 +741,31 @@ struct GTY(()) cgraph_global_info {
will be replaced by another tree while versioning. */
struct GTY(()) ipa_replace_map
{
- /* The tree that will be replaced. */
- tree old_tree;
/* The new (replacing) tree. */
tree new_tree;
/* Parameter number to replace, when old_tree is NULL. */
int parm_num;
- /* True when a substitution should be done, false otherwise. */
- bool replace_p;
- /* True when we replace a reference to old_tree. */
- bool ref_p;
};
struct GTY(()) cgraph_clone_info
{
+ /* Constants discovered by IPA-CP, i.e. which parameter should be replaced
+ with what. */
vec<ipa_replace_map *, va_gc> *tree_map;
- bitmap args_to_skip;
- bitmap combined_args_to_skip;
+ /* Parameter modification that IPA-SRA decided to perform. */
+ ipa_param_adjustments *param_adjustments;
+ /* Lists of dummy-decl and offset pairs representing split formal parameters
+ in the caller. Offsets of all new replacements are enumerated, those
+ coming from the same original parameter have the same dummy decl stored
+ along with them.
+
+ Dummy decls sit in call statement arguments followed by new parameter
+ decls (or their SSA names) in between (caller) clone materialization and
+ call redirection. Redirection then recognizes the dummy variable and
+ together with the stored offsets can reconstruct what exactly the new
+ parameter decls represent and can leave in place only those that the
+ callee expects. */
+ vec<ipa_param_performed_split, va_gc> *performed_splits;
};
enum cgraph_simd_clone_arg_type
@@ -976,15 +985,16 @@ struct GTY((tag ("SYMTAB_FUNCTION"))) cgraph_node : public symtab_node
vec<cgraph_edge *> redirect_callers,
bool call_duplication_hook,
cgraph_node *new_inlined_to,
- bitmap args_to_skip, const char *suffix = NULL);
+ ipa_param_adjustments *param_adjustments,
+ const char *suffix = NULL);
/* Create callgraph node clone with new declaration. The actual body will be
copied later at compilation stage. The name of the new clone will be
constructed from the name of the original node, SUFFIX and NUM_SUFFIX. */
cgraph_node *create_virtual_clone (vec<cgraph_edge *> redirect_callers,
vec<ipa_replace_map *, va_gc> *tree_map,
- bitmap args_to_skip, const char * suffix,
- unsigned num_suffix);
+ ipa_param_adjustments *param_adjustments,
+ const char * suffix, unsigned num_suffix);
/* cgraph node being removed from symbol table; see if its entry can be
replaced by other inline clone. */
@@ -1033,9 +1043,10 @@ struct GTY((tag ("SYMTAB_FUNCTION"))) cgraph_node : public symtab_node
Return the new version's cgraph node. */
cgraph_node *create_version_clone_with_body
(vec<cgraph_edge *> redirect_callers,
- vec<ipa_replace_map *, va_gc> *tree_map, bitmap args_to_skip,
- bool skip_return, bitmap bbs_to_copy, basic_block new_entry_block,
- const char *clone_name, tree target_attributes = NULL_TREE);
+ vec<ipa_replace_map *, va_gc> *tree_map,
+ ipa_param_adjustments *param_adjustments,
+ bitmap bbs_to_copy, basic_block new_entry_block, const char *clone_name,
+ tree target_attributes = NULL_TREE);
/* Insert a new cgraph_function_version_info node into cgraph_fnver_htab
corresponding to cgraph_node. */
@@ -2459,14 +2470,12 @@ tree clone_function_name (tree decl, const char *suffix,
tree clone_function_name (tree decl, const char *suffix);
void tree_function_versioning (tree, tree, vec<ipa_replace_map *, va_gc> *,
- bool, bitmap, bool, bitmap, basic_block);
+ ipa_param_adjustments *,
+ bool, bitmap, basic_block);
void dump_callgraph_transformation (const cgraph_node *original,
const cgraph_node *clone,
const char *suffix);
-tree cgraph_build_function_type_skip_args (tree orig_type, bitmap args_to_skip,
- bool skip_return);
-
/* In cgraphbuild.c */
int compute_call_stmt_bb_frequency (tree, basic_block bb);
void record_references_in_initializer (tree, bool);
diff --git a/gcc/cgraphclones.c b/gcc/cgraphclones.c
index fa753697c78..909407b9a71 100644
--- a/gcc/cgraphclones.c
+++ b/gcc/cgraphclones.c
@@ -142,96 +142,6 @@ cgraph_edge::clone (cgraph_node *n, gcall *call_stmt, unsigned stmt_uid,
return new_edge;
}
-/* Build variant of function type ORIG_TYPE skipping ARGS_TO_SKIP and the
- return value if SKIP_RETURN is true. */
-
-tree
-cgraph_build_function_type_skip_args (tree orig_type, bitmap args_to_skip,
- bool skip_return)
-{
- tree new_type = NULL;
- tree args, new_args = NULL;
- tree new_reversed;
- int i = 0;
-
- for (args = TYPE_ARG_TYPES (orig_type); args && args != void_list_node;
- args = TREE_CHAIN (args), i++)
- if (!args_to_skip || !bitmap_bit_p (args_to_skip, i))
- new_args = tree_cons (NULL_TREE, TREE_VALUE (args), new_args);
-
- new_reversed = nreverse (new_args);
- if (args)
- {
- if (new_reversed)
- TREE_CHAIN (new_args) = void_list_node;
- else
- new_reversed = void_list_node;
- }
-
- /* Use copy_node to preserve as much as possible from original type
- (debug info, attribute lists etc.)
- Exception is METHOD_TYPEs must have THIS argument.
- When we are asked to remove it, we need to build new FUNCTION_TYPE
- instead. */
- if (TREE_CODE (orig_type) != METHOD_TYPE
- || !args_to_skip
- || !bitmap_bit_p (args_to_skip, 0))
- {
- new_type = build_distinct_type_copy (orig_type);
- TYPE_ARG_TYPES (new_type) = new_reversed;
- }
- else
- {
- new_type
- = build_distinct_type_copy (build_function_type (TREE_TYPE (orig_type),
- new_reversed));
- TYPE_CONTEXT (new_type) = TYPE_CONTEXT (orig_type);
- }
-
- if (skip_return)
- TREE_TYPE (new_type) = void_type_node;
-
- return new_type;
-}
-
-/* Build variant of function decl ORIG_DECL skipping ARGS_TO_SKIP and the
- return value if SKIP_RETURN is true.
-
- Arguments from DECL_ARGUMENTS list can't be removed now, since they are
- linked by TREE_CHAIN directly. The caller is responsible for eliminating
- them when they are being duplicated (i.e. copy_arguments_for_versioning). */
-
-static tree
-build_function_decl_skip_args (tree orig_decl, bitmap args_to_skip,
- bool skip_return)
-{
- tree new_decl = copy_node (orig_decl);
- tree new_type;
-
- new_type = TREE_TYPE (orig_decl);
- if (prototype_p (new_type)
- || (skip_return && !VOID_TYPE_P (TREE_TYPE (new_type))))
- new_type
- = cgraph_build_function_type_skip_args (new_type, args_to_skip,
- skip_return);
- TREE_TYPE (new_decl) = new_type;
-
- /* For declarations setting DECL_VINDEX (i.e. methods)
- we expect first argument to be THIS pointer. */
- if (args_to_skip && bitmap_bit_p (args_to_skip, 0))
- DECL_VINDEX (new_decl) = NULL_TREE;
-
- /* When signature changes, we need to clear builtin info. */
- if (fndecl_built_in_p (new_decl)
- && args_to_skip
- && !bitmap_empty_p (args_to_skip))
- set_decl_built_in_function (new_decl, NOT_BUILT_IN, 0);
- /* The FE might have information and assumptions about the other
- arguments. */
- DECL_LANG_SPECIFIC (new_decl) = NULL;
- return new_decl;
-}
-
/* Set flags of NEW_NODE and its decl. NEW_NODE is a newly created private
clone or its thunk. */
@@ -281,35 +191,21 @@ duplicate_thunk_for_node (cgraph_node *thunk, cgraph_node *node)
return cs->caller;
tree new_decl;
- if (!node->clone.args_to_skip)
- new_decl = copy_node (thunk->decl);
- else
+ if (node->clone.param_adjustments)
{
/* We do not need to duplicate this_adjusting thunks if we have removed
this. */
if (thunk->thunk.this_adjusting
- && bitmap_bit_p (node->clone.args_to_skip, 0))
+ && !node->clone.param_adjustments->first_param_intact_p ())
return node;
- new_decl = build_function_decl_skip_args (thunk->decl,
- node->clone.args_to_skip,
- false);
- }
-
- tree *link = &DECL_ARGUMENTS (new_decl);
- int i = 0;
- for (tree pd = DECL_ARGUMENTS (thunk->decl); pd; pd = DECL_CHAIN (pd), i++)
- {
- if (!node->clone.args_to_skip
- || !bitmap_bit_p (node->clone.args_to_skip, i))
- {
- tree nd = copy_node (pd);
- DECL_CONTEXT (nd) = new_decl;
- *link = nd;
- link = &DECL_CHAIN (nd);
- }
+ new_decl = copy_node (thunk->decl);
+ ipa_param_body_adjustments body_adj (node->clone.param_adjustments,
+ new_decl);
+ body_adj.modify_formal_parameters ();
}
- *link = NULL_TREE;
+ else
+ new_decl = copy_node (thunk->decl);
gcc_checking_assert (!DECL_STRUCT_FUNCTION (new_decl));
gcc_checking_assert (!DECL_INITIAL (new_decl));
@@ -331,8 +227,7 @@ duplicate_thunk_for_node (cgraph_node *thunk, cgraph_node *node)
new_thunk->thunk = thunk->thunk;
new_thunk->unique_name = in_lto_p;
new_thunk->former_clone_of = thunk->decl;
- new_thunk->clone.args_to_skip = node->clone.args_to_skip;
- new_thunk->clone.combined_args_to_skip = node->clone.combined_args_to_skip;
+ new_thunk->clone.param_adjustments = node->clone.param_adjustments;
cgraph_edge *e = new_thunk->create_edge (node, NULL, new_thunk->count);
symtab->call_edge_duplication_hooks (thunk->callees, e);
@@ -415,7 +310,11 @@ dump_callgraph_transformation (const cgraph_node *original,
If the new node is being inlined into another one, NEW_INLINED_TO should be
the outline function the new one is (even indirectly) inlined to. All hooks
will see this in node's global.inlined_to, when invoked. Can be NULL if the
- node is not inlined. */
+ node is not inlined.
+
+ If PARAM_ADJUSTMENTS is non-NULL, the parameter manipulation information
+ will be overwritten by the new structure. Otherwise the new node will
+ share parameter manipulation information with the original node. */
cgraph_node *
cgraph_node::create_clone (tree new_decl, profile_count prof_count,
@@ -423,7 +322,8 @@ cgraph_node::create_clone (tree new_decl, profile_count prof_count,
vec<cgraph_edge *> redirect_callers,
bool call_duplication_hook,
cgraph_node *new_inlined_to,
- bitmap args_to_skip, const char *suffix)
+ ipa_param_adjustments *param_adjustments,
+ const char *suffix)
{
cgraph_node *new_node = symtab->create_empty ();
cgraph_edge *e;
@@ -467,19 +367,13 @@ cgraph_node::create_clone (tree new_decl, profile_count prof_count,
new_node->merged_comdat = merged_comdat;
new_node->thunk = thunk;
+ if (param_adjustments)
+ new_node->clone.param_adjustments = param_adjustments;
+ else
+ new_node->clone.param_adjustments = clone.param_adjustments;
new_node->clone.tree_map = NULL;
- new_node->clone.args_to_skip = args_to_skip;
+ new_node->clone.performed_splits = vec_safe_copy (clone.performed_splits);
new_node->split_part = split_part;
- if (!args_to_skip)
- new_node->clone.combined_args_to_skip = clone.combined_args_to_skip;
- else if (clone.combined_args_to_skip)
- {
- new_node->clone.combined_args_to_skip = BITMAP_GGC_ALLOC ();
- bitmap_ior (new_node->clone.combined_args_to_skip,
- clone.combined_args_to_skip, args_to_skip);
- }
- else
- new_node->clone.combined_args_to_skip = args_to_skip;
FOR_EACH_VEC_ELT (redirect_callers, i, e)
{
@@ -621,8 +515,8 @@ clone_function_name (tree decl, const char *suffix)
cgraph_node *
cgraph_node::create_virtual_clone (vec<cgraph_edge *> redirect_callers,
vec<ipa_replace_map *, va_gc> *tree_map,
- bitmap args_to_skip, const char * suffix,
- unsigned num_suffix)
+ ipa_param_adjustments *param_adjustments,
+ const char * suffix, unsigned num_suffix)
{
tree old_decl = decl;
cgraph_node *new_node = NULL;
@@ -632,13 +526,16 @@ cgraph_node::create_virtual_clone (vec<cgraph_edge *> redirect_callers,
char *name;
gcc_checking_assert (local.versionable);
- gcc_assert (local.can_change_signature || !args_to_skip);
+ /* TODO: It would be nice if we could recognize that param_adjustments do not
+ actually perform any changes, but at the moment let's require it simply
+ does not exist. */
+ gcc_assert (local.can_change_signature || !param_adjustments);
/* Make a new FUNCTION_DECL tree node */
- if (!args_to_skip)
+ if (!param_adjustments)
new_decl = copy_node (old_decl);
else
- new_decl = build_function_decl_skip_args (old_decl, args_to_skip, false);
+ new_decl = param_adjustments->adjust_decl (old_decl);
/* These pointers represent function body and will be populated only when clone
is materialized. */
@@ -662,7 +559,8 @@ cgraph_node::create_virtual_clone (vec<cgraph_edge *> redirect_callers,
SET_DECL_RTL (new_decl, NULL);
new_node = create_clone (new_decl, count, false,
- redirect_callers, false, NULL, args_to_skip, suffix);
+ redirect_callers, false, NULL, param_adjustments,
+ suffix);
/* Update the properties.
Make clone visible only within this translation unit. Make sure
@@ -1021,9 +919,10 @@ cgraph_node::create_version_clone (tree new_decl,
cgraph_node *
cgraph_node::create_version_clone_with_body
(vec<cgraph_edge *> redirect_callers,
- vec<ipa_replace_map *, va_gc> *tree_map, bitmap args_to_skip,
- bool skip_return, bitmap bbs_to_copy, basic_block new_entry_block,
- const char *suffix, tree target_attributes)
+ vec<ipa_replace_map *, va_gc> *tree_map,
+ ipa_param_adjustments *param_adjustments,
+ bitmap bbs_to_copy, basic_block new_entry_block, const char *suffix,
+ tree target_attributes)
{
tree old_decl = decl;
cgraph_node *new_version_node = NULL;
@@ -1032,14 +931,16 @@ cgraph_node::create_version_clone_with_body
if (!tree_versionable_function_p (old_decl))
return NULL;
- gcc_assert (local.can_change_signature || !args_to_skip);
+ /* TODO: Restore an assert that we do not change signature if
+ local.can_change_signature is false. We cannot just check that
+ param_adjustments is NULL because unfortunately ipa-split removes return
+ values from such functions. */
/* Make a new FUNCTION_DECL tree node for the new version. */
- if (!args_to_skip && !skip_return)
- new_decl = copy_node (old_decl);
+ if (param_adjustments)
+ new_decl = param_adjustments->adjust_decl (old_decl);
else
- new_decl
- = build_function_decl_skip_args (old_decl, args_to_skip, skip_return);
+ new_decl = copy_node (old_decl);
/* Generate a new name for the new version. */
DECL_NAME (new_decl) = clone_function_name_numbered (old_decl, suffix);
@@ -1076,8 +977,8 @@ cgraph_node::create_version_clone_with_body
new_version_node->ipa_transforms_to_apply
= ipa_transforms_to_apply.copy ();
/* Copy the OLD_VERSION_NODE function tree to the new version. */
- tree_function_versioning (old_decl, new_decl, tree_map, false, args_to_skip,
- skip_return, bbs_to_copy, new_entry_block);
+ tree_function_versioning (old_decl, new_decl, tree_map, param_adjustments,
+ false, bbs_to_copy, new_entry_block);
/* Update the new version's properties.
Make The new version visible only within this translation unit. Make sure
@@ -1117,9 +1018,8 @@ cgraph_materialize_clone (cgraph_node *node)
node->former_clone_of = node->clone_of->former_clone_of;
/* Copy the OLD_VERSION_NODE function tree to the new version. */
tree_function_versioning (node->clone_of->decl, node->decl,
- node->clone.tree_map, true,
- node->clone.args_to_skip, false,
- NULL, NULL);
+ node->clone.tree_map, node->clone.param_adjustments,
+ true, NULL, NULL);
if (symtab->dump_file)
{
dump_function_to_file (node->clone_of->decl, symtab->dump_file,
@@ -1194,28 +1094,15 @@ symbol_table::materialize_all_clones (void)
{
ipa_replace_map *replace_info;
replace_info = (*node->clone.tree_map)[i];
- print_generic_expr (symtab->dump_file,
- replace_info->old_tree);
- fprintf (symtab->dump_file, " -> ");
+ fprintf (symtab->dump_file, "%i -> ",
+ (*node->clone.tree_map)[i]->parm_num);
print_generic_expr (symtab->dump_file,
replace_info->new_tree);
- fprintf (symtab->dump_file, "%s%s;",
- replace_info->replace_p ? "(replace)":"",
- replace_info->ref_p ? "(ref)":"");
}
fprintf (symtab->dump_file, "\n");
}
- if (node->clone.args_to_skip)
- {
- fprintf (symtab->dump_file, " args_to_skip: ");
- dump_bitmap (symtab->dump_file,
- node->clone.args_to_skip);
- }
- if (node->clone.args_to_skip)
- {
- fprintf (symtab->dump_file, " combined_args_to_skip:");
- dump_bitmap (symtab->dump_file, node->clone.combined_args_to_skip);
- }
+ if (node->clone.param_adjustments)
+ node->clone.param_adjustments->dump (symtab->dump_file);
}
cgraph_materialize_clone (node);
stabilized = false;
diff --git a/gcc/coretypes.h b/gcc/coretypes.h
index fc0e09b2000..257de226326 100644
--- a/gcc/coretypes.h
+++ b/gcc/coretypes.h
@@ -141,6 +141,7 @@ struct gomp_teams;
struct symtab_node;
struct cgraph_node;
struct varpool_node;
+struct cgraph_edge;
union section;
typedef union section section;
diff --git a/gcc/dbgcnt.def b/gcc/dbgcnt.def
index ef981aa6967..7c9daafe35d 100644
--- a/gcc/dbgcnt.def
+++ b/gcc/dbgcnt.def
@@ -156,7 +156,6 @@ DEBUG_COUNTER (df_byte_scan)
DEBUG_COUNTER (dse)
DEBUG_COUNTER (dse1)
DEBUG_COUNTER (dse2)
-DEBUG_COUNTER (eipa_sra)
DEBUG_COUNTER (gcse2_delete)
DEBUG_COUNTER (global_alloc_at_func)
DEBUG_COUNTER (global_alloc_at_reg)
@@ -168,6 +167,8 @@ DEBUG_COUNTER (if_after_combine)
DEBUG_COUNTER (if_after_reload)
DEBUG_COUNTER (if_conversion)
DEBUG_COUNTER (if_conversion_tree)
+DEBUG_COUNTER (ipa_sra_params)
+DEBUG_COUNTER (ipa_sra_retvalues)
DEBUG_COUNTER (ira_move)
DEBUG_COUNTER (local_alloc_for_sched)
DEBUG_COUNTER (merged_ipa_icf)
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 6d67c121be0..83016a5a8ee 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -11870,6 +11870,11 @@ parameters only when their cumulative size is less or equal to
@option{ipa-sra-ptr-growth-factor} times the size of the original
pointer parameter.
+@item ipa-sra-max-replacements
+Maximum pieces of an aggregate that IPA-SRA tracks. As a
+consequence, it is also the maximum number of replacements of a formal
+parameter.
+
@item sra-max-scalarization-size-Ospeed
@itemx sra-max-scalarization-size-Osize
The two Scalar Reduction of Aggregates passes (SRA and IPA-SRA) aim to
diff --git a/gcc/ipa-cp.c b/gcc/ipa-cp.c
index 33d52fe5537..b4fb74e097e 100644
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2 - Build # 14 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2
Culprit:
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
</cut>
Results regressed to (for first_bad == 0b92cf305dcf34387a8e2564e55ca8948df3b47a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-0b92cf305dcf34387a8e2564e55ca8948df3b47a/results_id:
1
# 447.dealII,[.] _ZSt18_Rb_tree_incrementPKSt18_Rb_tree_node_ba regressed by 806
from (for last_good == 7552c36afa1f9058bb39f336ae84f019621885a0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-7552c36afa1f9058bb39f336ae84f019621885a0/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/2493
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/2500
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
cd investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 0b92cf305dcf34387a8e2564e55ca8948df3b47a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 7552c36afa1f9058bb39f336ae84f019621885a0
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
---
gcc/ChangeLog | 8 ++++++++
gcc/doc/invoke.texi | 8 ++++++++
gcc/ipa-inline.c | 22 ++++++++++++++--------
gcc/params.def | 6 +++++-
gcc/testsuite/ChangeLog | 9 +++++++++
gcc/testsuite/g++.dg/tree-ssa/pr61034.C | 2 +-
gcc/testsuite/g++.dg/tree-ssa/pr8781.C | 2 +-
gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C | 2 +-
gcc/testsuite/gcc.dg/ipa/pr63416.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c | 2 +-
gcc/testsuite/gcc.dg/vect/pr66142.c | 2 +-
11 files changed, 50 insertions(+), 15 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index bb4de20ab16..b4c4292c299 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * doc/invoke.texi (early-inlining-insns-O2): Document.
+ (early-inlining-insns): Update.
+ * params.def (early-inlining-insns-O2): New bound.
+ (early-inlining-insns): Update docs.
+ * ipa-inline.c (want_early_inline_function_p): Use new bound.
+
2019-10-01 Oleg Endo <olegendo(a)gcc.gnu.org>
PR target/88562
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 83016a5a8ee..4281ee7c614 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -11291,9 +11291,17 @@ recursion depth can be guessed from the probability that function recurses
via a given call expression. This parameter limits inlining only to call
expressions whose probability exceeds the given threshold (in percents).
+@item early-inlining-insns-O2
+Specify growth that the early inliner can make. In effect it increases
+the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O1} or @option{-O2}
+optimization levels.
+
@item early-inlining-insns
Specify growth that the early inliner can make. In effect it increases
the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O3} or @option{-Ofast}
+optimization levels.
@item max-early-inliner-iterations
Limit of iterations of the early inliner. This basically bounds
diff --git a/gcc/ipa-inline.c b/gcc/ipa-inline.c
index b62d280eb25..c8689c7d9a8 100644
--- a/gcc/ipa-inline.c
+++ b/gcc/ipa-inline.c
@@ -641,6 +641,10 @@ want_early_inline_function_p (struct cgraph_edge *e)
{
int growth = estimate_edge_growth (e);
int n;
+ int early_inlining_insns = opt_for_fn (e->caller->decl, optimize) >= 3
+ ? PARAM_VALUE (PARAM_EARLY_INLINING_INSNS)
+ : PARAM_VALUE (PARAM_EARLY_INLINING_INSNS_O2);
+
if (growth <= PARAM_VALUE (PARAM_MAX_INLINE_INSNS_SIZE))
;
@@ -654,26 +658,28 @@ want_early_inline_function_p (struct cgraph_edge *e)
growth);
want_inline = false;
}
- else if (growth > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ else if (growth > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns\n",
- e->caller, callee,
- growth);
+ "growth %i exceeds --param early-inlining-insns%s\n",
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
else if ((n = num_calls (callee)) != 0
- && growth * (n + 1) > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ && growth * (n + 1) > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns "
+ "growth %i exceeds --param early-inlining-insns%s "
"divided by number of calls\n",
- e->caller, callee,
- growth);
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
}
diff --git a/gcc/params.def b/gcc/params.def
index d2d957fc6b1..0acf29b6c4d 100644
--- a/gcc/params.def
+++ b/gcc/params.def
@@ -233,8 +233,12 @@ DEFPARAM(PARAM_IPCP_UNIT_GROWTH,
10, 0, 0)
DEFPARAM(PARAM_EARLY_INLINING_INSNS,
"early-inlining-insns",
- "Maximal estimated growth of function body caused by early inlining of single call.",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O3 and -Ofast.",
14, 0, 0)
+DEFPARAM(PARAM_EARLY_INLINING_INSNS_O2,
+ "early-inlining-insns-O2",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O1 and -O2.",
+ 6, 0, 0)
DEFPARAM(PARAM_LARGE_STACK_FRAME,
"large-stack-frame",
"The size of stack frame to be considered large.",
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index df6105f3d13..0dcaf4b6292 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
+ * g++.dg/tree-ssa/pr8781.C: Likewise.
+ * g++.dg/warn/Wstringop-truncation-1.C: Likewise.
+ * gcc.dg/ipa/pr63416.c: likewise.
+ * gcc.dg/vect/pr66142.c: Likewise.
+ * gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
+
2019-10-01 Jakub Jelinek <jakub(a)redhat.com>
PR c++/91925
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
index 870b2372166..2e3dfecacb4 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
@@ -1,5 +1,5 @@
// { dg-do compile }
-// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks" }
+// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks --param early-inlining-insns-O2=14" }
#define assume(x) if(!(x))__builtin_unreachable()
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
index 1f115b2b26d..5bc1ef03520 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1" } */
+/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1 --param early-inlining-insns-O2=14" } */
int f();
diff --git a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
index 83066019772..49dde0a65ba 100644
--- a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
+++ b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
@@ -1,7 +1,7 @@
/* PR/tree-optimization/84480 - bogus -Wstringop-truncation despite
assignment with an inlined string literal
{ dg-do compile }
- { dg-options "-O2 -Wstringop-truncation" } */
+ { dg-options "-O2 -Wstringop-truncation --param early-inlining-insns-O2=14" } */
#include <string.h>
diff --git a/gcc/testsuite/gcc.dg/ipa/pr63416.c b/gcc/testsuite/gcc.dg/ipa/pr63416.c
index b5374c51fe9..5873954fba3 100644
--- a/gcc/testsuite/gcc.dg/ipa/pr63416.c
+++ b/gcc/testsuite/gcc.dg/ipa/pr63416.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fdump-tree-optimized --param early-inlining-insns-O2=14" } */
#define _UNUSED_ __attribute__((__unused__))
typedef int TEST_F30 (int *v);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
index 67526762f2c..216de23d791 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
@@ -56,7 +56,7 @@ bmp_iter_and_compl (bitmap_iterator * bi, unsigned *bit_no)
}
extern int VEC_int_base_length (VEC_int_base *);
-bitmap
+inline bitmap
compute_idf (bitmap def_blocks, bitmap_head * dfs)
{
bitmap_iterator bi;
diff --git a/gcc/testsuite/gcc.dg/vect/pr66142.c b/gcc/testsuite/gcc.dg/vect/pr66142.c
index 8c79f290767..a0316f1f01e 100644
--- a/gcc/testsuite/gcc.dg/vect/pr66142.c
+++ b/gcc/testsuite/gcc.dg/vect/pr66142.c
@@ -1,6 +1,6 @@
/* PR middle-end/66142 */
/* { dg-do compile } */
-/* { dg-additional-options "-ffast-math -fopenmp-simd" } */
+/* { dg-additional-options "-ffast-math -fopenmp-simd --param early-inlining-insns-O2=14" } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
struct A { float x, y; };
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2 - Build # 13 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2
Culprit:
<cut>
commit 4fc1d2629ab373945a30031c1b49bdfa4e9f5f12
Author: Iain Sandoe <iain(a)sandoe.co.uk>
Date: Thu Sep 26 18:50:55 2019 +0000
[Darwin, PPC, Mode Iterators 2/n] Eliminate picbase expanders.
We can use the mode iterators directly with an @pattern to avoid the
need for an expander that was only there to pass the mode through.
gcc/ChangeLog:
2019-09-26 Iain Sandoe <iain(a)sandoe.co.uk>
* config/rs6000/darwin.md: Replace the expanders for
load_macho_picbase and reload_macho_picbase with use of '@'
in their respective define_insns.
(nonlocal_goto_receiver): Pass Pmode to gen_reload_macho_picbase.
* config/rs6000/rs6000-logue.c (rs6000_emit_prologue): Pass
Pmode to gen_load_macho_picbase.
* config/rs6000/rs6000.md: Likewise.
From-SVN: r276159
</cut>
Results regressed to (for first_bad == 4fc1d2629ab373945a30031c1b49bdfa4e9f5f12)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-4fc1d2629ab373945a30031c1b49bdfa4e9f5f12/results_id:
1
# 453.povray,[.] _ZN3povL23All_Plane_IntersectionsEPNS_13Object regressed by 113
from (for last_good == 0bfc204142439b8167bf3447d7d12b65d1da82f8)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-0bfc204142439b8167bf3447d7d12b65d1da82f8/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/2460
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/2450
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-4fc1d2629ab373945a30031c1b49bdfa4e9f5f12
cd investigate-gcc-4fc1d2629ab373945a30031c1b49bdfa4e9f5f12
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 4fc1d2629ab373945a30031c1b49bdfa4e9f5f12
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 0bfc204142439b8167bf3447d7d12b65d1da82f8
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 4fc1d2629ab373945a30031c1b49bdfa4e9f5f12
Author: Iain Sandoe <iain(a)sandoe.co.uk>
Date: Thu Sep 26 18:50:55 2019 +0000
[Darwin, PPC, Mode Iterators 2/n] Eliminate picbase expanders.
We can use the mode iterators directly with an @pattern to avoid the
need for an expander that was only there to pass the mode through.
gcc/ChangeLog:
2019-09-26 Iain Sandoe <iain(a)sandoe.co.uk>
* config/rs6000/darwin.md: Replace the expanders for
load_macho_picbase and reload_macho_picbase with use of '@'
in their respective define_insns.
(nonlocal_goto_receiver): Pass Pmode to gen_reload_macho_picbase.
* config/rs6000/rs6000-logue.c (rs6000_emit_prologue): Pass
Pmode to gen_load_macho_picbase.
* config/rs6000/rs6000.md: Likewise.
From-SVN: r276159
---
gcc/ChangeLog | 10 ++++++++++
gcc/config/rs6000/darwin.md | 34 +++-------------------------------
gcc/config/rs6000/rs6000-logue.c | 2 +-
gcc/config/rs6000/rs6000.md | 2 +-
4 files changed, 15 insertions(+), 33 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index 1358d4b3542..9bbae7af2e2 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,13 @@
+2019-09-26 Iain Sandoe <iain(a)sandoe.co.uk>
+
+ * config/rs6000/darwin.md: Replace the expanders for
+ load_macho_picbase and reload_macho_picbase with use of '@'
+ and <mode> in their respective define_insns.
+ (nonlocal_goto_receiver): Pass Pmode to gen_reload_macho_picbase.
+ * config/rs6000/rs6000-logue.c (rs6000_emit_prologue): Pass
+ Pmode to gen_load_macho_picbase.
+ * config/rs6000/rs6000.md: Likewise.
+
2019-09-25 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/91896
diff --git a/gcc/config/rs6000/darwin.md b/gcc/config/rs6000/darwin.md
index 4a284211afb..a5c5a3af39e 100644
--- a/gcc/config/rs6000/darwin.md
+++ b/gcc/config/rs6000/darwin.md
@@ -216,21 +216,7 @@ You should have received a copy of the GNU General Public License
(match_dup 2))]
"")
-(define_expand "load_macho_picbase"
- [(set (reg LR_REGNO)
- (unspec [(match_operand 0 "")]
- UNSPEC_LD_MPIC))]
- "(DEFAULT_ABI == ABI_DARWIN) && flag_pic"
-{
- if (TARGET_32BIT)
- emit_insn (gen_load_macho_picbase_si (operands[0]));
- else
- emit_insn (gen_load_macho_picbase_di (operands[0]));
-
- DONE;
-})
-
-(define_insn "load_macho_picbase_<mode>"
+(define_insn "@load_macho_picbase_<mode>"
[(set (reg:P LR_REGNO)
(unspec:P [(match_operand:P 0 "immediate_operand" "s")
(pc)] UNSPEC_LD_MPIC))]
@@ -284,21 +270,7 @@ You should have received a copy of the GNU General Public License
"addis %0,%1,ha16(%2-%3)\n\taddi %0,%0,lo16(%2-%3)"
[(set_attr "length" "8")])
-(define_expand "reload_macho_picbase"
- [(set (reg LR_REGNO)
- (unspec [(match_operand 0 "")]
- UNSPEC_RELD_MPIC))]
- "(DEFAULT_ABI == ABI_DARWIN) && flag_pic"
-{
- if (TARGET_32BIT)
- emit_insn (gen_reload_macho_picbase_si (operands[0]));
- else
- emit_insn (gen_reload_macho_picbase_di (operands[0]));
-
- DONE;
-})
-
-(define_insn "reload_macho_picbase_<mode>"
+(define_insn "@reload_macho_picbase_<mode>"
[(set (reg:P LR_REGNO)
(unspec:P [(match_operand:P 0 "immediate_operand" "s")
(pc)] UNSPEC_RELD_MPIC))]
@@ -342,7 +314,7 @@ You should have received a copy of the GNU General Public License
ASM_GENERATE_INTERNAL_LABEL(tmplab, "Lnlgr", ++n);
tmplrtx = gen_rtx_SYMBOL_REF (Pmode, ggc_strdup (tmplab));
- emit_insn (gen_reload_macho_picbase (tmplrtx));
+ emit_insn (gen_reload_macho_picbase (Pmode, tmplrtx));
emit_move_insn (picreg, gen_rtx_REG (Pmode, LR_REGNO));
emit_insn (gen_macho_correct_pic (picreg, picreg, picrtx, tmplrtx));
}
diff --git a/gcc/config/rs6000/rs6000-logue.c b/gcc/config/rs6000/rs6000-logue.c
index 633a253e439..e98893a440c 100644
--- a/gcc/config/rs6000/rs6000-logue.c
+++ b/gcc/config/rs6000/rs6000-logue.c
@@ -3809,7 +3809,7 @@ rs6000_emit_prologue (void)
if (!info->lr_save_p)
emit_move_insn (gen_rtx_REG (Pmode, 0), lr);
- emit_insn (gen_load_macho_picbase (src));
+ emit_insn (gen_load_macho_picbase (Pmode, src));
emit_move_insn (gen_rtx_REG (Pmode,
RS6000_PIC_OFFSET_TABLE_REGNUM),
diff --git a/gcc/config/rs6000/rs6000.md b/gcc/config/rs6000/rs6000.md
index 4dbf85bbc95..c5443bab9e8 100644
--- a/gcc/config/rs6000/rs6000.md
+++ b/gcc/config/rs6000/rs6000.md
@@ -10053,7 +10053,7 @@
CODE_LABEL_NUMBER (operands[0]));
tmplabrtx = gen_rtx_SYMBOL_REF (Pmode, ggc_strdup (tmplab));
- emit_insn (gen_load_macho_picbase (tmplabrtx));
+ emit_insn (gen_load_macho_picbase (Pmode, tmplabrtx));
emit_move_insn (picreg, gen_rtx_REG (Pmode, LR_REGNO));
emit_insn (gen_macho_correct_pic (picreg, picreg, picrtx, tmplabrtx));
}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gnu/gnu-master-arm-check_gcc - Build # 2 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gnu/gnu-master-arm-check_gcc. So far, this commit has regressed CI configurations:
- tcwg_gnu/gnu-master-arm-check_gcc
Culprit:
<cut>
commit 34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3
Author: Marek Polacek <polacek(a)redhat.com>
Date: Tue Jul 20 16:26:28 2021 -0400
include: Fix -Wundef warnings in ansidecl.h
This quashes -Wundef warnings in ansidecl.h when compiled in C or C++.
In C, __cpp_constexpr and __cplusplus aren't defined so we evaluate
them to 0; conversely, __STDC_VERSION__ is not defined in C++.
This has caused grief when -Wundef is used with -Werror.
I've also tested -traditional-cpp.
include/ChangeLog:
* ansidecl.h: Check if __cplusplus is defined before checking
the value of __cpp_constexpr and __cplusplus. Don't check
__STDC_VERSION__ in C++.
</cut>
Results regressed to (for first_bad == 34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=gcc.c-torture/execute/execute.exp:
1
# Getting actual results from build directory /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/libstdc++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/gfortran.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/libitm.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/libgomp.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/libatomic.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/g++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_0/artifacts/build-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3/sumfiles/gcc.sum
# Manifest: gcc-compare-results/contrib/testsuite-management/flaky/gnu-master-arm-check_gcc.xfail
# Getting actual results from build directory base-artifacts/sumfiles
# base-artifacts/sumfiles/libstdc++.sum
# base-artifacts/sumfiles/gfortran.sum
# base-artifacts/sumfiles/libitm.sum
# base-artifacts/sumfiles/libgomp.sum
# base-artifacts/sumfiles/libatomic.sum
# base-artifacts/sumfiles/g++.sum
# base-artifacts/sumfiles/gcc.sum
#
#
# Unexpected results in this build (new failures)
# === gcc tests ===
#
# Running gcc.c-torture/execute/execute.exp ...
# FAIL: gcc.c-torture/execute/20030117-1.c -Os execution test
# FAIL: gcc.c-torture/execute/20031215-1.c -O1 execution test
#
# === Results Summary ===
from (for last_good == ead235f60139edc6eb408d8d083cbb15e417b447)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=gcc.c-torture/execute/execute.exp:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/artifa…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/artifa…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3
cd investigate-gcc-34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/artifa… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/artifa… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/artifa… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach ead235f60139edc6eb408d8d083cbb15e417b447
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/artifa…
Build log: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-arm-check_gcc/2/consol…
Full commit (up to 1000 lines):
<cut>
commit 34dbb5f346459a1b36cd0cfbfe1cf18cd099fdf3
Author: Marek Polacek <polacek(a)redhat.com>
Date: Tue Jul 20 16:26:28 2021 -0400
include: Fix -Wundef warnings in ansidecl.h
This quashes -Wundef warnings in ansidecl.h when compiled in C or C++.
In C, __cpp_constexpr and __cplusplus aren't defined so we evaluate
them to 0; conversely, __STDC_VERSION__ is not defined in C++.
This has caused grief when -Wundef is used with -Werror.
I've also tested -traditional-cpp.
include/ChangeLog:
* ansidecl.h: Check if __cplusplus is defined before checking
the value of __cpp_constexpr and __cplusplus. Don't check
__STDC_VERSION__ in C++.
---
include/ansidecl.h | 6 +++---
1 file changed, 3 insertions(+), 3 deletions(-)
diff --git a/include/ansidecl.h b/include/ansidecl.h
index 0515228f325..2efe3e85e59 100644
--- a/include/ansidecl.h
+++ b/include/ansidecl.h
@@ -79,7 +79,7 @@ So instead we use the macro below and test it against specific values. */
/* inline requires special treatment; it's in C99, and GCC >=2.7 supports
it too, but it's not in C89. */
#undef inline
-#if __STDC_VERSION__ >= 199901L || defined(__cplusplus) || (defined(__SUNPRO_C) && defined(__C99FEATURES__))
+#if (!defined(__cplusplus) && __STDC_VERSION__ >= 199901L) || defined(__cplusplus) || (defined(__SUNPRO_C) && defined(__C99FEATURES__))
/* it's a keyword */
#else
# if GCC_VERSION >= 2007
@@ -356,7 +356,7 @@ So instead we use the macro below and test it against specific values. */
#define ENUM_BITFIELD(TYPE) unsigned int
#endif
-#if __cpp_constexpr >= 200704
+#if defined(__cplusplus) && __cpp_constexpr >= 200704
#define CONSTEXPR constexpr
#else
#define CONSTEXPR
@@ -419,7 +419,7 @@ So instead we use the macro below and test it against specific values. */
so that most attempts at copy are caught at compile-time. */
-#if __cplusplus >= 201103
+#if defined(__cplusplus) && __cplusplus >= 201103
#define DISABLE_COPY_AND_ASSIGN(TYPE) \
TYPE (const TYPE&) = delete; \
void operator= (const TYPE &) = delete
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_gnu/gnu-master-aarch64-check_gcc - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_gnu/gnu-master-aarch64-check_gcc. So far, this commit has regressed CI configurations:
- tcwg_gnu/gnu-master-aarch64-check_gcc
Culprit:
<cut>
commit 13586172d0b70c9d7ca464fc5a2a46a8532b06d7
Author: Martin Jambor <mjambor(a)suse.cz>
Date: Tue Jul 27 10:02:38 2021 +0200
ipa: Adjust references to identify read-only globals
this patch has been motivated by SPEC 2017's 544.nab_r in which there is
a static variable which is never written to and so zero throughout the
run-time of the benchmark. However, it is passed by reference to a
function in which it is read and (after some multiplications) passed
into __builtin_exp which in turn unnecessarily consumes almost 10% of
the total benchmark run-time. The situation is illustrated by the added
testcase remref-3.c.
The patch adds a flag to ipa-prop descriptor of each parameter to mark
such parameters. IPA-CP and inling then take the effort to remove
IPA_REF_ADDR references in the caller and only add IPA_REF_LOAD
reference to the clone/overall inlined function. This is sufficient
for subsequent symbol table analysis code to identify the read-only
variable as such and optimize the code.
There are two changes from the RFC version posted to the list earlier.
First, three missing calls to get_base_address were added (there was
another one in an assert). Second, references are not stripped off
the callers if the cloned function cannot change the signature. The
second change reveals a real shortcoming stemming from the fact we
cannot adjust function prototypes with fnspecs. But that is a more
general problem.
gcc/ChangeLog:
2021-07-20 Martin Jambor <mjambor(a)suse.cz>
* cgraph.h (ipa_replace_map): New field force_load_ref.
* ipa-prop.h (ipa_param_descriptor): Reduce precision of move_cost,
aded new flag load_dereferenced, adjusted comments.
(ipa_get_param_dereferenced): New function.
(ipa_set_param_dereferenced): Likewise.
* cgraphclones.c (cgraph_node::create_virtual_clone): Follow it.
* ipa-cp.c: Include gimple.h.
(ipcp_discover_new_direct_edges): Take into account dereferenced flag.
(get_replacement_map): New parameter force_load_ref, set the
appropriate flag in ipa_replace_map if set.
(struct symbol_and_index_together): New type.
(adjust_refs_in_act_callers): New function.
(adjust_references_in_caller): Likewise.
(create_specialized_node): When appropriate, call
adjust_references_in_caller and force only load references.
* ipa-prop.c (load_from_dereferenced_name): New function.
(ipa_analyze_controlled_uses): Also detect loads from a
dereference, harden testing of call statements.
(ipa_write_node_info): Stream the dereferenced flag.
(ipa_read_node_info): Likewise.
(ipa_set_jf_constant): Also create refdesc when jump function
references a variable.
(cgraph_node_for_jfunc): Rename to symtab_node_for_jfunc, work
also on references of variables and return a symtab_node. Adjust
all callers.
(propagate_controlled_uses): Also remove references to VAR_DECLs.
gcc/testsuite/ChangeLog:
2021-06-29 Martin Jambor <mjambor(a)suse.cz>
* gcc.dg/ipa/remref-3.c: New test.
* gcc.dg/ipa/remref-4.c: Likewise.
* gcc.dg/ipa/remref-5.c: Likewise.
* gcc.dg/ipa/remref-6.c: Likewise.
</cut>
Results regressed to (for first_bad == 13586172d0b70c9d7ca464fc5a2a46a8532b06d7)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=g++.dg/dg.exp --set runtestflags=g++.dg/vect/vect.exp --set runtestflags=gcc.dg/ipa/ipa.exp:
1
# Getting actual results from build directory /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/libstdc++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/gfortran.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/libitm.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/libgomp.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/libatomic.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/g++.sum
# /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-13586172d0b70c9d7ca464fc5a2a46a8532b06d7/sumfiles/gcc.sum
# Manifest: gcc-compare-results/contrib/testsuite-management/flaky/gnu-master-aarch64-check_gcc.xfail
# Getting actual results from build directory base-artifacts/sumfiles
# base-artifacts/sumfiles/libstdc++.sum
# base-artifacts/sumfiles/gfortran.sum
# base-artifacts/sumfiles/libitm.sum
# base-artifacts/sumfiles/libgomp.sum
# base-artifacts/sumfiles/libatomic.sum
# base-artifacts/sumfiles/g++.sum
# base-artifacts/sumfiles/gcc.sum
#
#
# Unexpected results in this build (new failures)
# === g++ tests ===
#
# Running g++.dg/vect/vect.exp ...
# FAIL: g++.dg/vect/pr99149.cc -std=c++98 scan-tree-dump-times slp2 "stmt.*COMPLEX_MUL" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++98 scan-tree-dump-times slp2 "stmt.*COMPLEX_FMA" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++14 scan-tree-dump-times slp2 "stmt.*COMPLEX_MUL" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++14 scan-tree-dump-times slp2 "stmt.*COMPLEX_FMA" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++17 scan-tree-dump-times slp2 "stmt.*COMPLEX_MUL" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++17 scan-tree-dump-times slp2 "stmt.*COMPLEX_FMA" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++2a scan-tree-dump-times slp2 "stmt.*COMPLEX_MUL" 1
# FAIL: g++.dg/vect/pr99149.cc -std=c++2a scan-tree-dump-times slp2 "stmt.*COMPLEX_FMA" 1
# === gcc tests ===
#
# Running g++.dg/dg.exp ...
# FAIL: g++.dg/pr77550.C (test for excess errors)
# UNRESOLVED: g++.dg/pr77550.C compilation failed to produce executable
#
# Running gcc.dg/ipa/ipa.exp ...
# UNRESOLVED: gcc.dg/ipa/remref-6.c scan-ipa-dump inline "Removed a reference"
# UNRESOLVED: gcc.dg/ipa/remref-6.c scan-ipa-dump inline "replaced it with LOAD"
#
# === Results Summary ===
from (for last_good == a21bd3cebd6f54af70a37c18b8fbeae933fb6515)
# reset_artifacts:
-10
# build_abe binutils:
-2
# build_abe gcc:
-1
# build_abe dejagnu:
0
# build_abe check_gcc -- --set runtestflags=g++.dg/dg.exp --set runtestflags=g++.dg/vect/vect.exp --set runtestflags=gcc.dg/ipa/ipa.exp:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/ar…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/ar…
Build top page/logs: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-13586172d0b70c9d7ca464fc5a2a46a8532b06d7
cd investigate-gcc-13586172d0b70c9d7ca464fc5a2a46a8532b06d7
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/ar… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/ar… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/ar… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 13586172d0b70c9d7ca464fc5a2a46a8532b06d7
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach a21bd3cebd6f54af70a37c18b8fbeae933fb6515
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/ar…
Build log: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_gcc/1/co…
Full commit (up to 1000 lines):
<cut>
commit 13586172d0b70c9d7ca464fc5a2a46a8532b06d7
Author: Martin Jambor <mjambor(a)suse.cz>
Date: Tue Jul 27 10:02:38 2021 +0200
ipa: Adjust references to identify read-only globals
this patch has been motivated by SPEC 2017's 544.nab_r in which there is
a static variable which is never written to and so zero throughout the
run-time of the benchmark. However, it is passed by reference to a
function in which it is read and (after some multiplications) passed
into __builtin_exp which in turn unnecessarily consumes almost 10% of
the total benchmark run-time. The situation is illustrated by the added
testcase remref-3.c.
The patch adds a flag to ipa-prop descriptor of each parameter to mark
such parameters. IPA-CP and inling then take the effort to remove
IPA_REF_ADDR references in the caller and only add IPA_REF_LOAD
reference to the clone/overall inlined function. This is sufficient
for subsequent symbol table analysis code to identify the read-only
variable as such and optimize the code.
There are two changes from the RFC version posted to the list earlier.
First, three missing calls to get_base_address were added (there was
another one in an assert). Second, references are not stripped off
the callers if the cloned function cannot change the signature. The
second change reveals a real shortcoming stemming from the fact we
cannot adjust function prototypes with fnspecs. But that is a more
general problem.
gcc/ChangeLog:
2021-07-20 Martin Jambor <mjambor(a)suse.cz>
* cgraph.h (ipa_replace_map): New field force_load_ref.
* ipa-prop.h (ipa_param_descriptor): Reduce precision of move_cost,
aded new flag load_dereferenced, adjusted comments.
(ipa_get_param_dereferenced): New function.
(ipa_set_param_dereferenced): Likewise.
* cgraphclones.c (cgraph_node::create_virtual_clone): Follow it.
* ipa-cp.c: Include gimple.h.
(ipcp_discover_new_direct_edges): Take into account dereferenced flag.
(get_replacement_map): New parameter force_load_ref, set the
appropriate flag in ipa_replace_map if set.
(struct symbol_and_index_together): New type.
(adjust_refs_in_act_callers): New function.
(adjust_references_in_caller): Likewise.
(create_specialized_node): When appropriate, call
adjust_references_in_caller and force only load references.
* ipa-prop.c (load_from_dereferenced_name): New function.
(ipa_analyze_controlled_uses): Also detect loads from a
dereference, harden testing of call statements.
(ipa_write_node_info): Stream the dereferenced flag.
(ipa_read_node_info): Likewise.
(ipa_set_jf_constant): Also create refdesc when jump function
references a variable.
(cgraph_node_for_jfunc): Rename to symtab_node_for_jfunc, work
also on references of variables and return a symtab_node. Adjust
all callers.
(propagate_controlled_uses): Also remove references to VAR_DECLs.
gcc/testsuite/ChangeLog:
2021-06-29 Martin Jambor <mjambor(a)suse.cz>
* gcc.dg/ipa/remref-3.c: New test.
* gcc.dg/ipa/remref-4.c: Likewise.
* gcc.dg/ipa/remref-5.c: Likewise.
* gcc.dg/ipa/remref-6.c: Likewise.
---
gcc/cgraph.h | 4 +
gcc/cgraphclones.c | 10 ++-
gcc/ipa-cp.c | 156 ++++++++++++++++++++++++++++++---
gcc/ipa-prop.c | 166 ++++++++++++++++++++++++++++--------
gcc/ipa-prop.h | 29 ++++++-
gcc/testsuite/gcc.dg/ipa/remref-3.c | 23 +++++
gcc/testsuite/gcc.dg/ipa/remref-4.c | 31 +++++++
gcc/testsuite/gcc.dg/ipa/remref-5.c | 38 +++++++++
gcc/testsuite/gcc.dg/ipa/remref-6.c | 24 ++++++
9 files changed, 431 insertions(+), 50 deletions(-)
diff --git a/gcc/cgraph.h b/gcc/cgraph.h
index 8c776d6f3a8..d54a258c2ee 100644
--- a/gcc/cgraph.h
+++ b/gcc/cgraph.h
@@ -700,6 +700,10 @@ struct GTY(()) ipa_replace_map
tree new_tree;
/* Parameter number to replace, when old_tree is NULL. */
int parm_num;
+ /* Set if the newly added reference should not be an address one, but a load
+ one from the operand of the ADDR_EXPR in NEW_TREE. This is for cases when
+ the corresponding parameter p is used only as *p. */
+ unsigned force_load_ref : 1;
};
enum cgraph_simd_clone_arg_type
diff --git a/gcc/cgraphclones.c b/gcc/cgraphclones.c
index fef4a231f85..b16e68194e1 100644
--- a/gcc/cgraphclones.c
+++ b/gcc/cgraphclones.c
@@ -633,7 +633,15 @@ cgraph_node::create_virtual_clone (const vec<cgraph_edge *> &redirect_callers,
|| in_lto_p)
new_node->unique_name = true;
FOR_EACH_VEC_SAFE_ELT (tree_map, i, map)
- new_node->maybe_create_reference (map->new_tree, NULL);
+ {
+ tree repl = map->new_tree;
+ if (map->force_load_ref)
+ {
+ gcc_assert (TREE_CODE (repl) == ADDR_EXPR);
+ repl = get_base_address (TREE_OPERAND (repl, 0));
+ }
+ new_node->maybe_create_reference (repl, NULL);
+ }
if (ipa_transforms_to_apply.exists ())
new_node->ipa_transforms_to_apply
diff --git a/gcc/ipa-cp.c b/gcc/ipa-cp.c
index ce28ada19fe..55b9216337f 100644
--- a/gcc/ipa-cp.c
+++ b/gcc/ipa-cp.c
@@ -106,6 +106,7 @@ along with GCC; see the file COPYING3. If not see
#include "backend.h"
#include "tree.h"
#include "gimple-expr.h"
+#include "gimple.h"
#include "predict.h"
#include "alloc-pool.h"
#include "tree-pass.h"
@@ -4008,7 +4009,8 @@ ipcp_discover_new_direct_edges (struct cgraph_node *node,
{
ipa_node_params *info = ipa_node_params_sum->get (node);
int c = ipa_get_controlled_uses (info, param_index);
- if (c != IPA_UNDESCRIBED_USE)
+ if (c != IPA_UNDESCRIBED_USE
+ && !ipa_get_param_load_dereferenced (info, param_index))
{
struct ipa_ref *to_del;
@@ -4317,10 +4319,14 @@ gather_edges_for_value (ipcp_value<valtype> *val, cgraph_node *dest,
}
/* Construct a replacement map for a know VALUE for a formal parameter PARAM.
