Current Milestones:
|| || Planned || Estimate || Actual ||
||cp15-rework || 2012-01-06 || 2012-06-23 || 2012-06-24 ||
||a15-lpae-support || 2012-07-13 || 2012-07-20 || 2012-07-20 ||
||clean-up-kvm-patches || || || ||
||track-kvm-abi-changes || || || ||
||fake-trustzone || || || ||
== clean-up-kvm-patches ==
* started on driving "read/write cp15 regs from kernel" from the existing
QEMU hashtable of cp regs it knows about. First cut seems to work,
but needs more testing and also qemu's ARMCPRegInfo struct needs to
provide raw_read/write methods which bypass access permission and
similar checks.
== other ==
* shepherded various things into upstream QEMU for 1.2 release freeze:
arm-devs patch queue, linux-user patches, some minor stuff
* qemu-linaro 2012.08 released
* travel booked for Connect/ELC-E/KVM Forum; rest is blocked on
the Connect conference hotel discount rate/booking info appearing
KVM blueprint progress tracker:
http://apus.seabright.co.nz/helpers/backlog?group_by=topic&colour_by=state&…
-- PMM
The Linaro Toolchain Working Group is pleased to announce the 2012.08
release of both Linaro GCC 4.7 and Linaro GCC 4.6.
Linaro GCC 4.7 2012.08 is the fifth release in the 4.7 series. Based
off the latest GCC 4.7.1+svn189992 release, it includes many
ARM-focused performance improvements and bug fixes.
Interesting changes include:
* Updates to GCC 4.7.1+svn189992
* An ABI fix for vectors with the wrong layout
* Backports improvements to the NEON vdup instruction with immediates
* Backports a fix to performance regressions in partial redundancy
elimination at high optimisation
* Backports faster 64 bit core register adds with immediates
A bug has been fixed in GCC's implementation of the AAPCS rules for
the layout of vectors that could lead to wrong code being generated.
Vectors larger than 8 bytes in size are now by default aligned to an
8-byte boundary. This is an ABI change: code that makes explicit use
of vector types may be incompatible with binary objects built with
older versions of GCC. Auto-vectorized code is not affected by this
change.
Fixes:
* LP: #1020601 Strange behaviour with __builtin_unreachable()
* PR38785 huge performance regression on EEMBC bitmnp01
* PR53447 missed optimization of 64bit ALU operation with small constant
Linaro GCC 4.6 2012.08 is the eighteenth release in the 4.6 series.
Based off the latest GCC 4.6.3+svn189991 release, this is the fifth
release after entering maintenance.
Interesting changes include:
* Updates to 4.6.3+svn189991
* An ABI fix for vectors with the wrong layout
The source tarballs are available from:
https://launchpad.net/gcc-linaro/+milestone/4.7-2012.08https://launchpad.net/gcc-linaro/+milestone/4.6-2012.08
Downloads are available from the Linaro GCC page on Launchpad:
https://launchpad.net/gcc-linaro
More information on the features and issues are available from the
release page:
https://launchpad.net/gcc-linaro/4.7/4.7-2012.08
Mailing list: http://lists.linaro.org/mailman/listinfo/linaro-toolchain
Bugs: https://bugs.launchpad.net/gcc-linaro/
Questions? https://ask.linaro.org/
Interested in commercial support? Inquire at support(a)linaro.org
-- Michael
== Progress ==
* Out of office Friday 17
* Attended Virtual Connect sessions:
* Vectorization
* PGO/LTO: provided benchmarking results on Webkit computed in ST last
year.
* At last managed to have bzr working
* Prepared a patch for "constant vec permute operation for the vext
instruction" blue-print, based on linaro-gcc/4.7
* Some pending internal work
== Next week ==
* Out of office Monday 20
* Check reviews for my patch to have it accepted.
Hi Matt. I've fleshed out the Etherpad for the PGO and LTO session at:
http://pad.linaro.org/GzRj35tXFt
It's a topic list that needs some specifics. Could you make sure we
have basic answers to any correctness or performance questions?
Ramana, could you add the specifics from the performance call? I
can't seem to find the right meeting in the logs.
-- Michael
== Progress ==
* Out of office Friday 17
* Attended Virtual Connect sessions
* Vectorization
* Ran PGO/LTO session
* Lurked on AArch64/OpenEmbedded and Dalvik Performance sessions
* Did the 2012.08 release of the Toolchain
* Ran into infrastructure problems with armv5 builds
* Most of the build process is now done
* Start working on symbol_ref split benchmarking.
