This is an automated email from the git hooks/post-receive script.
unknown user pushed a change to branch master in repository llvm.
from 1be8ec9 ScheduleDAGInstrs.cpp: Don't peel the iterator when it points [...] new 10ea516 AMDGPU: llvm.SI.fs.constant is a source of divergence new 8478bd5 AMDGPU/SI: Use the hazard recognizer to break SMEM soft clauses
The 2 revisions listed above as "new" are entirely new to this repository and will be described in separate emails. The revisions listed as "adds" were already present in the repository and have only been added to this reference.
Summary of changes: lib/Target/AMDGPU/AMDGPUTargetTransformInfo.cpp | 1 + lib/Target/AMDGPU/GCNHazardRecognizer.cpp | 72 +++++++++++++++++++++- lib/Target/AMDGPU/GCNHazardRecognizer.h | 1 + lib/Target/AMDGPU/SIInsertWaits.cpp | 3 +- .../DivergenceAnalysis/AMDGPU/interp-intrinsics.ll | 22 +++++++ test/CodeGen/AMDGPU/atomic_cmp_swap_local.ll | 8 +-- test/CodeGen/AMDGPU/fneg-fabs.f64.ll | 59 +++++++++--------- test/CodeGen/AMDGPU/schedule-kernel-arg-loads.ll | 9 +-- 8 files changed, 132 insertions(+), 43 deletions(-) create mode 100644 test/Analysis/DivergenceAnalysis/AMDGPU/interp-intrinsics.ll