- Return it or NULL if for some reason it cannot be created. */
+ Return it or NULL if for some reason it cannot be created. FORCE_LOAD_REF
+ should be set to true when the reference created for the constant should be
+ a load one and not an address one because the corresponding parameter p is
+ only used as *p. */
static struct ipa_replace_map *
-get_replacement_map (class ipa_node_params *info, tree value, int parm_num)
+get_replacement_map (class ipa_node_params *info, tree value, int parm_num,
+ bool force_load_ref)
{
struct ipa_replace_map *replace_map;
@@ -4332,10 +4338,15 @@ get_replacement_map (class ipa_node_params *info, tree value, int parm_num)
fprintf (dump_file, " with const ");
print_generic_expr (dump_file, value);
- fprintf (dump_file, "\n");
+
+ if (force_load_ref)
+ fprintf (dump_file, " - forcing load reference\n");
+ else
+ fprintf (dump_file, "\n");
}
replace_map->parm_num = parm_num;
replace_map->new_tree = value;
+ replace_map->force_load_ref = force_load_ref;
return replace_map;
}
@@ -4488,6 +4499,113 @@ update_specialized_profile (struct cgraph_node *new_node,
dump_profile_updates (orig_node, new_node);
}
+static void adjust_references_in_caller (cgraph_edge *cs,
+ symtab_node *symbol, int index);
+
+/* Simple structure to pass a symbol and index (with same meaning as parameters
+ of adjust_references_in_caller) through a void* parameter of a
+ call_for_symbol_thunks_and_aliases callback. */
+struct symbol_and_index_together
+{
+ symtab_node *symbol;
+ int index;
+};
+
+/* Worker callback of call_for_symbol_thunks_and_aliases to recursively call
+ adjust_references_in_caller on edges up in the call-graph, if necessary. */
+static bool
+adjust_refs_in_act_callers (struct cgraph_node *node, void *data)
+{
+ symbol_and_index_together *pack = (symbol_and_index_together *) data;
+ for (cgraph_edge *cs = node->callers; cs; cs = cs->next_caller)
+ if (!cs->caller->thunk)
+ adjust_references_in_caller (cs, pack->symbol, pack->index);
+ return false;
+}
+
+/* At INDEX of a function being called by CS there is an ADDR_EXPR of a
+ variable which is only dereferenced and which is represented by SYMBOL. See
+ if we can remove ADDR reference in callers assosiated witht the call. */
+
+static void
+adjust_references_in_caller (cgraph_edge *cs, symtab_node *symbol, int index)
+{
+ ipa_edge_args *args = ipa_edge_args_sum->get (cs);
+ ipa_jump_func *jfunc = ipa_get_ith_jump_func (args, index);
+ if (jfunc->type == IPA_JF_CONST)
+ {
+ ipa_ref *to_del = cs->caller->find_reference (symbol, cs->call_stmt,
+ cs->lto_stmt_uid);
+ if (!to_del)
+ return;
+ to_del->remove_reference ();
+ if (dump_file)
+ fprintf (dump_file, " Removed a reference from %s to %s.\n",
+ cs->caller->dump_name (), symbol->dump_name ());
+ return;
+ }
+
+ if (jfunc->type != IPA_JF_PASS_THROUGH
+ || ipa_get_jf_pass_through_operation (jfunc) != NOP_EXPR)
+ return;
+
+ int fidx = ipa_get_jf_pass_through_formal_id (jfunc);
+ cgraph_node *caller = cs->caller;
+ ipa_node_params *caller_info = ipa_node_params_sum->get (caller);
+ /* TODO: This consistency check may be too big and not really
+ that useful. Consider removing it. */
+ tree cst;
+ if (caller_info->ipcp_orig_node)
+ cst = caller_info->known_csts[fidx];
+ else
+ {
+ ipcp_lattice<tree> *lat = ipa_get_scalar_lat (caller_info, fidx);
+ gcc_assert (lat->is_single_const ());
+ cst = lat->values->value;
+ }
+ gcc_assert (TREE_CODE (cst) == ADDR_EXPR
+ && (symtab_node::get (get_base_address (TREE_OPERAND (cst, 0)))
+ == symbol));
+
+ int cuses = ipa_get_controlled_uses (caller_info, fidx);
+ if (cuses == IPA_UNDESCRIBED_USE)
+ return;
+ gcc_assert (cuses > 0);
+ cuses--;
+ ipa_set_controlled_uses (caller_info, fidx, cuses);
+ if (cuses)
+ return;
+
+ if (caller_info->ipcp_orig_node)
+ {
+ /* Cloning machinery has created a reference here, we need to either
+ remove it or change it to a read one. */
+ ipa_ref *to_del = caller->find_reference (symbol, NULL, 0);
+ if (to_del && to_del->use == IPA_REF_ADDR)
+ {
+ to_del->remove_reference ();
+ if (dump_file)
+ fprintf (dump_file, " Removed a reference from %s to %s.\n",
+ cs->caller->dump_name (), symbol->dump_name ());
+ if (ipa_get_param_load_dereferenced (caller_info, fidx))
+ {
+ caller->create_reference (symbol, IPA_REF_LOAD, NULL);
+ if (dump_file)
+ fprintf (dump_file,
+ " ...and replaced it with LOAD one.\n");
+ }
+ }
+ }
+
+ symbol_and_index_together pack;
+ pack.symbol = symbol;
+ pack.index = fidx;
+ if (caller->can_change_signature)
+ caller->call_for_symbol_thunks_and_aliases (adjust_refs_in_act_callers,
+ &pack, true);
+}
+
+
/* Return true if we would like to remove a parameter from NODE when cloning it
with KNOWN_CSTS scalar constants. */
@@ -4595,15 +4713,31 @@ create_specialized_node (struct cgraph_node *node,
for (i = 0; i < count; i++)
{
tree t = known_csts[i];
- if (t)
- {
- struct ipa_replace_map *replace_map;
+ if (!t)
+ continue;
- gcc_checking_assert (TREE_CODE (t) != TREE_BINFO);
- replace_map = get_replacement_map (info, t, i);
- if (replace_map)
- vec_safe_push (replace_trees, replace_map);
+ gcc_checking_assert (TREE_CODE (t) != TREE_BINFO);
+
+ bool load_ref = false;
+ symtab_node *ref_symbol;
+ if (TREE_CODE (t) == ADDR_EXPR)
+ {
+ tree base = get_base_address (TREE_OPERAND (t, 0));
+ if (TREE_CODE (base) == VAR_DECL
+ && ipa_get_controlled_uses (info, i) == 0
+ && ipa_get_param_load_dereferenced (info, i)
+ && (ref_symbol = symtab_node::get (base)))
+ {
+ load_ref = true;
+ if (node->can_change_signature)
+ for (cgraph_edge *caller : callers)
+ adjust_references_in_caller (caller, ref_symbol, i);
+ }
}
+
+ ipa_replace_map *replace_map = get_replacement_map (info, t, i, load_ref);
+ if (replace_map)
+ vec_safe_push (replace_trees, replace_map);
}
auto_vec<cgraph_edge *, 2> self_recursive_calls;
for (i = callers.length () - 1; i >= 0; i--)
diff --git a/gcc/ipa-prop.c b/gcc/ipa-prop.c
index 43f46a578c6..0afd05eb95c 100644
--- a/gcc/ipa-prop.c
+++ b/gcc/ipa-prop.c
@@ -544,7 +544,9 @@ ipa_set_jf_constant (struct ipa_jump_func *jfunc, tree constant,
jfunc->value.constant.value = unshare_expr_without_location (constant);
if (TREE_CODE (constant) == ADDR_EXPR
- && TREE_CODE (TREE_OPERAND (constant, 0)) == FUNCTION_DECL)
+ && (TREE_CODE (TREE_OPERAND (constant, 0)) == FUNCTION_DECL
+ || (TREE_CODE (TREE_OPERAND (constant, 0)) == VAR_DECL
+ && TREE_STATIC (TREE_OPERAND (constant, 0)))))
{
struct ipa_cst_ref_desc *rdesc;
@@ -2876,6 +2878,16 @@ ipa_analyze_params_uses_in_bb (struct ipa_func_body_info *fbi, basic_block bb)
visit_ref_for_mod_analysis);
}
+/* Return true EXPR is a load from a dereference of SSA_NAME NAME. */
+
+static bool
+load_from_dereferenced_name (tree expr, tree name)
+{
+ tree base = get_base_address (expr);
+ return (TREE_CODE (base) == MEM_REF
+ && TREE_OPERAND (base, 0) == name);
+}
+
/* Calculate controlled uses of parameters of NODE. */
static void
@@ -2886,7 +2898,8 @@ ipa_analyze_controlled_uses (struct cgraph_node *node)
for (int i = 0; i < ipa_get_param_count (info); i++)
{
tree parm = ipa_get_param (info, i);
- int controlled_uses = 0;
+ int call_uses = 0;
+ bool load_dereferenced = false;
/* For SSA regs see if parameter is used. For non-SSA we compute
the flag during modification analysis. */
@@ -2897,27 +2910,77 @@ ipa_analyze_controlled_uses (struct cgraph_node *node)
if (ddef && !has_zero_uses (ddef))
{
imm_use_iterator imm_iter;
- use_operand_p use_p;
+ gimple *stmt;
ipa_set_param_used (info, i, true);
- FOR_EACH_IMM_USE_FAST (use_p, imm_iter, ddef)
- if (!is_gimple_call (USE_STMT (use_p)))
- {
- if (!is_gimple_debug (USE_STMT (use_p)))
- {
- controlled_uses = IPA_UNDESCRIBED_USE;
- break;
- }
- }
- else
- controlled_uses++;
+ FOR_EACH_IMM_USE_STMT (stmt, imm_iter, ddef)
+ {
+ if (is_gimple_debug (stmt))
+ continue;
+
+ int all_stmt_uses = 0;
+ use_operand_p use_p;
+ FOR_EACH_IMM_USE_ON_STMT (use_p, imm_iter)
+ all_stmt_uses++;
+
+ if (is_gimple_call (stmt))
+ {
+ if (gimple_call_internal_p (stmt))
+ {
+ call_uses = IPA_UNDESCRIBED_USE;
+ break;
+ }
+ int recognized_stmt_uses;
+ if (gimple_call_fn (stmt) == ddef)
+ recognized_stmt_uses = 1;
+ else
+ recognized_stmt_uses = 0;
+ unsigned arg_count = gimple_call_num_args (stmt);
+ for (unsigned i = 0; i < arg_count; i++)
+ {
+ tree arg = gimple_call_arg (stmt, i);
+ if (arg == ddef)
+ recognized_stmt_uses++;
+ else if (load_from_dereferenced_name (arg, ddef))
+ {
+ load_dereferenced = true;
+ recognized_stmt_uses++;
+ }
+ }
+
+ if (recognized_stmt_uses != all_stmt_uses)
+ {
+ call_uses = IPA_UNDESCRIBED_USE;
+ break;
+ }
+ if (call_uses >= 0)
+ call_uses += all_stmt_uses;
+ }
+ else if (gimple_assign_single_p (stmt))
+ {
+ tree rhs = gimple_assign_rhs1 (stmt);
+ if (all_stmt_uses != 1
+ || !load_from_dereferenced_name (rhs, ddef))
+ {
+ call_uses = IPA_UNDESCRIBED_USE;
+ break;
+ }
+ load_dereferenced = true;
+ }
+ else
+ {
+ call_uses = IPA_UNDESCRIBED_USE;
+ break;
+ }
+ }
}
else
- controlled_uses = 0;
+ call_uses = 0;
}
else
- controlled_uses = IPA_UNDESCRIBED_USE;
- ipa_set_controlled_uses (info, i, controlled_uses);
+ call_uses = IPA_UNDESCRIBED_USE;
+ ipa_set_controlled_uses (info, i, call_uses);
+ ipa_set_param_load_dereferenced (info, i, load_dereferenced);
}
}
@@ -3640,16 +3703,17 @@ jfunc_rdesc_usable (struct ipa_jump_func *jfunc)
declaration, return the associated call graph node. Otherwise return
NULL. */
-static cgraph_node *
-cgraph_node_for_jfunc (struct ipa_jump_func *jfunc)
+static symtab_node *
+symtab_node_for_jfunc (struct ipa_jump_func *jfunc)
{
gcc_checking_assert (jfunc->type == IPA_JF_CONST);
tree cst = ipa_get_jf_constant (jfunc);
if (TREE_CODE (cst) != ADDR_EXPR
- || TREE_CODE (TREE_OPERAND (cst, 0)) != FUNCTION_DECL)
+ || (TREE_CODE (TREE_OPERAND (cst, 0)) != FUNCTION_DECL
+ && TREE_CODE (TREE_OPERAND (cst, 0)) != VAR_DECL))
return NULL;
- return cgraph_node::get (TREE_OPERAND (cst, 0));
+ return symtab_node::get (TREE_OPERAND (cst, 0));
}
@@ -3666,7 +3730,7 @@ try_decrement_rdesc_refcount (struct ipa_jump_func *jfunc)
&& (rdesc = jfunc_rdesc_usable (jfunc))
&& --rdesc->refcount == 0)
{
- symtab_node *symbol = cgraph_node_for_jfunc (jfunc);
+ symtab_node *symbol = symtab_node_for_jfunc (jfunc);
if (!symbol)
return false;
@@ -3721,8 +3785,8 @@ try_make_edge_direct_simple_call (struct cgraph_edge *ie,
gcc_checking_assert (cs->callee
&& (cs != ie
|| jfunc->type != IPA_JF_CONST
- || !cgraph_node_for_jfunc (jfunc)
- || cs->callee == cgraph_node_for_jfunc (jfunc)));
+ || !symtab_node_for_jfunc (jfunc)
+ || cs->callee == symtab_node_for_jfunc (jfunc)));
ok = try_decrement_rdesc_refcount (jfunc);
gcc_checking_assert (ok);
}
@@ -4085,7 +4149,15 @@ propagate_controlled_uses (struct cgraph_edge *cs)
== NOP_EXPR || c == IPA_UNDESCRIBED_USE);
c = combine_controlled_uses_counters (c, d);
ipa_set_controlled_uses (new_root_info, src_idx, c);
- if (c == 0 && new_root_info->ipcp_orig_node)
+ bool lderef = true;
+ if (c != IPA_UNDESCRIBED_USE)
+ {
+ lderef = (ipa_get_param_load_dereferenced (new_root_info, src_idx)
+ || ipa_get_param_load_dereferenced (old_root_info, i));
+ ipa_set_param_load_dereferenced (new_root_info, src_idx, lderef);
+ }
+
+ if (c == 0 && !lderef && new_root_info->ipcp_orig_node)
{
struct cgraph_node *n;
struct ipa_ref *ref;
@@ -4114,17 +4186,27 @@ propagate_controlled_uses (struct cgraph_edge *cs)
if (rdesc->refcount == 0)
{
tree cst = ipa_get_jf_constant (jf);
- struct cgraph_node *n;
gcc_checking_assert (TREE_CODE (cst) == ADDR_EXPR
- && TREE_CODE (TREE_OPERAND (cst, 0))
- == FUNCTION_DECL);
- n = cgraph_node::get (TREE_OPERAND (cst, 0));
+ && ((TREE_CODE (TREE_OPERAND (cst, 0))
+ == FUNCTION_DECL)
+ || (TREE_CODE (TREE_OPERAND (cst, 0))
+ == VAR_DECL)));
+
+ symtab_node *n = symtab_node::get (TREE_OPERAND (cst, 0));
if (n)
{
struct cgraph_node *clone;
- bool ok;
- ok = remove_described_reference (n, rdesc);
- gcc_checking_assert (ok);
+ bool removed = remove_described_reference (n, rdesc);
+ /* The reference might have been removed by IPA-CP. */
+ if (removed
+ && ipa_get_param_load_dereferenced (old_root_info, i))
+ {
+ new_root->create_reference (n, IPA_REF_LOAD, NULL);
+ if (dump_file)
+ fprintf (dump_file, "ipa-prop: ...replaced it with "
+ " LOAD one from %s to %s.\n",
+ new_root->dump_name (), n->dump_name ());
+ }
clone = cs->caller;
while (clone->inlined_to
@@ -4347,7 +4429,7 @@ ipa_edge_args_sum_t::duplicate (cgraph_edge *src, cgraph_edge *dst,
else if (src->caller == dst->caller)
{
struct ipa_ref *ref;
- symtab_node *n = cgraph_node_for_jfunc (src_jf);
+ symtab_node *n = symtab_node_for_jfunc (src_jf);
gcc_checking_assert (n);
ref = src->caller->find_reference (n, src->call_stmt,
src->lto_stmt_uid);
@@ -4574,7 +4656,9 @@ ipa_print_node_params (FILE *f, struct cgraph_node *node)
if (c == IPA_UNDESCRIBED_USE)
fprintf (f, " undescribed_use");
else
- fprintf (f, " controlled_uses=%i", c);
+ fprintf (f, " controlled_uses=%i %s", c,
+ ipa_get_param_load_dereferenced (info, i)
+ ? "(load_dereferenced)" : "");
fprintf (f, "\n");
}
}
@@ -4969,7 +5053,13 @@ ipa_write_node_info (struct output_block *ob, struct cgraph_node *node)
gcc_assert (!info->node_enqueued);
gcc_assert (!info->ipcp_orig_node);
for (j = 0; j < ipa_get_param_count (info); j++)
- bp_pack_value (&bp, ipa_is_param_used (info, j), 1);
+ {
+ /* TODO: We could just not stream the bit in the undescribed case. */
+ bool d = (ipa_get_controlled_uses (info, j) != IPA_UNDESCRIBED_USE)
+ ? ipa_get_param_load_dereferenced (info, j) : true;
+ bp_pack_value (&bp, d, 1);
+ bp_pack_value (&bp, ipa_is_param_used (info, j), 1);
+ }
streamer_write_bitpack (&bp);
for (j = 0; j < ipa_get_param_count (info); j++)
{
@@ -5095,10 +5185,14 @@ ipa_read_node_info (class lto_input_block *ib, struct cgraph_node *node,
bp = streamer_read_bitpack (ib);
for (k = 0; k < param_count; k++)
{
+ bool load_dereferenced = bp_unpack_value (&bp, 1);
bool used = bp_unpack_value (&bp, 1);
if (prevails)
- ipa_set_param_used (info, k, used);
+ {
+ ipa_set_param_load_dereferenced (info, k, load_dereferenced);
+ ipa_set_param_used (info, k, used);
+ }
}
for (k = 0; k < param_count; k++)
{
diff --git a/gcc/ipa-prop.h b/gcc/ipa-prop.h
index 2fe220acf84..19751f10974 100644
--- a/gcc/ipa-prop.h
+++ b/gcc/ipa-prop.h
@@ -550,14 +550,21 @@ struct GTY(()) ipa_param_descriptor
tree decl_or_type;
/* If all uses of the parameter are described by ipa-prop structures, this
says how many there are. If any use could not be described by means of
- ipa-prop structures, this is IPA_UNDESCRIBED_USE. */
+ ipa-prop structures (which include flag dereferenced below), this is
+ IPA_UNDESCRIBED_USE. */
int controlled_uses;
- unsigned int move_cost : 28;
+ unsigned int move_cost : 27;
/* The parameter is used. */
unsigned used : 1;
unsigned used_by_ipa_predicates : 1;
unsigned used_by_indirect_call : 1;
unsigned used_by_polymorphic_call : 1;
+ /* Set to true when in addition to being used in call statements, the
+ parameter has also been used for loads (but not for writes, does not
+ escape, etc.). This allows us to identify parameters p which are only
+ used as *p, and so when we propagate a constant to them, we can generate a
+ LOAD and not ADDR reference to them. */
+ unsigned load_dereferenced : 1;
};
/* ipa_node_params stores information related to formal parameters of functions
@@ -795,6 +802,24 @@ ipa_set_controlled_uses (class ipa_node_params *info, int i, int val)
(*info->descriptors)[i].controlled_uses = val;
}
+/* Assuming a parameter does not have IPA_UNDESCRIBED_USE controlled uses,
+ return flag which indicates it has been dereferenced but only in a load. */
+static inline int
+ipa_get_param_load_dereferenced (class ipa_node_params *info, int i)
+{
+ gcc_assert (ipa_get_controlled_uses (info, i) != IPA_UNDESCRIBED_USE);
+ return (*info->descriptors)[i].load_dereferenced;
+}
+
+/* Set the load_dereferenced flag of a given parameter. */
+
+static inline void
+ipa_set_param_load_dereferenced (class ipa_node_params *info, int i, bool val)
+{
+ gcc_checking_assert (info->descriptors);
+ (*info->descriptors)[i].load_dereferenced = val;
+}
+
/* Return the used flag corresponding to the Ith formal parameter of the
function associated with INFO. */
diff --git a/gcc/testsuite/gcc.dg/ipa/remref-3.c b/gcc/testsuite/gcc.dg/ipa/remref-3.c
new file mode 100644
index 00000000000..8a82ca65c68
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ipa/remref-3.c
@@ -0,0 +1,23 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-early-inlining -fdump-ipa-cp-details -fdump-tree-optimized" } */
+
+static double global = 0.0;
+
+double foo_temp5;
+
+static void foo(double *ptr) {
+ static double abcd;
+ double v, exp_res;
+ v = *ptr;
+ exp_res = __builtin_exp(v);
+ foo_temp5 = exp_res * abcd;
+ abcd += foo_temp5;
+}
+
+void entry()
+{
+ foo(&global);
+}
+
+/* { dg-final { scan-ipa-dump "Removed a reference" "cp" } } */
+/* { dg-final { scan-tree-dump-not "builtin_exp" "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/ipa/remref-4.c b/gcc/testsuite/gcc.dg/ipa/remref-4.c
new file mode 100644
index 00000000000..5a55437e971
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ipa/remref-4.c
@@ -0,0 +1,31 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-early-inlining -fdump-ipa-cp-details -fdump-tree-optimized" } */
+
+static double global = 0.0;
+double foo_temp5;
+
+static void foo(double *ptr) {
+ static double abcd;
+ double v, exp_res;
+ v = *ptr;
+ exp_res = __builtin_exp(v);
+ foo_temp5 = exp_res * abcd;
+ abcd += foo_temp5;
+}
+
+double last_value;
+
+static void bar(double *ptr)
+{
+ last_value = *ptr;
+ foo (ptr);
+}
+
+void entry()
+{
+ bar (&global);
+}
+
+/* { dg-final { scan-ipa-dump "Removed a reference" "cp" } } */
+/* { dg-final { scan-ipa-dump "replaced it with LOAD" "cp" } } */
+/* { dg-final { scan-tree-dump-not "builtin_exp" "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/ipa/remref-5.c b/gcc/testsuite/gcc.dg/ipa/remref-5.c
new file mode 100644
index 00000000000..c520e34d809
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ipa/remref-5.c
@@ -0,0 +1,38 @@
+/* { dg-do compile } */
+/* { dg-options "-O3 -fno-early-inlining -fdump-ipa-cp-details -fdump-tree-optimized" } */
+
+static double global = 0.0;
+double foo_temp5;
+
+static void foo(double *ptr) {
+ static double abcd;
+ double v, exp_res;
+ v = *ptr;
+ exp_res = __builtin_exp(v);
+ foo_temp5 = exp_res * abcd;
+ abcd += foo_temp5;
+}
+
+double last_value;
+
+static void bar(double *ptr)
+{
+ last_value = *ptr;
+ for (unsigned i = 0; i < 200; i++)
+ foo (ptr);
+}
+
+void entry()
+{
+ bar (&global);
+}
+
+void decoy(double *ptr)
+{
+ bar (ptr);
+}
+
+
+/* { dg-final { scan-ipa-dump "Removed a reference" "cp" } } */
+/* { dg-final { scan-ipa-dump "replaced it with LOAD" "cp" } } */
+/* { dg-final { scan-tree-dump-times "builtin_exp" 1 "optimized" } } */
diff --git a/gcc/testsuite/gcc.dg/ipa/remref-6.c b/gcc/testsuite/gcc.dg/ipa/remref-6.c
new file mode 100644
index 00000000000..de3649315c2
--- /dev/null
+++ b/gcc/testsuite/gcc.dg/ipa/remref-6.c
@@ -0,0 +1,24 @@
+/* { dg-do compile } */
+/* { dg-options "-O2 -fno-early-inlining -fno-ipa-cp -fdump-tree-optimized" } */
+
+static double global = 0.0;
+
+double foo_temp5;
+
+static void foo(double *ptr) {
+ static double abcd;
+ double v, exp_res;
+ v = *ptr;
+ exp_res = __builtin_exp(v);
+ foo_temp5 = exp_res * abcd;
+ abcd += foo_temp5;
+}
+
+void entry()
+{
+ foo(&global);
+}
+
+/* { dg-final { scan-ipa-dump "Removed a reference" "inline" } } */
+/* { dg-final { scan-ipa-dump "replaced it with LOAD" "inline" } } */
+/* { dg-final { scan-tree-dump-not "builtin_exp" "optimized" } } */
</cut>
4 years, 1 month
- 1
- 0
[ACTIVITY] report week ending 30 July
by Peter Maydell
Progress:
* UM-2 [QEMU upstream maintainership]
+ collected up/reviewed arm patches ready for rc1
+ sent patch fixing a silly crash if the user tried to pass both a
guest kernel and a firmware blob to the raspi3 machine
+ patchset fixing a lot of places in our docs where we used `foo`
in rST markup but we meant ``foo``
+ some docs patches converting old .txt files to .rst so we
actually ship the docs to users
+ patchset doing a bit of cleanup on arch-init.c
+ patches implementing M-profile trap-on-division-by-zero
+ started to look at refactoring the M-profile systick timer to
no longer rely on an ugly global variable to specify the frequency
* QEMU-406 [QEMU support for MVE (M-profile Vector Extension; Helium)]
+ sent out MVE patchset for review which has full coverage of the
instruction set and includes "enable MVE on Cortex-M55"
+ remaining TODO items: fault on unaligned accesses; report MVE
registers via gdbstub; optimize codegen for the no-predication case
-- PMM
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-O2 - Build # 12 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-O2
Culprit:
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
</cut>
Results regressed to (for first_bad == 0b92cf305dcf34387a8e2564e55ca8948df3b47a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-0b92cf305dcf34387a8e2564e55ca8948df3b47a/results_id:
1
# 447.dealII,[.] _ZSt18_Rb_tree_incrementPKSt18_Rb_tree_node_ba regressed by 721
from (for last_good == 7552c36afa1f9058bb39f336ae84f019621885a0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-7552c36afa1f9058bb39f336ae84f019621885a0/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/2420
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-O2/2415
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
cd investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 0b92cf305dcf34387a8e2564e55ca8948df3b47a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 7552c36afa1f9058bb39f336ae84f019621885a0
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
---
gcc/ChangeLog | 8 ++++++++
gcc/doc/invoke.texi | 8 ++++++++
gcc/ipa-inline.c | 22 ++++++++++++++--------
gcc/params.def | 6 +++++-
gcc/testsuite/ChangeLog | 9 +++++++++
gcc/testsuite/g++.dg/tree-ssa/pr61034.C | 2 +-
gcc/testsuite/g++.dg/tree-ssa/pr8781.C | 2 +-
gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C | 2 +-
gcc/testsuite/gcc.dg/ipa/pr63416.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c | 2 +-
gcc/testsuite/gcc.dg/vect/pr66142.c | 2 +-
11 files changed, 50 insertions(+), 15 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index bb4de20ab16..b4c4292c299 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * doc/invoke.texi (early-inlining-insns-O2): Document.
+ (early-inlining-insns): Update.
+ * params.def (early-inlining-insns-O2): New bound.
+ (early-inlining-insns): Update docs.
+ * ipa-inline.c (want_early_inline_function_p): Use new bound.
+
2019-10-01 Oleg Endo <olegendo(a)gcc.gnu.org>
PR target/88562
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 83016a5a8ee..4281ee7c614 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -11291,9 +11291,17 @@ recursion depth can be guessed from the probability that function recurses
via a given call expression. This parameter limits inlining only to call
expressions whose probability exceeds the given threshold (in percents).
+@item early-inlining-insns-O2
+Specify growth that the early inliner can make. In effect it increases
+the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O1} or @option{-O2}
+optimization levels.
+
@item early-inlining-insns
Specify growth that the early inliner can make. In effect it increases
the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O3} or @option{-Ofast}
+optimization levels.
@item max-early-inliner-iterations
Limit of iterations of the early inliner. This basically bounds
diff --git a/gcc/ipa-inline.c b/gcc/ipa-inline.c
index b62d280eb25..c8689c7d9a8 100644
--- a/gcc/ipa-inline.c
+++ b/gcc/ipa-inline.c
@@ -641,6 +641,10 @@ want_early_inline_function_p (struct cgraph_edge *e)
{
int growth = estimate_edge_growth (e);
int n;
+ int early_inlining_insns = opt_for_fn (e->caller->decl, optimize) >= 3
+ ? PARAM_VALUE (PARAM_EARLY_INLINING_INSNS)
+ : PARAM_VALUE (PARAM_EARLY_INLINING_INSNS_O2);
+
if (growth <= PARAM_VALUE (PARAM_MAX_INLINE_INSNS_SIZE))
;
@@ -654,26 +658,28 @@ want_early_inline_function_p (struct cgraph_edge *e)
growth);
want_inline = false;
}
- else if (growth > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ else if (growth > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns\n",
- e->caller, callee,
- growth);
+ "growth %i exceeds --param early-inlining-insns%s\n",
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
else if ((n = num_calls (callee)) != 0
- && growth * (n + 1) > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ && growth * (n + 1) > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns "
+ "growth %i exceeds --param early-inlining-insns%s "
"divided by number of calls\n",
- e->caller, callee,
- growth);
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
}
diff --git a/gcc/params.def b/gcc/params.def
index d2d957fc6b1..0acf29b6c4d 100644
--- a/gcc/params.def
+++ b/gcc/params.def
@@ -233,8 +233,12 @@ DEFPARAM(PARAM_IPCP_UNIT_GROWTH,
10, 0, 0)
DEFPARAM(PARAM_EARLY_INLINING_INSNS,
"early-inlining-insns",
- "Maximal estimated growth of function body caused by early inlining of single call.",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O3 and -Ofast.",
14, 0, 0)
+DEFPARAM(PARAM_EARLY_INLINING_INSNS_O2,
+ "early-inlining-insns-O2",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O1 and -O2.",
+ 6, 0, 0)
DEFPARAM(PARAM_LARGE_STACK_FRAME,
"large-stack-frame",
"The size of stack frame to be considered large.",
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index df6105f3d13..0dcaf4b6292 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
+ * g++.dg/tree-ssa/pr8781.C: Likewise.
+ * g++.dg/warn/Wstringop-truncation-1.C: Likewise.
+ * gcc.dg/ipa/pr63416.c: likewise.
+ * gcc.dg/vect/pr66142.c: Likewise.
+ * gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
+
2019-10-01 Jakub Jelinek <jakub(a)redhat.com>
PR c++/91925
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
index 870b2372166..2e3dfecacb4 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
@@ -1,5 +1,5 @@
// { dg-do compile }
-// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks" }
+// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks --param early-inlining-insns-O2=14" }
#define assume(x) if(!(x))__builtin_unreachable()
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
index 1f115b2b26d..5bc1ef03520 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1" } */
+/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1 --param early-inlining-insns-O2=14" } */
int f();
diff --git a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
index 83066019772..49dde0a65ba 100644
--- a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
+++ b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
@@ -1,7 +1,7 @@
/* PR/tree-optimization/84480 - bogus -Wstringop-truncation despite
assignment with an inlined string literal
{ dg-do compile }
- { dg-options "-O2 -Wstringop-truncation" } */
+ { dg-options "-O2 -Wstringop-truncation --param early-inlining-insns-O2=14" } */
#include <string.h>
diff --git a/gcc/testsuite/gcc.dg/ipa/pr63416.c b/gcc/testsuite/gcc.dg/ipa/pr63416.c
index b5374c51fe9..5873954fba3 100644
--- a/gcc/testsuite/gcc.dg/ipa/pr63416.c
+++ b/gcc/testsuite/gcc.dg/ipa/pr63416.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fdump-tree-optimized --param early-inlining-insns-O2=14" } */
#define _UNUSED_ __attribute__((__unused__))
typedef int TEST_F30 (int *v);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
index 67526762f2c..216de23d791 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
@@ -56,7 +56,7 @@ bmp_iter_and_compl (bitmap_iterator * bi, unsigned *bit_no)
}
extern int VEC_int_base_length (VEC_int_base *);
-bitmap
+inline bitmap
compute_idf (bitmap def_blocks, bitmap_head * dfs)
{
bitmap_iterator bi;
diff --git a/gcc/testsuite/gcc.dg/vect/pr66142.c b/gcc/testsuite/gcc.dg/vect/pr66142.c
index 8c79f290767..a0316f1f01e 100644
--- a/gcc/testsuite/gcc.dg/vect/pr66142.c
+++ b/gcc/testsuite/gcc.dg/vect/pr66142.c
@@ -1,6 +1,6 @@
/* PR middle-end/66142 */
/* { dg-do compile } */
-/* { dg-additional-options "-ffast-math -fopenmp-simd" } */
+/* { dg-additional-options "-ffast-math -fopenmp-simd --param early-inlining-insns-O2=14" } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
struct A { float x, y; };
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/gnu-release-arm-spec2k6-O2 - Build # 24 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tk1/gnu-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tk1/gnu-release-arm-spec2k6-O2
Culprit:
<cut>
commit 5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd
Author: Richard Biener <rguenther(a)suse.de>
Date: Thu May 23 11:35:16 2019 +0000
re PR tree-optimization/88440 (size optimization of memcpy-like code)
2019-05-23 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/88440
* opts.c (default_options_table): Enable -ftree-loop-distribute-patterns
at -O[2s]+.
* tree-loop-distribution.c (generate_memset_builtin): Fold the
generated call.
(generate_memcpy_builtin): Likewise.
(distribute_loop): Pass in whether to only distribute patterns.
(prepare_perfect_loop_nest): Also allow size optimization.
(pass_loop_distribution::execute): When optimizing a loop
nest for size allow pattern replacement.
* gcc.dg/tree-ssa/ldist-37.c: New testcase.
* gcc.dg/tree-ssa/ldist-38.c: Likewise.
* gcc.dg/vect/vect.exp: Add -fno-tree-loop-distribute-patterns.
* gcc.dg/tree-ssa/ldist-37.c: Adjust.
* gcc.dg/tree-ssa/ldist-38.c: Likewise.
* g++.dg/tree-ssa/pr78847.C: Likewise.
* gcc.dg/autopar/pr39500-1.c: Likewise.
* gcc.dg/autopar/reduc-1char.c: Likewise.
* gcc.dg/autopar/reduc-7.c: Likewise.
* gcc.dg/tree-ssa/ivopts-lt-2.c: Likewise.
* gcc.dg/tree-ssa/ivopts-lt.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-1.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-2.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-3.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-4.c: Likewise.
* gcc.dg/tree-ssa/prefetch-7.c: Likewise.
* gcc.dg/tree-ssa/prefetch-8.c: Likewise.
* gcc.dg/tree-ssa/prefetch-9.c: Likewise.
* gcc.dg/tree-ssa/scev-11.c: Likewise.
* gcc.dg/vect/costmodel/i386/costmodel-vect-31.c: Likewise.
* gcc.dg/vect/costmodel/i386/costmodel-vect-33.c: Likewise.
* gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c: Likewise.
* gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c: Likewise.
* gcc.target/i386/pr30970.c: Likewise.
* gcc.target/i386/vect-double-1.c: Likewise.
* gcc.target/i386/vect-double-2.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-2.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-26.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-28.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-32.c: Likewise.
* gfortran.dg/vect/vect-5.f90: Likewise.
* gfortran.dg/vect/vect-8.f90: Likewise.
From-SVN: r271553
</cut>
Results regressed to (for first_bad == 5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2_marm -- artifacts/build-5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd/results_id:
1
# 403.gcc,libc-2.32.so regressed by 122
# 403.gcc,[.] memset regressed by 126
# 481.wrf,libc-2.32.so regressed by 176
# 447.dealII,libstdc++.so.6.0.26 regressed by 111
# 447.dealII,[.] _ZSt18_Rb_tree_incrementPSt18_Rb_tree_node_bas regressed by 117
# 401.bzip2,bzip2_base.default regressed by 104
# 401.bzip2,[.] mainSort regressed by 111
from (for last_good == 32d941139e8144662e0dc182d64e3f3f9df89ad4)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2_marm -- artifacts/build-32d941139e8144662e0dc182d64e3f3f9df89ad4/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Results ID of last_good: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-release-arm-spec2k6-O2/2360
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Results ID of first_bad: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-release-arm-spec2k6-O2/2376
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd
cd investigate-gcc-5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 32d941139e8144662e0dc182d64e3f3f9df89ad4
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit 5879ab5fafedc8f6f9bfe95a4cf8501b0df90edd
Author: Richard Biener <rguenther(a)suse.de>
Date: Thu May 23 11:35:16 2019 +0000
re PR tree-optimization/88440 (size optimization of memcpy-like code)
2019-05-23 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/88440
* opts.c (default_options_table): Enable -ftree-loop-distribute-patterns
at -O[2s]+.
* tree-loop-distribution.c (generate_memset_builtin): Fold the
generated call.
(generate_memcpy_builtin): Likewise.
(distribute_loop): Pass in whether to only distribute patterns.
(prepare_perfect_loop_nest): Also allow size optimization.
(pass_loop_distribution::execute): When optimizing a loop
nest for size allow pattern replacement.
* gcc.dg/tree-ssa/ldist-37.c: New testcase.
* gcc.dg/tree-ssa/ldist-38.c: Likewise.
* gcc.dg/vect/vect.exp: Add -fno-tree-loop-distribute-patterns.
* gcc.dg/tree-ssa/ldist-37.c: Adjust.
* gcc.dg/tree-ssa/ldist-38.c: Likewise.
* g++.dg/tree-ssa/pr78847.C: Likewise.
* gcc.dg/autopar/pr39500-1.c: Likewise.
* gcc.dg/autopar/reduc-1char.c: Likewise.
* gcc.dg/autopar/reduc-7.c: Likewise.
* gcc.dg/tree-ssa/ivopts-lt-2.c: Likewise.
* gcc.dg/tree-ssa/ivopts-lt.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-1.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-2.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-3.c: Likewise.
* gcc.dg/tree-ssa/predcom-dse-4.c: Likewise.
* gcc.dg/tree-ssa/prefetch-7.c: Likewise.
* gcc.dg/tree-ssa/prefetch-8.c: Likewise.
* gcc.dg/tree-ssa/prefetch-9.c: Likewise.
* gcc.dg/tree-ssa/scev-11.c: Likewise.
* gcc.dg/vect/costmodel/i386/costmodel-vect-31.c: Likewise.
* gcc.dg/vect/costmodel/i386/costmodel-vect-33.c: Likewise.
* gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c: Likewise.
* gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c: Likewise.
* gcc.target/i386/pr30970.c: Likewise.
* gcc.target/i386/vect-double-1.c: Likewise.
* gcc.target/i386/vect-double-2.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-2.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-26.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-28.c: Likewise.
* gcc.dg/tree-ssa/gen-vect-32.c: Likewise.
* gfortran.dg/vect/vect-5.f90: Likewise.
* gfortran.dg/vect/vect-8.f90: Likewise.
From-SVN: r271553
---
gcc/ChangeLog | 13 ++++++++
gcc/opts.c | 2 +-
gcc/testsuite/ChangeLog | 36 ++++++++++++++++++++++
gcc/testsuite/g++.dg/tree-ssa/pr78847.C | 4 +--
gcc/testsuite/gcc.dg/autopar/pr39500-1.c | 2 +-
gcc/testsuite/gcc.dg/autopar/reduc-1char.c | 2 +-
gcc/testsuite/gcc.dg/autopar/reduc-7.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/gen-vect-2.c | 4 +--
gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c | 4 +--
gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c | 4 +--
gcc/testsuite/gcc.dg/tree-ssa/gen-vect-32.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt-2.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-1.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-2.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-3.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-4.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/prefetch-7.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/prefetch-8.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/prefetch-9.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/scev-11.c | 2 +-
.../gcc.dg/vect/costmodel/i386/costmodel-vect-31.c | 1 +
.../gcc.dg/vect/costmodel/i386/costmodel-vect-33.c | 1 +
.../vect/costmodel/x86_64/costmodel-vect-31.c | 1 +
.../vect/costmodel/x86_64/costmodel-vect-33.c | 1 +
gcc/testsuite/gcc.dg/vect/vect.exp | 2 +-
gcc/testsuite/gcc.target/i386/pr30970.c | 2 +-
gcc/testsuite/gcc.target/i386/vect-double-1.c | 2 +-
gcc/testsuite/gcc.target/i386/vect-double-2.c | 2 +-
gcc/testsuite/gfortran.dg/vect/vect-5.f90 | 2 +-
gcc/testsuite/gfortran.dg/vect/vect-8.f90 | 2 +-
gcc/tree-loop-distribution.c | 24 +++++++++------
32 files changed, 97 insertions(+), 38 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index e49c75847f1..695f9c4bb60 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,16 @@
+2019-05-23 Richard Biener <rguenther(a)suse.de>
+
+ PR tree-optimization/88440
+ * opts.c (default_options_table): Enable -ftree-loop-distribute-patterns
+ at -O[2s]+.
+ * tree-loop-distribution.c (generate_memset_builtin): Fold the
+ generated call.
+ (generate_memcpy_builtin): Likewise.
+ (distribute_loop): Pass in whether to only distribute patterns.
+ (prepare_perfect_loop_nest): Also allow size optimization.
+ (pass_loop_distribution::execute): When optimizing a loop
+ nest for size allow pattern replacement.
+
2019-05-23 Jakub Jelinek <jakub(a)redhat.com>
PR target/90568
diff --git a/gcc/opts.c b/gcc/opts.c
index 879ab17c362..2e3e8b20537 100644
--- a/gcc/opts.c
+++ b/gcc/opts.c
@@ -550,7 +550,7 @@ static const struct default_options default_options_table[] =
{ OPT_LEVELS_3_PLUS, OPT_fpredictive_commoning, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_fsplit_loops, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_fsplit_paths, NULL, 1 },
- { OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },
+ { OPT_LEVELS_2_PLUS, OPT_ftree_loop_distribute_patterns, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_loop_distribution, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_loop_vectorize, NULL, 1 },
{ OPT_LEVELS_3_PLUS, OPT_ftree_partial_pre, NULL, 1 },
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index b34d1cc74b4..01afd3b5b0a 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,39 @@
+2019-05-23 Richard Biener <rguenther(a)suse.de>
+
+ PR tree-optimization/88440
+ * gcc.dg/tree-ssa/ldist-37.c: New testcase.
+ * gcc.dg/tree-ssa/ldist-38.c: Likewise.
+ * gcc.dg/vect/vect.exp: Add -fno-tree-loop-distribute-patterns.
+ * gcc.dg/tree-ssa/ldist-37.c: Adjust.
+ * gcc.dg/tree-ssa/ldist-38.c: Likewise.
+ * g++.dg/tree-ssa/pr78847.C: Likewise.
+ * gcc.dg/autopar/pr39500-1.c: Likewise.
+ * gcc.dg/autopar/reduc-1char.c: Likewise.
+ * gcc.dg/autopar/reduc-7.c: Likewise.
+ * gcc.dg/tree-ssa/ivopts-lt-2.c: Likewise.
+ * gcc.dg/tree-ssa/ivopts-lt.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-1.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-2.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-3.c: Likewise.
+ * gcc.dg/tree-ssa/predcom-dse-4.c: Likewise.
+ * gcc.dg/tree-ssa/prefetch-7.c: Likewise.
+ * gcc.dg/tree-ssa/prefetch-8.c: Likewise.
+ * gcc.dg/tree-ssa/prefetch-9.c: Likewise.
+ * gcc.dg/tree-ssa/scev-11.c: Likewise.
+ * gcc.dg/vect/costmodel/i386/costmodel-vect-31.c: Likewise.
+ * gcc.dg/vect/costmodel/i386/costmodel-vect-33.c: Likewise.
+ * gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c: Likewise.
+ * gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c: Likewise.
+ * gcc.target/i386/pr30970.c: Likewise.
+ * gcc.target/i386/vect-double-1.c: Likewise.
+ * gcc.target/i386/vect-double-2.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-2.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-26.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-28.c: Likewise.
+ * gcc.dg/tree-ssa/gen-vect-32.c: Likewise.
+ * gfortran.dg/vect/vect-5.f90: Likewise.
+ * gfortran.dg/vect/vect-8.f90: Likewise.