* Struggled to get my jobs to spawn
* Started to backport Ramana's fix to PR54212
* Submitted merge request for 4.7 backport
== Next Week ==
* Ensure 2012.08 release is completed
* Get symbol_ref benchmarking going properly
* Complete backports of PR54212
* Follow up to Virtual Connect Sessions
== Future ==
* Get my name against some blue-prints
* Find a small patch to GCC to use to pipeclean the submission process
--
Matthew Gretton-Dann
Linaro Toolchain Working Group
matthew.gretton-dann(a)linaro.org
The Linaro Toolchain Working Group is pleased to announce the release of
Linaro QEMU 2012.08.
Linaro QEMU 2012.08 is the latest monthly release of qemu-linaro. Based
off upstream (trunk) QEMU, it includes a number of ARM-focused bug fixes
and enhancements.
There are no major changes in this month's release, though
it has been updated to track the latest upstream QEMU changes.
The source tarball is available at:
https://launchpad.net/qemu-linaro/+milestone/2012.08
More information on Linaro QEMU is available at:
https://launchpad.net/qemu-linaro
On 15 August 2012 00:45, Matthew Gretton-Dann
<matthew.gretton-dann(a)linaro.org> wrote:
> So looking at the logs this seems to be a transient data transfer error:
>
> The logs (http://builds.linaro.org/toolchain/gcc-linaro-4.7-2012.08/logs/armv7l-natty…)
> have:
>
> make[4]: Entering directory `/scratch/cbuild/slave/slaves/tcpanda02'
> make -s -f ../../lib/fetch.mk
> gcc-linaro-4.7-2012.08/gcc-linaro-4.7-2012.08.tar-spawn 2>&1 | grep -v
> '^make\['
> Trying http://builds.linaro.org/toolchain/snapshots/gcc-linaro-4.7/gcc-linaro-4.7-…
> Trying http://ex.seabright.co.nz/snapshots/gcc-linaro-4.7/gcc-linaro-4.7-2012.08.t…
> Trying http://builds.linaro.org/toolchain/snapshots/gcc-linaro-4.7-2012.08.tar.xz
> Trying http://ex.seabright.co.nz/snapshots/gcc-linaro-4.7-2012.08.tar.xz
> Trying http://builds.linaro.org/toolchain/snapshots/gcc-linaro-4.7/gcc-linaro-4.7-…
> Trying http://ex.seabright.co.nz/snapshots/gcc-linaro-4.7/gcc-linaro-4.7-2012.08.t…
> Trying http://builds.linaro.org/toolchain/snapshots/gcc-linaro-4.7-2012.08.tar.bz2
> Trying http://ex.seabright.co.nz/snapshots/gcc-linaro-4.7-2012.08.tar.bz2
> bunzip2: gcc-linaro-4.7-2012.08/gcc-linaro-4.7-2012.08.tar.bz2: data
> integrity (CRC) error in data
Not sure here. ex.seabright is the authoritative source. Perhaps
there was a fault with the proxy in the control lab?
The good news is that the test fired and the build failed early. I've
logged LP: #1036867 to see if it happens again.
> The x86_64 build has succeeded OK though, so I (well Ramana really)
> have, eventually, restarted that build. We did encounter some issues
> with restarting the build as follows:
>
> 1) My Launchpad ID doesn't have permissions to spawn jobs through the
> web interface at ex.seabright.co.nz
Fixed.
> 2) So I attempted to spawn the job manually as follows:
>
> $ ssh -p7023 cbuild(a)ex.seabright.co.nz ./cbuild/tools/spawn.sh
> gcc-linaro-4.7-2012.08 armv5-builder
> Spawning gcc-linaro-4.7-2012.08 into the queue benchmarks
> Spawned into a9-builder
>
> This wasn't exactly what I expected. What are the correct runes
> here to get a build?
Spawn picks the closest spawn class based on the filename or, if
supplied, the second argument. Here you supplied 'armv5...' which is
closest to 'benchmarks'.
What you want is to click 'Release' beside the job name in the
scheduler view, to respawn through the /spawn interface, or to touch
the .job file in cbuild@orion:~/queue/armv5-builder.
> I've left this job in place as I've probably done enough damage already...
>
> 3) Ramana then attempted to use the web-interface at
> http://ex.seabright.co.nz/helpers/recent to get the job to rebuild
> (http://ex.seabright.co.nz/helpers/scheduler/spawn?queue=armv7l&job=gcc-lina…).
> However, this results in a Python exception.
Real men don't use user-friendly argument checking :) Well, not on
hacks like this tool. There is no armv7l queue so an assert fired.
> 4) Finally we used Ramana's credentials on the spawn interface, and
> that seems to have spawned the rebuild correctly.
Good.
> I'll let this run and see what happens.
>
> Michael, can you just check that things are progressing properly
> please, and also give me appropriate permissions on the web interface?
Checking:
http://ex.seabright.co.nz/helpers/buildlog/gcc-linaro-4.7-2012
shows that the build finished on x86_64 and i686. Checking /scheduler
shows that ARM builds are in progress on a9hf, a9, and armv5. Most
are in the testsuite and have ~6 hours to go.