+
2019-05-23 Martin Liska <mliska(a)suse.cz>
PR sanitizer/90570
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr78847.C b/gcc/testsuite/g++.dg/tree-ssa/pr78847.C
index d5a83943804..e72e516d8d4 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr78847.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr78847.C
@@ -1,6 +1,6 @@
/* { dg-do compile } */
/* { dg-require-effective-target c++14 } */
-/* { dg-options "-O3 -fdump-tree-ldist" } */
+/* { dg-options "-O3 -fdump-tree-ldist-optimized" } */
#include <stddef.h>
#include <cstring>
@@ -23,4 +23,4 @@ void testWithLoopValue(const Foo foo, size_t ptr, char *buf_) {
buf_[ptr++] = c;
}
-/* { dg-final { scan-tree-dump "memcpy\[^\n\r\]*, 9\\);" "ldist" } } */
+/* { dg-final { scan-tree-dump "split to 0 loops and 1 library calls" "ldist" } } */
diff --git a/gcc/testsuite/gcc.dg/autopar/pr39500-1.c b/gcc/testsuite/gcc.dg/autopar/pr39500-1.c
index 28f47897b37..80ae92522db 100644
--- a/gcc/testsuite/gcc.dg/autopar/pr39500-1.c
+++ b/gcc/testsuite/gcc.dg/autopar/pr39500-1.c
@@ -1,7 +1,7 @@
/* pr39500: autopar fails to parallel */
/* origin: nemokingdom(a)gmail.com(LiFeng) */
/* { dg-do compile } */
-/* { dg-options "-O2 -ftree-parallelize-loops=4 -fdump-tree-parloops2-details" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-parallelize-loops=4 -fdump-tree-parloops2-details" } */
void abort (void);
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-1char.c b/gcc/testsuite/gcc.dg/autopar/reduc-1char.c
index 0d611b96eae..a340240b86b 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-1char.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-1char.c
@@ -61,5 +61,5 @@ int main (void)
/* { dg-final { scan-tree-dump-times "Detected reduction" 3 "parloops2" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 4 "parloops2" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops2" } } */
diff --git a/gcc/testsuite/gcc.dg/autopar/reduc-7.c b/gcc/testsuite/gcc.dg/autopar/reduc-7.c
index efae736db1d..85b9437298b 100644
--- a/gcc/testsuite/gcc.dg/autopar/reduc-7.c
+++ b/gcc/testsuite/gcc.dg/autopar/reduc-7.c
@@ -85,5 +85,5 @@ int main (void)
/* { dg-final { scan-tree-dump-times "Detected reduction" 2 "parloops2" } } */
-/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 3 "parloops2" } } */
+/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 2 "parloops2" } } */
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-2.c b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-2.c
index a2691294b07..42171a2fbf3 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-2.c
@@ -1,6 +1,6 @@
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic -mno-sse" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
+/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
index 8e5f1410612..242316893c0 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-26.c
@@ -1,6 +1,6 @@
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic -mno-sse" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
+/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
index ce97e0970b5..24853e0e0db 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-28.c
@@ -1,6 +1,6 @@
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic -mno-sse" { target { i?86-*-* x86_64-*-* } } } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fvect-cost-model=dynamic" } */
+/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-32.c b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-32.c
index 8fce4385d0b..c4bee19b75a 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-32.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/gen-vect-32.c
@@ -1,5 +1,5 @@
/* { dg-do run { target vect_cmdline_needed } } */
-/* { dg-options "-O2 -ftree-vectorize -fdump-tree-vect-details -fno-vect-cost-model" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -fdump-tree-vect-details -fno-vect-cost-model" } */
/* { dg-additional-options "-mno-sse" { target { i?86-*-* x86_64-*-* } } } */
#include <stdlib.h>
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt-2.c b/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt-2.c
index 634f1dd51d3..bdbdbff19ff 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-ivopts" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fdump-tree-ivopts" } */
/* { dg-skip-if "PR68644" { hppa*-*-* powerpc*-*-* } } */
void
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt.c b/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt.c
index 171c85ab38d..7d5859b3fce 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ivopts-lt.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-ivopts" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fdump-tree-ivopts" } */
/* { dg-require-effective-target stdint_types } */
#include "stdint.h"
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-1.c b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-1.c
index d3a2339e55e..b61b651fca8 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-1.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-1.c
@@ -1,5 +1,5 @@
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr[105] = {2, 3, 5, 7, 11};
int result0[10] = {2, 3, 5, 7, 11};
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-2.c b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-2.c
index c48d438e9e0..7f959a833f4 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-2.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-2.c
@@ -1,5 +1,5 @@
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr[105] = {2, 3, 5, 7, 11};
int result0[10] = {2, 3, 5, 7, 11};
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-3.c b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-3.c
index 9c2736cd0ad..ec08d6c0318 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-3.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-3.c
@@ -1,5 +1,5 @@
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr1[105] = {2, 3, 5, 7, 11, 13, 0};
int arr2[105] = {2, 3, 5, 7, 11, 13, 0};
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-4.c b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-4.c
index 302425a17cc..f97d32f4b41 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-4.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/predcom-dse-4.c
@@ -1,5 +1,5 @@
/* { dg-do run } */
-/* { dg-options "-O2 -fno-inline -fpredictive-commoning -fdump-tree-pcom-details" } */
+/* { dg-options "-O2 -fno-inline -fno-tree-loop-distribute-patterns -fpredictive-commoning -fdump-tree-pcom-details" } */
int arr[105] = {2, 3, 5, 7, 11};
int result0[10] = {2, 3, 5, 7, 11};
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/prefetch-7.c b/gcc/testsuite/gcc.dg/tree-ssa/prefetch-7.c
index c9f70271892..26de8719dc2 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/prefetch-7.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/prefetch-7.c
@@ -1,5 +1,5 @@
/* { dg-do compile { target { i?86-*-* x86_64-*-* } } } */
-/* { dg-options "-O2 -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
#define K 1000000
int a[K];
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/prefetch-8.c b/gcc/testsuite/gcc.dg/tree-ssa/prefetch-8.c
index fe433ac3a7f..cbd6a80d345 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/prefetch-8.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/prefetch-8.c
@@ -1,5 +1,5 @@
/* { dg-do compile { target { i?86-*-* x86_64-*-* } } } */
-/* { dg-options "-O2 -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
#define K 1000000
int a[K];
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/prefetch-9.c b/gcc/testsuite/gcc.dg/tree-ssa/prefetch-9.c
index 5be9282c9be..da4847320b1 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/prefetch-9.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/prefetch-9.c
@@ -1,5 +1,5 @@
/* { dg-do compile { target { i?86-*-* x86_64-*-* } } } */
-/* { dg-options "-O2 -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fno-tree-loop-distribute-patterns -fprefetch-loop-arrays -march=amdfam10 --param simultaneous-prefetches=100 -fdump-tree-aprefetch-details -fdump-tree-optimized" } */
#define K 1000000
int a[K], b[K];
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/scev-11.c b/gcc/testsuite/gcc.dg/tree-ssa/scev-11.c
index c665fd7f20d..2336239652e 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/scev-11.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/scev-11.c
@@ -15,7 +15,7 @@ foo (int n)
{
unsigned char uc = (unsigned char)i;
a[i] = i;
- b[uc] = 0;
+ b[uc] = 1;
}
bar (a);
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-31.c b/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-31.c
index 133ab0edca0..cc50a5bde01 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-31.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-31.c
@@ -1,4 +1,5 @@
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-33.c b/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-33.c
index 242427dc486..b82b8916be1 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-33.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/i386/costmodel-vect-33.c
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c b/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c
index 133ab0edca0..cc50a5bde01 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-31.c
@@ -1,4 +1,5 @@
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
diff --git a/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c b/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c
index 33bf7f1a5a6..5e4affae7db 100644
--- a/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c
+++ b/gcc/testsuite/gcc.dg/vect/costmodel/x86_64/costmodel-vect-33.c
@@ -1,5 +1,6 @@
/* { dg-do compile } */
/* { dg-require-effective-target vect_int } */
+/* { dg-additional-options "-fno-tree-loop-distribute-patterns" } */
#include <stdarg.h>
#include "../../tree-vect.h"
diff --git a/gcc/testsuite/gcc.dg/vect/vect.exp b/gcc/testsuite/gcc.dg/vect/vect.exp
index 8e012d49edf..9569ea5c02f 100644
--- a/gcc/testsuite/gcc.dg/vect/vect.exp
+++ b/gcc/testsuite/gcc.dg/vect/vect.exp
@@ -45,7 +45,7 @@ if ![check_vect_support_and_set_flags] {
}
# These flags are used for all targets.
-lappend DEFAULT_VECTCFLAGS "-ftree-vectorize" "-fno-vect-cost-model" "-fno-common"
+lappend DEFAULT_VECTCFLAGS "-ftree-vectorize" "-fno-tree-loop-distribute-patterns" "-fno-vect-cost-model" "-fno-common"
# Initialize `dg'.
dg-init
diff --git a/gcc/testsuite/gcc.target/i386/pr30970.c b/gcc/testsuite/gcc.target/i386/pr30970.c
index b1fc2d3ecfa..263db5e05a6 100644
--- a/gcc/testsuite/gcc.target/i386/pr30970.c
+++ b/gcc/testsuite/gcc.target/i386/pr30970.c
@@ -1,5 +1,5 @@
/* { dg-do compile }
-/* { dg-options "-msse2 -O2 -ftree-vectorize -mtune=generic" } */
+/* { dg-options "-msse2 -O2 -fno-tree-loop-distribute-patterns -ftree-vectorize -mtune=generic" } */
#define N 256
int b[N];
diff --git a/gcc/testsuite/gcc.target/i386/vect-double-1.c b/gcc/testsuite/gcc.target/i386/vect-double-1.c
index c44e669b0ef..180274c20a1 100644
--- a/gcc/testsuite/gcc.target/i386/vect-double-1.c
+++ b/gcc/testsuite/gcc.target/i386/vect-double-1.c
@@ -1,6 +1,6 @@
/* { dg-do compile } */
/* { dg-skip-if "" { *-*-* } { "-march=*" } { "-march=core2" } } */
-/* { dg-options "-O2 -ftree-vectorize -mfpmath=sse -march=core2 -fdump-tree-vect-stats" } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-loop-distribute-patterns -mfpmath=sse -march=core2 -fdump-tree-vect-stats" } */
/* { dg-add-options bind_pic_locally } */
extern void abort (void);
diff --git a/gcc/testsuite/gcc.target/i386/vect-double-2.c b/gcc/testsuite/gcc.target/i386/vect-double-2.c
index f6a43749407..eea53bfa6b1 100644
--- a/gcc/testsuite/gcc.target/i386/vect-double-2.c
+++ b/gcc/testsuite/gcc.target/i386/vect-double-2.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -ftree-vectorize -mfpmath=sse -msse2 -mtune=atom -fdump-tree-vect-stats" } */
+/* { dg-options "-O2 -ftree-vectorize -fno-tree-loop-distribute-patterns -mfpmath=sse -msse2 -mtune=atom -fdump-tree-vect-stats" } */
extern void abort (void);
diff --git a/gcc/testsuite/gfortran.dg/vect/vect-5.f90 b/gcc/testsuite/gfortran.dg/vect/vect-5.f90
index de283e8b85f..b11cabaee23 100644
--- a/gcc/testsuite/gfortran.dg/vect/vect-5.f90
+++ b/gcc/testsuite/gfortran.dg/vect/vect-5.f90
@@ -1,5 +1,5 @@
! { dg-require-effective-target vect_int }
-! { dg-additional-options "--param vect-max-peeling-for-alignment=0" }
+! { dg-additional-options "-fno-tree-loop-distribute-patterns --param vect-max-peeling-for-alignment=0" }
Subroutine foo (N, M)
Integer N
diff --git a/gcc/testsuite/gfortran.dg/vect/vect-8.f90 b/gcc/testsuite/gfortran.dg/vect/vect-8.f90
index 0ac5f1c390b..e26cdf95e51 100644
--- a/gcc/testsuite/gfortran.dg/vect/vect-8.f90
+++ b/gcc/testsuite/gfortran.dg/vect/vect-8.f90
@@ -1,6 +1,6 @@
! { dg-do compile }
! { dg-require-effective-target vect_double }
-! { dg-additional-options "-finline-matmul-limit=0" }
+! { dg-additional-options "-fno-tree-loop-distribute-patterns -finline-matmul-limit=0" }
module lfk_prec
integer, parameter :: dp=kind(1.d0)
diff --git a/gcc/tree-loop-distribution.c b/gcc/tree-loop-distribution.c
index 3d8f13c4d14..5f03b87f9c1 100644
--- a/gcc/tree-loop-distribution.c
+++ b/gcc/tree-loop-distribution.c
@@ -115,6 +115,7 @@ along with GCC; see the file COPYING3. If not see
#include "params.h"
#include "tree-vectorizer.h"
#include "tree-eh.h"
+#include "gimple-fold.h"
#define MAX_DATAREFS_NUM \
@@ -1028,6 +1029,7 @@ generate_memset_builtin (struct loop *loop, partition *partition)
fn = build_fold_addr_expr (builtin_decl_implicit (BUILT_IN_MEMSET));
fn_call = gimple_build_call (fn, 3, mem, val, nb_bytes);
gsi_insert_after (&gsi, fn_call, GSI_CONTINUE_LINKING);
+ fold_stmt (&gsi);
if (dump_file && (dump_flags & TDF_DETAILS))
{
@@ -1071,6 +1073,7 @@ generate_memcpy_builtin (struct loop *loop, partition *partition)
fn = build_fold_addr_expr (builtin_decl_implicit (kind));
fn_call = gimple_build_call (fn, 3, dest, src, nb_bytes);
gsi_insert_after (&gsi, fn_call, GSI_CONTINUE_LINKING);
+ fold_stmt (&gsi);
if (dump_file && (dump_flags & TDF_DETAILS))
{
@@ -2769,7 +2772,8 @@ finalize_partitions (struct loop *loop, vec<struct partition *> *partitions,
static int
distribute_loop (struct loop *loop, vec<gimple *> stmts,
- control_dependences *cd, int *nb_calls, bool *destroy_p)
+ control_dependences *cd, int *nb_calls, bool *destroy_p,
+ bool only_patterns_p)
{
ddrs_table = new hash_table<ddr_hasher> (389);
struct graph *rdg;
@@ -2843,7 +2847,7 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
/* If we are only distributing patterns but did not detect any,
simply bail out. */
- if (!flag_tree_loop_distribution
+ if (only_patterns_p
&& !any_builtin)
{
nbp = 0;
@@ -2855,7 +2859,7 @@ distribute_loop (struct loop *loop, vec<gimple *> stmts,
a loop into pieces, separated by builtin calls. That is, we
only want no or a single loop body remaining. */
struct partition *into;
- if (!flag_tree_loop_distribution)
+ if (only_patterns_p)
{
for (i = 0; partitions.iterate (i, &into); ++i)
if (!partition_builtin_p (into))
@@ -3085,7 +3089,6 @@ prepare_perfect_loop_nest (struct loop *loop)
&& loop_outer (outer)
&& outer->inner == loop && loop->next == NULL
&& single_exit (outer)
- && optimize_loop_for_speed_p (outer)
&& !chrec_contains_symbols_defined_in_loop (niters, outer->num)
&& (niters = number_of_latch_executions (outer)) != NULL_TREE
&& niters != chrec_dont_know)
@@ -3139,9 +3142,11 @@ pass_loop_distribution::execute (function *fun)
walking to innermost loops. */
FOR_EACH_LOOP (loop, LI_ONLY_INNERMOST)
{
- /* Don't distribute multiple exit edges loop, or cold loop. */
+ /* Don't distribute multiple exit edges loop, or cold loop when
+ not doing pattern detection. */
if (!single_exit (loop)
- || !optimize_loop_for_speed_p (loop))
+ || (!flag_tree_loop_distribute_patterns
+ && !optimize_loop_for_speed_p (loop)))
continue;
/* Don't distribute loop if niters is unknown. */
@@ -3169,9 +3174,10 @@ pass_loop_distribution::execute (function *fun)
bool destroy_p;
int nb_generated_loops, nb_generated_calls;
- nb_generated_loops = distribute_loop (loop, work_list, cd,
- &nb_generated_calls,
- &destroy_p);
+ nb_generated_loops
+ = distribute_loop (loop, work_list, cd, &nb_generated_calls,
+ &destroy_p, (!optimize_loop_for_speed_p (loop)
+ || !flag_tree_loop_distribution));
if (destroy_p)
loops_to_be_destroyed.safe_push (loop);
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-master-aarch64-spec2k6-O2_LTO - Build # 21 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-master-aarch64-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-master-aarch64-spec2k6-O2_LTO
Culprit:
<cut>
commit fedcf3c476aff7533741a1c61071200f0a38cf83
Author: Richard Biener <rguenther(a)suse.de>
Date: Thu Jul 8 09:52:49 2021 +0200
tree-optimization/101373 - avoid PRE across externally throwing call
PRE already tries to avoid hoisting possibly trapping expressions
across calls that might not return normally but fails to consider
const calls that throw externally. The following fixes that and
also plugs the hole of trapping references not pruned in case
they are not catched by the actuall call clobbering it.
At -Os we hit the same issue in RTL PRE and postreload-gcse has
even more incomplete checks so the patch adjusts both of those
as well.
2021-07-08 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/101373
* tree-ssa-pre.c (prune_clobbered_mems): Also prune trapping
references when the BB may not return.
(compute_avail): Pass in the function we're working on and
replace cfun references with it. Externally throwing
const calls also possibly terminate the function.
(pass_pre::execute): Pass down the function we're working on.
* gcse.c (compute_hash_table_work): Externally throwing
const/pure calls also need record_last_mem_set_info.
* postreload-gcse.c (record_opr_changes): Looping or externally
throwing const/pure calls also need record_last_mem_set_info.
* g++.dg/torture/pr101373.C: New testcase, XFAILed.
* gnat.dg/opt95.adb: Likewise.
</cut>
Results regressed to (for first_bad == fedcf3c476aff7533741a1c61071200f0a38cf83)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2_LTO -- artifacts/build-fedcf3c476aff7533741a1c61071200f0a38cf83/results_id:
1
# 429.mcf,mcf_base.default regressed by 106
from (for last_good == fe610051a803131822bd02a8842a67b573b8e46a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2_LTO -- artifacts/build-fe610051a803131822bd02a8842a67b573b8e46a/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-master-aarch64-spec2k6-O2_LTO/2345
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-master-aarch64-spec2k6-O2_LTO/2337
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-fedcf3c476aff7533741a1c61071200f0a38cf83
cd investigate-gcc-fedcf3c476aff7533741a1c61071200f0a38cf83
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach fedcf3c476aff7533741a1c61071200f0a38cf83
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach fe610051a803131822bd02a8842a67b573b8e46a
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Full commit (up to 1000 lines):
<cut>
commit fedcf3c476aff7533741a1c61071200f0a38cf83
Author: Richard Biener <rguenther(a)suse.de>
Date: Thu Jul 8 09:52:49 2021 +0200
tree-optimization/101373 - avoid PRE across externally throwing call
PRE already tries to avoid hoisting possibly trapping expressions
across calls that might not return normally but fails to consider
const calls that throw externally. The following fixes that and
also plugs the hole of trapping references not pruned in case
they are not catched by the actuall call clobbering it.
At -Os we hit the same issue in RTL PRE and postreload-gcse has
even more incomplete checks so the patch adjusts both of those
as well.
2021-07-08 Richard Biener <rguenther(a)suse.de>
PR tree-optimization/101373
* tree-ssa-pre.c (prune_clobbered_mems): Also prune trapping
references when the BB may not return.
(compute_avail): Pass in the function we're working on and
replace cfun references with it. Externally throwing
const calls also possibly terminate the function.
(pass_pre::execute): Pass down the function we're working on.
* gcse.c (compute_hash_table_work): Externally throwing
const/pure calls also need record_last_mem_set_info.
* postreload-gcse.c (record_opr_changes): Looping or externally
throwing const/pure calls also need record_last_mem_set_info.
* g++.dg/torture/pr101373.C: New testcase, XFAILed.
* gnat.dg/opt95.adb: Likewise.
---
gcc/gcse.c | 3 ++-
gcc/postreload-gcse.c | 4 +++-
gcc/testsuite/g++.dg/torture/pr101373.C | 33 +++++++++++++++++++++++++++
gcc/testsuite/gnat.dg/opt95.adb | 40 +++++++++++++++++++++++++++++++++
gcc/tree-ssa-pre.c | 34 +++++++++++++++++-----------
5 files changed, 99 insertions(+), 15 deletions(-)
diff --git a/gcc/gcse.c b/gcc/gcse.c
index ecf7e51aac5..ccd33664af5 100644
--- a/gcc/gcse.c
+++ b/gcc/gcse.c
@@ -1537,7 +1537,8 @@ compute_hash_table_work (struct gcse_hash_table_d *table)
record_last_reg_set_info (insn, regno);
if (! RTL_CONST_OR_PURE_CALL_P (insn)
- || RTL_LOOPING_CONST_OR_PURE_CALL_P (insn))
+ || RTL_LOOPING_CONST_OR_PURE_CALL_P (insn)
+ || can_throw_external (insn))
record_last_mem_set_info (insn);
}
diff --git a/gcc/postreload-gcse.c b/gcc/postreload-gcse.c
index 0b28247e299..6c95d09a1e5 100644
--- a/gcc/postreload-gcse.c
+++ b/gcc/postreload-gcse.c
@@ -779,7 +779,9 @@ record_opr_changes (rtx_insn *insn)
EXECUTE_IF_SET_IN_HARD_REG_SET (callee_clobbers, 0, regno, hrsi)
record_last_reg_set_info_regno (insn, regno);
- if (! RTL_CONST_OR_PURE_CALL_P (insn))
+ if (! RTL_CONST_OR_PURE_CALL_P (insn)
+ || RTL_LOOPING_CONST_OR_PURE_CALL_P (insn)
+ || can_throw_external (insn))
record_last_mem_set_info (insn);
}
}
diff --git a/gcc/testsuite/g++.dg/torture/pr101373.C b/gcc/testsuite/g++.dg/torture/pr101373.C
new file mode 100644
index 00000000000..f8c809739e2
--- /dev/null
+++ b/gcc/testsuite/g++.dg/torture/pr101373.C
@@ -0,0 +1,33 @@
+// { dg-do run }
+// { dg-xfail-run-if "PR100409" { *-*-* } }
+
+int __attribute__((const,noipa)) foo (int j)
+{
+ if (j != 0)
+ throw 1;
+ return 0;
+}
+
+int __attribute__((noipa)) bar (int *p, int n)
+{
+ int ret = 0;
+ if (n)
+ {
+ foo (n);
+ ret = *p;
+ }
+ ret += *p;
+ return ret;
+}
+
+int main()
+{
+ try
+ {
+ return bar (nullptr, 1);
+ }
+ catch (...)
+ {
+ return 0;
+ }
+}
diff --git a/gcc/testsuite/gnat.dg/opt95.adb b/gcc/testsuite/gnat.dg/opt95.adb
new file mode 100644
index 00000000000..2c72582b3f1
--- /dev/null
+++ b/gcc/testsuite/gnat.dg/opt95.adb
@@ -0,0 +1,40 @@
+-- { dg-do run }
+-- { dg-options "-O2 -gnatp" }
+
+procedure Opt95 is
+
+ function Foo (J : Integer) return Integer;
+ pragma Pure_Function (Foo);
+ pragma Machine_Attribute (Foo, "noipa");
+
+ function Foo (J : Integer) return Integer is
+ begin
+ if J /= 0 then
+ raise Constraint_Error;
+ end if;
+ return 0;
+ end;
+
+ function Bar (A : access Integer; N : Integer) return Integer;
+ pragma Machine_Attribute (Bar, "noipa");
+
+ function Bar (A : access Integer; N : Integer) return Integer is
+ Ret : Integer := 0;
+ Ret2 : Integer := 0;
+ begin
+ if N /= 0 then
+ Ret2 := Foo (N);
+ Ret := A.all;
+ end if;
+ Ret := Ret + A.all;
+ return Ret + Ret2;
+ end;
+
+ V : Integer;
+ pragma Volatile (V);
+
+begin
+ V := Bar (null, 1);
+exception
+ when Constraint_Error => null;
+end;
diff --git a/gcc/tree-ssa-pre.c b/gcc/tree-ssa-pre.c
index 69141c2f0c9..aa5244e678c 100644
--- a/gcc/tree-ssa-pre.c
+++ b/gcc/tree-ssa-pre.c
@@ -2071,6 +2071,13 @@ prune_clobbered_mems (bitmap_set_t set, basic_block block)
&& value_dies_in_block_x (expr, block))))
to_remove = i;
}
+ /* If the REFERENCE may trap make sure the block does not contain
+ a possible exit point.
+ ??? This is overly conservative if we translate AVAIL_OUT
+ as the available expression might be after the exit point. */
+ if (BB_MAY_NOTRETURN (block)
+ && vn_reference_may_trap (ref))
+ to_remove = i;
}
else if (expr->kind == NARY)
{
@@ -3860,7 +3867,7 @@ insert (void)
AVAIL_OUT[BLOCK] = AVAIL_IN[BLOCK] U PHI_GEN[BLOCK] U TMP_GEN[BLOCK]. */
static void
-compute_avail (void)
+compute_avail (function *fun)
{
basic_block block, son;
@@ -3871,7 +3878,7 @@ compute_avail (void)
/* We pretend that default definitions are defined in the entry block.
This includes function arguments and the static chain decl. */
- FOR_EACH_SSA_NAME (i, name, cfun)
+ FOR_EACH_SSA_NAME (i, name, fun)
{
pre_expr e;
if (!SSA_NAME_IS_DEFAULT_DEF (name)
@@ -3881,31 +3888,31 @@ compute_avail (void)
e = get_or_alloc_expr_for_name (name);
add_to_value (get_expr_value_id (e), e);
- bitmap_insert_into_set (TMP_GEN (ENTRY_BLOCK_PTR_FOR_FN (cfun)), e);
- bitmap_value_insert_into_set (AVAIL_OUT (ENTRY_BLOCK_PTR_FOR_FN (cfun)),
+ bitmap_insert_into_set (TMP_GEN (ENTRY_BLOCK_PTR_FOR_FN (fun)), e);
+ bitmap_value_insert_into_set (AVAIL_OUT (ENTRY_BLOCK_PTR_FOR_FN (fun)),
e);
}
if (dump_file && (dump_flags & TDF_DETAILS))
{
- print_bitmap_set (dump_file, TMP_GEN (ENTRY_BLOCK_PTR_FOR_FN (cfun)),
+ print_bitmap_set (dump_file, TMP_GEN (ENTRY_BLOCK_PTR_FOR_FN (fun)),
"tmp_gen", ENTRY_BLOCK);
- print_bitmap_set (dump_file, AVAIL_OUT (ENTRY_BLOCK_PTR_FOR_FN (cfun)),
+ print_bitmap_set (dump_file, AVAIL_OUT (ENTRY_BLOCK_PTR_FOR_FN (fun)),
"avail_out", ENTRY_BLOCK);
}
/* Allocate the worklist. */
- worklist = XNEWVEC (basic_block, n_basic_blocks_for_fn (cfun));
+ worklist = XNEWVEC (basic_block, n_basic_blocks_for_fn (fun));
/* Seed the algorithm by putting the dominator children of the entry
block on the worklist. */
- for (son = first_dom_son (CDI_DOMINATORS, ENTRY_BLOCK_PTR_FOR_FN (cfun));
+ for (son = first_dom_son (CDI_DOMINATORS, ENTRY_BLOCK_PTR_FOR_FN (fun));
son;
son = next_dom_son (CDI_DOMINATORS, son))
worklist[sp++] = son;
- BB_LIVE_VOP_ON_EXIT (ENTRY_BLOCK_PTR_FOR_FN (cfun))
- = ssa_default_def (cfun, gimple_vop (cfun));
+ BB_LIVE_VOP_ON_EXIT (ENTRY_BLOCK_PTR_FOR_FN (fun))
+ = ssa_default_def (fun, gimple_vop (fun));
/* Loop until the worklist is empty. */
while (sp)
@@ -3970,7 +3977,8 @@ compute_avail (void)
before it. */
int flags = gimple_call_flags (stmt);
if (!(flags & ECF_CONST)
- || (flags & ECF_LOOPING_CONST_OR_PURE))
+ || (flags & ECF_LOOPING_CONST_OR_PURE)
+ || stmt_can_throw_external (fun, stmt))
BB_MAY_NOTRETURN (block) = 1;
}
@@ -3987,7 +3995,7 @@ compute_avail (void)
BB_LIVE_VOP_ON_EXIT (block) = gimple_vdef (stmt);
if (gimple_has_side_effects (stmt)
- || stmt_could_throw_p (cfun, stmt)
+ || stmt_could_throw_p (fun, stmt)
|| is_gimple_debug (stmt))
continue;
@@ -4384,7 +4392,7 @@ pass_pre::execute (function *fun)
we require AVAIL. */
if (n_basic_blocks_for_fn (fun) < 4000)
{
- compute_avail ();
+ compute_avail (fun);
compute_antic ();
insert ();
}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-Os - Build # 21 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-Os. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-Os
Culprit:
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
</cut>
Results regressed to (for first_bad == 0b92cf305dcf34387a8e2564e55ca8948df3b47a)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -Os_mthumb -- artifacts/build-0b92cf305dcf34387a8e2564e55ca8948df3b47a/results_id:
1
# 447.dealII,[.] _ZSt18_Rb_tree_incrementPKSt18_Rb_tree_node_ba regressed by 1150
from (for last_good == 7552c36afa1f9058bb39f336ae84f019621885a0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -Os_mthumb -- artifacts/build-7552c36afa1f9058bb39f336ae84f019621885a0/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-Os/2301
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-Os/2288
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
cd investigate-gcc-0b92cf305dcf34387a8e2564e55ca8948df3b47a
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 0b92cf305dcf34387a8e2564e55ca8948df3b47a
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 7552c36afa1f9058bb39f336ae84f019621885a0
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 0b92cf305dcf34387a8e2564e55ca8948df3b47a
Author: Jan Hubicka <hubicka(a)ucw.cz>
Date: Tue Oct 1 18:58:35 2019 +0200
invoke.texi (early-inlining-insns-O2): Document.
* doc/invoke.texi (early-inlining-insns-O2): Document.
(early-inlining-insns): Update.
* params.def (early-inlining-insns-O2): New bound.
(early-inlining-insns): Update docs.
* ipa-inline.c (want_early_inline_function_p): Use new bound.
* g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
* g++.dg/tree-ssa/pr8781.C: Likewise.
* g++.dg/warn/Wstringop-truncation-1.C: Likewise.
* gcc.dg/ipa/pr63416.c: likewise.
* gcc.dg/vect/pr66142.c: Likewise.
* gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
From-SVN: r276416
---
gcc/ChangeLog | 8 ++++++++
gcc/doc/invoke.texi | 8 ++++++++
gcc/ipa-inline.c | 22 ++++++++++++++--------
gcc/params.def | 6 +++++-
gcc/testsuite/ChangeLog | 9 +++++++++
gcc/testsuite/g++.dg/tree-ssa/pr61034.C | 2 +-
gcc/testsuite/g++.dg/tree-ssa/pr8781.C | 2 +-
gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C | 2 +-
gcc/testsuite/gcc.dg/ipa/pr63416.c | 2 +-
gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c | 2 +-
gcc/testsuite/gcc.dg/vect/pr66142.c | 2 +-
11 files changed, 50 insertions(+), 15 deletions(-)
diff --git a/gcc/ChangeLog b/gcc/ChangeLog
index bb4de20ab16..b4c4292c299 100644
--- a/gcc/ChangeLog
+++ b/gcc/ChangeLog
@@ -1,3 +1,11 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * doc/invoke.texi (early-inlining-insns-O2): Document.
+ (early-inlining-insns): Update.
+ * params.def (early-inlining-insns-O2): New bound.
+ (early-inlining-insns): Update docs.
+ * ipa-inline.c (want_early_inline_function_p): Use new bound.
+
2019-10-01 Oleg Endo <olegendo(a)gcc.gnu.org>
PR target/88562
diff --git a/gcc/doc/invoke.texi b/gcc/doc/invoke.texi
index 83016a5a8ee..4281ee7c614 100644
--- a/gcc/doc/invoke.texi
+++ b/gcc/doc/invoke.texi
@@ -11291,9 +11291,17 @@ recursion depth can be guessed from the probability that function recurses
via a given call expression. This parameter limits inlining only to call
expressions whose probability exceeds the given threshold (in percents).
+@item early-inlining-insns-O2
+Specify growth that the early inliner can make. In effect it increases
+the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O1} or @option{-O2}
+optimization levels.
+
@item early-inlining-insns
Specify growth that the early inliner can make. In effect it increases
the amount of inlining for code having a large abstraction penalty.
+This is applied to functions compiled with @option{-O3} or @option{-Ofast}
+optimization levels.
@item max-early-inliner-iterations
Limit of iterations of the early inliner. This basically bounds
diff --git a/gcc/ipa-inline.c b/gcc/ipa-inline.c
index b62d280eb25..c8689c7d9a8 100644
--- a/gcc/ipa-inline.c
+++ b/gcc/ipa-inline.c
@@ -641,6 +641,10 @@ want_early_inline_function_p (struct cgraph_edge *e)
{
int growth = estimate_edge_growth (e);
int n;
+ int early_inlining_insns = opt_for_fn (e->caller->decl, optimize) >= 3
+ ? PARAM_VALUE (PARAM_EARLY_INLINING_INSNS)
+ : PARAM_VALUE (PARAM_EARLY_INLINING_INSNS_O2);
+
if (growth <= PARAM_VALUE (PARAM_MAX_INLINE_INSNS_SIZE))
;
@@ -654,26 +658,28 @@ want_early_inline_function_p (struct cgraph_edge *e)
growth);
want_inline = false;
}
- else if (growth > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ else if (growth > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns\n",
- e->caller, callee,
- growth);
+ "growth %i exceeds --param early-inlining-insns%s\n",
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
else if ((n = num_calls (callee)) != 0
- && growth * (n + 1) > PARAM_VALUE (PARAM_EARLY_INLINING_INSNS))
+ && growth * (n + 1) > early_inlining_insns)
{
if (dump_enabled_p ())
dump_printf_loc (MSG_MISSED_OPTIMIZATION, e->call_stmt,
" will not early inline: %C->%C, "
- "growth %i exceeds --param early-inlining-insns "
+ "growth %i exceeds --param early-inlining-insns%s "
"divided by number of calls\n",
- e->caller, callee,
- growth);
+ e->caller, callee, growth,
+ opt_for_fn (e->caller->decl, optimize) >= 3
+ ? "" : "-O2");
want_inline = false;
}
}
diff --git a/gcc/params.def b/gcc/params.def
index d2d957fc6b1..0acf29b6c4d 100644
--- a/gcc/params.def
+++ b/gcc/params.def
@@ -233,8 +233,12 @@ DEFPARAM(PARAM_IPCP_UNIT_GROWTH,
10, 0, 0)
DEFPARAM(PARAM_EARLY_INLINING_INSNS,
"early-inlining-insns",
- "Maximal estimated growth of function body caused by early inlining of single call.",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O3 and -Ofast.",
14, 0, 0)
+DEFPARAM(PARAM_EARLY_INLINING_INSNS_O2,
+ "early-inlining-insns-O2",
+ "Maximal estimated growth of function body caused by early inlining of single call with -O1 and -O2.",
+ 6, 0, 0)
DEFPARAM(PARAM_LARGE_STACK_FRAME,
"large-stack-frame",
"The size of stack frame to be considered large.",
diff --git a/gcc/testsuite/ChangeLog b/gcc/testsuite/ChangeLog
index df6105f3d13..0dcaf4b6292 100644
--- a/gcc/testsuite/ChangeLog
+++ b/gcc/testsuite/ChangeLog
@@ -1,3 +1,12 @@
+2019-10-01 Jan Hubicka <hubicka(a)ucw.cz>
+
+ * g++.dg/tree-ssa/pr61034.C: Set early-inlining-insns-O2=14.
+ * g++.dg/tree-ssa/pr8781.C: Likewise.
+ * g++.dg/warn/Wstringop-truncation-1.C: Likewise.
+ * gcc.dg/ipa/pr63416.c: likewise.
+ * gcc.dg/vect/pr66142.c: Likewise.
+ * gcc.dg/tree-ssa/ssa-thread-12.c: Mark compure_idf inline.
+
2019-10-01 Jakub Jelinek <jakub(a)redhat.com>
PR c++/91925
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
index 870b2372166..2e3dfecacb4 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr61034.C
@@ -1,5 +1,5 @@
// { dg-do compile }
-// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks" }
+// { dg-options "-O2 -fdump-tree-fre3 -fdump-tree-optimized -fdelete-null-pointer-checks --param early-inlining-insns-O2=14" }
#define assume(x) if(!(x))__builtin_unreachable()
diff --git a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
index 1f115b2b26d..5bc1ef03520 100644
--- a/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
+++ b/gcc/testsuite/g++.dg/tree-ssa/pr8781.C
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1" } */
+/* { dg-options "-O -fno-tree-sra -fdump-tree-fre1 --param early-inlining-insns-O2=14" } */
int f();
diff --git a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
index 83066019772..49dde0a65ba 100644
--- a/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
+++ b/gcc/testsuite/g++.dg/warn/Wstringop-truncation-1.C
@@ -1,7 +1,7 @@
/* PR/tree-optimization/84480 - bogus -Wstringop-truncation despite
assignment with an inlined string literal
{ dg-do compile }
- { dg-options "-O2 -Wstringop-truncation" } */
+ { dg-options "-O2 -Wstringop-truncation --param early-inlining-insns-O2=14" } */
#include <string.h>
diff --git a/gcc/testsuite/gcc.dg/ipa/pr63416.c b/gcc/testsuite/gcc.dg/ipa/pr63416.c
index b5374c51fe9..5873954fba3 100644
--- a/gcc/testsuite/gcc.dg/ipa/pr63416.c
+++ b/gcc/testsuite/gcc.dg/ipa/pr63416.c
@@ -1,5 +1,5 @@
/* { dg-do compile } */
-/* { dg-options "-O2 -fdump-tree-optimized" } */
+/* { dg-options "-O2 -fdump-tree-optimized --param early-inlining-insns-O2=14" } */
#define _UNUSED_ __attribute__((__unused__))
typedef int TEST_F30 (int *v);
diff --git a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
index 67526762f2c..216de23d791 100644
--- a/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
+++ b/gcc/testsuite/gcc.dg/tree-ssa/ssa-thread-12.c
@@ -56,7 +56,7 @@ bmp_iter_and_compl (bitmap_iterator * bi, unsigned *bit_no)
}
extern int VEC_int_base_length (VEC_int_base *);
-bitmap
+inline bitmap
compute_idf (bitmap def_blocks, bitmap_head * dfs)
{
bitmap_iterator bi;
diff --git a/gcc/testsuite/gcc.dg/vect/pr66142.c b/gcc/testsuite/gcc.dg/vect/pr66142.c
index 8c79f290767..a0316f1f01e 100644
--- a/gcc/testsuite/gcc.dg/vect/pr66142.c
+++ b/gcc/testsuite/gcc.dg/vect/pr66142.c
@@ -1,6 +1,6 @@
/* PR middle-end/66142 */
/* { dg-do compile } */
-/* { dg-additional-options "-ffast-math -fopenmp-simd" } */
+/* { dg-additional-options "-ffast-math -fopenmp-simd --param early-inlining-insns-O2=14" } */
/* { dg-additional-options "-mavx" { target avx_runtime } } */
struct A { float x, y; };
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O3_LTO - Build # 21 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O3_LTO
Culprit:
<cut>
commit a41f076ef1d611fcd255514d0c19cb06375e49b2
Author: Fangrui Song <i(a)maskray.me>
Date: Mon Apr 26 16:04:22 2021 -0700
[test] Fix tools/gold/X86/weak.ll after D94202
The order regressed after D94202: after `a b`, when adding `a c`, we may reorder
`a` to the right of `b`, causing the final order to be `b a c`.
</cut>
Results regressed to (for first_bad == a41f076ef1d611fcd255514d0c19cb06375e49b2)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO -- artifacts/build-a41f076ef1d611fcd255514d0c19cb06375e49b2/results_id:
1
# 447.dealII,dealII_base.default regressed by 107
from (for last_good == 262a72f50f1887591558ce0f521a5f7d3a17e2c2)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO -- artifacts/build-262a72f50f1887591558ce0f521a5f7d3a17e2c2/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3_LTO/2269
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O3_LTO/2253
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-a41f076ef1d611fcd255514d0c19cb06375e49b2
cd investigate-llvm-a41f076ef1d611fcd255514d0c19cb06375e49b2
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach a41f076ef1d611fcd255514d0c19cb06375e49b2
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 262a72f50f1887591558ce0f521a5f7d3a17e2c2
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit a41f076ef1d611fcd255514d0c19cb06375e49b2
Author: Fangrui Song <i(a)maskray.me>
Date: Mon Apr 26 16:04:22 2021 -0700
[test] Fix tools/gold/X86/weak.ll after D94202
The order regressed after D94202: after `a b`, when adding `a c`, we may reorder
`a` to the right of `b`, causing the final order to be `b a c`.
---
llvm/test/tools/gold/X86/Inputs/weak.ll | 1 +
llvm/test/tools/gold/X86/weak.ll | 3 ++-
2 files changed, 3 insertions(+), 1 deletion(-)
diff --git a/llvm/test/tools/gold/X86/Inputs/weak.ll b/llvm/test/tools/gold/X86/Inputs/weak.ll
index 5209d343f23f..8aba5b261001 100644
--- a/llvm/test/tools/gold/X86/Inputs/weak.ll
+++ b/llvm/test/tools/gold/X86/Inputs/weak.ll
@@ -1,3 +1,4 @@
+target triple = "x86_64-unknown-linux-gnu"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
@a = weak global i32 41
diff --git a/llvm/test/tools/gold/X86/weak.ll b/llvm/test/tools/gold/X86/weak.ll
index 384a0ab3ae8c..340de107b43b 100644
--- a/llvm/test/tools/gold/X86/weak.ll
+++ b/llvm/test/tools/gold/X86/weak.ll
@@ -6,6 +6,7 @@
; RUN: -shared %t.o %t2.o -o %t3.o
; RUN: llvm-dis %t3.o -o - | FileCheck %s
+target triple = "x86_64-unknown-linux-gnu"
target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
@a = weak global i32 42
@@ -13,6 +14,6 @@ target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
; Test that @b and @c end up pointing to the same variable.
-; CHECK: @a = weak global i32 42
; CHECK: @b = global i32* @a{{$}}
+; CHECK: @a = weak global i32 42
; CHECK: @c = global i32* @a{{$}}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_stm32/gnu_eabi-master-arm_eabi-coremark-Os - Build # 12 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_eabi_stm32/gnu_eabi-master-arm_eabi-coremark-Os. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_eabi_stm32/gnu_eabi-master-arm_eabi-coremark-Os
Culprit:
<cut>
commit 784de5292c34e287c848b382b431599b818ea76e
Author: Jakub Jelinek <jakub(a)redhat.com>
Date: Fri Apr 16 09:34:26 2021 +0200
c++: Fix up C++23 [] <...> requires primary -> type {} parsing [PR99850]
The requires clause parsing has code to suggest users wrapping
non-primary expressions in (), so if it e.g. parses a primary expression
and sees it is followed by ++, --, ., ( or -> among other things it
will try to reparse it as assignment expression or what and if that works
suggests wrapping it inside of parens.
When it is requires-clause that is after <typename T> etc. it already
has an exception from that as ( can occur in valid C++20 expression there
- starting the parameters of the lambda.
In C++23 another case can occur, as the parameters with the ()s can be
omitted, requires C can be followed immediately by -> which starts a
trailing return type. Even in that case, we don't want to parse that
as C->...
2021-04-16 Jakub Jelinek <jakub(a)redhat.com>
PR c++/99850
* parser.c (cp_parser_constraint_requires_parens) <case CPP_DEREF>:
If lambda_p, return pce_ok instead of pce_maybe_postfix.
* g++.dg/cpp23/lambda-specifiers2.C: New test.
</cut>
Results regressed to (for first_bad == 784de5292c34e287c848b382b431599b818ea76e)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-8
# build_abe newlib:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-5
# true:
0
# benchmark -Os_mthumb -- artifacts/build-784de5292c34e287c848b382b431599b818ea76e/results_id:
1
from (for last_good == 20eb7a1891cfd7fa85295a236cebe0322d041edd)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-8
# build_abe newlib:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-5
# true:
0
# benchmark -Os_mthumb -- artifacts/build-baseline/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Results ID of last_good: stm32_STM32L476RGTx/tcwg_bmk_gnu_eabi_stm32/baseline-gnu_eabi-master-arm_eabi-coremark-Os/2215
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Results ID of first_bad: stm32_STM32L476RGTx/tcwg_bmk_gnu_eabi_stm32/bisect-gnu_eabi-master-arm_eabi-coremark-Os/2252
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-784de5292c34e287c848b382b431599b818ea76e
cd investigate-gcc-784de5292c34e287c848b382b431599b818ea76e
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach 784de5292c34e287c848b382b431599b818ea76e
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 20eb7a1891cfd7fa85295a236cebe0322d041edd
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Full commit (up to 1000 lines):
<cut>
commit 784de5292c34e287c848b382b431599b818ea76e
Author: Jakub Jelinek <jakub(a)redhat.com>
Date: Fri Apr 16 09:34:26 2021 +0200
c++: Fix up C++23 [] <...> requires primary -> type {} parsing [PR99850]
The requires clause parsing has code to suggest users wrapping
non-primary expressions in (), so if it e.g. parses a primary expression
and sees it is followed by ++, --, ., ( or -> among other things it
will try to reparse it as assignment expression or what and if that works
suggests wrapping it inside of parens.
When it is requires-clause that is after <typename T> etc. it already
has an exception from that as ( can occur in valid C++20 expression there
- starting the parameters of the lambda.
In C++23 another case can occur, as the parameters with the ()s can be
omitted, requires C can be followed immediately by -> which starts a
trailing return type. Even in that case, we don't want to parse that
as C->...
2021-04-16 Jakub Jelinek <jakub(a)redhat.com>
PR c++/99850
* parser.c (cp_parser_constraint_requires_parens) <case CPP_DEREF>:
If lambda_p, return pce_ok instead of pce_maybe_postfix.
* g++.dg/cpp23/lambda-specifiers2.C: New test.
---
gcc/cp/parser.c | 13 +++++++++++++
gcc/testsuite/g++.dg/cpp23/lambda-specifiers2.C | 7 +++++++
2 files changed, 20 insertions(+)
diff --git a/gcc/cp/parser.c b/gcc/cp/parser.c
index 940751b5f05..dfc9b8251a7 100644
--- a/gcc/cp/parser.c
+++ b/gcc/cp/parser.c
@@ -28530,7 +28530,20 @@ cp_parser_constraint_requires_parens (cp_parser *parser, bool lambda_p)
case CPP_PLUS_PLUS:
case CPP_MINUS_MINUS:
case CPP_DOT:
+ /* Unenclosed postfix operator. */
+ return pce_maybe_postfix;
+
case CPP_DEREF:
+ /* A primary constraint that precedes the lambda-declarator of a
+ lambda expression is followed by trailing return type.
+
+ []<typename T> requires C -> void {}
+
+ Don't try to re-parse this as a postfix expression in
+ C++23 and later. In C++20 ( needs to come in between but we
+ allow it to be omitted with pedwarn. */
+ if (lambda_p)
+ return pce_ok;
/* Unenclosed postfix operator. */
return pce_maybe_postfix;
}
diff --git a/gcc/testsuite/g++.dg/cpp23/lambda-specifiers2.C b/gcc/testsuite/g++.dg/cpp23/lambda-specifiers2.C
new file mode 100644
index 00000000000..0cc69bebc64
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp23/lambda-specifiers2.C
@@ -0,0 +1,7 @@
+// PR c++/99850
+// P1102R2 - Down with ()!
+// { dg-do compile { target c++23 } }
+
+auto l = []<auto> requires true -> void {};
+template <typename...> concept C = true;
+auto m = []<typename... Ts> requires (C<Ts> && ...) -> void {};
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/gnu-master-aarch64-spec2k6-O2 - Build # 23 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tx1/gnu-master-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tx1/gnu-master-aarch64-spec2k6-O2
Culprit:
<cut>
commit d999d9b7e53b9a9cd2004a19e84c637e5e5013f5
Author: Patrick Palka <ppalka(a)redhat.com>
Date: Thu Jun 3 09:39:13 2021 -0400
c++: cv-qualified dependent name of alias tmpl [PR100592]
Here, the dependent template name in the return type of f() resolves to
an alias of int& after substitution, and we end up complaining about
qualifying this reference type with 'const' from cp_build_qualified_type
rather than just silently dropping the qualification as per [dcl.ref]/1.
The problem is ultimately that make_typename_type ignores the
tf_keep_type_decl flag when the dependent name is a template-id. This
in turn causes the TYPE_DECL check within tsubst <case TYPENAME_TYPE>
to fail, and so we end up not passing tf_ignore_bad_quals to
cp_build_qualified_type. This patch fixes this by making
make_typename_type respect the tf_keep_type_decl flag in this situation.
PR c++/100592
gcc/cp/ChangeLog:
* decl.c (make_typename_type): After calling
lookup_template_class, adjust the result to its TYPE_NAME and
then consider the tf_keep_type_decl flag.
gcc/testsuite/ChangeLog:
* g++.dg/cpp0x/alias-decl-71.C: New test.
</cut>
Results regressed to (for first_bad == d999d9b7e53b9a9cd2004a19e84c637e5e5013f5)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2 -- artifacts/build-d999d9b7e53b9a9cd2004a19e84c637e5e5013f5/results_id:
1
# 447.dealII,dealII_base.default regressed by 103
# 447.dealII,[.] _ZNK8MappingQILi3EE19transform_covariantEP6Ten regressed by 117
from (for last_good == 69f517ac20566a645ff41a9bfca535822205a538)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2 -- artifacts/build-69f517ac20566a645ff41a9bfca535822205a538/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Results ID of last_good: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-master-aarch64-spec2k6-O2/2208
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Results ID of first_bad: tx1_64/tcwg_bmk_gnu_tx1/bisect-gnu-master-aarch64-spec2k6-O2/2248
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-d999d9b7e53b9a9cd2004a19e84c637e5e5013f5
cd investigate-gcc-d999d9b7e53b9a9cd2004a19e84c637e5e5013f5
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach d999d9b7e53b9a9cd2004a19e84c637e5e5013f5
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 69f517ac20566a645ff41a9bfca535822205a538
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tx1-gnu-master-aa…
Full commit (up to 1000 lines):
<cut>
commit d999d9b7e53b9a9cd2004a19e84c637e5e5013f5
Author: Patrick Palka <ppalka(a)redhat.com>
Date: Thu Jun 3 09:39:13 2021 -0400
c++: cv-qualified dependent name of alias tmpl [PR100592]
Here, the dependent template name in the return type of f() resolves to
an alias of int& after substitution, and we end up complaining about
qualifying this reference type with 'const' from cp_build_qualified_type
rather than just silently dropping the qualification as per [dcl.ref]/1.
The problem is ultimately that make_typename_type ignores the
tf_keep_type_decl flag when the dependent name is a template-id. This
in turn causes the TYPE_DECL check within tsubst <case TYPENAME_TYPE>
to fail, and so we end up not passing tf_ignore_bad_quals to
cp_build_qualified_type. This patch fixes this by making
make_typename_type respect the tf_keep_type_decl flag in this situation.
PR c++/100592
gcc/cp/ChangeLog:
* decl.c (make_typename_type): After calling
lookup_template_class, adjust the result to its TYPE_NAME and
then consider the tf_keep_type_decl flag.
gcc/testsuite/ChangeLog:
* g++.dg/cpp0x/alias-decl-71.C: New test.
---
gcc/cp/decl.c | 13 +++++++++----
gcc/testsuite/g++.dg/cpp0x/alias-decl-71.C | 13 +++++++++++++
2 files changed, 22 insertions(+), 4 deletions(-)
diff --git a/gcc/cp/decl.c b/gcc/cp/decl.c
index fb21a3a1ae8..a3687dbb0dd 100644
--- a/gcc/cp/decl.c
+++ b/gcc/cp/decl.c
@@ -4136,10 +4136,15 @@ make_typename_type (tree context, tree name, enum tag_types tag_type,
return error_mark_node;
if (want_template)
- return lookup_template_class (t, TREE_OPERAND (fullname, 1),
- NULL_TREE, context,
- /*entering_scope=*/0,
- complain | tf_user);
+ {
+ t = lookup_template_class (t, TREE_OPERAND (fullname, 1),
+ NULL_TREE, context,
+ /*entering_scope=*/0,
+ complain | tf_user);
+ if (t == error_mark_node)
+ return error_mark_node;
+ t = TYPE_NAME (t);
+ }
if (DECL_ARTIFICIAL (t) || !(complain & tf_keep_type_decl))
t = TREE_TYPE (t);
diff --git a/gcc/testsuite/g++.dg/cpp0x/alias-decl-71.C b/gcc/testsuite/g++.dg/cpp0x/alias-decl-71.C
new file mode 100644
index 00000000000..6a61f93a0b0
--- /dev/null
+++ b/gcc/testsuite/g++.dg/cpp0x/alias-decl-71.C
@@ -0,0 +1,13 @@
+// PR c++/100592
+// { dg-do compile { target c++11 } }
+
+template<bool>
+struct meta {
+ template<class> using if_c = int&;
+};
+
+template<bool B>
+typename meta<B>::template if_c<void> const f();
+
+using type = decltype(f<true>());
+using type = int&;
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_stm32/gnu_eabi-release-arm_eabi-coremark-Os_LTO - Build # 1 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_eabi_stm32/gnu_eabi-release-arm_eabi-coremark-Os_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_eabi_stm32/gnu_eabi-release-arm_eabi-coremark-Os_LTO
Culprit:
<cut>
commit e9cc5cc589ca3fac2738c9def311e6079172f79f
Author: Martin Liska <mliska(a)suse.cz>
Date: Wed Apr 14 15:39:10 2021 +0200
Sync gcc-changelog scripts.
contrib/ChangeLog:
* gcc-changelog/git_commit.py: Sync with master.
* gcc-changelog/git_email.py: Likewise.
* gcc-changelog/git_update_version.py: Likewise.
* gcc-changelog/setup.cfg: Likewise.
* gcc-changelog/test_email.py: Likewise.
* gcc-changelog/test_patches.txt: Likewise.
</cut>
Results regressed to (for first_bad == e9cc5cc589ca3fac2738c9def311e6079172f79f)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-8
# build_abe newlib:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-5
# true:
0
# benchmark -Os_LTO_mthumb -- artifacts/build-e9cc5cc589ca3fac2738c9def311e6079172f79f/results_id:
1
from (for last_good == 062b65404f0d139d683411d88e46f972cdd3b372)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-8
# build_abe newlib:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer --set gcc_override_configure=--disable-multilib --set gcc_override_configure=--with-cpu=cortex-m4 --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--with-float=hard:
-5
# true:
0
# benchmark -Os_LTO_mthumb -- artifacts/build-baseline/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Results ID of last_good: stm32_STM32L476RGTx/tcwg_bmk_gnu_eabi_stm32/baseline-gnu_eabi-release-arm_eabi-coremark-Os_LTO/2198
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Results ID of first_bad: stm32_STM32L476RGTx/tcwg_bmk_gnu_eabi_stm32/bisect-gnu_eabi-release-arm_eabi-coremark-Os_LTO/2212
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-e9cc5cc589ca3fac2738c9def311e6079172f79f
cd investigate-gcc-e9cc5cc589ca3fac2738c9def311e6079172f79f
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
mkdir -p ./bisect
rsync -a --del --delete-excluded --exclude /bisect/ --exclude /artifacts/ --exclude /gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach e9cc5cc589ca3fac2738c9def311e6079172f79f
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 062b65404f0d139d683411d88e46f972cdd3b372
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu_eabi-bisect-tcwg_bmk_stm32-gnu_ea…
Full commit (up to 1000 lines):
<cut>
commit e9cc5cc589ca3fac2738c9def311e6079172f79f
Author: Martin Liska <mliska(a)suse.cz>
Date: Wed Apr 14 15:39:10 2021 +0200
Sync gcc-changelog scripts.
contrib/ChangeLog:
* gcc-changelog/git_commit.py: Sync with master.
* gcc-changelog/git_email.py: Likewise.
* gcc-changelog/git_update_version.py: Likewise.
* gcc-changelog/setup.cfg: Likewise.
* gcc-changelog/test_email.py: Likewise.
* gcc-changelog/test_patches.txt: Likewise.
---
contrib/gcc-changelog/git_commit.py | 51 ++++++++--
contrib/gcc-changelog/git_email.py | 2 +-
contrib/gcc-changelog/git_update_version.py | 4 +
contrib/gcc-changelog/setup.cfg | 3 +
contrib/gcc-changelog/test_email.py | 20 ++++
contrib/gcc-changelog/test_patches.txt | 147 ++++++++++++++++++++++++++++
6 files changed, 219 insertions(+), 8 deletions(-)
diff --git a/contrib/gcc-changelog/git_commit.py b/contrib/gcc-changelog/git_commit.py
index ee1973371be..b28f7deac23 100755
--- a/contrib/gcc-changelog/git_commit.py
+++ b/contrib/gcc-changelog/git_commit.py
@@ -214,6 +214,7 @@ class ChangeLogEntry:
self.lines = []
self.files = []
self.file_patterns = []
+ self.opened_parentheses = 0
def parse_file_names(self):
# Whether the content currently processed is between a star prefix the
@@ -223,8 +224,14 @@ class ChangeLogEntry:
for line in self.lines:
# If this line matches the star prefix, start the location
# processing on the information that follows the star.
+ # Note that we need to skip macro names that can be in form of:
+ #
+ # * config/i386/i386.md (*fix_trunc<mode>_i387_1,
+ # *add<mode>3_ne, *add<mode>3_eq_0, *add<mode>3_ne_0,
+ # *fist<mode>2_<rounding>_1, *<code><mode>3_1):
+ #
m = star_prefix_regex.match(line)
- if m:
+ if m and len(m.group('spaces')) == 1:
in_location = True
line = m.group('content')
@@ -307,8 +314,9 @@ class GitCommit:
if self.revert_commit:
self.info = self.commit_to_info_hook(self.revert_commit)
+ # Allow complete deletion of ChangeLog files in a commit
project_files = [f for f in self.info.modified_files
- if self.is_changelog_filename(f[0])
+ if (self.is_changelog_filename(f[0], allow_suffix=True) and f[1] != 'D')
or f[0] in misc_files]
ignored_files = [f for f in self.info.modified_files
if self.in_ignored_location(f[0])]
@@ -328,6 +336,7 @@ class GitCommit:
self.parse_changelog()
self.parse_file_names()
self.check_for_empty_description()
+ self.check_for_broken_parentheses()
self.deduce_changelog_locations()
self.check_file_patterns()
if not self.errors:
@@ -343,8 +352,14 @@ class GitCommit:
return [x[0] for x in self.info.modified_files if x[1] == 'A']
@classmethod
- def is_changelog_filename(cls, path):
- return path.endswith('/ChangeLog') or path == 'ChangeLog'
+ def is_changelog_filename(cls, path, allow_suffix=False):
+ basename = os.path.basename(path)
+ if basename == 'ChangeLog':
+ return True
+ elif allow_suffix and basename.startswith('ChangeLog'):
+ return True
+ else:
+ return False
@classmethod
def find_changelog_location(cls, name):
@@ -400,8 +415,10 @@ class GitCommit:
if line != line.rstrip():
self.errors.append(Error('trailing whitespace', line))
if len(line.replace('\t', ' ' * TAB_WIDTH)) > LINE_LIMIT:
- self.errors.append(Error('line exceeds %d character limit'
- % LINE_LIMIT, line))
+ # support long filenames
+ if not line.startswith('\t* ') or not line.endswith(':') or ' ' in line[3:-1]:
+ self.errors.append(Error('line exceeds %d character limit'
+ % LINE_LIMIT, line))
m = changelog_regex.match(line)
if m:
last_entry = ChangeLogEntry(m.group(1).rstrip('/'),
@@ -490,7 +507,8 @@ class GitCommit:
else:
m = star_prefix_regex.match(line)
if m:
- if len(m.group('spaces')) != 1:
+ if (len(m.group('spaces')) != 1 and
+ last_entry.opened_parentheses == 0):
msg = 'one space should follow asterisk'
self.errors.append(Error(msg, line))
else:
@@ -502,6 +520,7 @@ class GitCommit:
msg = f'empty group "{needle}" found'
self.errors.append(Error(msg, line))
last_entry.lines.append(line)
+ self.process_parentheses(last_entry, line)
else:
if last_entry.is_empty:
msg = 'first line should start with a tab, ' \
@@ -509,6 +528,18 @@ class GitCommit:
self.errors.append(Error(msg, line))
else:
last_entry.lines.append(line)
+ self.process_parentheses(last_entry, line)
+
+ def process_parentheses(self, last_entry, line):
+ for c in line:
+ if c == '(':
+ last_entry.opened_parentheses += 1
+ elif c == ')':
+ if last_entry.opened_parentheses == 0:
+ msg = 'bad wrapping of parenthesis'
+ self.errors.append(Error(msg, line))
+ else:
+ last_entry.opened_parentheses -= 1
def parse_file_names(self):
for entry in self.changelog_entries:
@@ -532,6 +563,12 @@ class GitCommit:
msg = 'missing description of a change'
self.errors.append(Error(msg, line))
+ def check_for_broken_parentheses(self):
+ for entry in self.changelog_entries:
+ if entry.opened_parentheses != 0:
+ msg = 'bad parentheses wrapping'
+ self.errors.append(Error(msg, entry.lines[0]))
+
def get_file_changelog_location(self, changelog_file):
for file in self.info.modified_files:
if file[0] == changelog_file:
diff --git a/contrib/gcc-changelog/git_email.py b/contrib/gcc-changelog/git_email.py
index 00ad00458f4..b0547b363aa 100755
--- a/contrib/gcc-changelog/git_email.py
+++ b/contrib/gcc-changelog/git_email.py
@@ -66,7 +66,7 @@ class GitEmail(GitCommit):
t = 'A'
else:
t = 'M'
- modified_files.append((target, t))
+ modified_files.append((target if t != 'D' else source, t))
git_info = GitInfo(None, date, author, body, modified_files)
super().__init__(git_info, strict=strict,
commit_to_info_hook=lambda x: None)
diff --git a/contrib/gcc-changelog/git_update_version.py b/contrib/gcc-changelog/git_update_version.py
index d2cadb8811c..1e2b22b008b 100755
--- a/contrib/gcc-changelog/git_update_version.py
+++ b/contrib/gcc-changelog/git_update_version.py
@@ -26,6 +26,9 @@ from git_repository import parse_git_revisions
current_timestamp = datetime.datetime.now().strftime('%Y%m%d\n')
+# Skip the following commits, they cannot be correctly processed
+IGNORED_COMMITS = ('c2be82058fb40f3ae891c68d185ff53e07f14f45')
+
def read_timestamp(path):
with open(path) as f:
@@ -98,6 +101,7 @@ def update_current_branch():
head = head.parents[1]
commits = parse_git_revisions(args.git_path, '%s..%s'
% (commit.hexsha, head.hexsha))
+ commits = [c for c in commits if c.info.hexsha not in IGNORED_COMMITS]
for git_commit in reversed(commits):
prepend_to_changelog_files(repo, args.git_path, git_commit,
not args.dry_mode)
diff --git a/contrib/gcc-changelog/setup.cfg b/contrib/gcc-changelog/setup.cfg
index 9e4a0f6479c..efc313f6d52 100644
--- a/contrib/gcc-changelog/setup.cfg
+++ b/contrib/gcc-changelog/setup.cfg
@@ -1,2 +1,5 @@
+[flake8]
+max-line-length = 120
+
[tool:pytest]
addopts = -vv --flake8
diff --git a/contrib/gcc-changelog/test_email.py b/contrib/gcc-changelog/test_email.py
index 5db56caef9e..8abf5c37487 100755
--- a/contrib/gcc-changelog/test_email.py
+++ b/contrib/gcc-changelog/test_email.py
@@ -404,3 +404,23 @@ class TestGccChangelog(unittest.TestCase):
email = self.from_patch_glob('0001-Add-horse2.patch')
assert not email.errors
assert email.changelog_entries[0].files == ['koníček.txt']
+
+ def test_modification_of_old_changelog(self):
+ email = self.from_patch_glob('0001-fix-old-ChangeLog.patch')
+ assert not email.errors
+
+ def test_multiline_parentheses(self):
+ email = self.from_patch_glob('0001-Add-macro.patch')
+ assert not email.errors
+
+ def test_multiline_bad_parentheses(self):
+ email = self.from_patch_glob('0002-Wrong-macro-changelog.patch')
+ assert email.errors[0].message == 'bad parentheses wrapping'
+
+ def test_changelog_removal(self):
+ email = self.from_patch_glob('0001-ChangeLog-removal.patch', strict=True)
+ assert not email.errors
+
+ def test_long_filenames(self):
+ email = self.from_patch_glob('0001-long-filenames')
+ assert not email.errors
diff --git a/contrib/gcc-changelog/test_patches.txt b/contrib/gcc-changelog/test_patches.txt
index ffd13682d5c..3f9806dc076 100644
--- a/contrib/gcc-changelog/test_patches.txt
+++ b/contrib/gcc-changelog/test_patches.txt
@@ -3398,4 +3398,151 @@ index 00000000000..56c67f58752
--
2.29.2
+=== 0001-fix-old-ChangeLog.patch ===
+From fd498465b2801203089616be9a0e3c1f4fc065a0 Mon Sep 17 00:00:00 2001
+From: Martin Liska <mliska(a)suse.cz>
+Date: Wed, 13 Jan 2021 11:45:37 +0100
+Subject: [PATCH] Fix a changelog.
+
+---
+ gcc/ChangeLog-2020 | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/gcc/ChangeLog-2020 b/gcc/ChangeLog-2020
+index 6553720acad..2c170ef014a 100644
+--- a/gcc/ChangeLog-2020
++++ b/gcc/ChangeLog-2020
+@@ -1 +1,2 @@
+
++
+
+--
+2.29.2
+=== 0001-Add-macro.patch ===
+From 9b7eedc932fe594547fb060b36dfd9e4178c4f9b Mon Sep 17 00:00:00 2001
+From: Martin Liska <mliska(a)suse.cz>
+Date: Wed, 13 Jan 2021 16:26:45 +0100
+Subject: [PATCH 1/2] Add macro.
+
+gcc/ChangeLog:
+
+ * config/i386/i386.md (*fix_trunc<mode>_i387_1, *add<mode>3_eq,
+ *add<mode>3_ne, *add<mode>3_eq_0, *add<mode>3_ne_0, *add<mode>3_eq,
+ *fist<mode>2_<rounding>_1, *<code><mode>3_1, *<code>di3_doubleword):
+ Use ix86_pre_reload_split instead of can_create_pseudo_p in condition.
+ * config/i386/sse.md
+ (*fix_trunc<mode>_i387_1, *add<mode>3_eq,
+ *add<mode>3_ne, *add<mode>3_eq_0, *add<mode>3_ne_0, *add<mode>3_eq,
+ *fist<mode>2_<rounding>_1): This should also work.
+---
+ gcc/config/i386/i386.md | 1 +
+ gcc/config/i386/sse.md | 1 +
+ 2 files changed, 2 insertions(+)
+
+diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
+index b60784a2908..ac63591b33f 100644
+--- a/gcc/config/i386/i386.md
++++ b/gcc/config/i386/i386.md
+@@ -1 +1,2 @@
+
++
+
+diff --git a/gcc/config/i386/sse.md b/gcc/config/i386/sse.md
+index 7f03fc491c3..0e17997db26 100644
+--- a/gcc/config/i386/sse.md
++++ b/gcc/config/i386/sse.md
+@@ -1 +1,2 @@
+
++
+
+--
+2.29.2
+
+=== 0002-Wrong-macro-changelog.patch ===
+From 3542802111d4c6752ac7233ef96655b7fb78aae4 Mon Sep 17 00:00:00 2001
+From: Martin Liska <mliska(a)suse.cz>
+Date: Wed, 13 Jan 2021 16:54:58 +0100
+Subject: [PATCH 2/2] Wrong macro changelog
+
+gcc/ChangeLog:
+ * config/i386/i386.md (*fix_trunc<mode>_i387_1,
+ (foo): Change it.
+---
+ gcc/config/i386/i386.md | 1 +
+ 1 file changed, 1 insertion(+)
+
+diff --git a/gcc/config/i386/i386.md b/gcc/config/i386/i386.md
+index ac63591b33f..ff4d61764e7 100644
+--- a/gcc/config/i386/i386.md
++++ b/gcc/config/i386/i386.md
+@@ -1 +1,2 @@
+
++
+--
+2.29.2
+
+=== 0001-ChangeLog-removal.patch ===
+From b39fadf9df1a9510afcab0a391182da7dc68de24 Mon Sep 17 00:00:00 2001
+From: Martin Liska <mliska(a)suse.cz>
+Date: Fri, 12 Mar 2021 09:10:55 +0100
+Subject: [PATCH] Test ChangeLog removal.
+
+gcc/ChangeLog:
+
+ * ipa-icf.c (make_pass_ipa_icf): Add line.
+---
+diff --git a/gcc/analyzer/ChangeLog b/gcc/analyzer/ChangeLog
+deleted file mode 100644
+index 94e87f6bcde..00000000000
+--- a/gcc/analyzer/ChangeLog
++++ /dev/null
+@@ -1,1 +0,0 @@
+- foo
+diff --git a/gcc/ipa-icf.c b/gcc/ipa-icf.c
+index 5dd33a75c3a..c4ce432cb98 100644
+--- a/gcc/ipa-icf.c
++++ b/gcc/ipa-icf.c
+@@ -3655,3 +3655,4 @@ make_pass_ipa_icf (gcc::context *ctxt)
+ {
+ return new ipa_icf::pass_ipa_icf (ctxt);
+ }
++
+--
+2.30.1
+
+=== 0001-long-filenames ===
+From 0a5b3f87bdac5e61f9a626c795d30f9e93198585 Mon Sep 17 00:00:00 2001
+From: Martin Liska <mliska(a)suse.cz>
+Date: Mon, 12 Apr 2021 13:10:14 +0200
+Subject: [PATCH] libstdc++: Fix some tests that fail in C++20 mode
+
+The linear_congruential_engine negative tests fail with a different
+error in C++20 mode, because double is no longer an invalid type for
+NTTP. Adjust the expected errors.
+
+libstdc++-v3/ChangeLog:
+
+ * testsuite/26_numerics/random/linear_congruential_engine/requirements/non_uint_neg.cc:
+ Adjust expected error for C++20 mode.
+ * testsuite/tr1/5_numerical_facilities/random/linear_congruential/requirements/non_uint_neg.cc:
+ Likewise.
+---
+ .../linear_congruential_engine/requirements/non_uint_neg.cc | 4 +++-
+ .../random/linear_congruential/requirements/non_uint_neg.cc | 3 ++-
+ 2 files changed, 5 insertions(+), 2 deletions(-)
+
+diff --git a/libstdc++-v3/testsuite/26_numerics/random/linear_congruential_engine/requirements/non_uint_neg.cc b/libstdc++-v3/testsuite/26_numerics/random/linear_congruential_engine/requirements/non_uint_neg.cc
+index e04e8ca6972..a36d63c6c7b 100644
+--- a/libstdc++-v3/testsuite/26_numerics/random/linear_congruential_engine/requirements/non_uint_neg.cc
++++ b/libstdc++-v3/testsuite/26_numerics/random/linear_congruential_engine/requirements/non_uint_neg.cc
+@@ -1 +1,2 @@
+
++
+diff --git a/libstdc++-v3/testsuite/tr1/5_numerical_facilities/random/linear_congruential/requirements/non_uint_neg.cc b/libstdc++-v3/testsuite/tr1/5_numerical_facilities/random/linear_congruential/requirements/non_uint_neg.cc
+index 5ad82db1def..53b15f32516 100644
+--- a/libstdc++-v3/testsuite/tr1/5_numerical_facilities/random/linear_congruential/requirements/non_uint_neg.cc
++++ b/libstdc++-v3/testsuite/tr1/5_numerical_facilities/random/linear_congruential/requirements/non_uint_neg.cc
+@@ -1 +1,2 @@
+
++
</cut>
4 years, 1 month
- 1
- 0
clang-aarch64-quick times out on full build
by Galina Kistanova
Dear Linaro Toolchain Working Group,
https://lab.llvm.org/buildbot/#/builders/clang-aarch64-quick builder hits a
timeout when it builds a clean build. It builds incrementally just fine.
Here is an example - https://lab.llvm.org/buildbot#builders/188/builds/1518
The time out is 20 minutes without any TTY, which looks more than enough.
Could you investigate on what test it gets stuck and what would be a proper
fix, please?
Thanks
Galina
4 years, 1 month
- 2
- 1
ILP32 build BKM/script
by Joey Ye
Hi toolchain experts,
Is there any BKM or build script that can build AArch64 ILP32 glibc?
Sincerely appreciate any help from Linaro.
Thanks,
Joey
4 years, 1 month
- 3
- 3
[ACTIVITY] 19 - 23 July 2021
by Prathamesh Kulkarni
== This Week ==
* PR66791 (replace builtins with vector extensions in arm_neon.h intrinsics)
- vshl_n: Submitted patch for review and addressing comments by Richard.
- vmul_n fp: Investigated regression on arm-none-eabi and followed up
with Christophe.
- vmul_n int: Waiting for feedback.
- vld1: Created patch.
* Misc
- Fixed breakage in vect metric CI job due to type annotations.
* Off on thursday
- Public holiday
== Next Week ==
- Continue with PR66791
4 years, 1 month
- 1
- 0
[ACTIVITY] week ending Jul. 25 2021
by Alex Bennée
VirtIO Initiative ([STR-9])
===========================
VirtIO RPMB ([STR-5])
- posted [PATCH] virtio-rpmb: fix the description for multi-block
reads Message-Id: <20210722110903.8769-1-alex.bennee(a)linaro.org>
- Ruchika realised the spec didn't allow for multi-block reads
- she also suggested some [fixes for the C daemon]
- finally spent about 1/2 day on my [hacking branch] but making better
progress now trained ;-)
- create some sub-cards to track what we are doing
[STR-5] <https://projects.linaro.org/browse/STR-5>
[fixes for the C daemon]
<https://github.com/ruchi393/qemu/tree/vhost-user-rpmb-fixes>
[hacking branch] <https://github.com/stsquad/virtio-rpmb/tree/hacking>
QEMU Upstream Work ([UM-2])
===========================
- spent some time pulling together various maintainer trees for final
6.1 PRs
- hopefully [this is the last iteration before Monday]
- posted [PATCH for 6.1 v2 0/5] custom device configs Message-Id:
<20210707131744.26027-1-alex.bennee(a)linaro.org>
- chips away at the mega ARM re-factor patch set
- posted [PATCH v1 0/2] some device emulation documentation cleanup
Message-Id: <20210707184549.24436-1-alex.bennee(a)linaro.org>
- posted [PULL for 6.1 00/40] testing and plugin updates Message-Id:
<20210712122653.11354-1-alex.bennee(a)linaro.org>
- posted [PATCH for 6.1 v3 0/3] tricore fixes Message-Id:
<20210720114057.32053-1-alex.bennee(a)linaro.org>
- various iterations of review of rth's breakpoints
- posted [PULL for 6.1-rc1 00/28] doc, metadata, plugin and testing
updates Message-Id: <20210723170354.18975-1-alex.bennee(a)linaro.org>
[UM-2] <https://projects.linaro.org/browse/UM-2>
[this is the last iteration before Monday]
<https://patchew.org/QEMU/20210709143005.1554-1-alex.bennee@linaro.org/>
Enable plugins by default on TCG builds
- [X] clean-up testing matrix
Write a generic overview of vhost user usage for the manual
Other
=====
- preparing for [LOD discussion]
- some hackbox disk space admin
[LOD discussion]
<https://linaro.atlassian.net/wiki/spaces/LOD/pages/28544303418/2021-07-23+M…>
Completed Reviews [7/7]
=======================
[PATCH v6 0/4] GitLab Custom Runners and Jobs (was: QEMU Gating CI)
Message-Id: <20210608031425.833536-1-crosa(a)redhat.com>
[PATCH v4 00/22] tests/docker: start using libvirt-ci's "lcitool" for dockerfiles
Message-Id: <20210623142245.307776-1-berrange(a)redhat.com>
[PATCH v4 0/5] plugins: New TCG plugin for cache modelling
Message-Id: <20210623125458.450462-1-ma.mandourr(a)gmail.com>
[PATCH v3 0/2] execlog TCG plugin to log instructions
Message-Id: <20210702081307.1653644-1-erdnaxe(a)crans.org>
[PATCH 0/3] ci: use cirrus-run to utilize Cirrus CI from GitLab CI
Message-Id: <20210625172211.451010-1-berrange(a)redhat.com>
[PATCH v3 0/4] virtio: Add vhost-user based RNG
Message-Id: <20210710005929.1702431-1-mathieu.poirier(a)linaro.org>
[PATCH for-6.1 v6 00/17] tcg: breakpoint reorg
Message-Id: <20210720195439.626594-1-richard.henderson(a)linaro.org>
Absences
========
- several days of internet outages made things tricky
- July 26th-29th holiday
- On holiday for large chunks of August
Current Review Queue
====================
Needs reorganising ;-)
--
Alex Bennée
4 years, 1 month
- 1
- 0
[ACTIVITY] report week ending 23 July
by Peter Maydell
Progress:
* UM-2 [QEMU upstream maintainership]
+ Noticed we didn't enforce the M-profile "low 2 bits of SP are always 0"
rule, and wrote a patch to fix that
+ Found and fixed a handful of other corner-case M-profile bugs
+ Some minor docs improvements
* QEMU-406 [QEMU support for MVE (M-profile Vector Extension; Helium)]
+ Implemented the last 4 instruction patterns (VCVT, VRINT), bringing
us to Progress: 210/210 (100%)
+ Found and fixed a few bugs in already-implemented instructions
+ Started looking at how to make the MVE loads/stores correctly
raise alignment faults for unaligned addresses (this runs into
problems because QEMU doesn't currently have a good API for doing
the load/store the way we want to do it and also handling alignment
faults)
+ Remaining TODO list for this task:
- alignment fault behaviour, if not too difficult
- report MVE registers via the gdbstub (pending on the XML format being
fixed by gdb upstream)
- send out patches for code review
-- PMM
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-master-arm-spec2k6-O3_LTO - Build # 14 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O3_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O3_LTO
Culprit:
<cut>
commit c77230856eac2d28eb7bf10985846885c3c8727b
Author: Iain Buclaw <ibuclaw(a)gdcproject.org>
Date: Sat Jul 3 00:13:29 2021 +0200
d: RHS value lost when a target_expr modifies LHS in a cond_expr
To prevent the RHS of an assignment modifying the LHS before the
assignment proper, a target_expr is forced so that function calls that
return with slot optimization modify the temporary instead. This did
not work for conditional expressions however, to give one example. So
now the RHS is always forced to a temporary.
PR d/101282
gcc/d/ChangeLog:
* d-codegen.cc (build_assign): Force target_expr on RHS for non-POD
assignment expressions.
gcc/testsuite/ChangeLog:
* gdc.dg/torture/pr101282.d: New test.
</cut>
Results regressed to (for first_bad == c77230856eac2d28eb7bf10985846885c3c8727b)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO_marm -- artifacts/build-c77230856eac2d28eb7bf10985846885c3c8727b/results_id:
1
# 447.dealII,dealII_base.default regressed by 103
from (for last_good == 6feb628a706e86eb3f303aff388c74bdb29e7381)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3_LTO_marm -- artifacts/build-6feb628a706e86eb3f303aff388c74bdb29e7381/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-O3_LTO/1951
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-O3_LTO/1938
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-c77230856eac2d28eb7bf10985846885c3c8727b
cd investigate-gcc-c77230856eac2d28eb7bf10985846885c3c8727b
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach c77230856eac2d28eb7bf10985846885c3c8727b
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 6feb628a706e86eb3f303aff388c74bdb29e7381
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit c77230856eac2d28eb7bf10985846885c3c8727b
Author: Iain Buclaw <ibuclaw(a)gdcproject.org>
Date: Sat Jul 3 00:13:29 2021 +0200
d: RHS value lost when a target_expr modifies LHS in a cond_expr
To prevent the RHS of an assignment modifying the LHS before the
assignment proper, a target_expr is forced so that function calls that
return with slot optimization modify the temporary instead. This did
not work for conditional expressions however, to give one example. So
now the RHS is always forced to a temporary.
PR d/101282
gcc/d/ChangeLog:
* d-codegen.cc (build_assign): Force target_expr on RHS for non-POD
assignment expressions.
gcc/testsuite/ChangeLog:
* gdc.dg/torture/pr101282.d: New test.
---
gcc/d/d-codegen.cc | 7 +++++++
gcc/testsuite/gdc.dg/torture/pr101282.d | 23 +++++++++++++++++++++++
2 files changed, 30 insertions(+)
diff --git a/gcc/d/d-codegen.cc b/gcc/d/d-codegen.cc
index 9a9447371aa..ce7c17baaaf 100644
--- a/gcc/d/d-codegen.cc
+++ b/gcc/d/d-codegen.cc
@@ -1344,6 +1344,13 @@ build_assign (tree_code code, tree lhs, tree rhs)
d_mark_addressable (lhs);
CALL_EXPR_RETURN_SLOT_OPT (rhs) = true;
}
+ /* If modifying an LHS whose type is marked TREE_ADDRESSABLE. */
+ else if (code == MODIFY_EXPR && TREE_ADDRESSABLE (TREE_TYPE (lhs))
+ && TREE_SIDE_EFFECTS (rhs) && TREE_CODE (rhs) != TARGET_EXPR)
+ {
+ /* LHS may be referenced by the RHS expression, so force a temporary. */
+ rhs = force_target_expr (rhs);
+ }
/* The LHS assignment replaces the temporary in TARGET_EXPR_SLOT. */
if (TREE_CODE (rhs) == TARGET_EXPR)
diff --git a/gcc/testsuite/gdc.dg/torture/pr101282.d b/gcc/testsuite/gdc.dg/torture/pr101282.d
new file mode 100644
index 00000000000..b75d5fc678f
--- /dev/null
+++ b/gcc/testsuite/gdc.dg/torture/pr101282.d
@@ -0,0 +1,23 @@
+// https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101282
+// { dg-do run }
+
+void main()
+{
+ struct S101282
+ {
+ int impl;
+ S101282 opUnary(string op : "-")()
+ {
+ return S101282(-impl);
+ }
+ int opCmp(int i)
+ {
+ return (impl < i) ? -1 : (impl > i) ? 1 : 0;
+ }
+ }
+ auto a = S101282(120);
+ a = -a;
+ assert(a.impl == -120);
+ a = a >= 0 ? a : -a;
+ assert(a.impl == 120);
+}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3 - Build # 6 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3
Culprit:
<cut>
commit 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Mon Oct 12 22:19:17 2020 +0300
Reland "[SCEV] Model ptrtoint(SCEVUnknown) cast not as unknown, but as zext/trunc/self of SCEVUnknown"
This relands commit 1c021c64caef83cccb719c9bf0a2554faa6563af which was
reverted in commit 17cec6a11a12f815052d56a17ef738cf246a2d9a because
an assertion was being triggered, since `BuildConstantFromSCEV()`
wasn't updated to handle the case where the constant we want to truncate
is actually a pointer. I was unsuccessful in coming up with a test case
where we'd end there with constant zext/sext of a pointer,
so i didn't handle those cases there until there is a test case.
Original commit message:
While we indeed can't treat them as no-ops, i believe we can/should
do better than just modelling them as `unknown`. `inttoptr` story
is complicated, but for `ptrtoint`, it seems straight-forward
to model it just as a zext-or-trunc of unknown.
This may be important now that we track towards
making inttoptr/ptrtoint casts not no-op,
and towards preventing folding them into loads/etc
(see D88979/D88789/D88788)
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D88806
</cut>
Results regressed to (for first_bad == 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3 -- artifacts/build-1fb610429308a7c29c5065f5cc35dcc3fd69c8b1/results_id:
1
# 400.perlbench,perlbench_base.default regressed by 104
from (for last_good == 73818f450e3a90fc89eca143ee30777ed7e660e9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3 -- artifacts/build-73818f450e3a90fc89eca143ee30777ed7e660e9/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3/1930
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3/1947
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
cd investigate-llvm-1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 73818f450e3a90fc89eca143ee30777ed7e660e9
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Mon Oct 12 22:19:17 2020 +0300
Reland "[SCEV] Model ptrtoint(SCEVUnknown) cast not as unknown, but as zext/trunc/self of SCEVUnknown"
This relands commit 1c021c64caef83cccb719c9bf0a2554faa6563af which was
reverted in commit 17cec6a11a12f815052d56a17ef738cf246a2d9a because
an assertion was being triggered, since `BuildConstantFromSCEV()`
wasn't updated to handle the case where the constant we want to truncate
is actually a pointer. I was unsuccessful in coming up with a test case
where we'd end there with constant zext/sext of a pointer,
so i didn't handle those cases there until there is a test case.
Original commit message:
While we indeed can't treat them as no-ops, i believe we can/should
do better than just modelling them as `unknown`. `inttoptr` story
is complicated, but for `ptrtoint`, it seems straight-forward
to model it just as a zext-or-trunc of unknown.
This may be important now that we track towards
making inttoptr/ptrtoint casts not no-op,
and towards preventing folding them into loads/etc
(see D88979/D88789/D88788)
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D88806
---
llvm/lib/Analysis/ScalarEvolution.cpp | 50 ++++++--
llvm/lib/Transforms/Utils/SimplifyIndVar.cpp | 2 +-
.../add-expr-pointer-operand-sorting.ll | 4 +-
.../Analysis/ScalarEvolution/no-wrap-add-exprs.ll | 4 +-
.../ScalarEvolution/ptrtoint-constantexpr-loop.ll | 130 ++++++++-------------
llvm/test/Analysis/ScalarEvolution/ptrtoint.ll | 60 +++++-----
llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll | 4 +-
llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll | 4 +-
.../IndVarSimplify/2011-11-01-lftrptr.ll | 16 +--
.../Isl/CodeGen/scev_looking_through_bitcasts.ll | 3 +-
10 files changed, 140 insertions(+), 137 deletions(-)
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 1d3e26b93cb6..74bffc0facdb 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -3505,15 +3505,15 @@ const SCEV *ScalarEvolution::getUMinExpr(SmallVectorImpl<const SCEV *> &Ops) {
}
const SCEV *ScalarEvolution::getSizeOfExpr(Type *IntTy, Type *AllocTy) {
- // We can bypass creating a target-independent
- // constant expression and then folding it back into a ConstantInt.
- // This is just a compile-time optimization.
if (isa<ScalableVectorType>(AllocTy)) {
Constant *NullPtr = Constant::getNullValue(AllocTy->getPointerTo());
Constant *One = ConstantInt::get(IntTy, 1);
Constant *GEP = ConstantExpr::getGetElementPtr(AllocTy, NullPtr, One);
- return getSCEV(ConstantExpr::getPtrToInt(GEP, IntTy));
+ return getUnknown(ConstantExpr::getPtrToInt(GEP, IntTy));
}
+ // We can bypass creating a target-independent
+ // constant expression and then folding it back into a ConstantInt.
+ // This is just a compile-time optimization.
return getConstant(IntTy, getDataLayout().getTypeAllocSize(AllocTy));
}
@@ -6301,6 +6301,36 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
return getSCEV(U->getOperand(0));
break;
+ case Instruction::PtrToInt: {
+ // It's tempting to handle inttoptr and ptrtoint as no-ops,
+ // however this can lead to pointer expressions which cannot safely be
+ // expanded to GEPs because ScalarEvolution doesn't respect
+ // the GEP aliasing rules when simplifying integer expressions.
+ //
+ // However, given
+ // %x = ???
+ // %y = ptrtoint %x
+ // %z = ptrtoint %x
+ // it is safe to say that %y and %z are the same thing.
+ //
+ // So instead of modelling the cast itself as unknown,
+ // since the casts are transparent within SCEV,
+ // we can at least model the casts original value as unknow instead.
+
+ // BUT, there's caveat. If we simply model %x as unknown, unrelated uses
+ // of %x will also see it as unknown, which is obviously bad.
+ // So we can only do this iff %x would be modelled as unknown anyways.
+ auto *OpSCEV = getSCEV(U->getOperand(0));
+ if (isa<SCEVUnknown>(OpSCEV))
+ return getTruncateOrZeroExtend(OpSCEV, U->getType());
+ // If we can model the operand, however, we must fallback to modelling
+ // the whole cast as unknown instead.
+ LLVM_FALLTHROUGH;
+ }
+ case Instruction::IntToPtr:
+ // We can't do this for inttoptr at all, however.
+ return getUnknown(V);
+
case Instruction::SDiv:
// If both operands are non-negative, this is just an udiv.
if (isKnownNonNegative(getSCEV(U->getOperand(0))) &&
@@ -6315,11 +6345,6 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
return getURemExpr(getSCEV(U->getOperand(0)), getSCEV(U->getOperand(1)));
break;
- // It's tempting to handle inttoptr and ptrtoint as no-ops, however this can
- // lead to pointer expressions which cannot safely be expanded to GEPs,
- // because ScalarEvolution doesn't respect the GEP aliasing rules when
- // simplifying integer expressions.
-
case Instruction::GetElementPtr:
return createNodeForGEP(cast<GEPOperator>(U));
@@ -7974,8 +7999,11 @@ static Constant *BuildConstantFromSCEV(const SCEV *V) {
}
case scTruncate: {
const SCEVTruncateExpr *ST = cast<SCEVTruncateExpr>(V);
- if (Constant *CastOp = BuildConstantFromSCEV(ST->getOperand()))
- return ConstantExpr::getTrunc(CastOp, ST->getType());
+ if (Constant *CastOp = BuildConstantFromSCEV(ST->getOperand())) {
+ if (!CastOp->getType()->isPointerTy())
+ return ConstantExpr::getTrunc(CastOp, ST->getType());
+ return ConstantExpr::getPtrToInt(CastOp, ST->getType());
+ }
break;
}
case scAddExpr: {
diff --git a/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp b/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp
index 2d71b0fff889..3e280a66175c 100644
--- a/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp
@@ -427,7 +427,7 @@ static bool willNotOverflow(ScalarEvolution *SE, Instruction::BinaryOps BinOp,
: &ScalarEvolution::getZeroExtendExpr;
// Check ext(LHS op RHS) == ext(LHS) op ext(RHS)
- auto *NarrowTy = cast<IntegerType>(LHS->getType());
+ auto *NarrowTy = cast<IntegerType>(SE->getEffectiveSCEVType(LHS->getType()));
auto *WideTy =
IntegerType::get(NarrowTy->getContext(), NarrowTy->getBitWidth() * 2);
diff --git a/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll b/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll
index 93a3bf4d4c37..e798e2715ba1 100644
--- a/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll
+++ b/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll
@@ -33,9 +33,9 @@ define i32 @d(i32 %base) {
; CHECK-NEXT: %1 = load i32*, i32** @c, align 8
; CHECK-NEXT: --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %sub.ptr.lhs.cast = ptrtoint i32* %1 to i64
-; CHECK-NEXT: --> %sub.ptr.lhs.cast U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT: --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %sub.ptr.sub = sub i64 %sub.ptr.lhs.cast, ptrtoint ([1 x i32]* @b to i64)
-; CHECK-NEXT: --> ((-1 * ptrtoint ([1 x i32]* @b to i64)) + %sub.ptr.lhs.cast) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT: --> ((-1 * @b) + %1) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %sub.ptr.div = sdiv exact i64 %sub.ptr.sub, 4
; CHECK-NEXT: --> %sub.ptr.div U: full-set S: [-2305843009213693952,2305843009213693952) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %arrayidx1 = getelementptr inbounds [1 x i8], [1 x i8]* %arrayidx, i64 0, i64 %sub.ptr.div
diff --git a/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll b/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll
index 5a7bb3c9e5cd..eb669cab0c79 100644
--- a/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll
+++ b/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll
@@ -170,14 +170,14 @@ define void @f3(i8* %x_addr, i8* %y_addr, i32* %tmp_addr) {
%int5 = add i32 %int0, 5
%int.zext = zext i32 %int5 to i64
; CHECK: %int.zext = zext i32 %int5 to i64
-; CHECK-NEXT: --> (1 + (zext i32 (4 + %int0) to i64))<nuw><nsw> U: [1,4294967294) S: [1,4294967297)
+; CHECK-NEXT: --> (1 + (zext i32 (4 + (trunc [16 x i8]* @z_addr to i32)) to i64))<nuw><nsw> U: [1,4294967294) S: [1,4294967297)
%ptr_noalign = bitcast [16 x i8]* @z_addr_noalign to i8*
%int0_na = ptrtoint i8* %ptr_noalign to i32
%int5_na = add i32 %int0_na, 5
%int.zext_na = zext i32 %int5_na to i64
; CHECK: %int.zext_na = zext i32 %int5_na to i64
-; CHECK-NEXT: --> (zext i32 (5 + %int0_na) to i64) U: [0,4294967296) S: [0,4294967296)
+; CHECK-NEXT: --> (zext i32 (5 + (trunc [16 x i8]* @z_addr_noalign to i32)) to i64) U: [0,4294967296) S: [0,4294967296)
%tmp = load i32, i32* %tmp_addr
%mul = and i32 %tmp, -4
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll
index 8cfa041e7552..d0ead6028071 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll
@@ -11,48 +11,31 @@
@global = external hidden global [0 x i8]
define hidden i32* @i64(i8* %arg, i32* %arg10) {
-; PTR64_IDX64-LABEL: 'i64'
-; PTR64_IDX64-NEXT: Classifying expressions for: @i64
-; PTR64_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR64_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: Determining loop execution counts for: @i64
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
-;
-; PTR64_IDX32-LABEL: 'i64'
-; PTR64_IDX32-NEXT: Classifying expressions for: @i64
-; PTR64_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR64_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX32-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: Determining loop execution counts for: @i64
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
+; X64-LABEL: 'i64'
+; X64-NEXT: Classifying expressions for: @i64
+; X64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
+; X64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
+; X64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
+; X64-NEXT: %tmp18 = add i32 %tmp, 2
+; X64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: Determining loop execution counts for: @i64
+; X64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
;
; PTR32_IDX32-LABEL: 'i64'
; PTR32_IDX32-NEXT: Classifying expressions for: @i64
; PTR32_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR32_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -67,9 +50,9 @@ define hidden i32* @i64(i8* %arg, i32* %arg10) {
; PTR32_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR32_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: [0,8589934591) S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: [0,8589934591) S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
@@ -103,9 +86,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR64_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR64_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR64_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR64_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR64_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR64_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
@@ -120,9 +103,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR64_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR64_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR64_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR64_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR64_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR64_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -137,9 +120,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR32_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR32_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -154,9 +137,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR32_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR32_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
@@ -185,48 +168,31 @@ bb17: ; preds = %bb11
br label %bb11
}
define hidden i32* @i64_to_i128(i8* %arg, i32* %arg10) {
-; PTR64_IDX64-LABEL: 'i64_to_i128'
-; PTR64_IDX64-NEXT: Classifying expressions for: @i64_to_i128
-; PTR64_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR64_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: Determining loop execution counts for: @i64_to_i128
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
-;
-; PTR64_IDX32-LABEL: 'i64_to_i128'
-; PTR64_IDX32-NEXT: Classifying expressions for: @i64_to_i128
-; PTR64_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR64_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX32-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: Determining loop execution counts for: @i64_to_i128
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
+; X64-LABEL: 'i64_to_i128'
+; X64-NEXT: Classifying expressions for: @i64_to_i128
+; X64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
+; X64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
+; X64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
+; X64-NEXT: %tmp18 = add i32 %tmp, 2
+; X64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: Determining loop execution counts for: @i64_to_i128
+; X64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
;
; PTR32_IDX32-LABEL: 'i64_to_i128'
; PTR32_IDX32-NEXT: Classifying expressions for: @i64_to_i128
; PTR32_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR32_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -241,9 +207,9 @@ define hidden i32* @i64_to_i128(i8* %arg, i32* %arg10) {
; PTR32_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR32_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: [0,8589934591) S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: [0,8589934591) S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index e3e9330e241f..ac08fb24775e 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -16,25 +16,25 @@ define void @ptrtoint(i8* %in, i64* %out0, i32* %out1, i16* %out2, i128* %out3)
; X64-LABEL: 'ptrtoint'
; X64-NEXT: Classifying expressions for: @ptrtoint
; X64-NEXT: %p0 = ptrtoint i8* %in to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: %p1 = ptrtoint i8* %in to i32
-; X64-NEXT: --> %p1 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8* %in to i32) U: full-set S: full-set
; X64-NEXT: %p2 = ptrtoint i8* %in to i16
-; X64-NEXT: --> %p2 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8* %in to i16) U: full-set S: full-set
; X64-NEXT: %p3 = ptrtoint i8* %in to i128
-; X64-NEXT: --> %p3 U: [0,18446744073709551616) S: [-18446744073709551616,18446744073709551616)
+; X64-NEXT: --> (zext i8* %in to i128) U: [0,18446744073709551616) S: [0,18446744073709551616)
; X64-NEXT: Determining loop execution counts for: @ptrtoint
;
; X32-LABEL: 'ptrtoint'
; X32-NEXT: Classifying expressions for: @ptrtoint
; X32-NEXT: %p0 = ptrtoint i8* %in to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: %p1 = ptrtoint i8* %in to i32
-; X32-NEXT: --> %p1 U: full-set S: full-set
+; X32-NEXT: --> %in U: full-set S: full-set
; X32-NEXT: %p2 = ptrtoint i8* %in to i16
-; X32-NEXT: --> %p2 U: full-set S: full-set
+; X32-NEXT: --> (trunc i8* %in to i16) U: full-set S: full-set
; X32-NEXT: %p3 = ptrtoint i8* %in to i128
-; X32-NEXT: --> %p3 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in to i128) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint
;
%p0 = ptrtoint i8* %in to i64
@@ -53,25 +53,25 @@ define void @ptrtoint_as1(i8 addrspace(1)* %in, i64* %out0, i32* %out1, i16* %ou
; X64-LABEL: 'ptrtoint_as1'
; X64-NEXT: Classifying expressions for: @ptrtoint_as1
; X64-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: %p1 = ptrtoint i8 addrspace(1)* %in to i32
-; X64-NEXT: --> %p1 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8 addrspace(1)* %in to i32) U: full-set S: full-set
; X64-NEXT: %p2 = ptrtoint i8 addrspace(1)* %in to i16
-; X64-NEXT: --> %p2 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8 addrspace(1)* %in to i16) U: full-set S: full-set
; X64-NEXT: %p3 = ptrtoint i8 addrspace(1)* %in to i128
-; X64-NEXT: --> %p3 U: [0,18446744073709551616) S: [-18446744073709551616,18446744073709551616)
+; X64-NEXT: --> (zext i8 addrspace(1)* %in to i128) U: [0,18446744073709551616) S: [0,18446744073709551616)
; X64-NEXT: Determining loop execution counts for: @ptrtoint_as1
;
; X32-LABEL: 'ptrtoint_as1'
; X32-NEXT: Classifying expressions for: @ptrtoint_as1
; X32-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8 addrspace(1)* %in to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: %p1 = ptrtoint i8 addrspace(1)* %in to i32
-; X32-NEXT: --> %p1 U: full-set S: full-set
+; X32-NEXT: --> %in U: full-set S: full-set
; X32-NEXT: %p2 = ptrtoint i8 addrspace(1)* %in to i16
-; X32-NEXT: --> %p2 U: full-set S: full-set
+; X32-NEXT: --> (trunc i8 addrspace(1)* %in to i16) U: full-set S: full-set
; X32-NEXT: %p3 = ptrtoint i8 addrspace(1)* %in to i128
-; X32-NEXT: --> %p3 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8 addrspace(1)* %in to i128) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_as1
;
%p0 = ptrtoint i8 addrspace(1)* %in to i64
@@ -92,7 +92,7 @@ define void @ptrtoint_of_bitcast(i8* %in, i64* %out0) {
; X64-NEXT: %in_casted = bitcast i8* %in to float*
; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: %p0 = ptrtoint float* %in_casted to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_bitcast
;
; X32-LABEL: 'ptrtoint_of_bitcast'
@@ -100,7 +100,7 @@ define void @ptrtoint_of_bitcast(i8* %in, i64* %out0) {
; X32-NEXT: %in_casted = bitcast i8* %in to float*
; X32-NEXT: --> %in U: full-set S: full-set
; X32-NEXT: %p0 = ptrtoint float* %in_casted to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_bitcast
;
%in_casted = bitcast i8* %in to float*
@@ -116,7 +116,7 @@ define void @ptrtoint_of_addrspacecast(i8* %in, i64* %out0) {
; X64-NEXT: %in_casted = addrspacecast i8* %in to i8 addrspace(1)*
; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in_casted to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_addrspacecast
;
; X32-LABEL: 'ptrtoint_of_addrspacecast'
@@ -124,7 +124,7 @@ define void @ptrtoint_of_addrspacecast(i8* %in, i64* %out0) {
; X32-NEXT: %in_casted = addrspacecast i8* %in to i8 addrspace(1)*
; X32-NEXT: --> %in_casted U: full-set S: full-set
; X32-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in_casted to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8 addrspace(1)* %in_casted to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_addrspacecast
;
%in_casted = addrspacecast i8* %in to i8 addrspace(1)*
@@ -140,7 +140,7 @@ define void @ptrtoint_of_inttoptr(i64 %in, i64* %out0) {
; X64-NEXT: %in_casted = inttoptr i64 %in to i8*
; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: %p0 = ptrtoint i8* %in_casted to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_inttoptr
;
; X32-LABEL: 'ptrtoint_of_inttoptr'
@@ -148,7 +148,7 @@ define void @ptrtoint_of_inttoptr(i64 %in, i64* %out0) {
; X32-NEXT: %in_casted = inttoptr i64 %in to i8*
; X32-NEXT: --> %in_casted U: full-set S: full-set
; X32-NEXT: %p0 = ptrtoint i8* %in_casted to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in_casted to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_inttoptr
;
%in_casted = inttoptr i64 %in to i8*
@@ -197,11 +197,17 @@ define void @ptrtoint_of_nullptr(i64* %out0) {
; A constant inttoptr argument of an ptrtoint is still bad.
define void @ptrtoint_of_constantexpr_inttoptr(i64* %out0) {
-; ALL-LABEL: 'ptrtoint_of_constantexpr_inttoptr'
-; ALL-NEXT: Classifying expressions for: @ptrtoint_of_constantexpr_inttoptr
-; ALL-NEXT: %p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
-; ALL-NEXT: --> %p0 U: [42,43) S: [-64,64)
-; ALL-NEXT: Determining loop execution counts for: @ptrtoint_of_constantexpr_inttoptr
+; X64-LABEL: 'ptrtoint_of_constantexpr_inttoptr'
+; X64-NEXT: Classifying expressions for: @ptrtoint_of_constantexpr_inttoptr
+; X64-NEXT: %p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
+; X64-NEXT: --> inttoptr (i64 42 to i8*) U: [42,43) S: [-64,64)
+; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_constantexpr_inttoptr
+;
+; X32-LABEL: 'ptrtoint_of_constantexpr_inttoptr'
+; X32-NEXT: Classifying expressions for: @ptrtoint_of_constantexpr_inttoptr
+; X32-NEXT: %p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
+; X32-NEXT: --> (zext i8* inttoptr (i64 42 to i8*) to i64) U: [42,43) S: [0,4294967296)
+; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_constantexpr_inttoptr
;
%p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
store i64 %p0, i64* %out0
diff --git a/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll b/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll
index 564328d99998..e73397214475 100644
--- a/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll
+++ b/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll
@@ -186,7 +186,9 @@ define linkonce_odr i32 @vector_insert(%"class.std::__1::vector.182"*, [1 x i32]
br i1 %114, label %124, label %115
; CHECK-LABEL: .preheader:
-; CHECK-NEXT: sub i32 [[OLD_CAST]], [[NEW_CAST]]
+; CHECK-NEXT: [[NEG_NEW:%[0-9]+]] = sub i32 0, [[NEW_CAST]]
+; CHECK-NEXT: getelementptr i8, i8* %97, i32 [[NEG_NEW]]
+
; <label>:115: ; preds = %111, %115
%116 = phi i8* [ %118, %115 ], [ %97, %111 ]
%117 = phi i8* [ %119, %115 ], [ %11, %111 ]
diff --git a/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll b/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
index 670477c4c285..d4dd7352aa52 100644
--- a/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
+++ b/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
@@ -268,9 +268,9 @@ define i8* @SyFgets(i8* %line, i64 %length, i64 %fid) {
; CHECK-NEXT: LBB0_48: ## %if.then1477
; CHECK-NEXT: movl $1, %edx
; CHECK-NEXT: callq _write
-; CHECK-NEXT: subq %rbx, %r14
; CHECK-NEXT: movq _syHistory(a){{.*}}(%rip), %rax
-; CHECK-NEXT: leaq 8189(%r14,%rax), %rax
+; CHECK-NEXT: subq %rbx, %rax
+; CHECK-NEXT: leaq 8189(%rax,%r14), %rax
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: LBB0_49: ## %for.body1723
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
diff --git a/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll b/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll
index e1ef6bd6635d..bc756c666bde 100644
--- a/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll
+++ b/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll
@@ -166,21 +166,23 @@ define i8 @testnullptrint(i8* %buf, i8* %end) nounwind {
; PTR64-NEXT: ret i8 [[RET]]
;
; PTR32-LABEL: @testnullptrint(
+; PTR32-NEXT: [[BUF1:%.*]] = ptrtoint i8* [[BUF:%.*]] to i32
; PTR32-NEXT: br label [[LOOPGUARD:%.*]]
; PTR32: loopguard:
-; PTR32-NEXT: [[BI:%.*]] = ptrtoint i8* [[BUF:%.*]] to i32
+; PTR32-NEXT: [[BI:%.*]] = ptrtoint i8* [[BUF]] to i32
; PTR32-NEXT: [[EI:%.*]] = ptrtoint i8* [[END:%.*]] to i32
; PTR32-NEXT: [[CNT:%.*]] = sub i32 [[EI]], [[BI]]
-; PTR32-NEXT: [[CNT1:%.*]] = inttoptr i32 [[CNT]] to i8*
; PTR32-NEXT: [[GUARD:%.*]] = icmp ult i32 0, [[CNT]]
; PTR32-NEXT: br i1 [[GUARD]], label [[PREHEADER:%.*]], label [[EXIT:%.*]]
; PTR32: preheader:
+; PTR32-NEXT: [[TMP1:%.*]] = sub i32 0, [[BUF1]]
+; PTR32-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[END]], i32 [[TMP1]]
; PTR32-NEXT: br label [[LOOP:%.*]]
; PTR32: loop:
; PTR32-NEXT: [[P_01_US_US:%.*]] = phi i8* [ null, [[PREHEADER]] ], [ [[GEP:%.*]], [[LOOP]] ]
; PTR32-NEXT: [[GEP]] = getelementptr inbounds i8, i8* [[P_01_US_US]], i64 1
-; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]]
-; PTR32-NEXT: [[EXITCOND:%.*]] = icmp ne i8* [[GEP]], [[CNT1]]
+; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]], align 1
+; PTR32-NEXT: [[EXITCOND:%.*]] = icmp ne i8* [[GEP]], [[SCEVGEP]]
; PTR32-NEXT: br i1 [[EXITCOND]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]]
; PTR32: exit.loopexit:
; PTR32-NEXT: [[SNEXT_LCSSA:%.*]] = phi i8 [ [[SNEXT]], [[LOOP]] ]
@@ -256,10 +258,10 @@ define i8 @testptrint(i8* %buf, i8* %end) nounwind {
; PTR32-NEXT: [[P_01_US_US:%.*]] = phi i8* [ [[BUF]], [[PREHEADER]] ], [ [[GEP:%.*]], [[LOOP]] ]
; PTR32-NEXT: [[IV:%.*]] = phi i32 [ [[BI]], [[PREHEADER]] ], [ [[IVNEXT:%.*]], [[LOOP]] ]
; PTR32-NEXT: [[GEP]] = getelementptr inbounds i8, i8* [[P_01_US_US]], i64 1
-; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]]
+; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]], align 1
; PTR32-NEXT: [[IVNEXT]] = add nuw i32 [[IV]], 1
-; PTR32-NEXT: [[EXITCOND:%.*]] = icmp ne i32 [[IVNEXT]], [[CNT]]
-; PTR32-NEXT: br i1 [[EXITCOND]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]]
+; PTR32-NEXT: [[CMP:%.*]] = icmp ult i32 [[IVNEXT]], [[CNT]]
+; PTR32-NEXT: br i1 [[CMP]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]]
; PTR32: exit.loopexit:
; PTR32-NEXT: [[SNEXT_LCSSA:%.*]] = phi i8 [ [[SNEXT]], [[LOOP]] ]
; PTR32-NEXT: br label [[EXIT]]
diff --git a/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll b/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll
index 1012e23cd3a2..321e98ab6772 100644
--- a/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll
+++ b/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll
@@ -32,6 +32,5 @@ bitmap_element_allocate.exit:
; CHECK: polly.stmt.cond.end73.i:
-; CHECK-NEXT: %0 = bitcast %structty** %b.s2a to i8**
-; CHECK-NEXT: store i8* undef, i8** %0
+; CHECK-NEXT: store %structty* undef, %structty** %b.s2a
; CHECK-NEXT: br label %polly.exiting
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-release-arm-spec2k6-Os - Build # 19 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-Os. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-release-arm-spec2k6-Os
Culprit:
<cut>
commit ab97c9bdb747c873cd35a18229e2694156a7607d
Author: David Green <david.green(a)arm.com>
Date: Sat Dec 12 14:21:40 2020 +0000
[LV] Fix scalar cost for tail predicated loops
When it comes to the scalar cost of any predicated block, the loop
vectorizer by default regards this predication as a sign that it is
looking at an if-conversion and divides the scalar cost of the block by
2, assuming it would only be executed half the time. This however makes
no sense if the predication has been introduced to tail predicate the
loop.
Original patch by Anna Welker
Differential Revision: https://reviews.llvm.org/D86452
</cut>
Results regressed to (for first_bad == ab97c9bdb747c873cd35a18229e2694156a7607d)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -Os_mthumb -- artifacts/build-ab97c9bdb747c873cd35a18229e2694156a7607d/results_id:
1
# 401.bzip2,bzip2_base.default regressed by 103
# 401.bzip2,[.] BZ2_compressBlock regressed by 113
# 473.astar,astar_base.default regressed by 103
from (for last_good == d716eab197abec0b9aab4a76cd1a52b248b8c3b1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=thumb --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -Os_mthumb -- artifacts/build-d716eab197abec0b9aab4a76cd1a52b248b8c3b1/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-Os/1878
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-release-arm-spec2k6-Os/1876
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-ab97c9bdb747c873cd35a18229e2694156a7607d
cd investigate-llvm-ab97c9bdb747c873cd35a18229e2694156a7607d
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach ab97c9bdb747c873cd35a18229e2694156a7607d
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach d716eab197abec0b9aab4a76cd1a52b248b8c3b1
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit ab97c9bdb747c873cd35a18229e2694156a7607d
Author: David Green <david.green(a)arm.com>
Date: Sat Dec 12 14:21:40 2020 +0000
[LV] Fix scalar cost for tail predicated loops
When it comes to the scalar cost of any predicated block, the loop
vectorizer by default regards this predication as a sign that it is
looking at an if-conversion and divides the scalar cost of the block by
2, assuming it would only be executed half the time. This however makes
no sense if the predication has been introduced to tail predicate the
loop.
Original patch by Anna Welker
Differential Revision: https://reviews.llvm.org/D86452
---
llvm/lib/Transforms/Vectorize/LoopVectorize.cpp | 7 ++++---
llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll | 2 +-
2 files changed, 5 insertions(+), 4 deletions(-)
diff --git a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
index c381377b67c9..663ea50c4c02 100644
--- a/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
+++ b/llvm/lib/Transforms/Vectorize/LoopVectorize.cpp
@@ -6483,9 +6483,10 @@ LoopVectorizationCostModel::expectedCost(ElementCount VF) {
// if-converted. This means that the block's instructions (aside from
// stores and instructions that may divide by zero) will now be
// unconditionally executed. For the scalar case, we may not always execute
- // the predicated block. Thus, scale the block's cost by the probability of
- // executing it.
- if (VF.isScalar() && blockNeedsPredication(BB))
+ // the predicated block, if it is an if-else block. Thus, scale the block's
+ // cost by the probability of executing it. blockNeedsPredication from
+ // Legal is used so as to not include all blocks in tail folded loops.
+ if (VF.isScalar() && Legal->blockNeedsPredication(BB))
BlockCost.first /= getReciprocalPredBlockProb();
Cost.first += BlockCost.first;
diff --git a/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll b/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll
index 959fbe676e67..fc8ea4fc938c 100644
--- a/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll
+++ b/llvm/test/Transforms/LoopVectorize/ARM/scalar-block-cost.ll
@@ -15,7 +15,7 @@ define void @pred_loop(i32* %off, i32* %data, i32* %dst, i32 %n) #0 {
; CHECK-COST-NEXT: LV: Found an estimated cost of 1 for VF 1 For instruction: store i32 %add1, i32* %arrayidx2, align 4
; CHECK-COST-NEXT: LV: Found an estimated cost of 1 for VF 1 For instruction: %exitcond.not = icmp eq i32 %add, %n
; CHECK-COST-NEXT: LV: Found an estimated cost of 0 for VF 1 For instruction: br i1 %exitcond.not, label %exit.loopexit, label %for.body
-; CHECK-COST-NEXT: LV: Scalar loop costs: 2.
+; CHECK-COST-NEXT: LV: Scalar loop costs: 5.
entry:
%cmp8 = icmp sgt i32 %n, 0
</cut>
4 years, 1 month
- 2
- 1
Re: [CI-NOTIFY]: TCWG Bisect tcwg_gnu/gnu-master-aarch64-check_bootstrap - Build # 80 - Successful!
by Maxim Kuvyrkov
Reported to upstream at https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101506 .
--
Maxim Kuvyrkov
https://www.linaro.org
> On 19 Jul 2021, at 02:30, ci_notify(a)linaro.org wrote:
>
> Successfully identified regression in *gcc* in CI configuration tcwg_gnu/gnu-master-aarch64-check_bootstrap. So far, this commit has regressed CI configurations:
> - tcwg_gnu/gnu-master-aarch64-check_bootstrap
>
> Culprit:
> <cut>
> commit 1dd3f21095858fbfd3e28a149578d5fb67e75f95
> Author: Richard Biener <rguenther(a)suse.de>
> Date: Tue Jul 13 13:59:15 2021 +0200
>
> Support reduction def re-use for epilogue with different vector size
>
> The following adds support for re-using the vector reduction def
> from the main loop in vectorized epilogue loops on architectures
> which use different vector sizes for the epilogue. That's only
> x86 as far as I am aware.
>
> 2021-07-13 Richard Biener <rguenther(a)suse.de>
>
> * tree-vect-loop.c (vect_find_reusable_accumulator): Handle
> vector types where the old vector type has a multiple of
> the new vector type elements.
> (vect_create_partial_epilog): New function, split out from...
> (vect_create_epilog_for_reduction): ... here.
> (vect_transform_cycle_phi): Reduce the re-used accumulator
> to the new vector type.
>
> * gcc.target/i386/vect-reduc-1.c: New testcase.
> </cut>
>
> Results regressed to (for first_bad == 1dd3f21095858fbfd3e28a149578d5fb67e75f95)
> # reset_artifacts:
> -10
> # build_abe binutils:
> -2
> # build_abe bootstrap:
> -1
> # build_abe dejagnu:
> 0
> # build_abe check_bootstrap -- --set runtestflags=g++.dg/dg.exp --set runtestflags=gcc.target/aarch64/aarch64.exp:
> 1
> # Getting actual results from build directory /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/libstdc++.sum
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/gfortran.sum
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/libitm.sum
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/libgomp.sum
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/libatomic.sum
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/g++.sum
> # /home/tcwg-buildslave/workspace/tcwg_gnu_3/artifacts/build-1dd3f21095858fbfd3e28a149578d5fb67e75f95/sumfiles/gcc.sum
> # Manifest: gcc-compare-results/contrib/testsuite-management/flaky/gnu-master-aarch64-check_bootstrap.xfail
> # Getting actual results from build directory base-artifacts/sumfiles
> # base-artifacts/sumfiles/libstdc++.sum
> # base-artifacts/sumfiles/gfortran.sum
> # base-artifacts/sumfiles/libitm.sum
> # base-artifacts/sumfiles/libgomp.sum
> # base-artifacts/sumfiles/libatomic.sum
> # base-artifacts/sumfiles/g++.sum
> # base-artifacts/sumfiles/gcc.sum
> #
> #
> # Unexpected results in this build (new failures)
> # === gcc tests ===
> #
> # Running gcc.target/aarch64/aarch64.exp ...
> # FAIL: gcc.target/aarch64/vect-fmaxv-fminv-compile.c scan-assembler fminnmv
> # FAIL: gcc.target/aarch64/vect-fmaxv-fminv-compile.c scan-assembler fmaxnmv
> #
> # === Results Summary ===
>
> from (for last_good == a7098d6ef4e4e799dab8ef925c62b199d707694b)
> # reset_artifacts:
> -10
> # build_abe binutils:
> -2
> # build_abe bootstrap:
> -1
> # build_abe dejagnu:
> 0
> # build_abe check_bootstrap -- --set runtestflags=g++.dg/dg.exp --set runtestflags=gcc.target/aarch64/aarch64.exp:
> 1
>
> Artifacts of last_good build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra…
> Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra…
> Build top page/logs: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra…
>
> Configuration details:
>
>
> Reproduce builds:
> <cut>
> mkdir investigate-gcc-1dd3f21095858fbfd3e28a149578d5fb67e75f95
> cd investigate-gcc-1dd3f21095858fbfd3e28a149578d5fb67e75f95
>
> git clone https://git.linaro.org/toolchain/jenkins-scripts
>
> mkdir -p artifacts/manifests
> curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra… --fail
> curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra… --fail
> curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra… --fail
> chmod +x artifacts/test.sh
>
> # Reproduce the baseline build (build all pre-requisites)
> ./jenkins-scripts/tcwg_gnu-build.sh @@ artifacts/manifests/build-baseline.sh
>
> # Save baseline build state (which is then restored in artifacts/test.sh)
> rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude gcc/ ./ ./bisect/baseline/
>
> cd gcc
>
> # Reproduce first_bad build
> git checkout --detach 1dd3f21095858fbfd3e28a149578d5fb67e75f95
> ../artifacts/test.sh
>
> # Reproduce last_good build
> git checkout --detach a7098d6ef4e4e799dab8ef925c62b199d707694b
> ../artifacts/test.sh
>
> cd ..
> </cut>
>
> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
>
> Artifacts: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra…
> Build log: https://ci.linaro.org/job/tcwg_gcc-bisect-gnu-master-aarch64-check_bootstra…
>
> Full commit (up to 1000 lines):
> <cut>
> commit 1dd3f21095858fbfd3e28a149578d5fb67e75f95
> Author: Richard Biener <rguenther(a)suse.de>
> Date: Tue Jul 13 13:59:15 2021 +0200
>
> Support reduction def re-use for epilogue with different vector size
>
> The following adds support for re-using the vector reduction def
> from the main loop in vectorized epilogue loops on architectures
> which use different vector sizes for the epilogue. That's only
> x86 as far as I am aware.
>
> 2021-07-13 Richard Biener <rguenther(a)suse.de>
>
> * tree-vect-loop.c (vect_find_reusable_accumulator): Handle
> vector types where the old vector type has a multiple of
> the new vector type elements.
> (vect_create_partial_epilog): New function, split out from...
> (vect_create_epilog_for_reduction): ... here.
> (vect_transform_cycle_phi): Reduce the re-used accumulator
> to the new vector type.
>
> * gcc.target/i386/vect-reduc-1.c: New testcase.
> ---
> gcc/testsuite/gcc.target/i386/vect-reduc-1.c | 17 ++
> gcc/tree-vect-loop.c | 227 ++++++++++++++++-----------
> 2 files changed, 156 insertions(+), 88 deletions(-)
>
> diff --git a/gcc/testsuite/gcc.target/i386/vect-reduc-1.c b/gcc/testsuite/gcc.target/i386/vect-reduc-1.c
> new file mode 100644
> index 00000000000..9ee9ba4e736
> --- /dev/null
> +++ b/gcc/testsuite/gcc.target/i386/vect-reduc-1.c
> @@ -0,0 +1,17 @@
> +/* { dg-do compile } */
> +/* { dg-options "-O3 -mavx2 -mno-avx512f -fdump-tree-vect-details" } */
> +
> +#define N 32
> +int foo (int *a, int n)
> +{
> + int sum = 1;
> + for (int i = 0; i < 8*N + 4; ++i)
> + sum += a[i];
> + return sum;
> +}
> +
> +/* The reduction epilog should be vectorized and the accumulator
> + re-used. */
> +/* { dg-final { scan-tree-dump "LOOP EPILOGUE VECTORIZED" "vect" } } */
> +/* { dg-final { scan-assembler-times "psrl" 2 } } */
> +/* { dg-final { scan-assembler-times "padd" 5 } } */
> diff --git a/gcc/tree-vect-loop.c b/gcc/tree-vect-loop.c
> index 8c27d75f889..e9780158a51 100644
> --- a/gcc/tree-vect-loop.c
> +++ b/gcc/tree-vect-loop.c
> @@ -4896,12 +4896,11 @@ vect_find_reusable_accumulator (loop_vec_info loop_vinfo,
> accumulator->reduc_info->reduc_scalar_results.begin ()))
> return false;
>
> - /* For now, only handle the case in which both loops are operating on the
> - same vector types. In future we could reduce wider vectors to narrower
> - ones as well. */
> + /* Handle the case where we can reduce wider vectors to narrower ones. */
> tree vectype = STMT_VINFO_VECTYPE (reduc_info);
> tree old_vectype = TREE_TYPE (accumulator->reduc_input);
> - if (!useless_type_conversion_p (old_vectype, vectype))
> + if (!constant_multiple_p (TYPE_VECTOR_SUBPARTS (old_vectype),
> + TYPE_VECTOR_SUBPARTS (vectype)))
> return false;
>
> /* Non-SLP reductions might apply an adjustment after the reduction
> @@ -4935,6 +4934,101 @@ vect_find_reusable_accumulator (loop_vec_info loop_vinfo,
> return true;
> }
>
> +/* Reduce the vector VEC_DEF down to VECTYPE with reduction operation
> + CODE emitting stmts before GSI. Returns a vector def of VECTYPE. */
> +
> +static tree
> +vect_create_partial_epilog (tree vec_def, tree vectype, enum tree_code code,
> + gimple_seq *seq)
> +{
> + unsigned nunits = TYPE_VECTOR_SUBPARTS (TREE_TYPE (vec_def)).to_constant ();
> + unsigned nunits1 = TYPE_VECTOR_SUBPARTS (vectype).to_constant ();
> + tree stype = TREE_TYPE (vectype);
> + tree new_temp = vec_def;
> + while (nunits > nunits1)
> + {
> + nunits /= 2;
> + tree vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype),
> + stype, nunits);
> + unsigned int bitsize = tree_to_uhwi (TYPE_SIZE (vectype1));
> +
> + /* The target has to make sure we support lowpart/highpart
> + extraction, either via direct vector extract or through
> + an integer mode punning. */
> + tree dst1, dst2;
> + gimple *epilog_stmt;
> + if (convert_optab_handler (vec_extract_optab,
> + TYPE_MODE (TREE_TYPE (new_temp)),
> + TYPE_MODE (vectype1))
> + != CODE_FOR_nothing)
> + {
> + /* Extract sub-vectors directly once vec_extract becomes
> + a conversion optab. */
> + dst1 = make_ssa_name (vectype1);
> + epilog_stmt
> + = gimple_build_assign (dst1, BIT_FIELD_REF,
> + build3 (BIT_FIELD_REF, vectype1,
> + new_temp, TYPE_SIZE (vectype1),
> + bitsize_int (0)));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + dst2 = make_ssa_name (vectype1);
> + epilog_stmt
> + = gimple_build_assign (dst2, BIT_FIELD_REF,
> + build3 (BIT_FIELD_REF, vectype1,
> + new_temp, TYPE_SIZE (vectype1),
> + bitsize_int (bitsize)));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + }
> + else
> + {
> + /* Extract via punning to appropriately sized integer mode
> + vector. */
> + tree eltype = build_nonstandard_integer_type (bitsize, 1);
> + tree etype = build_vector_type (eltype, 2);
> + gcc_assert (convert_optab_handler (vec_extract_optab,
> + TYPE_MODE (etype),
> + TYPE_MODE (eltype))
> + != CODE_FOR_nothing);
> + tree tem = make_ssa_name (etype);
> + epilog_stmt = gimple_build_assign (tem, VIEW_CONVERT_EXPR,
> + build1 (VIEW_CONVERT_EXPR,
> + etype, new_temp));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + new_temp = tem;
> + tem = make_ssa_name (eltype);
> + epilog_stmt
> + = gimple_build_assign (tem, BIT_FIELD_REF,
> + build3 (BIT_FIELD_REF, eltype,
> + new_temp, TYPE_SIZE (eltype),
> + bitsize_int (0)));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + dst1 = make_ssa_name (vectype1);
> + epilog_stmt = gimple_build_assign (dst1, VIEW_CONVERT_EXPR,
> + build1 (VIEW_CONVERT_EXPR,
> + vectype1, tem));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + tem = make_ssa_name (eltype);
> + epilog_stmt
> + = gimple_build_assign (tem, BIT_FIELD_REF,
> + build3 (BIT_FIELD_REF, eltype,
> + new_temp, TYPE_SIZE (eltype),
> + bitsize_int (bitsize)));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + dst2 = make_ssa_name (vectype1);
> + epilog_stmt = gimple_build_assign (dst2, VIEW_CONVERT_EXPR,
> + build1 (VIEW_CONVERT_EXPR,
> + vectype1, tem));
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + }
> +
> + new_temp = make_ssa_name (vectype1);
> + epilog_stmt = gimple_build_assign (new_temp, code, dst1, dst2);
> + gimple_seq_add_stmt_without_update (seq, epilog_stmt);
> + }
> +
> + return new_temp;
> +}
> +
> /* Function vect_create_epilog_for_reduction
>
> Create code at the loop-epilog to finalize the result of a reduction
> @@ -5684,87 +5778,11 @@ vect_create_epilog_for_reduction (loop_vec_info loop_vinfo,
>
> /* First reduce the vector to the desired vector size we should
> do shift reduction on by combining upper and lower halves. */
> - new_temp = reduc_inputs[0];
> - while (nunits > nunits1)
> - {
> - nunits /= 2;
> - vectype1 = get_related_vectype_for_scalar_type (TYPE_MODE (vectype),
> - stype, nunits);
> - unsigned int bitsize = tree_to_uhwi (TYPE_SIZE (vectype1));
> -
> - /* The target has to make sure we support lowpart/highpart
> - extraction, either via direct vector extract or through
> - an integer mode punning. */
> - tree dst1, dst2;
> - if (convert_optab_handler (vec_extract_optab,
> - TYPE_MODE (TREE_TYPE (new_temp)),
> - TYPE_MODE (vectype1))
> - != CODE_FOR_nothing)
> - {
> - /* Extract sub-vectors directly once vec_extract becomes
> - a conversion optab. */
> - dst1 = make_ssa_name (vectype1);
> - epilog_stmt
> - = gimple_build_assign (dst1, BIT_FIELD_REF,
> - build3 (BIT_FIELD_REF, vectype1,
> - new_temp, TYPE_SIZE (vectype1),
> - bitsize_int (0)));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - dst2 = make_ssa_name (vectype1);
> - epilog_stmt
> - = gimple_build_assign (dst2, BIT_FIELD_REF,
> - build3 (BIT_FIELD_REF, vectype1,
> - new_temp, TYPE_SIZE (vectype1),
> - bitsize_int (bitsize)));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - }
> - else
> - {
> - /* Extract via punning to appropriately sized integer mode
> - vector. */
> - tree eltype = build_nonstandard_integer_type (bitsize, 1);
> - tree etype = build_vector_type (eltype, 2);
> - gcc_assert (convert_optab_handler (vec_extract_optab,
> - TYPE_MODE (etype),
> - TYPE_MODE (eltype))
> - != CODE_FOR_nothing);
> - tree tem = make_ssa_name (etype);
> - epilog_stmt = gimple_build_assign (tem, VIEW_CONVERT_EXPR,
> - build1 (VIEW_CONVERT_EXPR,
> - etype, new_temp));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - new_temp = tem;
> - tem = make_ssa_name (eltype);
> - epilog_stmt
> - = gimple_build_assign (tem, BIT_FIELD_REF,
> - build3 (BIT_FIELD_REF, eltype,
> - new_temp, TYPE_SIZE (eltype),
> - bitsize_int (0)));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - dst1 = make_ssa_name (vectype1);
> - epilog_stmt = gimple_build_assign (dst1, VIEW_CONVERT_EXPR,
> - build1 (VIEW_CONVERT_EXPR,
> - vectype1, tem));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - tem = make_ssa_name (eltype);
> - epilog_stmt
> - = gimple_build_assign (tem, BIT_FIELD_REF,
> - build3 (BIT_FIELD_REF, eltype,
> - new_temp, TYPE_SIZE (eltype),
> - bitsize_int (bitsize)));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - dst2 = make_ssa_name (vectype1);
> - epilog_stmt = gimple_build_assign (dst2, VIEW_CONVERT_EXPR,
> - build1 (VIEW_CONVERT_EXPR,
> - vectype1, tem));
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - }
> -
> - new_temp = make_ssa_name (vectype1);
> - epilog_stmt = gimple_build_assign (new_temp, code, dst1, dst2);
> - gsi_insert_before (&exit_gsi, epilog_stmt, GSI_SAME_STMT);
> - reduc_inputs[0] = new_temp;
> - }
> + gimple_seq stmts = NULL;
> + new_temp = vect_create_partial_epilog (reduc_inputs[0], vectype1,
> + code, &stmts);
> + gsi_insert_seq_before (&exit_gsi, stmts, GSI_SAME_STMT);
> + reduc_inputs[0] = new_temp;
>
> if (reduce_with_shift && !slp_reduc)
> {
> @@ -7681,13 +7699,46 @@ vect_transform_cycle_phi (loop_vec_info loop_vinfo,
>
> if (auto *accumulator = reduc_info->reused_accumulator)
> {
> + tree def = accumulator->reduc_input;
> + unsigned int nreduc;
> + bool res = constant_multiple_p (TYPE_VECTOR_SUBPARTS (TREE_TYPE (def)),
> + TYPE_VECTOR_SUBPARTS (vectype_out),
> + &nreduc);
> + gcc_assert (res);
> + if (nreduc != 1)
> + {
> + /* Reduce the single vector to a smaller one. */
> + gimple_seq stmts = NULL;
> + def = vect_create_partial_epilog (def, vectype_out,
> + STMT_VINFO_REDUC_CODE (reduc_info),
> + &stmts);
> + /* Adjust the input so we pick up the partially reduced value
> + for the skip edge in vect_create_epilog_for_reduction. */
> + accumulator->reduc_input = def;
> + if (loop_vinfo->main_loop_edge)
> + {
> + /* While we'd like to insert on the edge this will split
> + blocks and disturb bookkeeping, we also will eventually
> + need this on the skip edge. Rely on sinking to
> + fixup optimal placement and insert in the pred. */
> + gimple_stmt_iterator gsi
> + = gsi_last_bb (loop_vinfo->main_loop_edge->src);
> + /* Insert before a cond that eventually skips the
> + epilogue. */
> + if (!gsi_end_p (gsi) && stmt_ends_bb_p (gsi_stmt (gsi)))
> + gsi_prev (&gsi);
> + gsi_insert_seq_after (&gsi, stmts, GSI_CONTINUE_LINKING);
> + }
> + else
> + gsi_insert_seq_on_edge_immediate (loop_preheader_edge (loop),
> + stmts);
> + }
> if (loop_vinfo->main_loop_edge)
> vec_initial_defs[0]
> - = vect_get_main_loop_result (loop_vinfo, accumulator->reduc_input,
> + = vect_get_main_loop_result (loop_vinfo, def,
> vec_initial_defs[0]);
> else
> - vec_initial_defs.safe_push (accumulator->reduc_input);
> - gcc_assert (vec_initial_defs.length () == 1);
> + vec_initial_defs.safe_push (def);
> }
>
> /* Generate the reduction PHIs upfront. */
> </cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O2 - Build # 11 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O2
Culprit:
<cut>
commit 3d31adaec443daee75c62823082fa2912bbd267e
Author: Evgeniy Brevnov <ybrevnov(a)azul.com>
Date: Thu Oct 29 14:27:54 2020 +0700
[DSE] Improve partial overlap detection
Currently isOverwrite returns OW_MaybePartial even for accesss known not to overlap. This is not a big problem for legacy implementation (since isPartialOverwrite follows isOverwrite and clarifies the result). Contrary SSA based version does a lot of work to later find out that accesses don't overlap. Besides negative impact on compile time we quickly reach MemorySSAPartialStoreLimit and miss optimization opportunities.
Note: In fact, I think it would be cleaner implementation if isOverwrite returned fully clarified result in the first place whithout need to call isPartialOverwrite. This can be done as a follow up. What do you think?
Reviewed By: fhahn, asbirlea
Differential Revision: https://reviews.llvm.org/D90371
</cut>
Results regressed to (for first_bad == 3d31adaec443daee75c62823082fa2912bbd267e)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2 -- artifacts/build-3d31adaec443daee75c62823082fa2912bbd267e/results_id:
1
# 464.h264ref,h264ref_base.default regressed by 106
# 464.h264ref,[.] FastFullPelBlockMotionSearch regressed by 142
from (for last_good == 1eeae4310771d8a6896fe09effe88883998f34e8)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2 -- artifacts/build-1eeae4310771d8a6896fe09effe88883998f34e8/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O2/1862
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O2/1864
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-3d31adaec443daee75c62823082fa2912bbd267e
cd investigate-llvm-3d31adaec443daee75c62823082fa2912bbd267e
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 3d31adaec443daee75c62823082fa2912bbd267e
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 1eeae4310771d8a6896fe09effe88883998f34e8
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 3d31adaec443daee75c62823082fa2912bbd267e
Author: Evgeniy Brevnov <ybrevnov(a)azul.com>
Date: Thu Oct 29 14:27:54 2020 +0700
[DSE] Improve partial overlap detection
Currently isOverwrite returns OW_MaybePartial even for accesss known not to overlap. This is not a big problem for legacy implementation (since isPartialOverwrite follows isOverwrite and clarifies the result). Contrary SSA based version does a lot of work to later find out that accesses don't overlap. Besides negative impact on compile time we quickly reach MemorySSAPartialStoreLimit and miss optimization opportunities.
Note: In fact, I think it would be cleaner implementation if isOverwrite returned fully clarified result in the first place whithout need to call isPartialOverwrite. This can be done as a follow up. What do you think?
Reviewed By: fhahn, asbirlea
Differential Revision: https://reviews.llvm.org/D90371
---
.../lib/Transforms/Scalar/DeadStoreElimination.cpp | 50 ++++++++++------
.../MSSA/combined-partial-overwrites.ll | 53 +++++-----------
.../MSSA/multiblock-overlap.ll | 70 +++++++---------------
3 files changed, 69 insertions(+), 104 deletions(-)
diff --git a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
index acdb1c4fa8c3..e578d15dfc50 100644
--- a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
+++ b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp
@@ -501,28 +501,40 @@ isOverwrite(const Instruction *LaterI, const Instruction *EarlierI,
if (BP1 != BP2)
return OW_Unknown;
- // The later store completely overlaps the earlier store if:
- //
- // 1. Both start at the same offset and the later one's size is greater than
- // or equal to the earlier one's, or
- //
- // |--earlier--|
- // |-- later --|
- //
- // 2. The earlier store has an offset greater than the later offset, but which
- // still lies completely within the later store.
- //
- // |--earlier--|
- // |----- later ------|
+ // The later access completely overlaps the earlier store if and only if
+ // both start and end of the earlier one is "inside" the later one:
+ // |<->|--earlier--|<->|
+ // |-------later-------|
+ // Accesses may overlap if and only if start of one of them is "inside"
+ // another one:
+ // |<->|--earlier--|<----->|
+ // |-------later-------|
+ // OR
+ // |----- earlier -----|
+ // |<->|---later---|<----->|
//
// We have to be careful here as *Off is signed while *.Size is unsigned.
- if (EarlierOff >= LaterOff &&
- LaterSize >= EarlierSize &&
- uint64_t(EarlierOff - LaterOff) + EarlierSize <= LaterSize)
- return OW_Complete;
- // Later may overwrite earlier completely with other partial writes.
- return OW_MaybePartial;
+ // Check if the earlier access starts "not before" the later one.
+ if (EarlierOff >= LaterOff) {
+ // If the earlier access ends "not after" the later access then the earlier
+ // one is completely overwritten by the later one.
+ if (uint64_t(EarlierOff - LaterOff) + EarlierSize <= LaterSize)
+ return OW_Complete;
+ // If start of the earlier access is "before" end of the later access then
+ // accesses overlap.
+ else if ((uint64_t)(EarlierOff - LaterOff) < LaterSize)
+ return OW_MaybePartial;
+ }
+ // If start of the later access is "before" end of the earlier access then
+ // accesses overlap.
+ else if ((uint64_t)(LaterOff - EarlierOff) < EarlierSize) {
+ return OW_MaybePartial;
+ }
+
+ // Can reach here only if accesses are known not to overlap. There is no
+ // dedicated code to indicate no overlap so signal "unknown".
+ return OW_Unknown;
}
/// Return 'OW_Complete' if a store to the 'Later' location completely
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/combined-partial-overwrites.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/combined-partial-overwrites.ll
index ec1b9a5ee514..ab957e0c3cf0 100644
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/combined-partial-overwrites.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/combined-partial-overwrites.ll
@@ -1,6 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -S -dse -enable-dse-partial-store-merging=false < %s | FileCheck --check-prefixes=CHECK,DEFAULT-LIMIT %s
-; RUN: opt -S -dse -enable-dse-partial-store-merging=false -dse-memoryssa-partial-store-limit=10 < %s | FileCheck --check-prefixes=CHECK,LARGER-LIMIT %s
+; RUN: opt -S -dse -enable-dse-partial-store-merging=false < %s | FileCheck --check-prefixes=CHECK %s
target datalayout = "E-m:e-i64:64-n32:64"
target triple = "powerpc64le-unknown-linux"
@@ -213,41 +212,21 @@ declare i32 @fa(i8*, i8**, i32, i8, i8*)
; We miss this case, because of an aggressive limit of partial overlap analysis.
; With a larger partial store limit, we remove the memset.
define void @test4() {
-; DEFAULT-LIMIT-LABEL: @test4(
-; DEFAULT-LIMIT-NEXT: entry:
-; DEFAULT-LIMIT-NEXT: [[BANG:%.*]] = alloca [[STRUCT_FOOSTRUCT:%.*]], align 8
-; DEFAULT-LIMIT-NEXT: [[V1:%.*]] = bitcast %struct.foostruct* [[BANG]] to i8*
-; DEFAULT-LIMIT-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[V1]], i64 32
-; DEFAULT-LIMIT-NEXT: call void @llvm.memset.p0i8.i64(i8* align 8 [[TMP0]], i8 0, i64 8, i1 false)
-; DEFAULT-LIMIT-NEXT: [[V2:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 0
-; DEFAULT-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V2]], align 8
-; DEFAULT-LIMIT-NEXT: [[V3:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 1
-; DEFAULT-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V3]], align 8
-; DEFAULT-LIMIT-NEXT: [[V4:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 2
-; DEFAULT-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V4]], align 8
-; DEFAULT-LIMIT-NEXT: [[V5:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 3
-; DEFAULT-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V5]], align 8
-; DEFAULT-LIMIT-NEXT: [[V6:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 4
-; DEFAULT-LIMIT-NEXT: store void (i8*, i32, i32)* null, void (i8*, i32, i32)** [[V6]], align 8
-; DEFAULT-LIMIT-NEXT: call void @goFunc(%struct.foostruct* [[BANG]])
-; DEFAULT-LIMIT-NEXT: ret void
-;
-; LARGER-LIMIT-LABEL: @test4(
-; LARGER-LIMIT-NEXT: entry:
-; LARGER-LIMIT-NEXT: [[BANG:%.*]] = alloca [[STRUCT_FOOSTRUCT:%.*]], align 8
-; LARGER-LIMIT-NEXT: [[V2:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 0
-; LARGER-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V2]], align 8
-; LARGER-LIMIT-NEXT: [[V3:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 1
-; LARGER-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V3]], align 8
-; LARGER-LIMIT-NEXT: [[V4:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 2
-; LARGER-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V4]], align 8
-; LARGER-LIMIT-NEXT: [[V5:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 3
-; LARGER-LIMIT-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V5]], align 8
-; LARGER-LIMIT-NEXT: [[V6:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 4
-; LARGER-LIMIT-NEXT: store void (i8*, i32, i32)* null, void (i8*, i32, i32)** [[V6]], align 8
-; LARGER-LIMIT-NEXT: call void @goFunc(%struct.foostruct* [[BANG]])
-; LARGER-LIMIT-NEXT: ret void
-;
+; CHECK-LABEL: @test4(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: [[BANG:%.*]] = alloca [[STRUCT_FOOSTRUCT:%.*]], align 8
+; CHECK-NEXT: [[V2:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 0
+; CHECK-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V2]], align 8
+; CHECK-NEXT: [[V3:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 1
+; CHECK-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V3]], align 8
+; CHECK-NEXT: [[V4:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 2
+; CHECK-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V4]], align 8
+; CHECK-NEXT: [[V5:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 3
+; CHECK-NEXT: store i32 (i8*, i8**, i32, i8, i8*)* @fa, i32 (i8*, i8**, i32, i8, i8*)** [[V5]], align 8
+; CHECK-NEXT: [[V6:%.*]] = getelementptr inbounds [[STRUCT_FOOSTRUCT]], %struct.foostruct* [[BANG]], i64 0, i32 4
+; CHECK-NEXT: store void (i8*, i32, i32)* null, void (i8*, i32, i32)** [[V6]], align 8
+; CHECK-NEXT: call void @goFunc(%struct.foostruct* [[BANG]])
+; CHECK-NEXT: ret void
entry:
%bang = alloca %struct.foostruct, align 8
diff --git a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-overlap.ll b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-overlap.ll
index 8a71c7397917..2ed717343a8a 100644
--- a/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-overlap.ll
+++ b/llvm/test/Transforms/DeadStoreElimination/MSSA/multiblock-overlap.ll
@@ -1,6 +1,5 @@
; NOTE: Assertions have been autogenerated by utils/update_test_checks.py
-; RUN: opt -dse %s -S | FileCheck --check-prefixes=CHECK,DEFAULT-LIMIT %s
-; RUN: opt -dse -dse-memoryssa-partial-store-limit=10 %s -S | FileCheck --check-prefixes=CHECK,LARGER-LIMIT %s
+; RUN: opt -dse %s -S | FileCheck --check-prefixes=CHECK %s
%struct.ham = type { [3 x double], [3 x double]}
@@ -11,52 +10,27 @@ declare void @llvm.memset.p0i8.i64(i8* nocapture writeonly, i8, i64, i1 immarg)
; We miss this case, because of an aggressive limit of partial overlap analysis.
; With a larger partial store limit, we remove the memset.
define void @overlap1(%struct.ham* %arg, i1 %cond) {
-; DEFAULT-LIMIT-LABEL: @overlap1(
-; DEFAULT-LIMIT-NEXT: bb:
-; DEFAULT-LIMIT-NEXT: [[TMP:%.*]] = getelementptr inbounds [[STRUCT_HAM:%.*]], %struct.ham* [[ARG:%.*]], i64 0, i32 0, i64 2
-; DEFAULT-LIMIT-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 1
-; DEFAULT-LIMIT-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 0
-; DEFAULT-LIMIT-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 2
-; DEFAULT-LIMIT-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 1
-; DEFAULT-LIMIT-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i32 0
-; DEFAULT-LIMIT-NEXT: [[TMP6:%.*]] = bitcast double* [[TMP2]] to i8*
-; DEFAULT-LIMIT-NEXT: [[TMP0:%.*]] = getelementptr inbounds i8, i8* [[TMP6]], i64 32
-; DEFAULT-LIMIT-NEXT: call void @llvm.memset.p0i8.i64(i8* nonnull align 8 dereferenceable(48) [[TMP0]], i8 0, i64 16, i1 false)
-; DEFAULT-LIMIT-NEXT: br i1 [[COND:%.*]], label [[BB7:%.*]], label [[BB8:%.*]]
-; DEFAULT-LIMIT: bb7:
-; DEFAULT-LIMIT-NEXT: br label [[BB9:%.*]]
-; DEFAULT-LIMIT: bb8:
-; DEFAULT-LIMIT-NEXT: br label [[BB9]]
-; DEFAULT-LIMIT: bb9:
-; DEFAULT-LIMIT-NEXT: store double 1.000000e+00, double* [[TMP2]], align 8
-; DEFAULT-LIMIT-NEXT: store double 2.000000e+00, double* [[TMP1]], align 8
-; DEFAULT-LIMIT-NEXT: store double 3.000000e+00, double* [[TMP]], align 8
-; DEFAULT-LIMIT-NEXT: store double 4.000000e+00, double* [[TMP5]], align 8
-; DEFAULT-LIMIT-NEXT: store double 5.000000e+00, double* [[TMP4]], align 8
-; DEFAULT-LIMIT-NEXT: store double 6.000000e+00, double* [[TMP3]], align 8
-; DEFAULT-LIMIT-NEXT: ret void
-;
-; LARGER-LIMIT-LABEL: @overlap1(
-; LARGER-LIMIT-NEXT: bb:
-; LARGER-LIMIT-NEXT: [[TMP:%.*]] = getelementptr inbounds [[STRUCT_HAM:%.*]], %struct.ham* [[ARG:%.*]], i64 0, i32 0, i64 2
-; LARGER-LIMIT-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 1
-; LARGER-LIMIT-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 0
-; LARGER-LIMIT-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 2
-; LARGER-LIMIT-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 1
-; LARGER-LIMIT-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i32 0
-; LARGER-LIMIT-NEXT: br i1 [[COND:%.*]], label [[BB7:%.*]], label [[BB8:%.*]]
-; LARGER-LIMIT: bb7:
-; LARGER-LIMIT-NEXT: br label [[BB9:%.*]]
-; LARGER-LIMIT: bb8:
-; LARGER-LIMIT-NEXT: br label [[BB9]]
-; LARGER-LIMIT: bb9:
-; LARGER-LIMIT-NEXT: store double 1.000000e+00, double* [[TMP2]], align 8
-; LARGER-LIMIT-NEXT: store double 2.000000e+00, double* [[TMP1]], align 8
-; LARGER-LIMIT-NEXT: store double 3.000000e+00, double* [[TMP]], align 8
-; LARGER-LIMIT-NEXT: store double 4.000000e+00, double* [[TMP5]], align 8
-; LARGER-LIMIT-NEXT: store double 5.000000e+00, double* [[TMP4]], align 8
-; LARGER-LIMIT-NEXT: store double 6.000000e+00, double* [[TMP3]], align 8
-; LARGER-LIMIT-NEXT: ret void
+; CHECK-LABEL: @overlap1(
+; CHECK-NEXT: bb:
+; CHECK-NEXT: [[TMP:%.*]] = getelementptr inbounds [[STRUCT_HAM:%.*]], %struct.ham* [[ARG:%.*]], i64 0, i32 0, i64 2
+; CHECK-NEXT: [[TMP1:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 1
+; CHECK-NEXT: [[TMP2:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 0, i64 0
+; CHECK-NEXT: [[TMP3:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 2
+; CHECK-NEXT: [[TMP4:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i64 1
+; CHECK-NEXT: [[TMP5:%.*]] = getelementptr inbounds [[STRUCT_HAM]], %struct.ham* [[ARG]], i64 0, i32 1, i32 0
+; CHECK-NEXT: br i1 [[COND:%.*]], label [[BB7:%.*]], label [[BB8:%.*]]
+; CHECK: bb7:
+; CHECK-NEXT: br label [[BB9:%.*]]
+; CHECK: bb8:
+; CHECK-NEXT: br label [[BB9]]
+; CHECK: bb9:
+; CHECK-NEXT: store double 1.000000e+00, double* [[TMP2]], align 8
+; CHECK-NEXT: store double 2.000000e+00, double* [[TMP1]], align 8
+; CHECK-NEXT: store double 3.000000e+00, double* [[TMP]], align 8
+; CHECK-NEXT: store double 4.000000e+00, double* [[TMP5]], align 8
+; CHECK-NEXT: store double 5.000000e+00, double* [[TMP4]], align 8
+; CHECK-NEXT: store double 6.000000e+00, double* [[TMP3]], align 8
+; CHECK-NEXT: ret void
;
bb:
%tmp = getelementptr inbounds %struct.ham, %struct.ham* %arg, i64 0, i32 0, i64 2
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/llvm-master-arm-spec2k6-O2 - Build # 10 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tk1/llvm-master-arm-spec2k6-O2
Culprit:
<cut>
commit d181fd918d18cbd99768f025e14a69d35d275f14
Author: Simon Pilgrim <llvm-dev(a)redking.me.uk>
Date: Fri Jul 2 14:27:27 2021 +0100
[CostModel][X86] Drop some hard coded fp<->int scalarization costs
Scalarization costs handling is a lot better now, and the hard coded costs were higher than the worse case numbers from the script in D103695
</cut>
Results regressed to (for first_bad == d181fd918d18cbd99768f025e14a69d35d275f14)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-d181fd918d18cbd99768f025e14a69d35d275f14/results_id:
1
# 400.perlbench,libc-2.33.9000.so regressed by 113
from (for last_good == 5df556ac8bb8c5f4ef3dff1a2039dd389d1d27c0)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_marm -- artifacts/build-5df556ac8bb8c5f4ef3dff1a2039dd389d1d27c0/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Results ID of last_good: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-O2/1840
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Results ID of first_bad: tk1_32/tcwg_bmk_llvm_tk1/bisect-llvm-master-arm-spec2k6-O2/1837
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-d181fd918d18cbd99768f025e14a69d35d275f14
cd investigate-llvm-d181fd918d18cbd99768f025e14a69d35d275f14
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach d181fd918d18cbd99768f025e14a69d35d275f14
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 5df556ac8bb8c5f4ef3dff1a2039dd389d1d27c0
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tk1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit d181fd918d18cbd99768f025e14a69d35d275f14
Author: Simon Pilgrim <llvm-dev(a)redking.me.uk>
Date: Fri Jul 2 14:27:27 2021 +0100
[CostModel][X86] Drop some hard coded fp<->int scalarization costs
Scalarization costs handling is a lot better now, and the hard coded costs were higher than the worse case numbers from the script in D103695
---
llvm/lib/Target/X86/X86TargetTransformInfo.cpp | 13 -------------
llvm/test/Analysis/CostModel/X86/sitofp.ll | 6 +++---
2 files changed, 3 insertions(+), 16 deletions(-)
diff --git a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
index d55cd8a8c7a8..9eb5abe4dd9b 100644
--- a/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
+++ b/llvm/lib/Target/X86/X86TargetTransformInfo.cpp
@@ -1977,13 +1977,6 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
{ ISD::UINT_TO_FP, MVT::v8f64, MVT::v8i32, 10 },
{ ISD::UINT_TO_FP, MVT::v2f64, MVT::v2i64, 5 },
{ ISD::UINT_TO_FP, MVT::v4f64, MVT::v4i64, 6 },
- // The generic code to compute the scalar overhead is currently broken.
- // Workaround this limitation by estimating the scalarization overhead
- // here. We have roughly 10 instructions per scalar element.
- // Multiply that by the vector width.
- // FIXME: remove that when PR19268 is fixed.
- { ISD::SINT_TO_FP, MVT::v4f64, MVT::v4i64, 13 },
- { ISD::SINT_TO_FP, MVT::v4f64, MVT::v4i64, 13 },
{ ISD::FP_TO_SINT, MVT::v8i8, MVT::v8f32, 4 },
{ ISD::FP_TO_SINT, MVT::v4i8, MVT::v4f64, 3 },
@@ -2003,12 +1996,6 @@ InstructionCost X86TTIImpl::getCastInstrCost(unsigned Opcode, Type *Dst,
{ ISD::FP_TO_UINT, MVT::v8i16, MVT::v8f32, 3 },
{ ISD::FP_TO_UINT, MVT::v8i32, MVT::v8f32, 9 },
{ ISD::FP_TO_UINT, MVT::v8i32, MVT::v8f64, 19 },
- // This node is expanded into scalarized operations but BasicTTI is overly
- // optimistic estimating its cost. It computes 3 per element (one
- // vector-extract, one scalar conversion and one vector-insert). The
- // problem is that the inserts form a read-modify-write chain so latency
- // should be factored in too. Inflating the cost per element by 1.
- { ISD::FP_TO_UINT, MVT::v4i32, MVT::v4f64, 4*4 },
{ ISD::FP_EXTEND, MVT::v4f64, MVT::v4f32, 1 },
{ ISD::FP_ROUND, MVT::v4f32, MVT::v4f64, 1 },
diff --git a/llvm/test/Analysis/CostModel/X86/sitofp.ll b/llvm/test/Analysis/CostModel/X86/sitofp.ll
index b3c400c93b9f..b327454c1d09 100644
--- a/llvm/test/Analysis/CostModel/X86/sitofp.ll
+++ b/llvm/test/Analysis/CostModel/X86/sitofp.ll
@@ -122,14 +122,14 @@ define i32 @sitofp_i64_double() {
; AVX-LABEL: 'sitofp_i64_double'
; AVX-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cvt_i64_f64 = sitofp i64 undef to double
; AVX-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %cvt_v2i64_v2f64 = sitofp <2 x i64> undef to <2 x double>
-; AVX-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cvt_v4i64_v4f64 = sitofp <4 x i64> undef to <4 x double>
-; AVX-NEXT: Cost Model: Found an estimated cost of 26 for instruction: %cvt_v8i64_v8f64 = sitofp <8 x i64> undef to <8 x double>
+; AVX-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %cvt_v4i64_v4f64 = sitofp <4 x i64> undef to <4 x double>
+; AVX-NEXT: Cost Model: Found an estimated cost of 22 for instruction: %cvt_v8i64_v8f64 = sitofp <8 x i64> undef to <8 x double>
; AVX-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
; AVX512F-LABEL: 'sitofp_i64_double'
; AVX512F-NEXT: Cost Model: Found an estimated cost of 1 for instruction: %cvt_i64_f64 = sitofp i64 undef to double
; AVX512F-NEXT: Cost Model: Found an estimated cost of 8 for instruction: %cvt_v2i64_v2f64 = sitofp <2 x i64> undef to <2 x double>
-; AVX512F-NEXT: Cost Model: Found an estimated cost of 13 for instruction: %cvt_v4i64_v4f64 = sitofp <4 x i64> undef to <4 x double>
+; AVX512F-NEXT: Cost Model: Found an estimated cost of 11 for instruction: %cvt_v4i64_v4f64 = sitofp <4 x i64> undef to <4 x double>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 25 for instruction: %cvt_v8i64_v8f64 = sitofp <8 x i64> undef to <8 x double>
; AVX512F-NEXT: Cost Model: Found an estimated cost of 0 for instruction: ret i32 undef
;
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-master-aarch64-spec2k6-O2_LTO - Build # 18 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2_LTO. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-master-aarch64-spec2k6-O2_LTO
Culprit:
<cut>
commit 428a62f65f16f1640b1bfe033d20e6a4f545dd3e
Author: thomasraoux <thomasraoux(a)google.com>
Date: Wed Jun 9 09:42:32 2021 -0700
[mlir][gpu] Add op to create MMA constant matrix
This allow creating a matrix with all elements set to a given value. This is
needed to be able to implement a simple dot op.
Differential Revision: https://reviews.llvm.org/D103870
</cut>
Results regressed to (for first_bad == 428a62f65f16f1640b1bfe033d20e6a4f545dd3e)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_LTO -- artifacts/build-428a62f65f16f1640b1bfe033d20e6a4f545dd3e/results_id:
1
# 400.perlbench,perlbench_base.default regressed by 103
from (for last_good == 3b46283c1539f89619f2b40ab7732f434d7c68ff)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O2_LTO -- artifacts/build-3b46283c1539f89619f2b40ab7732f434d7c68ff/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2_LTO/1827
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-master-aarch64-spec2k6-O2_LTO/1831
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-428a62f65f16f1640b1bfe033d20e6a4f545dd3e
cd investigate-llvm-428a62f65f16f1640b1bfe033d20e6a4f545dd3e
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 428a62f65f16f1640b1bfe033d20e6a4f545dd3e
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 3b46283c1539f89619f2b40ab7732f434d7c68ff
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-master-…
Full commit (up to 1000 lines):
<cut>
commit 428a62f65f16f1640b1bfe033d20e6a4f545dd3e
Author: thomasraoux <thomasraoux(a)google.com>
Date: Wed Jun 9 09:42:32 2021 -0700
[mlir][gpu] Add op to create MMA constant matrix
This allow creating a matrix with all elements set to a given value. This is
needed to be able to implement a simple dot op.
Differential Revision: https://reviews.llvm.org/D103870
---
mlir/include/mlir/Dialect/GPU/GPUOps.td | 45 ++++++++++++++++++++++
mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp | 42 +++++++++++++++++++-
.../Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir | 25 ++++++++++++
mlir/test/Dialect/GPU/ops.mlir | 4 ++
4 files changed, 115 insertions(+), 1 deletion(-)
diff --git a/mlir/include/mlir/Dialect/GPU/GPUOps.td b/mlir/include/mlir/Dialect/GPU/GPUOps.td
index 8e2520b675ae..1e78e4af4d51 100644
--- a/mlir/include/mlir/Dialect/GPU/GPUOps.td
+++ b/mlir/include/mlir/Dialect/GPU/GPUOps.td
@@ -1022,4 +1022,49 @@ def GPU_SubgroupMmaComputeOp : GPU_Op<"subgroup_mma_compute",
let verifier = [{ return ::verify(*this); }];
}
+def GPU_SubgroupMmaConstantMatrixOp : GPU_Op<"subgroup_mma_constant_matrix",
+ [NoSideEffect,
+ TypesMatchWith<"value type matches element type of mma_matrix",
+ "res", "value",
+ "$_self.cast<gpu::MMAMatrixType>().getElementType()">]>{
+
+ let summary = "GPU warp synchronous constant matrix";
+
+ let description = [{
+ The `gpu.subgroup_mma_constant_matrix` creates a `!gpu.mma_matrix` with
+ constant elements.
+
+ The operation takes a scalar input and return a `!gpu.mma_matrix` where each
+ element of is equal to the operand constant. The destination mma_matrix type
+ must have elememt type equal to the constant type. Since the layout of
+ `!gpu.mma_matrix` is opaque this only support setting all the elements to
+ the same value.
+
+ This op is meant to be used along with `gpu.subgroup_mma_compute`.
+
+ Example:
+
+ ```mlir
+ %0 = gpu.subgroup_mma_constant_matrix %a :
+ !gpu.mma_matrix<16x16xf16, "AOp">
+ %1 = gpu.subgroup_mma_constant_matrix %b :
+ !gpu.mma_matrix<16x16xf32, "COp">
+ ```
+ }];
+
+ let arguments = (ins AnyTypeOf<[F16, F32]>:$value);
+
+ let results = (outs GPU_MMAMatrix:$res);
+
+ let extraClassDeclaration = [{
+ gpu::MMAMatrixType getType() {
+ return res().getType().cast<gpu::MMAMatrixType>();
+ }
+ }];
+
+ let assemblyFormat = [{
+ $value attr-dict `:` type($res)
+ }];
+}
+
#endif // GPU_OPS
diff --git a/mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp b/mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
index d72c8c217f86..d46a185dec22 100644
--- a/mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
+++ b/mlir/lib/Conversion/GPUToNVVM/WmmaOpsToNvvm.cpp
@@ -348,12 +348,52 @@ struct WmmaMmaOpToNVVMLowering
}
};
+/// Convert GPU MMA ConstantMatrixOp to a chain of InsertValueOp.
+struct WmmaConstantOpToNVVMLowering
+ : public ConvertOpToLLVMPattern<gpu::SubgroupMmaConstantMatrixOp> {
+ using ConvertOpToLLVMPattern<
+ gpu::SubgroupMmaConstantMatrixOp>::ConvertOpToLLVMPattern;
+
+ LogicalResult
+ matchAndRewrite(gpu::SubgroupMmaConstantMatrixOp subgroupMmaConstantOp,
+ ArrayRef<Value> operands,
+ ConversionPatternRewriter &rewriter) const override {
+ if (failed(areAllLLVMTypes(subgroupMmaConstantOp.getOperation(), operands,
+ rewriter)))
+ return failure();
+ Location loc = subgroupMmaConstantOp.getLoc();
+ Value cst = operands[0];
+ LLVM::LLVMStructType type = convertMMAToLLVMType(
+ subgroupMmaConstantOp.getType().cast<gpu::MMAMatrixType>());
+ // If the element type is a vector create a vector from the operand.
+ if (auto vecType = type.getBody()[0].dyn_cast<VectorType>()) {
+ Value vecCst = rewriter.create<LLVM::UndefOp>(loc, vecType);
+ for (int64_t vecEl = 0; vecEl < vecType.getNumElements(); vecEl++) {
+ Value idx = rewriter.create<LLVM::ConstantOp>(
+ loc, typeConverter->convertType(rewriter.getIntegerType(32)),
+ rewriter.getI32ArrayAttr(vecEl));
+ vecCst = rewriter.create<LLVM::InsertElementOp>(loc, vecType, vecCst,
+ cst, idx);
+ }
+ cst = vecCst;
+ }
+ Value matrixStruct = rewriter.create<LLVM::UndefOp>(loc, type);
+ for (size_t i : llvm::seq(size_t(0), type.getBody().size())) {
+ matrixStruct = rewriter.create<LLVM::InsertValueOp>(
+ loc, matrixStruct, cst, rewriter.getI32ArrayAttr(i));
+ }
+ rewriter.replaceOp(subgroupMmaConstantOp, matrixStruct);
+ return success();
+ }
+};
+
} // anonymous namespace
namespace mlir {
void populateGpuWMMAToNVVMConversionPatterns(LLVMTypeConverter &converter,
RewritePatternSet &patterns) {
patterns.insert<WmmaLoadOpToNVVMLowering, WmmaMmaOpToNVVMLowering,
- WmmaStoreOpToNVVMLowering>(converter);
+ WmmaStoreOpToNVVMLowering, WmmaConstantOpToNVVMLowering>(
+ converter);
}
} // namespace mlir
diff --git a/mlir/test/Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir b/mlir/test/Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir
index de5d0d3fcf1c..f692dffdfcba 100644
--- a/mlir/test/Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir
+++ b/mlir/test/Conversion/GPUToNVVM/wmma-ops-to-nvvm.mlir
@@ -151,3 +151,28 @@ gpu.module @test_module {
return
}
}
+
+
+// -----
+
+gpu.module @test_module {
+
+// CHECK-LABEL: func @gpu_wmma_constant_op
+// CHECK: %[[CST:.+]] = llvm.mlir.constant(1.000000e+00 : f16) : f16
+// CHECK: %[[V0:.+]] = llvm.mlir.undef : vector<2xf16>
+// CHECK: %[[C0:.+]] = llvm.mlir.constant([0 : i32]) : i32
+// CHECK: %[[V1:.+]] = llvm.insertelement %[[CST]], %[[V0]][%[[C0]] : i32] : vector<2xf16>
+// CHECK: %[[C1:.+]] = llvm.mlir.constant([1 : i32]) : i32
+// CHECK: %[[V2:.+]] = llvm.insertelement %[[CST]], %[[V1]][%[[C1]] : i32] : vector<2xf16>
+// CHECK: %[[M0:.+]] = llvm.mlir.undef : !llvm.struct<(vector<2xf16>, vector<2xf16>, vector<2xf16>, vector<2xf16>)>
+// CHECK: %[[M1:.+]] = llvm.insertvalue %[[V2]], %[[M0]][0 : i32] : !llvm.struct<(vector<2xf16>, vector<2xf16>, vector<2xf16>, vector<2xf16>)>
+// CHECK: %[[M2:.+]] = llvm.insertvalue %[[V2]], %[[M1]][1 : i32] : !llvm.struct<(vector<2xf16>, vector<2xf16>, vector<2xf16>, vector<2xf16>)>
+// CHECK: %[[M3:.+]] = llvm.insertvalue %[[V2]], %[[M2]][2 : i32] : !llvm.struct<(vector<2xf16>, vector<2xf16>, vector<2xf16>, vector<2xf16>)>
+// CHECK: %[[M4:.+]] = llvm.insertvalue %[[V2]], %[[M3]][3 : i32] : !llvm.struct<(vector<2xf16>, vector<2xf16>, vector<2xf16>, vector<2xf16>)>
+// CHECK: llvm.return %[[M4]] : !llvm.struct<(vector<2xf16>, vector<2xf16>, vector<2xf16>, vector<2xf16>)>
+ func @gpu_wmma_constant_op() ->(!gpu.mma_matrix<16x16xf16, "COp">) {
+ %cst = constant 1.0 : f16
+ %C = gpu.subgroup_mma_constant_matrix %cst : !gpu.mma_matrix<16x16xf16, "COp">
+ return %C : !gpu.mma_matrix<16x16xf16, "COp">
+ }
+}
diff --git a/mlir/test/Dialect/GPU/ops.mlir b/mlir/test/Dialect/GPU/ops.mlir
index a98fe1c49683..1bed13c4b21a 100644
--- a/mlir/test/Dialect/GPU/ops.mlir
+++ b/mlir/test/Dialect/GPU/ops.mlir
@@ -201,8 +201,12 @@ module attributes {gpu.container_module} {
// CHECK: %[[wg:.*]] = memref.alloca()
%i = constant 16 : index
// CHECK: %[[i:.*]] = constant 16 : index
+ %cst = constant 1.000000e+00 : f32
+ // CHECK: %[[cst:.*]] = constant 1.000000e+00 : f32
%0 = gpu.subgroup_mma_load_matrix %wg[%i, %i] {leadDimension = 32 : index} : memref<32x32xf16, 3> -> !gpu.mma_matrix<16x16xf16, "AOp">
// CHECK: gpu.subgroup_mma_load_matrix %[[wg]][%[[i]], %[[i]]] {leadDimension = 32 : index} : memref<32x32xf16, 3> -> !gpu.mma_matrix<16x16xf16, "AOp">
+ %1 = gpu.subgroup_mma_constant_matrix %cst : !gpu.mma_matrix<16x16xf32, "COp">
+ // CHECK: gpu.subgroup_mma_constant_matrix %[[cst]] : !gpu.mma_matrix<16x16xf32, "COp">
return
}
}
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tk1/gnu-release-arm-spec2k6-O2 - Build # 22 - Fixed!
by ci_notify＠linaro.org
Successfully identified regression in *gcc* in CI configuration tcwg_bmk_gnu_tk1/gnu-release-arm-spec2k6-O2. So far, this commit has regressed CI configurations:
- tcwg_bmk_gnu_tk1/gnu-release-arm-spec2k6-O2
Culprit:
<cut>
commit bf09e559b22b44e74a91ccc00507a1885ec3d578
Author: Thomas Koenig <tkoenig(a)gcc.gnu.org>
Date: Sun May 19 10:21:06 2019 +0000
re PR fortran/88821 (Inline packing of non-contiguous arguments)
2019-05-19 Thomas Koenig <tkoenig(a)gcc.gnu.org>
PR fortran/88821
* expr.c (gfc_is_simply_contiguous): Return true for
an EXPR_ARRAY.
* trans-array.c (is_pointer): New function.
(gfc_conv_array_parameter): Call gfc_conv_subref_array_arg
when not optimizing and not optimizing for size if the formal
arg is passed by reference.
* trans-expr.c (gfc_conv_subref_array_arg): Add arguments
fsym, proc_name and sym. Add run-time warning for temporary
array creation. Wrap argument if passing on an optional
argument to an optional argument.
* trans.h (gfc_conv_subref_array_arg): Add optional arguments
fsym, proc_name and sym to prototype.
2019-05-19 Thomas Koenig <tkoenig(a)gcc.gnu.org>
PR fortran/88821
* gfortran.dg/alloc_comp_auto_array_3.f90: Add -O0 to dg-options
to make sure the test for internal_pack is retained.
* gfortran.dg/assumed_type_2.f90: Split compile and run time
tests into this and
* gfortran.dg/assumed_type_2a.f90: New file.
* gfortran.dg/c_loc_test_22.f90: Likewise.
* gfortran.dg/contiguous_3.f90: Likewise.
* gfortran.dg/internal_pack_11.f90: Likewise.
* gfortran.dg/internal_pack_12.f90: Likewise.
* gfortran.dg/internal_pack_16.f90: Likewise.
* gfortran.dg/internal_pack_17.f90: Likewise.
* gfortran.dg/internal_pack_18.f90: Likewise.
* gfortran.dg/internal_pack_4.f90: Likewise.
* gfortran.dg/internal_pack_5.f90: Add -O0 to dg-options
to make sure the test for internal_pack is retained.
* gfortran.dg/internal_pack_6.f90: Split compile and run time
tests into this and
* gfortran.dg/internal_pack_6a.f90: New file.
* gfortran.dg/internal_pack_8.f90: Likewise.
* gfortran.dg/missing_optional_dummy_6: Split compile and run time
tests into this and
* gfortran.dg/missing_optional_dummy_6a.f90: New file.
* gfortran.dg/no_arg_check_2.f90: Split compile and run time tests
into this and
* gfortran.dg/no_arg_check_2a.f90: New file.
* gfortran.dg/typebound_assignment_5.f90: Split compile and run time
tests into this and
* gfortran.dg/typebound_assignment_5a.f90: New file.
* gfortran.dg/typebound_assignment_6.f90: Split compile and run time
tests into this and
* gfortran.dg/typebound_assignment_6a.f90: New file.
* gfortran.dg/internal_pack_19.f90: New file.
* gfortran.dg/internal_pack_20.f90: New file.
* gfortran.dg/internal_pack_21.f90: New file.
From-SVN: r271377
</cut>
Results regressed to (for first_bad == bf09e559b22b44e74a91ccc00507a1885ec3d578)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2_marm -- artifacts/build-bf09e559b22b44e74a91ccc00507a1885ec3d578/results_id:
1
# 481.wrf,wrf_base.default regressed by 107
# 481.wrf,[.] __module_small_step_em_MOD_advance_w regressed by 112
from (for last_good == 14688b8de389740f07079a945edf887a682fc9d1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--with-mode=arm --set gcc_override_configure=--disable-libsanitizer:
-5
# true:
0
# benchmark -O2_marm -- artifacts/build-14688b8de389740f07079a945edf887a682fc9d1/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Results ID of last_good: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-release-arm-spec2k6-O2/1812
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Results ID of first_bad: tk1_32/tcwg_bmk_gnu_tk1/bisect-gnu-release-arm-spec2k6-O2/1816
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-gcc-bf09e559b22b44e74a91ccc00507a1885ec3d578
cd investigate-gcc-bf09e559b22b44e74a91ccc00507a1885ec3d578
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude gcc/ ./ ./bisect/baseline/
cd gcc
# Reproduce first_bad build
git checkout --detach bf09e559b22b44e74a91ccc00507a1885ec3d578
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 14688b8de389740f07079a945edf887a682fc9d1
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_gnu-bisect-tcwg_bmk_tk1-gnu-release-a…
Full commit (up to 1000 lines):
<cut>
commit bf09e559b22b44e74a91ccc00507a1885ec3d578
Author: Thomas Koenig <tkoenig(a)gcc.gnu.org>
Date: Sun May 19 10:21:06 2019 +0000
re PR fortran/88821 (Inline packing of non-contiguous arguments)
2019-05-19 Thomas Koenig <tkoenig(a)gcc.gnu.org>
PR fortran/88821
* expr.c (gfc_is_simply_contiguous): Return true for
an EXPR_ARRAY.
* trans-array.c (is_pointer): New function.
(gfc_conv_array_parameter): Call gfc_conv_subref_array_arg
when not optimizing and not optimizing for size if the formal
arg is passed by reference.
* trans-expr.c (gfc_conv_subref_array_arg): Add arguments
fsym, proc_name and sym. Add run-time warning for temporary
array creation. Wrap argument if passing on an optional
argument to an optional argument.
* trans.h (gfc_conv_subref_array_arg): Add optional arguments
fsym, proc_name and sym to prototype.
2019-05-19 Thomas Koenig <tkoenig(a)gcc.gnu.org>
PR fortran/88821
* gfortran.dg/alloc_comp_auto_array_3.f90: Add -O0 to dg-options
to make sure the test for internal_pack is retained.
* gfortran.dg/assumed_type_2.f90: Split compile and run time
tests into this and
* gfortran.dg/assumed_type_2a.f90: New file.
* gfortran.dg/c_loc_test_22.f90: Likewise.
* gfortran.dg/contiguous_3.f90: Likewise.
* gfortran.dg/internal_pack_11.f90: Likewise.
* gfortran.dg/internal_pack_12.f90: Likewise.
* gfortran.dg/internal_pack_16.f90: Likewise.
* gfortran.dg/internal_pack_17.f90: Likewise.
* gfortran.dg/internal_pack_18.f90: Likewise.
* gfortran.dg/internal_pack_4.f90: Likewise.
* gfortran.dg/internal_pack_5.f90: Add -O0 to dg-options
to make sure the test for internal_pack is retained.
* gfortran.dg/internal_pack_6.f90: Split compile and run time
tests into this and
* gfortran.dg/internal_pack_6a.f90: New file.
* gfortran.dg/internal_pack_8.f90: Likewise.
* gfortran.dg/missing_optional_dummy_6: Split compile and run time
tests into this and
* gfortran.dg/missing_optional_dummy_6a.f90: New file.
* gfortran.dg/no_arg_check_2.f90: Split compile and run time tests
into this and
* gfortran.dg/no_arg_check_2a.f90: New file.
* gfortran.dg/typebound_assignment_5.f90: Split compile and run time
tests into this and
* gfortran.dg/typebound_assignment_5a.f90: New file.
* gfortran.dg/typebound_assignment_6.f90: Split compile and run time
tests into this and
* gfortran.dg/typebound_assignment_6a.f90: New file.
* gfortran.dg/internal_pack_19.f90: New file.
* gfortran.dg/internal_pack_20.f90: New file.
* gfortran.dg/internal_pack_21.f90: New file.
From-SVN: r271377
---
gcc/fortran/expr.c | 3 +
gcc/fortran/trans-array.c | 31 +++++
gcc/fortran/trans-expr.c | 83 +++++++++++-
gcc/fortran/trans.h | 5 +-
.../gfortran.dg/alloc_comp_auto_array_3.f90 | 2 +-
gcc/testsuite/gfortran.dg/assumed_type_2.f90 | 4 +-
gcc/testsuite/gfortran.dg/assumed_type_2a.f90 | 139 +++++++++++++++++++++
gcc/testsuite/gfortran.dg/c_loc_test_22.f90 | 2 +-
gcc/testsuite/gfortran.dg/contiguous_3.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_11.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_12.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_16.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_17.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_18.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_19.f90 | 23 ++++
gcc/testsuite/gfortran.dg/internal_pack_20.f90 | 23 ++++
gcc/testsuite/gfortran.dg/internal_pack_21.f90 | 24 ++++
gcc/testsuite/gfortran.dg/internal_pack_4.f90 | 4 -
gcc/testsuite/gfortran.dg/internal_pack_5.f90 | 2 +-
gcc/testsuite/gfortran.dg/internal_pack_6.f90 | 4 +-
gcc/testsuite/gfortran.dg/internal_pack_6a.f90 | 56 +++++++++
gcc/testsuite/gfortran.dg/internal_pack_9.f90 | 2 +-
.../gfortran.dg/missing_optional_dummy_6.f90 | 11 --
.../gfortran.dg/missing_optional_dummy_6a.f90 | 59 +++++++++
gcc/testsuite/gfortran.dg/no_arg_check_2.f90 | 4 +-
gcc/testsuite/gfortran.dg/no_arg_check_2a.f90 | 121 ++++++++++++++++++
.../gfortran.dg/typebound_assignment_5.f03 | 4 +-
.../gfortran.dg/typebound_assignment_5a.f03 | 39 ++++++
.../gfortran.dg/typebound_assignment_6.f03 | 4 -
.../gfortran.dg/typebound_assignment_6a.f03 | 42 +++++++
30 files changed, 663 insertions(+), 40 deletions(-)
diff --git a/gcc/fortran/expr.c b/gcc/fortran/expr.c
index 474e9ecc401..949eff19cdd 100644
--- a/gcc/fortran/expr.c
+++ b/gcc/fortran/expr.c
@@ -5713,6 +5713,9 @@ gfc_is_simply_contiguous (gfc_expr *expr, bool strict, bool permit_element)
gfc_ref *ref, *part_ref = NULL;
gfc_symbol *sym;
+ if (expr->expr_type == EXPR_ARRAY)
+ return true;
+
if (expr->expr_type == EXPR_FUNCTION)
{
if (expr->value.function.esym)
diff --git a/gcc/fortran/trans-array.c b/gcc/fortran/trans-array.c
index 8a0de6140ed..9c96d897f41 100644
--- a/gcc/fortran/trans-array.c
+++ b/gcc/fortran/trans-array.c
@@ -7866,6 +7866,23 @@ array_parameter_size (tree desc, gfc_expr *expr, tree *size)
*size, fold_convert (gfc_array_index_type, elem));
}
+/* Helper function - return true if the argument is a pointer. */
+
+static bool
+is_pointer (gfc_expr *e)
+{
+ gfc_symbol *sym;
+
+ if (e->expr_type != EXPR_VARIABLE || e->symtree == NULL)
+ return false;
+
+ sym = e->symtree->n.sym;
+ if (sym == NULL)
+ return false;
+
+ return sym->attr.pointer || sym->attr.proc_pointer;
+}
+
/* Convert an array for passing as an actual parameter. */
void
@@ -8117,6 +8134,20 @@ gfc_conv_array_parameter (gfc_se * se, gfc_expr * expr, bool g77,
"Creating array temporary at %L", &expr->where);
}
+ /* When optmizing, we can use gfc_conv_subref_array_arg for
+ making the packing and unpacking operation visible to the
+ optimizers. */
+
+ if (g77 && optimize && !optimize_size && expr->expr_type == EXPR_VARIABLE
+ && !is_pointer (expr) && (fsym == NULL
+ || fsym->ts.type != BT_ASSUMED))
+ {
+ gfc_conv_subref_array_arg (se, expr, g77,
+ fsym ? fsym->attr.intent : INTENT_INOUT,
+ false, fsym, proc_name, sym);
+ return;
+ }
+
ptr = build_call_expr_loc (input_location,
gfor_fndecl_in_pack, 1, desc);
diff --git a/gcc/fortran/trans-expr.c b/gcc/fortran/trans-expr.c
index 3711c38b2f2..b7a8456c021 100644
--- a/gcc/fortran/trans-expr.c
+++ b/gcc/fortran/trans-expr.c
@@ -4576,8 +4576,10 @@ gfc_apply_interface_mapping (gfc_interface_mapping * mapping,
an actual argument derived type array is copied and then returned
after the function call. */
void
-gfc_conv_subref_array_arg (gfc_se * parmse, gfc_expr * expr, int g77,
- sym_intent intent, bool formal_ptr)
+gfc_conv_subref_array_arg (gfc_se *se, gfc_expr * expr, int g77,
+ sym_intent intent, bool formal_ptr,
+ const gfc_symbol *fsym, const char *proc_name,
+ gfc_symbol *sym)
{
gfc_se lse;
gfc_se rse;
@@ -4594,6 +4596,36 @@ gfc_conv_subref_array_arg (gfc_se * parmse, gfc_expr * expr, int g77,
stmtblock_t body;
int n;
int dimen;
+ gfc_se work_se;
+ gfc_se *parmse;
+ bool pass_optional;
+
+ pass_optional = fsym && fsym->attr.optional && sym && sym->attr.optional;
+
+ if (pass_optional)
+ {
+ gfc_init_se (&work_se, NULL);
+ parmse = &work_se;
+ }
+ else
+ parmse = se;
+
+ if (gfc_option.rtcheck & GFC_RTCHECK_ARRAY_TEMPS)
+ {
+ /* We will create a temporary array, so let us warn. */
+ char * msg;
+
+ if (fsym && proc_name)
+ msg = xasprintf ("An array temporary was created for argument "
+ "'%s' of procedure '%s'", fsym->name, proc_name);
+ else
+ msg = xasprintf ("An array temporary was created");
+
+ tmp = build_int_cst (logical_type_node, 1);
+ gfc_trans_runtime_check (false, true, tmp, &parmse->pre,
+ &expr->where, msg);
+ free (msg);
+ }
gfc_init_se (&lse, NULL);
gfc_init_se (&rse, NULL);
@@ -4848,6 +4880,53 @@ class_array_fcn:
else
parmse->expr = gfc_build_addr_expr (NULL_TREE, parmse->expr);
+ if (pass_optional)
+ {
+ tree present;
+ tree type;
+ stmtblock_t else_block;
+ tree pre_stmts, post_stmts;
+ tree pointer;
+ tree else_stmt;
+
+ /* Make this into
+
+ if (present (a))
+ {
+ parmse->pre;
+ optional = parse->expr;
+ }
+ else
+ optional = NULL;
+ call foo (optional);
+ if (present (a))
+ parmse->post;
+
+ */
+
+ type = TREE_TYPE (parmse->expr);
+ pointer = gfc_create_var (type, "optional");
+ tmp = gfc_conv_expr_present (sym);
+ present = gfc_evaluate_now (tmp, &se->pre);
+ gfc_add_modify (&parmse->pre, pointer, parmse->expr);
+ pre_stmts = gfc_finish_block (&parmse->pre);
+
+ gfc_init_block (&else_block);
+ gfc_add_modify (&else_block, pointer, build_int_cst (type, 0));
+ else_stmt = gfc_finish_block (&else_block);
+
+ tmp = fold_build3_loc (input_location, COND_EXPR, void_type_node, present,
+ pre_stmts, else_stmt);
+ gfc_add_expr_to_block (&se->pre, tmp);
+
+ post_stmts = gfc_finish_block (&parmse->post);
+ tmp = fold_build3_loc (input_location, COND_EXPR, void_type_node, present,
+ post_stmts, build_empty_stmt (input_location));
+ gfc_add_expr_to_block (&se->post, tmp);
+
+ se->expr = pointer;
+ }
+
return;
}
diff --git a/gcc/fortran/trans.h b/gcc/fortran/trans.h
index 273c75a422c..e0118abaf18 100644
--- a/gcc/fortran/trans.h
+++ b/gcc/fortran/trans.h
@@ -532,7 +532,10 @@ int gfc_is_intrinsic_libcall (gfc_expr *);
int gfc_conv_procedure_call (gfc_se *, gfc_symbol *, gfc_actual_arglist *,
gfc_expr *, vec<tree, va_gc> *);
-void gfc_conv_subref_array_arg (gfc_se *, gfc_expr *, int, sym_intent, bool);
+void gfc_conv_subref_array_arg (gfc_se *, gfc_expr *, int, sym_intent, bool,
+ const gfc_symbol *fsym = NULL,
+ const char *proc_name = NULL,
+ gfc_symbol *sym = NULL);
/* Generate code for a scalar assignment. */
tree gfc_trans_scalar_assign (gfc_se *, gfc_se *, gfc_typespec, bool, bool,
diff --git a/gcc/testsuite/gfortran.dg/alloc_comp_auto_array_3.f90 b/gcc/testsuite/gfortran.dg/alloc_comp_auto_array_3.f90
index 15f9ecb74de..2af089e84e8 100644
--- a/gcc/testsuite/gfortran.dg/alloc_comp_auto_array_3.f90
+++ b/gcc/testsuite/gfortran.dg/alloc_comp_auto_array_3.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! Test the fix for PR66082. The original problem was with the first
! call foo_1d.
diff --git a/gcc/testsuite/gfortran.dg/assumed_type_2.f90 b/gcc/testsuite/gfortran.dg/assumed_type_2.f90
index dce5ac6839c..5d3cd7eaece 100644
--- a/gcc/testsuite/gfortran.dg/assumed_type_2.f90
+++ b/gcc/testsuite/gfortran.dg/assumed_type_2.f90
@@ -1,5 +1,5 @@
-! { dg-do run }
-! { dg-options "-fdump-tree-original" }
+! { dg-do compile }
+! { dg-options "-O0 -fdump-tree-original" }
!
! PR fortran/48820
!
diff --git a/gcc/testsuite/gfortran.dg/assumed_type_2a.f90 b/gcc/testsuite/gfortran.dg/assumed_type_2a.f90
new file mode 100644
index 00000000000..125bfcbe839
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/assumed_type_2a.f90
@@ -0,0 +1,139 @@
+! { dg-do run }
+!
+! PR fortran/48820
+!
+! Test TYPE(*)
+!
+
+module mod
+ use iso_c_binding, only: c_loc, c_ptr, c_bool
+ implicit none
+ interface my_c_loc
+ function my_c_loc1(x) bind(C)
+ import c_ptr
+ type(*) :: x
+ type(c_ptr) :: my_c_loc1
+ end function
+ function my_c_loc2(x) bind(C)
+ import c_ptr
+ type(*) :: x(*)
+ type(c_ptr) :: my_c_loc2
+ end function
+ end interface my_c_loc
+contains
+ subroutine sub_scalar (arg1, presnt)
+ type(*), target, optional :: arg1
+ logical :: presnt
+ type(c_ptr) :: cpt
+ if (presnt .neqv. present (arg1)) STOP 1
+ cpt = c_loc (arg1)
+ end subroutine sub_scalar
+
+ subroutine sub_array_shape (arg2, lbounds, ubounds)
+ type(*), target :: arg2(:,:)
+ type(c_ptr) :: cpt
+ integer :: lbounds(2), ubounds(2)
+ if (any (lbound(arg2) /= lbounds)) STOP 2
+ if (any (ubound(arg2) /= ubounds)) STOP 3
+ if (any (shape(arg2) /= ubounds-lbounds+1)) STOP 4
+ if (size(arg2) /= product (ubounds-lbounds+1)) STOP 5
+ if (rank (arg2) /= 2) STOP 6
+! if (.not. is_continuous (arg2)) STOP 7 !<< Not yet implemented
+! cpt = c_loc (arg2) ! << FIXME: Valid since TS29113
+ call sub_array_assumed (arg2)
+ end subroutine sub_array_shape
+
+ subroutine sub_array_assumed (arg3)
+ type(*), target :: arg3(*)
+ type(c_ptr) :: cpt
+ cpt = c_loc (arg3)
+ end subroutine sub_array_assumed
+end module
+
+use mod
+use iso_c_binding, only: c_int, c_null_ptr
+implicit none
+type t1
+ integer :: a
+end type t1
+type :: t2
+ sequence
+ integer :: b
+end type t2
+type, bind(C) :: t3
+ integer(c_int) :: c
+end type t3
+
+integer :: scalar_int
+real, allocatable :: scalar_real_alloc
+character, pointer :: scalar_char_ptr
+
+integer :: array_int(3)
+real, allocatable :: array_real_alloc(:,:)
+character, pointer :: array_char_ptr(:,:)
+
+type(t1) :: scalar_t1
+type(t2), allocatable :: scalar_t2_alloc
+type(t3), pointer :: scalar_t3_ptr
+
+type(t1) :: array_t1(4)
+type(t2), allocatable :: array_t2_alloc(:,:)
+type(t3), pointer :: array_t3_ptr(:,:)
+
+class(t1), allocatable :: scalar_class_t1_alloc
+class(t1), pointer :: scalar_class_t1_ptr
+
+class(t1), allocatable :: array_class_t1_alloc(:,:)
+class(t1), pointer :: array_class_t1_ptr(:,:)
+
+scalar_char_ptr => null()
+scalar_t3_ptr => null()
+
+call sub_scalar (presnt=.false.)
+call sub_scalar (scalar_real_alloc, .false.)
+call sub_scalar (scalar_char_ptr, .false.)
+call sub_scalar (null (), .false.)
+call sub_scalar (scalar_t2_alloc, .false.)
+call sub_scalar (scalar_t3_ptr, .false.)
+
+allocate (scalar_real_alloc, scalar_char_ptr, scalar_t3_ptr)
+allocate (scalar_class_t1_alloc, scalar_class_t1_ptr, scalar_t2_alloc)
+allocate (array_real_alloc(3:5,2:4), array_char_ptr(-2:2,2))
+allocate (array_t2_alloc(3:5,2:4), array_t3_ptr(-2:2,2))
+allocate (array_class_t1_alloc(3,3), array_class_t1_ptr(4,4))
+
+call sub_scalar (scalar_int, .true.)
+call sub_scalar (scalar_real_alloc, .true.)
+call sub_scalar (scalar_char_ptr, .true.)
+call sub_scalar (array_int(2), .true.)
+call sub_scalar (array_real_alloc(3,2), .true.)
+call sub_scalar (array_char_ptr(0,1), .true.)
+call sub_scalar (scalar_t1, .true.)
+call sub_scalar (scalar_t2_alloc, .true.)
+call sub_scalar (scalar_t3_ptr, .true.)
+call sub_scalar (array_t1(2), .true.)
+call sub_scalar (array_t2_alloc(3,2), .true.)
+call sub_scalar (array_t3_ptr(0,1), .true.)
+call sub_scalar (array_class_t1_alloc(2,1), .true.)
+call sub_scalar (array_class_t1_ptr(3,3), .true.)
+
+call sub_array_assumed (array_int)
+call sub_array_assumed (array_real_alloc)
+call sub_array_assumed (array_char_ptr)
+call sub_array_assumed (array_t1)
+call sub_array_assumed (array_t2_alloc)
+call sub_array_assumed (array_t3_ptr)
+call sub_array_assumed (array_class_t1_alloc)
+call sub_array_assumed (array_class_t1_ptr)
+
+call sub_array_shape (array_real_alloc, [1,1], shape(array_real_alloc))
+call sub_array_shape (array_char_ptr, [1,1], shape(array_char_ptr))
+call sub_array_shape (array_t2_alloc, [1,1], shape(array_t2_alloc))
+call sub_array_shape (array_t3_ptr, [1,1], shape(array_t3_ptr))
+call sub_array_shape (array_class_t1_alloc, [1,1], shape(array_class_t1_alloc))
+call sub_array_shape (array_class_t1_ptr, [1,1], shape(array_class_t1_ptr))
+
+deallocate (scalar_char_ptr, scalar_class_t1_ptr, array_char_ptr)
+deallocate (array_class_t1_ptr, array_t3_ptr)
+
+end
diff --git a/gcc/testsuite/gfortran.dg/c_loc_test_22.f90 b/gcc/testsuite/gfortran.dg/c_loc_test_22.f90
index 5f4f9775b4a..9c40b26d830 100644
--- a/gcc/testsuite/gfortran.dg/c_loc_test_22.f90
+++ b/gcc/testsuite/gfortran.dg/c_loc_test_22.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! PR fortran/56907
!
diff --git a/gcc/testsuite/gfortran.dg/contiguous_3.f90 b/gcc/testsuite/gfortran.dg/contiguous_3.f90
index 724ec83ed10..ba0ccce8f9e 100644
--- a/gcc/testsuite/gfortran.dg/contiguous_3.f90
+++ b/gcc/testsuite/gfortran.dg/contiguous_3.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! PR fortran/40632
!
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_11.f90 b/gcc/testsuite/gfortran.dg/internal_pack_11.f90
index a1d357cee73..c341a1bbc5f 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_11.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_11.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! Test the fix for PR43173, where unnecessary calls to internal_pack/unpack
! were being produced below. These references are contiguous and so do not
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_12.f90 b/gcc/testsuite/gfortran.dg/internal_pack_12.f90
index 55631c80e6e..da507322cbb 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_12.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_12.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! Test the fix for PR43243, where unnecessary calls to internal_pack/unpack
! were being produced below. These references are contiguous and so do not
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_16.f90 b/gcc/testsuite/gfortran.dg/internal_pack_16.f90
index 7e34c2bf733..92c4b150db8 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_16.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_16.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-additional-options "-fdump-tree-original" }
+! { dg-additional-options "-O0 -fdump-tree-original" }
! PR 59345 - pack/unpack was not needed here.
SUBROUTINE S1(A)
REAL :: A(3)
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_17.f90 b/gcc/testsuite/gfortran.dg/internal_pack_17.f90
index c1b813b0c91..176ad879ba2 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_17.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_17.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-additional-options "-fdump-tree-original" }
+! { dg-additional-options "-O0 -fdump-tree-original" }
! PR 59345 - pack/unpack was not needed here.
! Original test case by Joost VandeVondele
SUBROUTINE S1(A)
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_18.f90 b/gcc/testsuite/gfortran.dg/internal_pack_18.f90
index ede0691bb9f..b4404726d12 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_18.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_18.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-additional-options "-fdump-tree-original" }
+! { dg-additional-options "-O0 -fdump-tree-original" }
! PR 57992 - this was packed/unpacked unnecessarily.
! Original case by Tobias Burnus.
subroutine test
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_19.f90 b/gcc/testsuite/gfortran.dg/internal_pack_19.f90
new file mode 100644
index 00000000000..06b916b7d8e
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/internal_pack_19.f90
@@ -0,0 +1,23 @@
+! { dg-do compile }
+! { dg-options "-Os -fdump-tree-original" }
+! Check that internal_pack is called with -Os.
+module x
+ implicit none
+contains
+ subroutine bar(a, n)
+ integer, intent(in) :: n
+ integer, intent(in), dimension(n) :: a
+ print *,a
+ end subroutine bar
+end module x
+
+program main
+ use x
+ implicit none
+ integer, parameter :: n = 10
+ integer, dimension(n) :: a
+ integer :: i
+ a = [(i,i=1,n)]
+ call bar(a(n:1:-1),n)
+end program main
+! { dg-final { scan-tree-dump-times "_gfortran_internal_pack" 1 "original" } }
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_20.f90 b/gcc/testsuite/gfortran.dg/internal_pack_20.f90
new file mode 100644
index 00000000000..f93f06bf272
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/internal_pack_20.f90
@@ -0,0 +1,23 @@
+! { dg-do compile }
+! { dg-options "-O -fdump-tree-original" }
+! Check that internal_pack is not called with -O.
+module x
+ implicit none
+contains
+ subroutine bar(a, n)
+ integer, intent(in) :: n
+ integer, intent(in), dimension(n) :: a
+ print *,a
+ end subroutine bar
+end module x
+
+program main
+ use x
+ implicit none
+ integer, parameter :: n = 10
+ integer, dimension(n) :: a
+ integer :: i
+ a = [(i,i=1,n)]
+ call bar(a(n:1:-1),n)
+end program main
+! { dg-final { scan-tree-dump-not "_gfortran_internal_pack" "original" } }
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_21.f90 b/gcc/testsuite/gfortran.dg/internal_pack_21.f90
new file mode 100644
index 00000000000..d0ce942a9f8
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/internal_pack_21.f90
@@ -0,0 +1,24 @@
+! { dg-do run }
+! { dg-options "-O -fdump-tree-original" }
+! Test handling of the optional argument.
+
+MODULE M1
+ INTEGER, PARAMETER :: dp=KIND(0.0D0)
+CONTAINS
+ SUBROUTINE S1(a)
+ REAL(dp), DIMENSION(45), INTENT(OUT), &
+ OPTIONAL :: a
+ if (present(a)) STOP 1
+ END SUBROUTINE S1
+ SUBROUTINE S2(a)
+ REAL(dp), DIMENSION(:, :), INTENT(OUT), &
+ OPTIONAL :: a
+ CALL S1(a)
+ END SUBROUTINE
+END MODULE M1
+
+USE M1
+CALL S2()
+END
+! { dg-final { scan-tree-dump-times "optional" 4 "original" } }
+! { dg-final { scan-tree-dump-not "_gfortran_internal_unpack" "original" } }
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_4.f90 b/gcc/testsuite/gfortran.dg/internal_pack_4.f90
index 00f316414bc..9de09ab072b 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_4.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_4.f90
@@ -1,5 +1,4 @@
! { dg-do run }
-! { dg-options "-fdump-tree-original" }
!
! PR fortran/36132
!
@@ -25,6 +24,3 @@ END MODULE M1
USE M1
CALL S2()
END
-
-! { dg-final { scan-tree-dump-times "a != 0B \\? \\\(.*\\\) _gfortran_internal_pack" 1 "original" } }
-! { dg-final { scan-tree-dump-times "if \\(a != 0B &&" 1 "original" } }
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_5.f90 b/gcc/testsuite/gfortran.dg/internal_pack_5.f90
index 3c5868f9efc..360ade491b5 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_5.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_5.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! PR fortran/36909
!
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_6.f90 b/gcc/testsuite/gfortran.dg/internal_pack_6.f90
index d6102761904..6d52a8c98c4 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_6.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_6.f90
@@ -1,5 +1,5 @@
-! { dg-do run }
-! { dg-options "-fdump-tree-original" }
+! { dg-do compile }
+! { dg-options "-O0 -fdump-tree-original" }
!
! Test the fix for PR41113 and PR41117, in which unnecessary calls
! to internal_pack and internal_unpack were being generated.
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_6a.f90 b/gcc/testsuite/gfortran.dg/internal_pack_6a.f90
new file mode 100644
index 00000000000..a9fb2b52d97
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/internal_pack_6a.f90
@@ -0,0 +1,56 @@
+! { dg-do run }
+!
+! Test the fix for PR41113 and PR41117, in which unnecessary calls
+! to internal_pack and internal_unpack were being generated.
+!
+! Contributed by Joost VandeVondele <jv244(a)cam.ac.uk>
+!
+MODULE M1
+ TYPE T1
+ REAL :: data(10) = [(i, i = 1, 10)]
+ END TYPE T1
+CONTAINS
+ SUBROUTINE S1(data, i, chksum)
+ REAL, DIMENSION(*) :: data
+ integer :: i, j
+ real :: subsum, chksum
+ subsum = 0
+ do j = 1, i
+ subsum = subsum + data(j)
+ end do
+ if (abs(subsum - chksum) > 1e-6) STOP 1
+ END SUBROUTINE S1
+END MODULE
+
+SUBROUTINE S2
+ use m1
+ TYPE(T1) :: d
+
+ real :: data1(10) = [(i, i = 1, 10)]
+ REAL :: data(-4:5,-4:5) = reshape ([(real(i), i = 1, 100)], [10,10])
+
+! PR41113
+ CALL S1(d%data, 10, sum (d%data))
+ CALL S1(data1, 10, sum (data1))
+
+! PR41117
+ DO i=-4,5
+ CALL S1(data(:,i), 10, sum (data(:,i)))
+ ENDDO
+
+! With the fix for PR41113/7 this is the only time that _internal_pack
+! was called. The final part of the fix for PR43072 put paid to it too.
+ DO i=-4,5
+ CALL S1(data(-2:,i), 8, sum (data(-2:,i)))
+ ENDDO
+ DO i=-4,4
+ CALL S1(data(:,i:i+1), 20, sum (reshape (data(:,i:i+1), [20])))
+ ENDDO
+ DO i=-4,5
+ CALL S1(data(2,i), 1, data(2,i))
+ ENDDO
+END SUBROUTINE S2
+
+ call s2
+end
+
diff --git a/gcc/testsuite/gfortran.dg/internal_pack_9.f90 b/gcc/testsuite/gfortran.dg/internal_pack_9.f90
index 9ce53f44354..2b44db5a805 100644
--- a/gcc/testsuite/gfortran.dg/internal_pack_9.f90
+++ b/gcc/testsuite/gfortran.dg/internal_pack_9.f90
@@ -1,5 +1,5 @@
! { dg-do compile }
-! { dg-options "-fdump-tree-original" }
+! { dg-options "-O0 -fdump-tree-original" }
!
! During the discussion of the fix for PR43072, in which unnecessary
! calls to internal PACK/UNPACK were being generated, the following,
diff --git a/gcc/testsuite/gfortran.dg/missing_optional_dummy_6.f90 b/gcc/testsuite/gfortran.dg/missing_optional_dummy_6.f90
index 4468ff159b9..cb6de2ebf61 100644
--- a/gcc/testsuite/gfortran.dg/missing_optional_dummy_6.f90
+++ b/gcc/testsuite/gfortran.dg/missing_optional_dummy_6.f90
@@ -46,14 +46,3 @@ contains
end subroutine scalar2
end program test
-
-! { dg-final { scan-tree-dump-times "scalar2 \\(slr1" 1 "original" } }
-
-! { dg-final { scan-tree-dump-times "= es1 != 0B" 1 "original" } }
-! { dg-final { scan-tree-dump-times "assumed_shape2 \\(es1" 0 "original" } }
-! { dg-final { scan-tree-dump-times "explicit_shape2 \\(es1" 1 "original" } }
-
-! { dg-final { scan-tree-dump-times "= as1 != 0B" 2 "original" } }
-! { dg-final { scan-tree-dump-times "assumed_shape2 \\(as1" 0 "original" } }
-! { dg-final { scan-tree-dump-times "explicit_shape2 \\(as1" 0 "original" } }
-
diff --git a/gcc/testsuite/gfortran.dg/missing_optional_dummy_6a.f90 b/gcc/testsuite/gfortran.dg/missing_optional_dummy_6a.f90
new file mode 100644
index 00000000000..0e08ed3aa0c
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/missing_optional_dummy_6a.f90
@@ -0,0 +1,59 @@
+! { dg-do compile }
+! { dg-options "-O0 -fdump-tree-original" }
+!
+! PR fortran/41907
+!
+program test
+ implicit none
+ call scalar1 ()
+ call assumed_shape1 ()
+ call explicit_shape1 ()
+contains
+
+ ! Calling functions
+ subroutine scalar1 (slr1)
+ integer, optional :: slr1
+ call scalar2 (slr1)
+ end subroutine scalar1
+
+ subroutine assumed_shape1 (as1)
+ integer, dimension(:), optional :: as1
+ call assumed_shape2 (as1)
+ call explicit_shape2 (as1)
+ end subroutine assumed_shape1
+
+ subroutine explicit_shape1 (es1)
+ integer, dimension(5), optional :: es1
+ call assumed_shape2 (es1)
+ call explicit_shape2 (es1)
+ end subroutine explicit_shape1
+
+
+ ! Called functions
+ subroutine assumed_shape2 (as2)
+ integer, dimension(:),optional :: as2
+ if (present (as2)) STOP 1
+ end subroutine assumed_shape2
+
+ subroutine explicit_shape2 (es2)
+ integer, dimension(5),optional :: es2
+ if (present (es2)) STOP 2
+ end subroutine explicit_shape2
+
+ subroutine scalar2 (slr2)
+ integer, optional :: slr2
+ if (present (slr2)) STOP 3
+ end subroutine scalar2
+
+end program test
+
+! { dg-final { scan-tree-dump-times "scalar2 \\(slr1" 1 "original" } }
+
+! { dg-final { scan-tree-dump-times "= es1 != 0B" 1 "original" } }
+! { dg-final { scan-tree-dump-times "assumed_shape2 \\(es1" 0 "original" } }
+! { dg-final { scan-tree-dump-times "explicit_shape2 \\(es1" 1 "original" } }
+
+! { dg-final { scan-tree-dump-times "= as1 != 0B" 2 "original" } }
+! { dg-final { scan-tree-dump-times "assumed_shape2 \\(as1" 0 "original" } }
+! { dg-final { scan-tree-dump-times "explicit_shape2 \\(as1" 0 "original" } }
+
diff --git a/gcc/testsuite/gfortran.dg/no_arg_check_2.f90 b/gcc/testsuite/gfortran.dg/no_arg_check_2.f90
index fe334883a3e..3570b9719eb 100644
--- a/gcc/testsuite/gfortran.dg/no_arg_check_2.f90
+++ b/gcc/testsuite/gfortran.dg/no_arg_check_2.f90
@@ -1,5 +1,5 @@
-! { dg-do run }
-! { dg-options "-fdump-tree-original" }
+! { dg-do compile }
+! { dg-options "-O0 -fdump-tree-original" }
!
! PR fortran/39505
!
diff --git a/gcc/testsuite/gfortran.dg/no_arg_check_2a.f90 b/gcc/testsuite/gfortran.dg/no_arg_check_2a.f90
new file mode 100644
index 00000000000..dc4adcb5619
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/no_arg_check_2a.f90
@@ -0,0 +1,121 @@
+! { dg-do run }
+!
+! PR fortran/39505
+!
+! Test NO_ARG_CHECK
+! Copied from assumed_type_2.f90
+!
+
+module mod
+ use iso_c_binding, only: c_loc, c_ptr, c_bool
+ implicit none
+ interface my_c_loc
+ function my_c_loc1(x) bind(C)
+ import c_ptr
+!GCC$ attributes NO_ARG_CHECK :: x
+ type(*) :: x
+ type(c_ptr) :: my_c_loc1
+ end function
+ end interface my_c_loc
+contains
+ subroutine sub_scalar (arg1, presnt)
+ integer(8), target, optional :: arg1
+ logical :: presnt
+ type(c_ptr) :: cpt
+!GCC$ attributes NO_ARG_CHECK :: arg1
+ if (presnt .neqv. present (arg1)) STOP 1
+ cpt = c_loc (arg1)
+ end subroutine sub_scalar
+
+ subroutine sub_array_assumed (arg3)
+!GCC$ attributes NO_ARG_CHECK :: arg3
+ logical(1), target :: arg3(*)
+ type(c_ptr) :: cpt
+ cpt = c_loc (arg3)
+ end subroutine sub_array_assumed
+end module
+
+use mod
+use iso_c_binding, only: c_int, c_null_ptr
+implicit none
+type t1
+ integer :: a
+end type t1
+type :: t2
+ sequence
+ integer :: b
+end type t2
+type, bind(C) :: t3
+ integer(c_int) :: c
+end type t3
+
+integer :: scalar_int
+real, allocatable :: scalar_real_alloc
+character, pointer :: scalar_char_ptr
+
+integer :: array_int(3)
+real, allocatable :: array_real_alloc(:,:)
+character, pointer :: array_char_ptr(:,:)
+
+type(t1) :: scalar_t1
+type(t2), allocatable :: scalar_t2_alloc
+type(t3), pointer :: scalar_t3_ptr
+
+type(t1) :: array_t1(4)
+type(t2), allocatable :: array_t2_alloc(:,:)
+type(t3), pointer :: array_t3_ptr(:,:)
+
+class(t1), allocatable :: scalar_class_t1_alloc
+class(t1), pointer :: scalar_class_t1_ptr
+
+class(t1), allocatable :: array_class_t1_alloc(:,:)
+class(t1), pointer :: array_class_t1_ptr(:,:)
+
+scalar_char_ptr => null()
+scalar_t3_ptr => null()
+
+call sub_scalar (presnt=.false.)
+call sub_scalar (scalar_real_alloc, .false.)
+call sub_scalar (scalar_char_ptr, .false.)
+call sub_scalar (null (), .false.)
+call sub_scalar (scalar_t2_alloc, .false.)
+call sub_scalar (scalar_t3_ptr, .false.)
+
+allocate (scalar_real_alloc, scalar_char_ptr, scalar_t3_ptr)
+allocate (scalar_class_t1_alloc, scalar_class_t1_ptr, scalar_t2_alloc)
+allocate (array_real_alloc(3:5,2:4), array_char_ptr(-2:2,2))
+allocate (array_t2_alloc(3:5,2:4), array_t3_ptr(-2:2,2))
+allocate (array_class_t1_alloc(3,3), array_class_t1_ptr(4,4))
+
+call sub_scalar (scalar_int, .true.)
+call sub_scalar (scalar_real_alloc, .true.)
+call sub_scalar (scalar_char_ptr, .true.)
+call sub_scalar (array_int(2), .true.)
+call sub_scalar (array_real_alloc(3,2), .true.)
+call sub_scalar (array_char_ptr(0,1), .true.)
+call sub_scalar (scalar_t1, .true.)
+call sub_scalar (scalar_t2_alloc, .true.)
+call sub_scalar (scalar_t3_ptr, .true.)
+call sub_scalar (array_t1(2), .true.)
+call sub_scalar (array_t2_alloc(3,2), .true.)
+call sub_scalar (array_t3_ptr(0,1), .true.)
+call sub_scalar (array_class_t1_alloc(2,1), .true.)
+call sub_scalar (array_class_t1_ptr(3,3), .true.)
+
+call sub_array_assumed (array_int)
+call sub_array_assumed (array_real_alloc)
+call sub_array_assumed (array_char_ptr)
+call sub_array_assumed (array_t1)
+call sub_array_assumed (array_t2_alloc)
+call sub_array_assumed (array_t3_ptr)
+call sub_array_assumed (array_class_t1_alloc)
+call sub_array_assumed (array_class_t1_ptr)
+
+deallocate (scalar_char_ptr, scalar_class_t1_ptr, array_char_ptr)
+deallocate (array_class_t1_ptr, array_t3_ptr)
+contains
+ subroutine sub(x)
+ integer :: x(:)
+ call sub_array_assumed (x)
+ end subroutine sub
+end
diff --git a/gcc/testsuite/gfortran.dg/typebound_assignment_5.f03 b/gcc/testsuite/gfortran.dg/typebound_assignment_5.f03
index f176b841fc0..e7c9126b35c 100644
--- a/gcc/testsuite/gfortran.dg/typebound_assignment_5.f03
+++ b/gcc/testsuite/gfortran.dg/typebound_assignment_5.f03
@@ -1,5 +1,5 @@
-! { dg-do run }
-! { dg-options "-fdump-tree-original" }
+! { dg-do compile }
+! { dg-options "-O0 -fdump-tree-original" }
!
! PR fortran/49074
! ICE on defined assignment with class arrays.
diff --git a/gcc/testsuite/gfortran.dg/typebound_assignment_5a.f03 b/gcc/testsuite/gfortran.dg/typebound_assignment_5a.f03
new file mode 100644
index 00000000000..b55b42b589c
--- /dev/null
+++ b/gcc/testsuite/gfortran.dg/typebound_assignment_5a.f03
@@ -0,0 +1,39 @@
+! { dg-do run }
+!
+! PR fortran/49074
+! ICE on defined assignment with class arrays.
+
+ module foo
+ type bar
+ integer :: i
+
+ contains
+
+ generic :: assignment (=) => assgn_bar
+ procedure, private :: assgn_bar
+ end type bar
+
+ contains
+
+ elemental subroutine assgn_bar (a, b)
+ class (bar), intent (inout) :: a
+ class (bar), intent (in) :: b
+
+ select type (b)
+ type is (bar)
+ a%i = b%i
+ end select
+
+ return
+ end subroutine assgn_bar
+ end module foo
+
+ program main
+ use foo
</cut>
4 years, 1 month
- 1
- 0
Re: [CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-arm-next-allyesconfig - Build # 13 - Successful!
by Maxim Kuvyrkov
Hi Alexey,
Your patch appears to break build on aarch64 and arm in allmodconfig and allyesconfig configurations.
Would you please investigate? Please let us know if it doesn't easily reproduce for you.
Thanks!
--
Maxim Kuvyrkov
https://www.linaro.org
> On Jul 17, 2021, at 8:08 PM, ci_notify(a)linaro.org wrote:
>
> Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-arm-next-allyesconfig. So far, this commit has regressed CI configurations:
> - tcwg_kernel/gnu-master-aarch64-next-allmodconfig
> - tcwg_kernel/llvm-master-aarch64-next-allyesconfig
> - tcwg_kernel/llvm-release-arm-next-allmodconfig
> - tcwg_kernel/llvm-release-arm-next-allyesconfig
>
> Culprit:
> <cut>
> commit 6f4266a78a4e090b452a0335c1414f3240684743
> Author: Alexey Dobriyan <adobriyan(a)gmail.com>
>
> kbuild: decouple build from userspace headers
> </cut>
>
> Results regressed to (for first_bad == 6f4266a78a4e090b452a0335c1414f3240684743)
> # reset_artifacts:
> -10
> # build_abe binutils:
> -9
> # build_llvm:
> -5
> # build_abe qemu:
> -2
> # linux_n_obj:
> 19710
> # First few build errors in logs:
> # 00:04:48 crypto/aegis128-neon-inner.c:11:10: fatal error: 'arm_neon.h' file not found
> # 00:04:48 make[1]: *** [crypto/aegis128-neon-inner.o] Error 1
> # 00:05:37 lib/raid6/recov_neon_inner.c:7:10: fatal error: 'arm_neon.h' file not found
> # 00:05:37 make[2]: *** [lib/raid6/recov_neon_inner.o] Error 1
> # 00:05:53 lib/raid6/neon1.c:27:10: fatal error: 'arm_neon.h' file not found
> # 00:05:53 make[2]: *** [lib/raid6/neon1.o] Error 1
> # 00:05:53 lib/raid6/neon2.c:27:10: fatal error: 'arm_neon.h' file not found
> # 00:05:53 make[2]: *** [lib/raid6/neon2.o] Error 1
> # 00:05:53 lib/raid6/neon4.c:27:10: fatal error: 'arm_neon.h' file not found
> # 00:05:53 make[2]: *** [lib/raid6/neon4.o] Error 1
>
> from (for last_good == d06391f28276b0ad28a59073bdb8eb10dc4ea495)
> # reset_artifacts:
> -10
> # build_abe binutils:
> -9
> # build_llvm:
> -5
> # build_abe qemu:
> -2
> # linux_n_obj:
> 19802
> # linux build successful:
> all
>
> Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
> Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
> Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
>
> Configuration details:
> rr[linux_url]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git"
> rr[linux_branch]="e9338abf0e186336022293d2e454c106761f262b"
>
> Reproduce builds:
> <cut>
> mkdir investigate-linux-6f4266a78a4e090b452a0335c1414f3240684743
> cd investigate-linux-6f4266a78a4e090b452a0335c1414f3240684743
>
> git clone https://git.linaro.org/toolchain/jenkins-scripts
>
> mkdir -p artifacts/manifests
> curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
> curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
> curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
> chmod +x artifacts/test.sh
>
> # Reproduce the baseline build (build all pre-requisites)
> ./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
>
> # Save baseline build state (which is then restored in artifacts/test.sh)
> rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude linux/ ./ ./bisect/baseline/
>
> cd linux
>
> # Reproduce first_bad build
> git checkout --detach 6f4266a78a4e090b452a0335c1414f3240684743
> ../artifacts/test.sh
>
> # Reproduce last_good build
> git checkout --detach d06391f28276b0ad28a59073bdb8eb10dc4ea495
> ../artifacts/test.sh
>
> cd ..
> </cut>
>
> History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
>
> Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
> Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
>
> Full commit (up to 1000 lines):
> <cut>
> commit 6f4266a78a4e090b452a0335c1414f3240684743
> Author: Alexey Dobriyan <adobriyan(a)gmail.com>
> Date: Fri Jul 16 13:44:03 2021 +1000
>
> kbuild: decouple build from userspace headers
>
> First, userspace headers can be under incompatible license.
>
> Second, kernel doesn't require userspace to operate and should not
> require anything from userspace to be built other than compiler.
> We would use -ffreestanding too if not builtin function shenanigans.
>
> To decouple:
>
> * ship minimal stdarg.h as <linux/stdarg.h>,
> 1 type, 4 macros
>
> GPL 2 version of <stdarg.h> can be extracted from
> http://archive.debian.org/debian/pool/main/g/gcc-4.2/gcc-4.2_4.2.4.orig.tar…
>
> * delete "-isystem" from command line arguments,
> this is what enables header leakage
>
> * fixup/delete include directives where necessary.
>
> Link: https://lkml.kernel.org/r/YO8ioz4sHwcUAkdt@localhost.localdomain
> Signed-off-by: Alexey Dobriyan <adobriyan(a)gmail.com>
> Cc: Arnd Bergmann <arnd(a)arndb.de>
> Cc: Masahiro Yamada <masahiroy(a)kernel.org>
> Cc: Christoph Hellwig <hch(a)infradead.org>
> Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
> Signed-off-by: Stephen Rothwell <sfr(a)canb.auug.org.au>
> ---
> Makefile | 2 +-
> arch/arm/kernel/process.c | 2 --
> arch/arm/mach-bcm/bcm_kona_smc.c | 2 --
> arch/arm64/kernel/process.c | 3 ---
> arch/openrisc/kernel/process.c | 2 --
> arch/parisc/kernel/firmware.c | 2 +-
> arch/parisc/kernel/process.c | 3 ---
> arch/powerpc/kernel/prom.c | 1 -
> arch/powerpc/kernel/prom_init.c | 2 +-
> arch/powerpc/kernel/rtas.c | 2 +-
> arch/powerpc/kernel/udbg.c | 2 +-
> arch/s390/boot/pgm_check_info.c | 2 +-
> arch/sparc/kernel/process_32.c | 3 ---
> arch/sparc/kernel/process_64.c | 3 ---
> arch/um/include/shared/irq_user.h | 1 -
> arch/um/include/shared/os.h | 1 -
> arch/um/os-Linux/signal.c | 2 +-
> arch/um/os-Linux/util.c | 1 +
> arch/x86/boot/boot.h | 2 +-
> crypto/aegis128-neon-inner.c | 2 --
> drivers/block/xen-blkback/xenbus.c | 1 -
> drivers/firmware/efi/libstub/efi-stub-helper.c | 2 +-
> drivers/firmware/efi/libstub/vsprintf.c | 2 +-
> drivers/gpu/drm/amd/display/dc/dc_helper.c | 2 +-
> drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 1 -
> drivers/gpu/drm/drm_print.c | 2 +-
> drivers/gpu/drm/msm/disp/msm_disp_snapshot.h | 1 -
> drivers/isdn/capi/capiutil.c | 2 +-
> drivers/macintosh/macio-adb.c | 1 -
> drivers/macintosh/via-cuda.c | 2 +-
> drivers/macintosh/via-macii.c | 2 --
> drivers/macintosh/via-pmu.c | 2 +-
> drivers/net/wireless/intersil/orinoco/hermes.c | 1 -
> drivers/net/wwan/iosm/iosm_ipc_imem.h | 1 -
> drivers/pinctrl/aspeed/pinmux-aspeed.h | 1 -
> drivers/scsi/elx/efct/efct_driver.h | 1 -
> .../media/atomisp/pci/hive_isp_css_common/host/isp_local.h | 2 --
> .../media/atomisp/pci/hive_isp_css_include/print_support.h | 2 +-
> drivers/staging/media/atomisp/pci/ia_css_env.h | 2 +-
> .../media/atomisp/pci/runtime/debug/interface/ia_css_debug.h | 2 +-
> drivers/staging/media/atomisp/pci/sh_css_internal.h | 2 +-
> drivers/xen/xen-scsiback.c | 2 --
> fs/befs/debug.c | 2 +-
> fs/reiserfs/prints.c | 2 +-
> fs/ufs/super.c | 2 +-
> include/acpi/platform/acgcc.h | 2 +-
> include/linux/filter.h | 2 --
> include/linux/kernel.h | 2 +-
> include/linux/mISDNif.h | 1 -
> include/linux/printk.h | 2 +-
> include/linux/stdarg.h | 11 +++++++++++
> include/linux/string.h | 2 +-
> kernel/debug/kdb/kdb_support.c | 1 -
> lib/debug_info.c | 3 +--
> lib/kasprintf.c | 2 +-
> lib/kunit/string-stream.h | 2 +-
> lib/vsprintf.c | 2 +-
> mm/kfence/report.c | 2 +-
> net/batman-adv/log.c | 2 +-
> sound/aoa/codecs/onyx.h | 1 -
> sound/aoa/codecs/tas.c | 1 -
> sound/core/info.c | 1 -
> 62 files changed, 44 insertions(+), 77 deletions(-)
>
> diff --git a/Makefile b/Makefile
> index eaa692976851..02591a333d86 100644
> --- a/Makefile
> +++ b/Makefile
> @@ -972,7 +972,7 @@ KBUILD_CFLAGS += -falign-functions=64
> endif
>
> # arch Makefile may override CC so keep this after arch Makefile is included
> -NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)
> +NOSTDINC_FLAGS += -nostdinc
>
> # warn about C99 declaration after statement
> KBUILD_CFLAGS += -Wdeclaration-after-statement
> diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
> index fc9e8b37eaa8..bb5ad8a6a4c3 100644
> --- a/arch/arm/kernel/process.c
> +++ b/arch/arm/kernel/process.c
> @@ -5,8 +5,6 @@
> * Copyright (C) 1996-2000 Russell King - Converted to ARM.
> * Original Copyright (C) 1995 Linus Torvalds
> */
> -#include <stdarg.h>
> -
> #include <linux/export.h>
> #include <linux/sched.h>
> #include <linux/sched/debug.h>
> diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c
> index 43a16f922b53..43829e49ad93 100644
> --- a/arch/arm/mach-bcm/bcm_kona_smc.c
> +++ b/arch/arm/mach-bcm/bcm_kona_smc.c
> @@ -10,8 +10,6 @@
> * of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
> * GNU General Public License for more details.
> */
> -
> -#include <stdarg.h>
> #include <linux/smp.h>
> #include <linux/io.h>
> #include <linux/ioport.h>
> diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
> index c8989b999250..5f7ac9a0f9a3 100644
> --- a/arch/arm64/kernel/process.c
> +++ b/arch/arm64/kernel/process.c
> @@ -6,9 +6,6 @@
> * Copyright (C) 1996-2000 Russell King - Converted to ARM.
> * Copyright (C) 2012 ARM Ltd.
> */
> -
> -#include <stdarg.h>
> -
> #include <linux/compat.h>
> #include <linux/efi.h>
> #include <linux/elf.h>
> diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
> index eb62429681fc..b0698d9ce14f 100644
> --- a/arch/openrisc/kernel/process.c
> +++ b/arch/openrisc/kernel/process.c
> @@ -14,8 +14,6 @@
> */
>
> #define __KERNEL_SYSCALLS__
> -#include <stdarg.h>
> -
> #include <linux/errno.h>
> #include <linux/sched.h>
> #include <linux/sched/debug.h>
> diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
> index 665b70086685..7034227dbdf3 100644
> --- a/arch/parisc/kernel/firmware.c
> +++ b/arch/parisc/kernel/firmware.c
> @@ -51,7 +51,7 @@
> * prumpf 991016
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include <linux/delay.h>
> #include <linux/init.h>
> diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
> index 184ec3c1eae4..38ec4ae81239 100644
> --- a/arch/parisc/kernel/process.c
> +++ b/arch/parisc/kernel/process.c
> @@ -17,9 +17,6 @@
> * Copyright (C) 2001-2014 Helge Deller <deller(a)gmx.de>
> * Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org>
> */
> -
> -#include <stdarg.h>
> -
> #include <linux/elf.h>
> #include <linux/errno.h>
> #include <linux/kernel.h>
> diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
> index f620e04dc9bf..a1e7ba0fad09 100644
> --- a/arch/powerpc/kernel/prom.c
> +++ b/arch/powerpc/kernel/prom.c
> @@ -11,7 +11,6 @@
>
> #undef DEBUG
>
> -#include <stdarg.h>
> #include <linux/kernel.h>
> #include <linux/string.h>
> #include <linux/init.h>
> diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
> index a5bf355ce1d6..10664633f7e3 100644
> --- a/arch/powerpc/kernel/prom_init.c
> +++ b/arch/powerpc/kernel/prom_init.c
> @@ -14,7 +14,7 @@
> /* we cannot use FORTIFY as it brings in new symbols */
> #define __NO_FORTIFY
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/kernel.h>
> #include <linux/string.h>
> #include <linux/init.h>
> diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
> index 99f2cce635fb..ff80bbad22a5 100644
> --- a/arch/powerpc/kernel/rtas.c
> +++ b/arch/powerpc/kernel/rtas.c
> @@ -7,7 +7,7 @@
> * Copyright (C) 2001 IBM.
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/kernel.h>
> #include <linux/types.h>
> #include <linux/spinlock.h>
> diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
> index 01595e8cafe7..b1544b2f6321 100644
> --- a/arch/powerpc/kernel/udbg.c
> +++ b/arch/powerpc/kernel/udbg.c
> @@ -5,7 +5,7 @@
> * c 2001 PPC 64 Team, IBM Corp
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/types.h>
> #include <linux/sched.h>
> #include <linux/console.h>
> diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
> index 3a46abed2549..b7d8dd88bbf2 100644
> --- a/arch/s390/boot/pgm_check_info.c
> +++ b/arch/s390/boot/pgm_check_info.c
> @@ -1,5 +1,6 @@
> // SPDX-License-Identifier: GPL-2.0
> #include <linux/kernel.h>
> +#include <linux/stdarg.h>
> #include <linux/string.h>
> #include <linux/ctype.h>
> #include <asm/stacktrace.h>
> @@ -8,7 +9,6 @@
> #include <asm/setup.h>
> #include <asm/sclp.h>
> #include <asm/uv.h>
> -#include <stdarg.h>
> #include "boot.h"
>
> const char hex_asc[] = "0123456789abcdef";
> diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
> index 93983d6d431d..bbbe0cfef746 100644
> --- a/arch/sparc/kernel/process_32.c
> +++ b/arch/sparc/kernel/process_32.c
> @@ -8,9 +8,6 @@
> /*
> * This file handles the architecture-dependent parts of process handling..
> */
> -
> -#include <stdarg.h>
> -
> #include <linux/elfcore.h>
> #include <linux/errno.h>
> #include <linux/module.h>
> diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
> index d33c58a58d4f..0cabcdfb23fd 100644
> --- a/arch/sparc/kernel/process_64.c
> +++ b/arch/sparc/kernel/process_64.c
> @@ -9,9 +9,6 @@
> /*
> * This file handles the architecture-dependent parts of process handling..
> */
> -
> -#include <stdarg.h>
> -
> #include <linux/errno.h>
> #include <linux/export.h>
> #include <linux/sched.h>
> diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h
> index 065829f443ae..86a8a573b65c 100644
> --- a/arch/um/include/shared/irq_user.h
> +++ b/arch/um/include/shared/irq_user.h
> @@ -7,7 +7,6 @@
> #define __IRQ_USER_H__
>
> #include <sysdep/ptrace.h>
> -#include <stdbool.h>
>
> enum um_irq_type {
> IRQ_READ,
> diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
> index 60b84edc8a68..96d400387c93 100644
> --- a/arch/um/include/shared/os.h
> +++ b/arch/um/include/shared/os.h
> @@ -8,7 +8,6 @@
> #ifndef __OS_H__
> #define __OS_H__
>
> -#include <stdarg.h>
> #include <irq_user.h>
> #include <longjmp.h>
> #include <mm_id.h>
> diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
> index 6de99bb16113..6cf098c23a39 100644
> --- a/arch/um/os-Linux/signal.c
> +++ b/arch/um/os-Linux/signal.c
> @@ -67,7 +67,7 @@ int signals_enabled;
> #ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
> static int signals_blocked;
> #else
> -#define signals_blocked false
> +#define signals_blocked 0
> #endif
> static unsigned int signals_pending;
> static unsigned int signals_active = 0;
> diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
> index 07327425d06e..41297ec404bf 100644
> --- a/arch/um/os-Linux/util.c
> +++ b/arch/um/os-Linux/util.c
> @@ -3,6 +3,7 @@
> * Copyright (C) 2000 - 2007 Jeff Dike (jdike(a){addtoit,linux.intel}.com)
> */
>
> +#include <stdarg.h>
> #include <stdio.h>
> #include <stdlib.h>
> #include <unistd.h>
> diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
> index ca866f1cca2e..34c9dbb6a47d 100644
> --- a/arch/x86/boot/boot.h
> +++ b/arch/x86/boot/boot.h
> @@ -18,7 +18,7 @@
>
> #ifndef __ASSEMBLY__
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/types.h>
> #include <linux/edd.h>
> #include <asm/setup.h>
> diff --git a/crypto/aegis128-neon-inner.c b/crypto/aegis128-neon-inner.c
> index 7de485907d81..6b37fbb79884 100644
> --- a/crypto/aegis128-neon-inner.c
> +++ b/crypto/aegis128-neon-inner.c
> @@ -15,8 +15,6 @@
>
> #define AEGIS_BLOCK_SIZE 16
>
> -#include <stddef.h>
> -
> extern int aegis128_have_aes_insn;
>
> void *memcpy(void *dest, const void *src, size_t n);
> diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
> index 125b22205d38..33eba3df4dd9 100644
> --- a/drivers/block/xen-blkback/xenbus.c
> +++ b/drivers/block/xen-blkback/xenbus.c
> @@ -8,7 +8,6 @@
>
> #define pr_fmt(fmt) "xen-blkback: " fmt
>
> -#include <stdarg.h>
> #include <linux/module.h>
> #include <linux/kthread.h>
> #include <xen/events.h>
> diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
> index aa8da0a49829..4921580e1725 100644
> --- a/drivers/firmware/efi/libstub/efi-stub-helper.c
> +++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
> @@ -7,7 +7,7 @@
> * Copyright 2011 Intel Corporation; author Matt Fleming
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include <linux/ctype.h>
> #include <linux/efi.h>
> diff --git a/drivers/firmware/efi/libstub/vsprintf.c b/drivers/firmware/efi/libstub/vsprintf.c
> index 1088e288c04d..71c71c222346 100644
> --- a/drivers/firmware/efi/libstub/vsprintf.c
> +++ b/drivers/firmware/efi/libstub/vsprintf.c
> @@ -10,7 +10,7 @@
> * Oh, it's a waste of space, but oh-so-yummy for debugging.
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include <linux/compiler.h>
> #include <linux/ctype.h>
> diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
> index a612ba6dc389..ab6bc5d79012 100644
> --- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
> +++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
> @@ -28,9 +28,9 @@
> */
>
> #include <linux/delay.h>
> +#include <linux/stdarg.h>
>
> #include "dm_services.h"
> -#include <stdarg.h>
>
> #include "dc.h"
> #include "dc_dmub_srv.h"
> diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
> index 7c4734f905d9..68fd451aca23 100644
> --- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
> +++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
> @@ -39,7 +39,6 @@
> #include <linux/types.h>
> #include <linux/string.h>
> #include <linux/delay.h>
> -#include <stdarg.h>
>
> #include "atomfirmware.h"
>
> diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
> index 111b932cf2a9..f783d4963d4b 100644
> --- a/drivers/gpu/drm/drm_print.c
> +++ b/drivers/gpu/drm/drm_print.c
> @@ -25,7 +25,7 @@
>
> #define DEBUG /* for pr_debug() */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include <linux/io.h>
> #include <linux/moduleparam.h>
> diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
> index c92a9508c8d3..0f9a5364cd86 100644
> --- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
> +++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
> @@ -25,7 +25,6 @@
> #include <linux/pm_runtime.h>
> #include <linux/kthread.h>
> #include <linux/devcoredump.h>
> -#include <stdarg.h>
> #include "msm_kms.h"
>
> #define MSM_DISP_SNAPSHOT_MAX_BLKS 10
> diff --git a/drivers/isdn/capi/capiutil.c b/drivers/isdn/capi/capiutil.c
> index f26bf3c66d7e..d7ae42edc4a8 100644
> --- a/drivers/isdn/capi/capiutil.c
> +++ b/drivers/isdn/capi/capiutil.c
> @@ -379,7 +379,7 @@ static char *pnames[] =
> /*2f */ "Useruserdata"
> };
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> /*-------------------------------------------------------*/
> static _cdebbuf *bufprint(_cdebbuf *cdb, char *fmt, ...)
> diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c
> index d4759db002c6..dc634c2932fd 100644
> --- a/drivers/macintosh/macio-adb.c
> +++ b/drivers/macintosh/macio-adb.c
> @@ -2,7 +2,6 @@
> /*
> * Driver for the ADB controller in the Mac I/O (Hydra) chip.
> */
> -#include <stdarg.h>
> #include <linux/types.h>
> #include <linux/errno.h>
> #include <linux/kernel.h>
> diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c
> index 3581abfb0c6a..cd267392289c 100644
> --- a/drivers/macintosh/via-cuda.c
> +++ b/drivers/macintosh/via-cuda.c
> @@ -9,7 +9,7 @@
> *
> * Copyright (C) 1996 Paul Mackerras.
> */
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/types.h>
> #include <linux/errno.h>
> #include <linux/kernel.h>
> diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
> index 060e03f2264b..db9270da5b8e 100644
> --- a/drivers/macintosh/via-macii.c
> +++ b/drivers/macintosh/via-macii.c
> @@ -23,8 +23,6 @@
> * Apple's "ADB Analyzer" bus sniffer is invaluable:
> * ftp://ftp.apple.com/developer/Tool_Chest/Devices_-_Hardware/Apple_Desktop_B…
> */
> -
> -#include <stdarg.h>
> #include <linux/types.h>
> #include <linux/errno.h>
> #include <linux/kernel.h>
> diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
> index 4bdd4c45e7a7..4b98bc26a94b 100644
> --- a/drivers/macintosh/via-pmu.c
> +++ b/drivers/macintosh/via-pmu.c
> @@ -18,7 +18,7 @@
> * a sleep or a freq. switch
> *
> */
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/mutex.h>
> #include <linux/types.h>
> #include <linux/errno.h>
> diff --git a/drivers/net/wireless/intersil/orinoco/hermes.c b/drivers/net/wireless/intersil/orinoco/hermes.c
> index 6d4b7f64efcf..256946552742 100644
> --- a/drivers/net/wireless/intersil/orinoco/hermes.c
> +++ b/drivers/net/wireless/intersil/orinoco/hermes.c
> @@ -79,7 +79,6 @@
>
> #undef HERMES_DEBUG
> #ifdef HERMES_DEBUG
> -#include <stdarg.h>
>
> #define DEBUG(lvl, stuff...) if ((lvl) <= HERMES_DEBUG) DMSG(stuff)
>
> diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h
> index 0d2f10e4cbc8..dc65b0712261 100644
> --- a/drivers/net/wwan/iosm/iosm_ipc_imem.h
> +++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h
> @@ -7,7 +7,6 @@
> #define IOSM_IPC_IMEM_H
>
> #include <linux/skbuff.h>
> -#include <stdbool.h>
>
> #include "iosm_ipc_mmio.h"
> #include "iosm_ipc_pcie.h"
> diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h
> index b69ba6b360a2..4d7548686f39 100644
> --- a/drivers/pinctrl/aspeed/pinmux-aspeed.h
> +++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h
> @@ -5,7 +5,6 @@
> #define ASPEED_PINMUX_H
>
> #include <linux/regmap.h>
> -#include <stdbool.h>
>
> /*
> * The ASPEED SoCs provide typically more than 200 pins for GPIO and other
> diff --git a/drivers/scsi/elx/efct/efct_driver.h b/drivers/scsi/elx/efct/efct_driver.h
> index dab8eac4f243..0e3c931db7c2 100644
> --- a/drivers/scsi/elx/efct/efct_driver.h
> +++ b/drivers/scsi/elx/efct/efct_driver.h
> @@ -10,7 +10,6 @@
> /***************************************************************************
> * OS specific includes
> */
> -#include <stdarg.h>
> #include <linux/module.h>
> #include <linux/debugfs.h>
> #include <linux/firmware.h>
> diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h
> index eceeb5d160ad..4dbec4063b3d 100644
> --- a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h
> +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h
> @@ -16,8 +16,6 @@
> #ifndef __ISP_LOCAL_H_INCLUDED__
> #define __ISP_LOCAL_H_INCLUDED__
>
> -#include <stdbool.h>
> -
> #include "isp_global.h"
>
> #include <isp2400_support.h>
> diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h
> index 540b405cc0f7..a3c7f3de6d17 100644
> --- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h
> +++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h
> @@ -16,7 +16,7 @@
> #ifndef __PRINT_SUPPORT_H_INCLUDED__
> #define __PRINT_SUPPORT_H_INCLUDED__
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> extern int (*sh_css_printf)(const char *fmt, va_list args);
> /* depends on host supplied print function in ia_css_init() */
> diff --git a/drivers/staging/media/atomisp/pci/ia_css_env.h b/drivers/staging/media/atomisp/pci/ia_css_env.h
> index 6b38723b27cd..3b89bbd837a0 100644
> --- a/drivers/staging/media/atomisp/pci/ia_css_env.h
> +++ b/drivers/staging/media/atomisp/pci/ia_css_env.h
> @@ -17,7 +17,7 @@
> #define __IA_CSS_ENV_H
>
> #include <type_support.h>
> -#include <stdarg.h> /* va_list */
> +#include <linux/stdarg.h> /* va_list */
> #include "ia_css_types.h"
> #include "ia_css_acc_types.h"
>
> diff --git a/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h b/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h
> index 5e6e7447ae00..e37ef4232c55 100644
> --- a/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h
> +++ b/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h
> @@ -19,7 +19,7 @@
> /*! \file */
>
> #include <type_support.h>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include "ia_css_types.h"
> #include "ia_css_binary.h"
> #include "ia_css_frame_public.h"
> diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h
> index 3c669ec79b68..496faa7297a5 100644
> --- a/drivers/staging/media/atomisp/pci/sh_css_internal.h
> +++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h
> @@ -20,7 +20,7 @@
> #include <math_support.h>
> #include <type_support.h>
> #include <platform_support.h>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #if !defined(ISP2401)
> #include "input_formatter.h"
> diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
> index 61ce0d142eea..0c5e565aa8cf 100644
> --- a/drivers/xen/xen-scsiback.c
> +++ b/drivers/xen/xen-scsiback.c
> @@ -33,8 +33,6 @@
>
> #define pr_fmt(fmt) "xen-pvscsi: " fmt
>
> -#include <stdarg.h>
> -
> #include <linux/module.h>
> #include <linux/utsname.h>
> #include <linux/interrupt.h>
> diff --git a/fs/befs/debug.c b/fs/befs/debug.c
> index eb7bd6c692c7..02fa66fb82c2 100644
> --- a/fs/befs/debug.c
> +++ b/fs/befs/debug.c
> @@ -14,7 +14,7 @@
> #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
> #ifdef __KERNEL__
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/string.h>
> #include <linux/spinlock.h>
> #include <linux/kernel.h>
> diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
> index 500f2000eb41..30319dc33c18 100644
> --- a/fs/reiserfs/prints.c
> +++ b/fs/reiserfs/prints.c
> @@ -8,7 +8,7 @@
> #include <linux/string.h>
> #include <linux/buffer_head.h>
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> static char error_buf[1024];
> static char fmt_buf[1024];
> diff --git a/fs/ufs/super.c b/fs/ufs/super.c
> index 74028b5a7b0a..00a01471ea05 100644
> --- a/fs/ufs/super.c
> +++ b/fs/ufs/super.c
> @@ -70,7 +70,7 @@
> #include <linux/module.h>
> #include <linux/bitops.h>
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include <linux/uaccess.h>
>
> diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h
> index f6656be81760..fb172a03a753 100644
> --- a/include/acpi/platform/acgcc.h
> +++ b/include/acpi/platform/acgcc.h
> @@ -22,7 +22,7 @@ typedef __builtin_va_list va_list;
> #define va_arg(v, l) __builtin_va_arg(v, l)
> #define va_copy(d, s) __builtin_va_copy(d, s)
> #else
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #endif
> #endif
>
> diff --git a/include/linux/filter.h b/include/linux/filter.h
> index 472f97074da0..45785fc231a8 100644
> --- a/include/linux/filter.h
> +++ b/include/linux/filter.h
> @@ -5,8 +5,6 @@
> #ifndef __LINUX_FILTER_H__
> #define __LINUX_FILTER_H__
>
> -#include <stdarg.h>
> -
> #include <linux/atomic.h>
> #include <linux/refcount.h>
> #include <linux/compat.h>
> diff --git a/include/linux/kernel.h b/include/linux/kernel.h
> index 1b2f0a7e00d6..2776423a587e 100644
> --- a/include/linux/kernel.h
> +++ b/include/linux/kernel.h
> @@ -2,7 +2,7 @@
> #ifndef _LINUX_KERNEL_H
> #define _LINUX_KERNEL_H
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/align.h>
> #include <linux/limits.h>
> #include <linux/linkage.h>
> diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h
> index a7330eb3ec64..7dd1f01ec4f9 100644
> --- a/include/linux/mISDNif.h
> +++ b/include/linux/mISDNif.h
> @@ -18,7 +18,6 @@
> #ifndef mISDNIF_H
> #define mISDNIF_H
>
> -#include <stdarg.h>
> #include <linux/types.h>
> #include <linux/errno.h>
> #include <linux/socket.h>
> diff --git a/include/linux/printk.h b/include/linux/printk.h
> index e834d78f0478..9f3f29ea348e 100644
> --- a/include/linux/printk.h
> +++ b/include/linux/printk.h
> @@ -2,7 +2,7 @@
> #ifndef __KERNEL_PRINTK__
> #define __KERNEL_PRINTK__
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/init.h>
> #include <linux/kern_levels.h>
> #include <linux/linkage.h>
> diff --git a/include/linux/stdarg.h b/include/linux/stdarg.h
> new file mode 100644
> index 000000000000..c8dc7f4f390c
> --- /dev/null
> +++ b/include/linux/stdarg.h
> @@ -0,0 +1,11 @@
> +// SPDX-License-Identifier: GPL-2.0-or-later
> +#ifndef _LINUX_STDARG_H
> +#define _LINUX_STDARG_H
> +
> +typedef __builtin_va_list va_list;
> +#define va_start(v, l) __builtin_va_start(v, l)
> +#define va_end(v) __builtin_va_end(v)
> +#define va_arg(v, T) __builtin_va_arg(v, T)
> +#define va_copy(d, s) __builtin_va_copy(d, s)
> +
> +#endif
> diff --git a/include/linux/string.h b/include/linux/string.h
> index b48d2d28e0b1..5e96d656be7a 100644
> --- a/include/linux/string.h
> +++ b/include/linux/string.h
> @@ -6,7 +6,7 @@
> #include <linux/types.h> /* for size_t */
> #include <linux/stddef.h> /* for NULL */
> #include <linux/errno.h> /* for E2BIG */
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <uapi/linux/string.h>
>
> extern char *strndup_user(const char __user *, long);
> diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
> index 9f50d22d68e6..4f9950678e7b 100644
> --- a/kernel/debug/kdb/kdb_support.c
> +++ b/kernel/debug/kdb/kdb_support.c
> @@ -10,7 +10,6 @@
> * 03/02/13 added new 2.5 kallsyms <xavier.bru(a)bull.net>
> */
>
> -#include <stdarg.h>
> #include <linux/types.h>
> #include <linux/sched.h>
> #include <linux/mm.h>
> diff --git a/lib/debug_info.c b/lib/debug_info.c
> index 36daf753293c..cc4723c74af5 100644
> --- a/lib/debug_info.c
> +++ b/lib/debug_info.c
> @@ -5,8 +5,6 @@
> * CONFIG_DEBUG_INFO_REDUCED. Please do not add actual code. However,
> * adding appropriate #includes is fine.
> */
> -#include <stdarg.h>
> -
> #include <linux/cred.h>
> #include <linux/crypto.h>
> #include <linux/dcache.h>
> @@ -22,6 +20,7 @@
> #include <linux/net.h>
> #include <linux/sched.h>
> #include <linux/slab.h>
> +#include <linux/stdarg.h>
> #include <linux/types.h>
> #include <net/addrconf.h>
> #include <net/sock.h>
> diff --git a/lib/kasprintf.c b/lib/kasprintf.c
> index bacf7b83ccf0..cd2f5974ed98 100644
> --- a/lib/kasprintf.c
> +++ b/lib/kasprintf.c
> @@ -5,7 +5,7 @@
> * Copyright (C) 1991, 1992 Linus Torvalds
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/export.h>
> #include <linux/slab.h>
> #include <linux/types.h>
> diff --git a/lib/kunit/string-stream.h b/lib/kunit/string-stream.h
> index 5e94b623454f..43f9508a55b4 100644
> --- a/lib/kunit/string-stream.h
> +++ b/lib/kunit/string-stream.h
> @@ -11,7 +11,7 @@
>
> #include <linux/spinlock.h>
> #include <linux/types.h>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> struct string_stream_fragment {
> struct kunit *test;
> diff --git a/lib/vsprintf.c b/lib/vsprintf.c
> index 26c83943748a..3bcb7be03f93 100644
> --- a/lib/vsprintf.c
> +++ b/lib/vsprintf.c
> @@ -17,7 +17,7 @@
> * - scnprintf and vscnprintf
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
> #include <linux/build_bug.h>
> #include <linux/clk.h>
> #include <linux/clk-provider.h>
> diff --git a/mm/kfence/report.c b/mm/kfence/report.c
> index 2a319c21c939..4b891dd75650 100644
> --- a/mm/kfence/report.c
> +++ b/mm/kfence/report.c
> @@ -5,7 +5,7 @@
> * Copyright (C) 2020, Google LLC.
> */
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include <linux/kernel.h>
> #include <linux/lockdep.h>
> diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
> index f0e5d1429662..7a93a1e94c40 100644
> --- a/net/batman-adv/log.c
> +++ b/net/batman-adv/log.c
> @@ -7,7 +7,7 @@
> #include "log.h"
> #include "main.h"
>
> -#include <stdarg.h>
> +#include <linux/stdarg.h>
>
> #include "trace.h"
>
> diff --git a/sound/aoa/codecs/onyx.h b/sound/aoa/codecs/onyx.h
> index 8a32c3c3d716..6c31b7373b78 100644
> --- a/sound/aoa/codecs/onyx.h
> +++ b/sound/aoa/codecs/onyx.h
> @@ -6,7 +6,6 @@
> */
> #ifndef __SND_AOA_CODEC_ONYX_H
> #define __SND_AOA_CODEC_ONYX_H
> -#include <stddef.h>
> #include <linux/i2c.h>
> #include <asm/pmac_low_i2c.h>
> #include <asm/prom.h>
> diff --git a/sound/aoa/codecs/tas.c b/sound/aoa/codecs/tas.c
> index ac246dd3ab49..ab19a37e2a68 100644
> --- a/sound/aoa/codecs/tas.c
> +++ b/sound/aoa/codecs/tas.c
> @@ -58,7 +58,6 @@
> * and up to the hardware designer to not wire
> * them up in some weird unusable way.
> */
> -#include <stddef.h>
> #include <linux/i2c.h>
> #include <asm/pmac_low_i2c.h>
> #include <asm/prom.h>
> diff --git a/sound/core/info.c b/sound/core/info.c
> index 9fec3070f8ba..a451b24199c3 100644
> --- a/sound/core/info.c
> +++ b/sound/core/info.c
> @@ -16,7 +16,6 @@
> #include <linux/utsname.h>
> #include <linux/proc_fs.h>
> #include <linux/mutex.h>
> -#include <stdarg.h>
>
> int snd_info_check_reserved_words(const char *str)
> {
> </cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_kernel/llvm-release-arm-next-allmodconfig - Build # 29 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *linux* in CI configuration tcwg_kernel/llvm-release-arm-next-allmodconfig. So far, this commit has regressed CI configurations:
- tcwg_kernel/llvm-release-arm-next-allmodconfig
Culprit:
<cut>
commit 6f4266a78a4e090b452a0335c1414f3240684743
Author: Alexey Dobriyan <adobriyan(a)gmail.com>
Date: Fri Jul 16 13:44:03 2021 +1000
kbuild: decouple build from userspace headers
First, userspace headers can be under incompatible license.
Second, kernel doesn't require userspace to operate and should not
require anything from userspace to be built other than compiler.
We would use -ffreestanding too if not builtin function shenanigans.
To decouple:
* ship minimal stdarg.h as <linux/stdarg.h>,
1 type, 4 macros
GPL 2 version of <stdarg.h> can be extracted from
http://archive.debian.org/debian/pool/main/g/gcc-4.2/gcc-4.2_4.2.4.orig.tar…
* delete "-isystem" from command line arguments,
this is what enables header leakage
* fixup/delete include directives where necessary.
Link: https://lkml.kernel.org/r/YO8ioz4sHwcUAkdt@localhost.localdomain
Signed-off-by: Alexey Dobriyan <adobriyan(a)gmail.com>
Cc: Arnd Bergmann <arnd(a)arndb.de>
Cc: Masahiro Yamada <masahiroy(a)kernel.org>
Cc: Christoph Hellwig <hch(a)infradead.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr(a)canb.auug.org.au>
</cut>
Results regressed to (for first_bad == 6f4266a78a4e090b452a0335c1414f3240684743)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
21684
# First few build errors in logs:
# 00:01:11 crypto/aegis128-neon-inner.c:11:10: fatal error: 'arm_neon.h' file not found
# 00:01:11 make[1]: *** [crypto/aegis128-neon-inner.o] Error 1
# 00:01:14 lib/raid6/recov_neon_inner.c:7:10: fatal error: 'arm_neon.h' file not found
# 00:01:14 make[2]: *** [lib/raid6/recov_neon_inner.o] Error 1
# 00:01:14 lib/raid6/neon1.c:27:10: fatal error: 'arm_neon.h' file not found
# 00:01:14 make[2]: *** [lib/raid6/neon1.o] Error 1
# 00:01:15 lib/raid6/neon2.c:27:10: fatal error: 'arm_neon.h' file not found
# 00:01:15 make[2]: *** [lib/raid6/neon2.o] Error 1
# 00:01:15 lib/raid6/neon4.c:27:10: fatal error: 'arm_neon.h' file not found
# 00:01:15 make[2]: *** [lib/raid6/neon4.o] Error 1
from (for last_good == d06391f28276b0ad28a59073bdb8eb10dc4ea495)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_llvm:
-5
# build_abe qemu:
-2
# linux_n_obj:
29753
# linux build successful:
all
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Build top page/logs: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Configuration details:
rr[linux_url]="https://git.kernel.org/pub/scm/linux/kernel/git/next/linux-next.git"
rr[linux_branch]="e9338abf0e186336022293d2e454c106761f262b"
Reproduce builds:
<cut>
mkdir investigate-linux-6f4266a78a4e090b452a0335c1414f3240684743
cd investigate-linux-6f4266a78a4e090b452a0335c1414f3240684743
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_kernel-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude linux/ ./ ./bisect/baseline/
cd linux
# Reproduce first_bad build
git checkout --detach 6f4266a78a4e090b452a0335c1414f3240684743
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach d06391f28276b0ad28a59073bdb8eb10dc4ea495
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Build log: https://ci.linaro.org/job/tcwg_kernel-llvm-bisect-llvm-release-arm-next-all…
Full commit (up to 1000 lines):
<cut>
commit 6f4266a78a4e090b452a0335c1414f3240684743
Author: Alexey Dobriyan <adobriyan(a)gmail.com>
Date: Fri Jul 16 13:44:03 2021 +1000
kbuild: decouple build from userspace headers
First, userspace headers can be under incompatible license.
Second, kernel doesn't require userspace to operate and should not
require anything from userspace to be built other than compiler.
We would use -ffreestanding too if not builtin function shenanigans.
To decouple:
* ship minimal stdarg.h as <linux/stdarg.h>,
1 type, 4 macros
GPL 2 version of <stdarg.h> can be extracted from
http://archive.debian.org/debian/pool/main/g/gcc-4.2/gcc-4.2_4.2.4.orig.tar…
* delete "-isystem" from command line arguments,
this is what enables header leakage
* fixup/delete include directives where necessary.
Link: https://lkml.kernel.org/r/YO8ioz4sHwcUAkdt@localhost.localdomain
Signed-off-by: Alexey Dobriyan <adobriyan(a)gmail.com>
Cc: Arnd Bergmann <arnd(a)arndb.de>
Cc: Masahiro Yamada <masahiroy(a)kernel.org>
Cc: Christoph Hellwig <hch(a)infradead.org>
Signed-off-by: Andrew Morton <akpm(a)linux-foundation.org>
Signed-off-by: Stephen Rothwell <sfr(a)canb.auug.org.au>
---
Makefile | 2 +-
arch/arm/kernel/process.c | 2 --
arch/arm/mach-bcm/bcm_kona_smc.c | 2 --
arch/arm64/kernel/process.c | 3 ---
arch/openrisc/kernel/process.c | 2 --
arch/parisc/kernel/firmware.c | 2 +-
arch/parisc/kernel/process.c | 3 ---
arch/powerpc/kernel/prom.c | 1 -
arch/powerpc/kernel/prom_init.c | 2 +-
arch/powerpc/kernel/rtas.c | 2 +-
arch/powerpc/kernel/udbg.c | 2 +-
arch/s390/boot/pgm_check_info.c | 2 +-
arch/sparc/kernel/process_32.c | 3 ---
arch/sparc/kernel/process_64.c | 3 ---
arch/um/include/shared/irq_user.h | 1 -
arch/um/include/shared/os.h | 1 -
arch/um/os-Linux/signal.c | 2 +-
arch/um/os-Linux/util.c | 1 +
arch/x86/boot/boot.h | 2 +-
crypto/aegis128-neon-inner.c | 2 --
drivers/block/xen-blkback/xenbus.c | 1 -
drivers/firmware/efi/libstub/efi-stub-helper.c | 2 +-
drivers/firmware/efi/libstub/vsprintf.c | 2 +-
drivers/gpu/drm/amd/display/dc/dc_helper.c | 2 +-
drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h | 1 -
drivers/gpu/drm/drm_print.c | 2 +-
drivers/gpu/drm/msm/disp/msm_disp_snapshot.h | 1 -
drivers/isdn/capi/capiutil.c | 2 +-
drivers/macintosh/macio-adb.c | 1 -
drivers/macintosh/via-cuda.c | 2 +-
drivers/macintosh/via-macii.c | 2 --
drivers/macintosh/via-pmu.c | 2 +-
drivers/net/wireless/intersil/orinoco/hermes.c | 1 -
drivers/net/wwan/iosm/iosm_ipc_imem.h | 1 -
drivers/pinctrl/aspeed/pinmux-aspeed.h | 1 -
drivers/scsi/elx/efct/efct_driver.h | 1 -
.../media/atomisp/pci/hive_isp_css_common/host/isp_local.h | 2 --
.../media/atomisp/pci/hive_isp_css_include/print_support.h | 2 +-
drivers/staging/media/atomisp/pci/ia_css_env.h | 2 +-
.../media/atomisp/pci/runtime/debug/interface/ia_css_debug.h | 2 +-
drivers/staging/media/atomisp/pci/sh_css_internal.h | 2 +-
drivers/xen/xen-scsiback.c | 2 --
fs/befs/debug.c | 2 +-
fs/reiserfs/prints.c | 2 +-
fs/ufs/super.c | 2 +-
include/acpi/platform/acgcc.h | 2 +-
include/linux/filter.h | 2 --
include/linux/kernel.h | 2 +-
include/linux/mISDNif.h | 1 -
include/linux/printk.h | 2 +-
include/linux/stdarg.h | 11 +++++++++++
include/linux/string.h | 2 +-
kernel/debug/kdb/kdb_support.c | 1 -
lib/debug_info.c | 3 +--
lib/kasprintf.c | 2 +-
lib/kunit/string-stream.h | 2 +-
lib/vsprintf.c | 2 +-
mm/kfence/report.c | 2 +-
net/batman-adv/log.c | 2 +-
sound/aoa/codecs/onyx.h | 1 -
sound/aoa/codecs/tas.c | 1 -
sound/core/info.c | 1 -
62 files changed, 44 insertions(+), 77 deletions(-)
diff --git a/Makefile b/Makefile
index eaa692976851..02591a333d86 100644
--- a/Makefile
+++ b/Makefile
@@ -972,7 +972,7 @@ KBUILD_CFLAGS += -falign-functions=64
endif
# arch Makefile may override CC so keep this after arch Makefile is included
-NOSTDINC_FLAGS += -nostdinc -isystem $(shell $(CC) -print-file-name=include)
+NOSTDINC_FLAGS += -nostdinc
# warn about C99 declaration after statement
KBUILD_CFLAGS += -Wdeclaration-after-statement
diff --git a/arch/arm/kernel/process.c b/arch/arm/kernel/process.c
index fc9e8b37eaa8..bb5ad8a6a4c3 100644
--- a/arch/arm/kernel/process.c
+++ b/arch/arm/kernel/process.c
@@ -5,8 +5,6 @@
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Original Copyright (C) 1995 Linus Torvalds
*/
-#include <stdarg.h>
-
#include <linux/export.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
diff --git a/arch/arm/mach-bcm/bcm_kona_smc.c b/arch/arm/mach-bcm/bcm_kona_smc.c
index 43a16f922b53..43829e49ad93 100644
--- a/arch/arm/mach-bcm/bcm_kona_smc.c
+++ b/arch/arm/mach-bcm/bcm_kona_smc.c
@@ -10,8 +10,6 @@
* of MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
* GNU General Public License for more details.
*/
-
-#include <stdarg.h>
#include <linux/smp.h>
#include <linux/io.h>
#include <linux/ioport.h>
diff --git a/arch/arm64/kernel/process.c b/arch/arm64/kernel/process.c
index c8989b999250..5f7ac9a0f9a3 100644
--- a/arch/arm64/kernel/process.c
+++ b/arch/arm64/kernel/process.c
@@ -6,9 +6,6 @@
* Copyright (C) 1996-2000 Russell King - Converted to ARM.
* Copyright (C) 2012 ARM Ltd.
*/
-
-#include <stdarg.h>
-
#include <linux/compat.h>
#include <linux/efi.h>
#include <linux/elf.h>
diff --git a/arch/openrisc/kernel/process.c b/arch/openrisc/kernel/process.c
index eb62429681fc..b0698d9ce14f 100644
--- a/arch/openrisc/kernel/process.c
+++ b/arch/openrisc/kernel/process.c
@@ -14,8 +14,6 @@
*/
#define __KERNEL_SYSCALLS__
-#include <stdarg.h>
-
#include <linux/errno.h>
#include <linux/sched.h>
#include <linux/sched/debug.h>
diff --git a/arch/parisc/kernel/firmware.c b/arch/parisc/kernel/firmware.c
index 665b70086685..7034227dbdf3 100644
--- a/arch/parisc/kernel/firmware.c
+++ b/arch/parisc/kernel/firmware.c
@@ -51,7 +51,7 @@
* prumpf 991016
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/delay.h>
#include <linux/init.h>
diff --git a/arch/parisc/kernel/process.c b/arch/parisc/kernel/process.c
index 184ec3c1eae4..38ec4ae81239 100644
--- a/arch/parisc/kernel/process.c
+++ b/arch/parisc/kernel/process.c
@@ -17,9 +17,6 @@
* Copyright (C) 2001-2014 Helge Deller <deller(a)gmx.de>
* Copyright (C) 2002 Randolph Chung <tausq with parisc-linux.org>
*/
-
-#include <stdarg.h>
-
#include <linux/elf.h>
#include <linux/errno.h>
#include <linux/kernel.h>
diff --git a/arch/powerpc/kernel/prom.c b/arch/powerpc/kernel/prom.c
index f620e04dc9bf..a1e7ba0fad09 100644
--- a/arch/powerpc/kernel/prom.c
+++ b/arch/powerpc/kernel/prom.c
@@ -11,7 +11,6 @@
#undef DEBUG
-#include <stdarg.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/init.h>
diff --git a/arch/powerpc/kernel/prom_init.c b/arch/powerpc/kernel/prom_init.c
index a5bf355ce1d6..10664633f7e3 100644
--- a/arch/powerpc/kernel/prom_init.c
+++ b/arch/powerpc/kernel/prom_init.c
@@ -14,7 +14,7 @@
/* we cannot use FORTIFY as it brings in new symbols */
#define __NO_FORTIFY
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/kernel.h>
#include <linux/string.h>
#include <linux/init.h>
diff --git a/arch/powerpc/kernel/rtas.c b/arch/powerpc/kernel/rtas.c
index 99f2cce635fb..ff80bbad22a5 100644
--- a/arch/powerpc/kernel/rtas.c
+++ b/arch/powerpc/kernel/rtas.c
@@ -7,7 +7,7 @@
* Copyright (C) 2001 IBM.
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/kernel.h>
#include <linux/types.h>
#include <linux/spinlock.h>
diff --git a/arch/powerpc/kernel/udbg.c b/arch/powerpc/kernel/udbg.c
index 01595e8cafe7..b1544b2f6321 100644
--- a/arch/powerpc/kernel/udbg.c
+++ b/arch/powerpc/kernel/udbg.c
@@ -5,7 +5,7 @@
* c 2001 PPC 64 Team, IBM Corp
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/console.h>
diff --git a/arch/s390/boot/pgm_check_info.c b/arch/s390/boot/pgm_check_info.c
index 3a46abed2549..b7d8dd88bbf2 100644
--- a/arch/s390/boot/pgm_check_info.c
+++ b/arch/s390/boot/pgm_check_info.c
@@ -1,5 +1,6 @@
// SPDX-License-Identifier: GPL-2.0
#include <linux/kernel.h>
+#include <linux/stdarg.h>
#include <linux/string.h>
#include <linux/ctype.h>
#include <asm/stacktrace.h>
@@ -8,7 +9,6 @@
#include <asm/setup.h>
#include <asm/sclp.h>
#include <asm/uv.h>
-#include <stdarg.h>
#include "boot.h"
const char hex_asc[] = "0123456789abcdef";
diff --git a/arch/sparc/kernel/process_32.c b/arch/sparc/kernel/process_32.c
index 93983d6d431d..bbbe0cfef746 100644
--- a/arch/sparc/kernel/process_32.c
+++ b/arch/sparc/kernel/process_32.c
@@ -8,9 +8,6 @@
/*
* This file handles the architecture-dependent parts of process handling..
*/
-
-#include <stdarg.h>
-
#include <linux/elfcore.h>
#include <linux/errno.h>
#include <linux/module.h>
diff --git a/arch/sparc/kernel/process_64.c b/arch/sparc/kernel/process_64.c
index d33c58a58d4f..0cabcdfb23fd 100644
--- a/arch/sparc/kernel/process_64.c
+++ b/arch/sparc/kernel/process_64.c
@@ -9,9 +9,6 @@
/*
* This file handles the architecture-dependent parts of process handling..
*/
-
-#include <stdarg.h>
-
#include <linux/errno.h>
#include <linux/export.h>
#include <linux/sched.h>
diff --git a/arch/um/include/shared/irq_user.h b/arch/um/include/shared/irq_user.h
index 065829f443ae..86a8a573b65c 100644
--- a/arch/um/include/shared/irq_user.h
+++ b/arch/um/include/shared/irq_user.h
@@ -7,7 +7,6 @@
#define __IRQ_USER_H__
#include <sysdep/ptrace.h>
-#include <stdbool.h>
enum um_irq_type {
IRQ_READ,
diff --git a/arch/um/include/shared/os.h b/arch/um/include/shared/os.h
index 60b84edc8a68..96d400387c93 100644
--- a/arch/um/include/shared/os.h
+++ b/arch/um/include/shared/os.h
@@ -8,7 +8,6 @@
#ifndef __OS_H__
#define __OS_H__
-#include <stdarg.h>
#include <irq_user.h>
#include <longjmp.h>
#include <mm_id.h>
diff --git a/arch/um/os-Linux/signal.c b/arch/um/os-Linux/signal.c
index 6de99bb16113..6cf098c23a39 100644
--- a/arch/um/os-Linux/signal.c
+++ b/arch/um/os-Linux/signal.c
@@ -67,7 +67,7 @@ int signals_enabled;
#ifdef UML_CONFIG_UML_TIME_TRAVEL_SUPPORT
static int signals_blocked;
#else
-#define signals_blocked false
+#define signals_blocked 0
#endif
static unsigned int signals_pending;
static unsigned int signals_active = 0;
diff --git a/arch/um/os-Linux/util.c b/arch/um/os-Linux/util.c
index 07327425d06e..41297ec404bf 100644
--- a/arch/um/os-Linux/util.c
+++ b/arch/um/os-Linux/util.c
@@ -3,6 +3,7 @@
* Copyright (C) 2000 - 2007 Jeff Dike (jdike(a){addtoit,linux.intel}.com)
*/
+#include <stdarg.h>
#include <stdio.h>
#include <stdlib.h>
#include <unistd.h>
diff --git a/arch/x86/boot/boot.h b/arch/x86/boot/boot.h
index ca866f1cca2e..34c9dbb6a47d 100644
--- a/arch/x86/boot/boot.h
+++ b/arch/x86/boot/boot.h
@@ -18,7 +18,7 @@
#ifndef __ASSEMBLY__
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/types.h>
#include <linux/edd.h>
#include <asm/setup.h>
diff --git a/crypto/aegis128-neon-inner.c b/crypto/aegis128-neon-inner.c
index 7de485907d81..6b37fbb79884 100644
--- a/crypto/aegis128-neon-inner.c
+++ b/crypto/aegis128-neon-inner.c
@@ -15,8 +15,6 @@
#define AEGIS_BLOCK_SIZE 16
-#include <stddef.h>
-
extern int aegis128_have_aes_insn;
void *memcpy(void *dest, const void *src, size_t n);
diff --git a/drivers/block/xen-blkback/xenbus.c b/drivers/block/xen-blkback/xenbus.c
index 125b22205d38..33eba3df4dd9 100644
--- a/drivers/block/xen-blkback/xenbus.c
+++ b/drivers/block/xen-blkback/xenbus.c
@@ -8,7 +8,6 @@
#define pr_fmt(fmt) "xen-blkback: " fmt
-#include <stdarg.h>
#include <linux/module.h>
#include <linux/kthread.h>
#include <xen/events.h>
diff --git a/drivers/firmware/efi/libstub/efi-stub-helper.c b/drivers/firmware/efi/libstub/efi-stub-helper.c
index aa8da0a49829..4921580e1725 100644
--- a/drivers/firmware/efi/libstub/efi-stub-helper.c
+++ b/drivers/firmware/efi/libstub/efi-stub-helper.c
@@ -7,7 +7,7 @@
* Copyright 2011 Intel Corporation; author Matt Fleming
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/ctype.h>
#include <linux/efi.h>
diff --git a/drivers/firmware/efi/libstub/vsprintf.c b/drivers/firmware/efi/libstub/vsprintf.c
index 1088e288c04d..71c71c222346 100644
--- a/drivers/firmware/efi/libstub/vsprintf.c
+++ b/drivers/firmware/efi/libstub/vsprintf.c
@@ -10,7 +10,7 @@
* Oh, it's a waste of space, but oh-so-yummy for debugging.
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/compiler.h>
#include <linux/ctype.h>
diff --git a/drivers/gpu/drm/amd/display/dc/dc_helper.c b/drivers/gpu/drm/amd/display/dc/dc_helper.c
index a612ba6dc389..ab6bc5d79012 100644
--- a/drivers/gpu/drm/amd/display/dc/dc_helper.c
+++ b/drivers/gpu/drm/amd/display/dc/dc_helper.c
@@ -28,9 +28,9 @@
*/
#include <linux/delay.h>
+#include <linux/stdarg.h>
#include "dm_services.h"
-#include <stdarg.h>
#include "dc.h"
#include "dc_dmub_srv.h"
diff --git a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
index 7c4734f905d9..68fd451aca23 100644
--- a/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
+++ b/drivers/gpu/drm/amd/display/dmub/inc/dmub_cmd.h
@@ -39,7 +39,6 @@
#include <linux/types.h>
#include <linux/string.h>
#include <linux/delay.h>
-#include <stdarg.h>
#include "atomfirmware.h"
diff --git a/drivers/gpu/drm/drm_print.c b/drivers/gpu/drm/drm_print.c
index 111b932cf2a9..f783d4963d4b 100644
--- a/drivers/gpu/drm/drm_print.c
+++ b/drivers/gpu/drm/drm_print.c
@@ -25,7 +25,7 @@
#define DEBUG /* for pr_debug() */
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/io.h>
#include <linux/moduleparam.h>
diff --git a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
index c92a9508c8d3..0f9a5364cd86 100644
--- a/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
+++ b/drivers/gpu/drm/msm/disp/msm_disp_snapshot.h
@@ -25,7 +25,6 @@
#include <linux/pm_runtime.h>
#include <linux/kthread.h>
#include <linux/devcoredump.h>
-#include <stdarg.h>
#include "msm_kms.h"
#define MSM_DISP_SNAPSHOT_MAX_BLKS 10
diff --git a/drivers/isdn/capi/capiutil.c b/drivers/isdn/capi/capiutil.c
index f26bf3c66d7e..d7ae42edc4a8 100644
--- a/drivers/isdn/capi/capiutil.c
+++ b/drivers/isdn/capi/capiutil.c
@@ -379,7 +379,7 @@ static char *pnames[] =
/*2f */ "Useruserdata"
};
-#include <stdarg.h>
+#include <linux/stdarg.h>
/*-------------------------------------------------------*/
static _cdebbuf *bufprint(_cdebbuf *cdb, char *fmt, ...)
diff --git a/drivers/macintosh/macio-adb.c b/drivers/macintosh/macio-adb.c
index d4759db002c6..dc634c2932fd 100644
--- a/drivers/macintosh/macio-adb.c
+++ b/drivers/macintosh/macio-adb.c
@@ -2,7 +2,6 @@
/*
* Driver for the ADB controller in the Mac I/O (Hydra) chip.
*/
-#include <stdarg.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/kernel.h>
diff --git a/drivers/macintosh/via-cuda.c b/drivers/macintosh/via-cuda.c
index 3581abfb0c6a..cd267392289c 100644
--- a/drivers/macintosh/via-cuda.c
+++ b/drivers/macintosh/via-cuda.c
@@ -9,7 +9,7 @@
*
* Copyright (C) 1996 Paul Mackerras.
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/kernel.h>
diff --git a/drivers/macintosh/via-macii.c b/drivers/macintosh/via-macii.c
index 060e03f2264b..db9270da5b8e 100644
--- a/drivers/macintosh/via-macii.c
+++ b/drivers/macintosh/via-macii.c
@@ -23,8 +23,6 @@
* Apple's "ADB Analyzer" bus sniffer is invaluable:
* ftp://ftp.apple.com/developer/Tool_Chest/Devices_-_Hardware/Apple_Desktop_B…
*/
-
-#include <stdarg.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/kernel.h>
diff --git a/drivers/macintosh/via-pmu.c b/drivers/macintosh/via-pmu.c
index 4bdd4c45e7a7..4b98bc26a94b 100644
--- a/drivers/macintosh/via-pmu.c
+++ b/drivers/macintosh/via-pmu.c
@@ -18,7 +18,7 @@
* a sleep or a freq. switch
*
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/mutex.h>
#include <linux/types.h>
#include <linux/errno.h>
diff --git a/drivers/net/wireless/intersil/orinoco/hermes.c b/drivers/net/wireless/intersil/orinoco/hermes.c
index 6d4b7f64efcf..256946552742 100644
--- a/drivers/net/wireless/intersil/orinoco/hermes.c
+++ b/drivers/net/wireless/intersil/orinoco/hermes.c
@@ -79,7 +79,6 @@
#undef HERMES_DEBUG
#ifdef HERMES_DEBUG
-#include <stdarg.h>
#define DEBUG(lvl, stuff...) if ((lvl) <= HERMES_DEBUG) DMSG(stuff)
diff --git a/drivers/net/wwan/iosm/iosm_ipc_imem.h b/drivers/net/wwan/iosm/iosm_ipc_imem.h
index 0d2f10e4cbc8..dc65b0712261 100644
--- a/drivers/net/wwan/iosm/iosm_ipc_imem.h
+++ b/drivers/net/wwan/iosm/iosm_ipc_imem.h
@@ -7,7 +7,6 @@
#define IOSM_IPC_IMEM_H
#include <linux/skbuff.h>
-#include <stdbool.h>
#include "iosm_ipc_mmio.h"
#include "iosm_ipc_pcie.h"
diff --git a/drivers/pinctrl/aspeed/pinmux-aspeed.h b/drivers/pinctrl/aspeed/pinmux-aspeed.h
index b69ba6b360a2..4d7548686f39 100644
--- a/drivers/pinctrl/aspeed/pinmux-aspeed.h
+++ b/drivers/pinctrl/aspeed/pinmux-aspeed.h
@@ -5,7 +5,6 @@
#define ASPEED_PINMUX_H
#include <linux/regmap.h>
-#include <stdbool.h>
/*
* The ASPEED SoCs provide typically more than 200 pins for GPIO and other
diff --git a/drivers/scsi/elx/efct/efct_driver.h b/drivers/scsi/elx/efct/efct_driver.h
index dab8eac4f243..0e3c931db7c2 100644
--- a/drivers/scsi/elx/efct/efct_driver.h
+++ b/drivers/scsi/elx/efct/efct_driver.h
@@ -10,7 +10,6 @@
/***************************************************************************
* OS specific includes
*/
-#include <stdarg.h>
#include <linux/module.h>
#include <linux/debugfs.h>
#include <linux/firmware.h>
diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h
index eceeb5d160ad..4dbec4063b3d 100644
--- a/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h
+++ b/drivers/staging/media/atomisp/pci/hive_isp_css_common/host/isp_local.h
@@ -16,8 +16,6 @@
#ifndef __ISP_LOCAL_H_INCLUDED__
#define __ISP_LOCAL_H_INCLUDED__
-#include <stdbool.h>
-
#include "isp_global.h"
#include <isp2400_support.h>
diff --git a/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h b/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h
index 540b405cc0f7..a3c7f3de6d17 100644
--- a/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h
+++ b/drivers/staging/media/atomisp/pci/hive_isp_css_include/print_support.h
@@ -16,7 +16,7 @@
#ifndef __PRINT_SUPPORT_H_INCLUDED__
#define __PRINT_SUPPORT_H_INCLUDED__
-#include <stdarg.h>
+#include <linux/stdarg.h>
extern int (*sh_css_printf)(const char *fmt, va_list args);
/* depends on host supplied print function in ia_css_init() */
diff --git a/drivers/staging/media/atomisp/pci/ia_css_env.h b/drivers/staging/media/atomisp/pci/ia_css_env.h
index 6b38723b27cd..3b89bbd837a0 100644
--- a/drivers/staging/media/atomisp/pci/ia_css_env.h
+++ b/drivers/staging/media/atomisp/pci/ia_css_env.h
@@ -17,7 +17,7 @@
#define __IA_CSS_ENV_H
#include <type_support.h>
-#include <stdarg.h> /* va_list */
+#include <linux/stdarg.h> /* va_list */
#include "ia_css_types.h"
#include "ia_css_acc_types.h"
diff --git a/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h b/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h
index 5e6e7447ae00..e37ef4232c55 100644
--- a/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h
+++ b/drivers/staging/media/atomisp/pci/runtime/debug/interface/ia_css_debug.h
@@ -19,7 +19,7 @@
/*! \file */
#include <type_support.h>
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include "ia_css_types.h"
#include "ia_css_binary.h"
#include "ia_css_frame_public.h"
diff --git a/drivers/staging/media/atomisp/pci/sh_css_internal.h b/drivers/staging/media/atomisp/pci/sh_css_internal.h
index 3c669ec79b68..496faa7297a5 100644
--- a/drivers/staging/media/atomisp/pci/sh_css_internal.h
+++ b/drivers/staging/media/atomisp/pci/sh_css_internal.h
@@ -20,7 +20,7 @@
#include <math_support.h>
#include <type_support.h>
#include <platform_support.h>
-#include <stdarg.h>
+#include <linux/stdarg.h>
#if !defined(ISP2401)
#include "input_formatter.h"
diff --git a/drivers/xen/xen-scsiback.c b/drivers/xen/xen-scsiback.c
index 61ce0d142eea..0c5e565aa8cf 100644
--- a/drivers/xen/xen-scsiback.c
+++ b/drivers/xen/xen-scsiback.c
@@ -33,8 +33,6 @@
#define pr_fmt(fmt) "xen-pvscsi: " fmt
-#include <stdarg.h>
-
#include <linux/module.h>
#include <linux/utsname.h>
#include <linux/interrupt.h>
diff --git a/fs/befs/debug.c b/fs/befs/debug.c
index eb7bd6c692c7..02fa66fb82c2 100644
--- a/fs/befs/debug.c
+++ b/fs/befs/debug.c
@@ -14,7 +14,7 @@
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
#ifdef __KERNEL__
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/string.h>
#include <linux/spinlock.h>
#include <linux/kernel.h>
diff --git a/fs/reiserfs/prints.c b/fs/reiserfs/prints.c
index 500f2000eb41..30319dc33c18 100644
--- a/fs/reiserfs/prints.c
+++ b/fs/reiserfs/prints.c
@@ -8,7 +8,7 @@
#include <linux/string.h>
#include <linux/buffer_head.h>
-#include <stdarg.h>
+#include <linux/stdarg.h>
static char error_buf[1024];
static char fmt_buf[1024];
diff --git a/fs/ufs/super.c b/fs/ufs/super.c
index 74028b5a7b0a..00a01471ea05 100644
--- a/fs/ufs/super.c
+++ b/fs/ufs/super.c
@@ -70,7 +70,7 @@
#include <linux/module.h>
#include <linux/bitops.h>
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/uaccess.h>
diff --git a/include/acpi/platform/acgcc.h b/include/acpi/platform/acgcc.h
index f6656be81760..fb172a03a753 100644
--- a/include/acpi/platform/acgcc.h
+++ b/include/acpi/platform/acgcc.h
@@ -22,7 +22,7 @@ typedef __builtin_va_list va_list;
#define va_arg(v, l) __builtin_va_arg(v, l)
#define va_copy(d, s) __builtin_va_copy(d, s)
#else
-#include <stdarg.h>
+#include <linux/stdarg.h>
#endif
#endif
diff --git a/include/linux/filter.h b/include/linux/filter.h
index 472f97074da0..45785fc231a8 100644
--- a/include/linux/filter.h
+++ b/include/linux/filter.h
@@ -5,8 +5,6 @@
#ifndef __LINUX_FILTER_H__
#define __LINUX_FILTER_H__
-#include <stdarg.h>
-
#include <linux/atomic.h>
#include <linux/refcount.h>
#include <linux/compat.h>
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index 1b2f0a7e00d6..2776423a587e 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -2,7 +2,7 @@
#ifndef _LINUX_KERNEL_H
#define _LINUX_KERNEL_H
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/align.h>
#include <linux/limits.h>
#include <linux/linkage.h>
diff --git a/include/linux/mISDNif.h b/include/linux/mISDNif.h
index a7330eb3ec64..7dd1f01ec4f9 100644
--- a/include/linux/mISDNif.h
+++ b/include/linux/mISDNif.h
@@ -18,7 +18,6 @@
#ifndef mISDNIF_H
#define mISDNIF_H
-#include <stdarg.h>
#include <linux/types.h>
#include <linux/errno.h>
#include <linux/socket.h>
diff --git a/include/linux/printk.h b/include/linux/printk.h
index e834d78f0478..9f3f29ea348e 100644
--- a/include/linux/printk.h
+++ b/include/linux/printk.h
@@ -2,7 +2,7 @@
#ifndef __KERNEL_PRINTK__
#define __KERNEL_PRINTK__
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/init.h>
#include <linux/kern_levels.h>
#include <linux/linkage.h>
diff --git a/include/linux/stdarg.h b/include/linux/stdarg.h
new file mode 100644
index 000000000000..c8dc7f4f390c
--- /dev/null
+++ b/include/linux/stdarg.h
@@ -0,0 +1,11 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+#ifndef _LINUX_STDARG_H
+#define _LINUX_STDARG_H
+
+typedef __builtin_va_list va_list;
+#define va_start(v, l) __builtin_va_start(v, l)
+#define va_end(v) __builtin_va_end(v)
+#define va_arg(v, T) __builtin_va_arg(v, T)
+#define va_copy(d, s) __builtin_va_copy(d, s)
+
+#endif
diff --git a/include/linux/string.h b/include/linux/string.h
index b48d2d28e0b1..5e96d656be7a 100644
--- a/include/linux/string.h
+++ b/include/linux/string.h
@@ -6,7 +6,7 @@
#include <linux/types.h> /* for size_t */
#include <linux/stddef.h> /* for NULL */
#include <linux/errno.h> /* for E2BIG */
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <uapi/linux/string.h>
extern char *strndup_user(const char __user *, long);
diff --git a/kernel/debug/kdb/kdb_support.c b/kernel/debug/kdb/kdb_support.c
index 9f50d22d68e6..4f9950678e7b 100644
--- a/kernel/debug/kdb/kdb_support.c
+++ b/kernel/debug/kdb/kdb_support.c
@@ -10,7 +10,6 @@
* 03/02/13 added new 2.5 kallsyms <xavier.bru(a)bull.net>
*/
-#include <stdarg.h>
#include <linux/types.h>
#include <linux/sched.h>
#include <linux/mm.h>
diff --git a/lib/debug_info.c b/lib/debug_info.c
index 36daf753293c..cc4723c74af5 100644
--- a/lib/debug_info.c
+++ b/lib/debug_info.c
@@ -5,8 +5,6 @@
* CONFIG_DEBUG_INFO_REDUCED. Please do not add actual code. However,
* adding appropriate #includes is fine.
*/
-#include <stdarg.h>
-
#include <linux/cred.h>
#include <linux/crypto.h>
#include <linux/dcache.h>
@@ -22,6 +20,7 @@
#include <linux/net.h>
#include <linux/sched.h>
#include <linux/slab.h>
+#include <linux/stdarg.h>
#include <linux/types.h>
#include <net/addrconf.h>
#include <net/sock.h>
diff --git a/lib/kasprintf.c b/lib/kasprintf.c
index bacf7b83ccf0..cd2f5974ed98 100644
--- a/lib/kasprintf.c
+++ b/lib/kasprintf.c
@@ -5,7 +5,7 @@
* Copyright (C) 1991, 1992 Linus Torvalds
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/export.h>
#include <linux/slab.h>
#include <linux/types.h>
diff --git a/lib/kunit/string-stream.h b/lib/kunit/string-stream.h
index 5e94b623454f..43f9508a55b4 100644
--- a/lib/kunit/string-stream.h
+++ b/lib/kunit/string-stream.h
@@ -11,7 +11,7 @@
#include <linux/spinlock.h>
#include <linux/types.h>
-#include <stdarg.h>
+#include <linux/stdarg.h>
struct string_stream_fragment {
struct kunit *test;
diff --git a/lib/vsprintf.c b/lib/vsprintf.c
index 26c83943748a..3bcb7be03f93 100644
--- a/lib/vsprintf.c
+++ b/lib/vsprintf.c
@@ -17,7 +17,7 @@
* - scnprintf and vscnprintf
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/build_bug.h>
#include <linux/clk.h>
#include <linux/clk-provider.h>
diff --git a/mm/kfence/report.c b/mm/kfence/report.c
index 2a319c21c939..4b891dd75650 100644
--- a/mm/kfence/report.c
+++ b/mm/kfence/report.c
@@ -5,7 +5,7 @@
* Copyright (C) 2020, Google LLC.
*/
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include <linux/kernel.h>
#include <linux/lockdep.h>
diff --git a/net/batman-adv/log.c b/net/batman-adv/log.c
index f0e5d1429662..7a93a1e94c40 100644
--- a/net/batman-adv/log.c
+++ b/net/batman-adv/log.c
@@ -7,7 +7,7 @@
#include "log.h"
#include "main.h"
-#include <stdarg.h>
+#include <linux/stdarg.h>
#include "trace.h"
diff --git a/sound/aoa/codecs/onyx.h b/sound/aoa/codecs/onyx.h
index 8a32c3c3d716..6c31b7373b78 100644
--- a/sound/aoa/codecs/onyx.h
+++ b/sound/aoa/codecs/onyx.h
@@ -6,7 +6,6 @@
*/
#ifndef __SND_AOA_CODEC_ONYX_H
#define __SND_AOA_CODEC_ONYX_H
-#include <stddef.h>
#include <linux/i2c.h>
#include <asm/pmac_low_i2c.h>
#include <asm/prom.h>
diff --git a/sound/aoa/codecs/tas.c b/sound/aoa/codecs/tas.c
index ac246dd3ab49..ab19a37e2a68 100644
--- a/sound/aoa/codecs/tas.c
+++ b/sound/aoa/codecs/tas.c
@@ -58,7 +58,6 @@
* and up to the hardware designer to not wire
* them up in some weird unusable way.
*/
-#include <stddef.h>
#include <linux/i2c.h>
#include <asm/pmac_low_i2c.h>
#include <asm/prom.h>
diff --git a/sound/core/info.c b/sound/core/info.c
index 9fec3070f8ba..a451b24199c3 100644
--- a/sound/core/info.c
+++ b/sound/core/info.c
@@ -16,7 +16,6 @@
#include <linux/utsname.h>
#include <linux/proc_fs.h>
#include <linux/mutex.h>
-#include <stdarg.h>
int snd_info_check_reserved_words(const char *str)
{
</cut>
4 years, 1 month
- 1
- 0
[CI-NOTIFY]: TCWG Bisect tcwg_bmk_tx1/llvm-release-aarch64-spec2k6-O3 - Build # 5 - Successful!
by ci_notify＠linaro.org
Successfully identified regression in *llvm* in CI configuration tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3. So far, this commit has regressed CI configurations:
- tcwg_bmk_llvm_tx1/llvm-release-aarch64-spec2k6-O3
Culprit:
<cut>
commit 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Mon Oct 12 22:19:17 2020 +0300
Reland "[SCEV] Model ptrtoint(SCEVUnknown) cast not as unknown, but as zext/trunc/self of SCEVUnknown"
This relands commit 1c021c64caef83cccb719c9bf0a2554faa6563af which was
reverted in commit 17cec6a11a12f815052d56a17ef738cf246a2d9a because
an assertion was being triggered, since `BuildConstantFromSCEV()`
wasn't updated to handle the case where the constant we want to truncate
is actually a pointer. I was unsuccessful in coming up with a test case
where we'd end there with constant zext/sext of a pointer,
so i didn't handle those cases there until there is a test case.
Original commit message:
While we indeed can't treat them as no-ops, i believe we can/should
do better than just modelling them as `unknown`. `inttoptr` story
is complicated, but for `ptrtoint`, it seems straight-forward
to model it just as a zext-or-trunc of unknown.
This may be important now that we track towards
making inttoptr/ptrtoint casts not no-op,
and towards preventing folding them into loads/etc
(see D88979/D88789/D88788)
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D88806
</cut>
Results regressed to (for first_bad == 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3 -- artifacts/build-1fb610429308a7c29c5065f5cc35dcc3fd69c8b1/results_id:
1
# 400.perlbench,perlbench_base.default regressed by 104
from (for last_good == 73818f450e3a90fc89eca143ee30777ed7e660e9)
# reset_artifacts:
-10
# build_abe binutils:
-9
# build_abe stage1 -- --set gcc_override_configure=--disable-libsanitizer:
-8
# build_abe linux:
-7
# build_abe glibc:
-6
# build_abe stage2 -- --set gcc_override_configure=--disable-libsanitizer:
-5
# build_llvm true:
-3
# true:
0
# benchmark -O3 -- artifacts/build-73818f450e3a90fc89eca143ee30777ed7e660e9/results_id:
1
Artifacts of last_good build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of last_good: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3/1768
Artifacts of first_bad build: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Results ID of first_bad: tx1_64/tcwg_bmk_llvm_tx1/bisect-llvm-release-aarch64-spec2k6-O3/1778
Build top page/logs: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Configuration details:
Reproduce builds:
<cut>
mkdir investigate-llvm-1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
cd investigate-llvm-1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
git clone https://git.linaro.org/toolchain/jenkins-scripts
mkdir -p artifacts/manifests
curl -o artifacts/manifests/build-baseline.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/manifests/build-parameters.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
curl -o artifacts/test.sh https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release… --fail
chmod +x artifacts/test.sh
# Reproduce the baseline build (build all pre-requisites)
./jenkins-scripts/tcwg_bmk-build.sh @@ artifacts/manifests/build-baseline.sh
# Save baseline build state (which is then restored in artifacts/test.sh)
rsync -a --del --delete-excluded --exclude bisect/ --exclude artifacts/ --exclude llvm/ ./ ./bisect/baseline/
cd llvm
# Reproduce first_bad build
git checkout --detach 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
../artifacts/test.sh
# Reproduce last_good build
git checkout --detach 73818f450e3a90fc89eca143ee30777ed7e660e9
../artifacts/test.sh
cd ..
</cut>
History of pending regressions and results: https://git.linaro.org/toolchain/ci/base-artifacts.git/log/?h=linaro-local/…
Artifacts: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Build log: https://ci.linaro.org/job/tcwg_bmk_ci_llvm-bisect-tcwg_bmk_tx1-llvm-release…
Full commit (up to 1000 lines):
<cut>
commit 1fb610429308a7c29c5065f5cc35dcc3fd69c8b1
Author: Roman Lebedev <lebedev.ri(a)gmail.com>
Date: Mon Oct 12 22:19:17 2020 +0300
Reland "[SCEV] Model ptrtoint(SCEVUnknown) cast not as unknown, but as zext/trunc/self of SCEVUnknown"
This relands commit 1c021c64caef83cccb719c9bf0a2554faa6563af which was
reverted in commit 17cec6a11a12f815052d56a17ef738cf246a2d9a because
an assertion was being triggered, since `BuildConstantFromSCEV()`
wasn't updated to handle the case where the constant we want to truncate
is actually a pointer. I was unsuccessful in coming up with a test case
where we'd end there with constant zext/sext of a pointer,
so i didn't handle those cases there until there is a test case.
Original commit message:
While we indeed can't treat them as no-ops, i believe we can/should
do better than just modelling them as `unknown`. `inttoptr` story
is complicated, but for `ptrtoint`, it seems straight-forward
to model it just as a zext-or-trunc of unknown.
This may be important now that we track towards
making inttoptr/ptrtoint casts not no-op,
and towards preventing folding them into loads/etc
(see D88979/D88789/D88788)
Reviewed By: mkazantsev
Differential Revision: https://reviews.llvm.org/D88806
---
llvm/lib/Analysis/ScalarEvolution.cpp | 50 ++++++--
llvm/lib/Transforms/Utils/SimplifyIndVar.cpp | 2 +-
.../add-expr-pointer-operand-sorting.ll | 4 +-
.../Analysis/ScalarEvolution/no-wrap-add-exprs.ll | 4 +-
.../ScalarEvolution/ptrtoint-constantexpr-loop.ll | 130 ++++++++-------------
llvm/test/Analysis/ScalarEvolution/ptrtoint.ll | 60 +++++-----
llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll | 4 +-
llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll | 4 +-
.../IndVarSimplify/2011-11-01-lftrptr.ll | 16 +--
.../Isl/CodeGen/scev_looking_through_bitcasts.ll | 3 +-
10 files changed, 140 insertions(+), 137 deletions(-)
diff --git a/llvm/lib/Analysis/ScalarEvolution.cpp b/llvm/lib/Analysis/ScalarEvolution.cpp
index 1d3e26b93cb6..74bffc0facdb 100644
--- a/llvm/lib/Analysis/ScalarEvolution.cpp
+++ b/llvm/lib/Analysis/ScalarEvolution.cpp
@@ -3505,15 +3505,15 @@ const SCEV *ScalarEvolution::getUMinExpr(SmallVectorImpl<const SCEV *> &Ops) {
}
const SCEV *ScalarEvolution::getSizeOfExpr(Type *IntTy, Type *AllocTy) {
- // We can bypass creating a target-independent
- // constant expression and then folding it back into a ConstantInt.
- // This is just a compile-time optimization.
if (isa<ScalableVectorType>(AllocTy)) {
Constant *NullPtr = Constant::getNullValue(AllocTy->getPointerTo());
Constant *One = ConstantInt::get(IntTy, 1);
Constant *GEP = ConstantExpr::getGetElementPtr(AllocTy, NullPtr, One);
- return getSCEV(ConstantExpr::getPtrToInt(GEP, IntTy));
+ return getUnknown(ConstantExpr::getPtrToInt(GEP, IntTy));
}
+ // We can bypass creating a target-independent
+ // constant expression and then folding it back into a ConstantInt.
+ // This is just a compile-time optimization.
return getConstant(IntTy, getDataLayout().getTypeAllocSize(AllocTy));
}
@@ -6301,6 +6301,36 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
return getSCEV(U->getOperand(0));
break;
+ case Instruction::PtrToInt: {
+ // It's tempting to handle inttoptr and ptrtoint as no-ops,
+ // however this can lead to pointer expressions which cannot safely be
+ // expanded to GEPs because ScalarEvolution doesn't respect
+ // the GEP aliasing rules when simplifying integer expressions.
+ //
+ // However, given
+ // %x = ???
+ // %y = ptrtoint %x
+ // %z = ptrtoint %x
+ // it is safe to say that %y and %z are the same thing.
+ //
+ // So instead of modelling the cast itself as unknown,
+ // since the casts are transparent within SCEV,
+ // we can at least model the casts original value as unknow instead.
+
+ // BUT, there's caveat. If we simply model %x as unknown, unrelated uses
+ // of %x will also see it as unknown, which is obviously bad.
+ // So we can only do this iff %x would be modelled as unknown anyways.
+ auto *OpSCEV = getSCEV(U->getOperand(0));
+ if (isa<SCEVUnknown>(OpSCEV))
+ return getTruncateOrZeroExtend(OpSCEV, U->getType());
+ // If we can model the operand, however, we must fallback to modelling
+ // the whole cast as unknown instead.
+ LLVM_FALLTHROUGH;
+ }
+ case Instruction::IntToPtr:
+ // We can't do this for inttoptr at all, however.
+ return getUnknown(V);
+
case Instruction::SDiv:
// If both operands are non-negative, this is just an udiv.
if (isKnownNonNegative(getSCEV(U->getOperand(0))) &&
@@ -6315,11 +6345,6 @@ const SCEV *ScalarEvolution::createSCEV(Value *V) {
return getURemExpr(getSCEV(U->getOperand(0)), getSCEV(U->getOperand(1)));
break;
- // It's tempting to handle inttoptr and ptrtoint as no-ops, however this can
- // lead to pointer expressions which cannot safely be expanded to GEPs,
- // because ScalarEvolution doesn't respect the GEP aliasing rules when
- // simplifying integer expressions.
-
case Instruction::GetElementPtr:
return createNodeForGEP(cast<GEPOperator>(U));
@@ -7974,8 +7999,11 @@ static Constant *BuildConstantFromSCEV(const SCEV *V) {
}
case scTruncate: {
const SCEVTruncateExpr *ST = cast<SCEVTruncateExpr>(V);
- if (Constant *CastOp = BuildConstantFromSCEV(ST->getOperand()))
- return ConstantExpr::getTrunc(CastOp, ST->getType());
+ if (Constant *CastOp = BuildConstantFromSCEV(ST->getOperand())) {
+ if (!CastOp->getType()->isPointerTy())
+ return ConstantExpr::getTrunc(CastOp, ST->getType());
+ return ConstantExpr::getPtrToInt(CastOp, ST->getType());
+ }
break;
}
case scAddExpr: {
diff --git a/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp b/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp
index 2d71b0fff889..3e280a66175c 100644
--- a/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp
+++ b/llvm/lib/Transforms/Utils/SimplifyIndVar.cpp
@@ -427,7 +427,7 @@ static bool willNotOverflow(ScalarEvolution *SE, Instruction::BinaryOps BinOp,
: &ScalarEvolution::getZeroExtendExpr;
// Check ext(LHS op RHS) == ext(LHS) op ext(RHS)
- auto *NarrowTy = cast<IntegerType>(LHS->getType());
+ auto *NarrowTy = cast<IntegerType>(SE->getEffectiveSCEVType(LHS->getType()));
auto *WideTy =
IntegerType::get(NarrowTy->getContext(), NarrowTy->getBitWidth() * 2);
diff --git a/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll b/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll
index 93a3bf4d4c37..e798e2715ba1 100644
--- a/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll
+++ b/llvm/test/Analysis/ScalarEvolution/add-expr-pointer-operand-sorting.ll
@@ -33,9 +33,9 @@ define i32 @d(i32 %base) {
; CHECK-NEXT: %1 = load i32*, i32** @c, align 8
; CHECK-NEXT: --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %sub.ptr.lhs.cast = ptrtoint i32* %1 to i64
-; CHECK-NEXT: --> %sub.ptr.lhs.cast U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT: --> %1 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %sub.ptr.sub = sub i64 %sub.ptr.lhs.cast, ptrtoint ([1 x i32]* @b to i64)
-; CHECK-NEXT: --> ((-1 * ptrtoint ([1 x i32]* @b to i64)) + %sub.ptr.lhs.cast) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
+; CHECK-NEXT: --> ((-1 * @b) + %1) U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %sub.ptr.div = sdiv exact i64 %sub.ptr.sub, 4
; CHECK-NEXT: --> %sub.ptr.div U: full-set S: [-2305843009213693952,2305843009213693952) Exits: <<Unknown>> LoopDispositions: { %for.cond: Variant }
; CHECK-NEXT: %arrayidx1 = getelementptr inbounds [1 x i8], [1 x i8]* %arrayidx, i64 0, i64 %sub.ptr.div
diff --git a/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll b/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll
index 5a7bb3c9e5cd..eb669cab0c79 100644
--- a/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll
+++ b/llvm/test/Analysis/ScalarEvolution/no-wrap-add-exprs.ll
@@ -170,14 +170,14 @@ define void @f3(i8* %x_addr, i8* %y_addr, i32* %tmp_addr) {
%int5 = add i32 %int0, 5
%int.zext = zext i32 %int5 to i64
; CHECK: %int.zext = zext i32 %int5 to i64
-; CHECK-NEXT: --> (1 + (zext i32 (4 + %int0) to i64))<nuw><nsw> U: [1,4294967294) S: [1,4294967297)
+; CHECK-NEXT: --> (1 + (zext i32 (4 + (trunc [16 x i8]* @z_addr to i32)) to i64))<nuw><nsw> U: [1,4294967294) S: [1,4294967297)
%ptr_noalign = bitcast [16 x i8]* @z_addr_noalign to i8*
%int0_na = ptrtoint i8* %ptr_noalign to i32
%int5_na = add i32 %int0_na, 5
%int.zext_na = zext i32 %int5_na to i64
; CHECK: %int.zext_na = zext i32 %int5_na to i64
-; CHECK-NEXT: --> (zext i32 (5 + %int0_na) to i64) U: [0,4294967296) S: [0,4294967296)
+; CHECK-NEXT: --> (zext i32 (5 + (trunc [16 x i8]* @z_addr_noalign to i32)) to i64) U: [0,4294967296) S: [0,4294967296)
%tmp = load i32, i32* %tmp_addr
%mul = and i32 %tmp, -4
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll
index 8cfa041e7552..d0ead6028071 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint-constantexpr-loop.ll
@@ -11,48 +11,31 @@
@global = external hidden global [0 x i8]
define hidden i32* @i64(i8* %arg, i32* %arg10) {
-; PTR64_IDX64-LABEL: 'i64'
-; PTR64_IDX64-NEXT: Classifying expressions for: @i64
-; PTR64_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR64_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: Determining loop execution counts for: @i64
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
-;
-; PTR64_IDX32-LABEL: 'i64'
-; PTR64_IDX32-NEXT: Classifying expressions for: @i64
-; PTR64_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR64_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX32-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: Determining loop execution counts for: @i64
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
+; X64-LABEL: 'i64'
+; X64-NEXT: Classifying expressions for: @i64
+; X64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
+; X64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
+; X64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
+; X64-NEXT: %tmp18 = add i32 %tmp, 2
+; X64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: Determining loop execution counts for: @i64
+; X64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
;
; PTR32_IDX32-LABEL: 'i64'
; PTR32_IDX32-NEXT: Classifying expressions for: @i64
; PTR32_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR32_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX32-NEXT: --> ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i64 ptrtoint ([0 x i8]* @global to i64) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -67,9 +50,9 @@ define hidden i32* @i64(i8* %arg, i32* %arg10) {
; PTR32_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i64 ptrtoint ([0 x i8]* @global to i64)
-; PTR32_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: [0,8589934591) S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX64-NEXT: --> (ptrtoint ([0 x i8]* @global to i64) + %arg) U: [0,8589934591) S: full-set Exits: (ptrtoint ([0 x i8]* @global to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
@@ -103,9 +86,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR64_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR64_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR64_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR64_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: full-set S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR64_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR64_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
@@ -120,9 +103,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR64_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR64_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR64_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR64_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR64_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR64_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR64_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR64_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -137,9 +120,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR32_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR32_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX32-NEXT: --> (ptrtoint ([0 x i8]* @global to i32) + %arg) U: full-set S: full-set Exits: (ptrtoint ([0 x i8]* @global to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -154,9 +137,9 @@ define hidden i32* @i64_to_i32(i8* %arg, i32* %arg10) {
; PTR32_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i32 ptrtoint ([0 x i8]* @global to i32)
-; PTR32_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX64-NEXT: --> ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 ptrtoint ([0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) U: [-2147483648,6442450943) S: full-set Exits: ((sext i32 (trunc [0 x i8]* @global to i32) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
@@ -185,48 +168,31 @@ bb17: ; preds = %bb11
br label %bb11
}
define hidden i32* @i64_to_i128(i8* %arg, i32* %arg10) {
-; PTR64_IDX64-LABEL: 'i64_to_i128'
-; PTR64_IDX64-NEXT: Classifying expressions for: @i64_to_i128
-; PTR64_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR64_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX64-NEXT: Determining loop execution counts for: @i64_to_i128
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
-;
-; PTR64_IDX32-LABEL: 'i64_to_i128'
-; PTR64_IDX32-NEXT: Classifying expressions for: @i64_to_i128
-; PTR64_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
-; PTR64_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR64_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR64_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
-; PTR64_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
-; PTR64_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
-; PTR64_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
-; PTR64_IDX32-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
-; PTR64_IDX32-NEXT: Determining loop execution counts for: @i64_to_i128
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
-; PTR64_IDX32-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
+; X64-LABEL: 'i64_to_i128'
+; X64-NEXT: Classifying expressions for: @i64_to_i128
+; X64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
+; X64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
+; X64-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
+; X64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
+; X64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
+; X64-NEXT: %tmp18 = add i32 %tmp, 2
+; X64-NEXT: --> {2,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
+; X64-NEXT: Determining loop execution counts for: @i64_to_i128
+; X64-NEXT: Loop %bb11: Unpredictable backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable max backedge-taken count.
+; X64-NEXT: Loop %bb11: Unpredictable predicated backedge-taken count.
;
; PTR32_IDX32-LABEL: 'i64_to_i128'
; PTR32_IDX32-NEXT: Classifying expressions for: @i64_to_i128
; PTR32_IDX32-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX32-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX32-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR32_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX32-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) U: full-set S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i32) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX32-NEXT: --> (@global + %arg) U: full-set S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX32-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX32-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX32-NEXT: %tmp18 = add i32 %tmp, 2
@@ -241,9 +207,9 @@ define hidden i32* @i64_to_i128(i8* %arg, i32* %arg10) {
; PTR32_IDX64-NEXT: %tmp = phi i32 [ 0, %bb ], [ %tmp18, %bb17 ]
; PTR32_IDX64-NEXT: --> {0,+,2}<%bb11> U: [0,-1) S: [-2147483648,2147483647) Exits: <<Unknown>> LoopDispositions: { %bb11: Computable }
; PTR32_IDX64-NEXT: %tmp12 = getelementptr i8, i8* %arg, i128 ptrtoint ([0 x i8]* @global to i128)
-; PTR32_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: [0,8589934591) S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp13 = bitcast i8* %tmp12 to i32*
-; PTR32_IDX64-NEXT: --> ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) U: [0,8589934591) S: full-set Exits: ((trunc i128 ptrtoint ([0 x i8]* @global to i128) to i64) + %arg) LoopDispositions: { %bb11: Invariant }
+; PTR32_IDX64-NEXT: --> (@global + %arg) U: [0,8589934591) S: full-set Exits: (@global + %arg) LoopDispositions: { %bb11: Invariant }
; PTR32_IDX64-NEXT: %tmp14 = load i32, i32* %tmp13, align 4
; PTR32_IDX64-NEXT: --> %tmp14 U: full-set S: full-set Exits: <<Unknown>> LoopDispositions: { %bb11: Variant }
; PTR32_IDX64-NEXT: %tmp18 = add i32 %tmp, 2
diff --git a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
index e3e9330e241f..ac08fb24775e 100644
--- a/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
+++ b/llvm/test/Analysis/ScalarEvolution/ptrtoint.ll
@@ -16,25 +16,25 @@ define void @ptrtoint(i8* %in, i64* %out0, i32* %out1, i16* %out2, i128* %out3)
; X64-LABEL: 'ptrtoint'
; X64-NEXT: Classifying expressions for: @ptrtoint
; X64-NEXT: %p0 = ptrtoint i8* %in to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: %p1 = ptrtoint i8* %in to i32
-; X64-NEXT: --> %p1 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8* %in to i32) U: full-set S: full-set
; X64-NEXT: %p2 = ptrtoint i8* %in to i16
-; X64-NEXT: --> %p2 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8* %in to i16) U: full-set S: full-set
; X64-NEXT: %p3 = ptrtoint i8* %in to i128
-; X64-NEXT: --> %p3 U: [0,18446744073709551616) S: [-18446744073709551616,18446744073709551616)
+; X64-NEXT: --> (zext i8* %in to i128) U: [0,18446744073709551616) S: [0,18446744073709551616)
; X64-NEXT: Determining loop execution counts for: @ptrtoint
;
; X32-LABEL: 'ptrtoint'
; X32-NEXT: Classifying expressions for: @ptrtoint
; X32-NEXT: %p0 = ptrtoint i8* %in to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: %p1 = ptrtoint i8* %in to i32
-; X32-NEXT: --> %p1 U: full-set S: full-set
+; X32-NEXT: --> %in U: full-set S: full-set
; X32-NEXT: %p2 = ptrtoint i8* %in to i16
-; X32-NEXT: --> %p2 U: full-set S: full-set
+; X32-NEXT: --> (trunc i8* %in to i16) U: full-set S: full-set
; X32-NEXT: %p3 = ptrtoint i8* %in to i128
-; X32-NEXT: --> %p3 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in to i128) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint
;
%p0 = ptrtoint i8* %in to i64
@@ -53,25 +53,25 @@ define void @ptrtoint_as1(i8 addrspace(1)* %in, i64* %out0, i32* %out1, i16* %ou
; X64-LABEL: 'ptrtoint_as1'
; X64-NEXT: Classifying expressions for: @ptrtoint_as1
; X64-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: %p1 = ptrtoint i8 addrspace(1)* %in to i32
-; X64-NEXT: --> %p1 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8 addrspace(1)* %in to i32) U: full-set S: full-set
; X64-NEXT: %p2 = ptrtoint i8 addrspace(1)* %in to i16
-; X64-NEXT: --> %p2 U: full-set S: full-set
+; X64-NEXT: --> (trunc i8 addrspace(1)* %in to i16) U: full-set S: full-set
; X64-NEXT: %p3 = ptrtoint i8 addrspace(1)* %in to i128
-; X64-NEXT: --> %p3 U: [0,18446744073709551616) S: [-18446744073709551616,18446744073709551616)
+; X64-NEXT: --> (zext i8 addrspace(1)* %in to i128) U: [0,18446744073709551616) S: [0,18446744073709551616)
; X64-NEXT: Determining loop execution counts for: @ptrtoint_as1
;
; X32-LABEL: 'ptrtoint_as1'
; X32-NEXT: Classifying expressions for: @ptrtoint_as1
; X32-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8 addrspace(1)* %in to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: %p1 = ptrtoint i8 addrspace(1)* %in to i32
-; X32-NEXT: --> %p1 U: full-set S: full-set
+; X32-NEXT: --> %in U: full-set S: full-set
; X32-NEXT: %p2 = ptrtoint i8 addrspace(1)* %in to i16
-; X32-NEXT: --> %p2 U: full-set S: full-set
+; X32-NEXT: --> (trunc i8 addrspace(1)* %in to i16) U: full-set S: full-set
; X32-NEXT: %p3 = ptrtoint i8 addrspace(1)* %in to i128
-; X32-NEXT: --> %p3 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8 addrspace(1)* %in to i128) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_as1
;
%p0 = ptrtoint i8 addrspace(1)* %in to i64
@@ -92,7 +92,7 @@ define void @ptrtoint_of_bitcast(i8* %in, i64* %out0) {
; X64-NEXT: %in_casted = bitcast i8* %in to float*
; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: %p0 = ptrtoint float* %in_casted to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in U: full-set S: full-set
; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_bitcast
;
; X32-LABEL: 'ptrtoint_of_bitcast'
@@ -100,7 +100,7 @@ define void @ptrtoint_of_bitcast(i8* %in, i64* %out0) {
; X32-NEXT: %in_casted = bitcast i8* %in to float*
; X32-NEXT: --> %in U: full-set S: full-set
; X32-NEXT: %p0 = ptrtoint float* %in_casted to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_bitcast
;
%in_casted = bitcast i8* %in to float*
@@ -116,7 +116,7 @@ define void @ptrtoint_of_addrspacecast(i8* %in, i64* %out0) {
; X64-NEXT: %in_casted = addrspacecast i8* %in to i8 addrspace(1)*
; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in_casted to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_addrspacecast
;
; X32-LABEL: 'ptrtoint_of_addrspacecast'
@@ -124,7 +124,7 @@ define void @ptrtoint_of_addrspacecast(i8* %in, i64* %out0) {
; X32-NEXT: %in_casted = addrspacecast i8* %in to i8 addrspace(1)*
; X32-NEXT: --> %in_casted U: full-set S: full-set
; X32-NEXT: %p0 = ptrtoint i8 addrspace(1)* %in_casted to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8 addrspace(1)* %in_casted to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_addrspacecast
;
%in_casted = addrspacecast i8* %in to i8 addrspace(1)*
@@ -140,7 +140,7 @@ define void @ptrtoint_of_inttoptr(i64 %in, i64* %out0) {
; X64-NEXT: %in_casted = inttoptr i64 %in to i8*
; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: %p0 = ptrtoint i8* %in_casted to i64
-; X64-NEXT: --> %p0 U: full-set S: full-set
+; X64-NEXT: --> %in_casted U: full-set S: full-set
; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_inttoptr
;
; X32-LABEL: 'ptrtoint_of_inttoptr'
@@ -148,7 +148,7 @@ define void @ptrtoint_of_inttoptr(i64 %in, i64* %out0) {
; X32-NEXT: %in_casted = inttoptr i64 %in to i8*
; X32-NEXT: --> %in_casted U: full-set S: full-set
; X32-NEXT: %p0 = ptrtoint i8* %in_casted to i64
-; X32-NEXT: --> %p0 U: [0,4294967296) S: [-4294967296,4294967296)
+; X32-NEXT: --> (zext i8* %in_casted to i64) U: [0,4294967296) S: [0,4294967296)
; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_inttoptr
;
%in_casted = inttoptr i64 %in to i8*
@@ -197,11 +197,17 @@ define void @ptrtoint_of_nullptr(i64* %out0) {
; A constant inttoptr argument of an ptrtoint is still bad.
define void @ptrtoint_of_constantexpr_inttoptr(i64* %out0) {
-; ALL-LABEL: 'ptrtoint_of_constantexpr_inttoptr'
-; ALL-NEXT: Classifying expressions for: @ptrtoint_of_constantexpr_inttoptr
-; ALL-NEXT: %p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
-; ALL-NEXT: --> %p0 U: [42,43) S: [-64,64)
-; ALL-NEXT: Determining loop execution counts for: @ptrtoint_of_constantexpr_inttoptr
+; X64-LABEL: 'ptrtoint_of_constantexpr_inttoptr'
+; X64-NEXT: Classifying expressions for: @ptrtoint_of_constantexpr_inttoptr
+; X64-NEXT: %p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
+; X64-NEXT: --> inttoptr (i64 42 to i8*) U: [42,43) S: [-64,64)
+; X64-NEXT: Determining loop execution counts for: @ptrtoint_of_constantexpr_inttoptr
+;
+; X32-LABEL: 'ptrtoint_of_constantexpr_inttoptr'
+; X32-NEXT: Classifying expressions for: @ptrtoint_of_constantexpr_inttoptr
+; X32-NEXT: %p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
+; X32-NEXT: --> (zext i8* inttoptr (i64 42 to i8*) to i64) U: [42,43) S: [0,4294967296)
+; X32-NEXT: Determining loop execution counts for: @ptrtoint_of_constantexpr_inttoptr
;
%p0 = ptrtoint i8* inttoptr (i64 42 to i8*) to i64
store i64 %p0, i64* %out0
diff --git a/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll b/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll
index 564328d99998..e73397214475 100644
--- a/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll
+++ b/llvm/test/CodeGen/ARM/lsr-undef-in-binop.ll
@@ -186,7 +186,9 @@ define linkonce_odr i32 @vector_insert(%"class.std::__1::vector.182"*, [1 x i32]
br i1 %114, label %124, label %115
; CHECK-LABEL: .preheader:
-; CHECK-NEXT: sub i32 [[OLD_CAST]], [[NEW_CAST]]
+; CHECK-NEXT: [[NEG_NEW:%[0-9]+]] = sub i32 0, [[NEW_CAST]]
+; CHECK-NEXT: getelementptr i8, i8* %97, i32 [[NEG_NEW]]
+
; <label>:115: ; preds = %111, %115
%116 = phi i8* [ %118, %115 ], [ %97, %111 ]
%117 = phi i8* [ %119, %115 ], [ %11, %111 ]
diff --git a/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll b/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
index 670477c4c285..d4dd7352aa52 100644
--- a/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
+++ b/llvm/test/CodeGen/X86/ragreedy-hoist-spill.ll
@@ -268,9 +268,9 @@ define i8* @SyFgets(i8* %line, i64 %length, i64 %fid) {
; CHECK-NEXT: LBB0_48: ## %if.then1477
; CHECK-NEXT: movl $1, %edx
; CHECK-NEXT: callq _write
-; CHECK-NEXT: subq %rbx, %r14
; CHECK-NEXT: movq _syHistory(a){{.*}}(%rip), %rax
-; CHECK-NEXT: leaq 8189(%r14,%rax), %rax
+; CHECK-NEXT: subq %rbx, %rax
+; CHECK-NEXT: leaq 8189(%rax,%r14), %rax
; CHECK-NEXT: .p2align 4, 0x90
; CHECK-NEXT: LBB0_49: ## %for.body1723
; CHECK-NEXT: ## =>This Inner Loop Header: Depth=1
diff --git a/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll b/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll
index e1ef6bd6635d..bc756c666bde 100644
--- a/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll
+++ b/llvm/test/Transforms/IndVarSimplify/2011-11-01-lftrptr.ll
@@ -166,21 +166,23 @@ define i8 @testnullptrint(i8* %buf, i8* %end) nounwind {
; PTR64-NEXT: ret i8 [[RET]]
;
; PTR32-LABEL: @testnullptrint(
+; PTR32-NEXT: [[BUF1:%.*]] = ptrtoint i8* [[BUF:%.*]] to i32
; PTR32-NEXT: br label [[LOOPGUARD:%.*]]
; PTR32: loopguard:
-; PTR32-NEXT: [[BI:%.*]] = ptrtoint i8* [[BUF:%.*]] to i32
+; PTR32-NEXT: [[BI:%.*]] = ptrtoint i8* [[BUF]] to i32
; PTR32-NEXT: [[EI:%.*]] = ptrtoint i8* [[END:%.*]] to i32
; PTR32-NEXT: [[CNT:%.*]] = sub i32 [[EI]], [[BI]]
-; PTR32-NEXT: [[CNT1:%.*]] = inttoptr i32 [[CNT]] to i8*
; PTR32-NEXT: [[GUARD:%.*]] = icmp ult i32 0, [[CNT]]
; PTR32-NEXT: br i1 [[GUARD]], label [[PREHEADER:%.*]], label [[EXIT:%.*]]
; PTR32: preheader:
+; PTR32-NEXT: [[TMP1:%.*]] = sub i32 0, [[BUF1]]
+; PTR32-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[END]], i32 [[TMP1]]
; PTR32-NEXT: br label [[LOOP:%.*]]
; PTR32: loop:
; PTR32-NEXT: [[P_01_US_US:%.*]] = phi i8* [ null, [[PREHEADER]] ], [ [[GEP:%.*]], [[LOOP]] ]
; PTR32-NEXT: [[GEP]] = getelementptr inbounds i8, i8* [[P_01_US_US]], i64 1
-; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]]
-; PTR32-NEXT: [[EXITCOND:%.*]] = icmp ne i8* [[GEP]], [[CNT1]]
+; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]], align 1
+; PTR32-NEXT: [[EXITCOND:%.*]] = icmp ne i8* [[GEP]], [[SCEVGEP]]
; PTR32-NEXT: br i1 [[EXITCOND]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]]
; PTR32: exit.loopexit:
; PTR32-NEXT: [[SNEXT_LCSSA:%.*]] = phi i8 [ [[SNEXT]], [[LOOP]] ]
@@ -256,10 +258,10 @@ define i8 @testptrint(i8* %buf, i8* %end) nounwind {
; PTR32-NEXT: [[P_01_US_US:%.*]] = phi i8* [ [[BUF]], [[PREHEADER]] ], [ [[GEP:%.*]], [[LOOP]] ]
; PTR32-NEXT: [[IV:%.*]] = phi i32 [ [[BI]], [[PREHEADER]] ], [ [[IVNEXT:%.*]], [[LOOP]] ]
; PTR32-NEXT: [[GEP]] = getelementptr inbounds i8, i8* [[P_01_US_US]], i64 1
-; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]]
+; PTR32-NEXT: [[SNEXT:%.*]] = load i8, i8* [[GEP]], align 1
; PTR32-NEXT: [[IVNEXT]] = add nuw i32 [[IV]], 1
-; PTR32-NEXT: [[EXITCOND:%.*]] = icmp ne i32 [[IVNEXT]], [[CNT]]
-; PTR32-NEXT: br i1 [[EXITCOND]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]]
+; PTR32-NEXT: [[CMP:%.*]] = icmp ult i32 [[IVNEXT]], [[CNT]]
+; PTR32-NEXT: br i1 [[CMP]], label [[LOOP]], label [[EXIT_LOOPEXIT:%.*]]
; PTR32: exit.loopexit:
; PTR32-NEXT: [[SNEXT_LCSSA:%.*]] = phi i8 [ [[SNEXT]], [[LOOP]] ]
; PTR32-NEXT: br label [[EXIT]]
diff --git a/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll b/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll
index 1012e23cd3a2..321e98ab6772 100644
--- a/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll
+++ b/polly/test/Isl/CodeGen/scev_looking_through_bitcasts.ll
@@ -32,6 +32,5 @@ bitmap_element_allocate.exit:
; CHECK: polly.stmt.cond.end73.i:
-; CHECK-NEXT: %0 = bitcast %structty** %b.s2a to i8**
-; CHECK-NEXT: store i8* undef, i8** %0
+; CHECK-NEXT: store %structty* undef, %structty** %b.s2a
; CHECK-NEXT: br label %polly.exiting
</cut>
4 years, 1 month
- 1
- 0