-- Michael
== Progress ==
Linaro tasks.
* Some work on the intrinsics patches.
* Looked into auto-inc-dec stuff. Not enough improvements with scheduler
changes.
* Helped Matt get up to speed and wrote up some stuff for Christophe
with the vext examples.
* Investigated a bug that Mans reported upstream with the compiler
generating vdupeq . Have a patch being tested.
== Plans ==
* Finish up pending patches upstream. (neon intrinsics patches need to
be committed)
* Finish handing over patches.
* Fix PR54212.
Looks like I missed sending this for 2 weeks in a row.
== Progress ==
Linaro tasks.
* Some upstream discussions on neon testsuite bug. Poked at ML for
quite a bit. Looks like regexps in the neon intrinsics testsuite is
just wrong.
* Looking at a better way of doing the 64 bit arithmetic patches that
carrot proposed. Don't like them.
* Discussed with Richard about ubfx for a while.
* Reviewed the backlog and came up with suggestions for things for
people to do . Thought a bit about some stuff that Michael asked me to
look at .
== Plans ==
* Look at auto-inc-dec patches more and investigate benchmark results.
* Follow up on Intrinsics work.
* Follow-up on my intrinsics patches upstream.
* Finish looking at PR53664 and clean up testsuite further.
* Set up a TC2 for Linaro for benchmarking in the validation lab.
== Absences ==
* 17th Sept - 5th Oct - Vacation approved.
* 29th Oct - 5th Nov - Copenhagen Linaro Connect. Travel and hotel to
be booked.
All,
Is there anything left to go into the branches that needs to be in the
releases this week?
I believe Uli's patches have gone in - is there anything else required?
I will start spinning the releases around 0800 UTC tomorrow if nothing
else is needed for the release.
Thanks,
Matt
--
Matthew Gretton-Dann
Linaro Toolchain Working Group
matthew.gretton-dann(a)linaro.org
I would like to run Ubuntu 12.04 on a A9 Cortex-MP/armv7-a
development system that has *no FPU* hardware floating point unit.
Does this mean the entire toolchain needs to be recompiled?
Could you please shed light on appropriate settings
(toolchain and/or kernel) soft FPU emulation related options
for armv7-a without a FPU?
Thank...Peter
== Progress ==
* Started Linaro ramp up process
* Lots of admin, PC setup, Linaro docs reading
* Still unable to make bzr work. Investigating proxy restrictions.
* Started working on "constant vec permute operation for the vext
instruction"
* Still some pending internal work
== Next week
* Out of office Wed 15, Friday 17 and Monday 20
* Attend appropriate Virtual Connect sessions
* Progress on "constant vec permute operation for the vext instruction"
Virtual Connect is up next week. We've got two sessions lined up: the
first on profile guided optimisation and link time optimisation, and
the second on next steps with the vectoriser. Some other highlights
are the ones on system trace, Dalvik, and Aarch64 via OpenEmbedded
bootstrap.
The schedule is up at:
http://www.linaro.org/linaro-blog/2012/08/07/linaro-announces-virtual-conne…
Our sessions are "Analyzing vectorizer performance regressions in GCC
4.7 and 4.8" at 1000 UTC on Monday and "Exploring The Performance
Impact of PGO and LTO on ARM" at 1000 UTC on Thursday.
You'll need Google Hangout set up to join. For those who can't make
it, the sessions also get recorded out to the Linaro OnAir YouTube
channel.
I've cancelled the Monday regular and Thursday stand up calls. See
you next week!
-- Michael
Current Milestones:
|| || Planned || Estimate || Actual ||
||cp15-rework || 2012-01-06 || 2012-06-23 || 2012-06-24 ||
||a15-lpae-support || 2012-07-13 || 2012-07-20 || 2012-07-20 ||
||clean-up-kvm-patches || || || ||
||track-kvm-abi-changes || || || ||
||fake-trustzone || || || ||
Overall KVM plan for 'do by end August': QEMU parts of this are a mix
of clean-up-kvm-patches and track-kvm-abi-changes blueprints, mostly.
http://cards.linaro.org/browse/CARD-167
== clean-up-kvm-patches ==
* did enough cleanup to be able to send a coherent initial RFC
patchset to qemu-devel/kvmarm.
== other ==
* upstream patch review, in preparation for QEMU 1.2 freeze next week
* put together qemu-linaro 2012.08 tarball (release next week)
KVM blueprint progress tracker:
http://apus.seabright.co.nz/helpers/backlog?group_by=topic&colour_by=state&…
-- PMM
== GCC ==
* Back-ported patch to change vector alignment to 8
to FSF GCC 4.6 and 4.7 and Linaro GCC 4.6 and 4.7.
* Investigated mp3player benchmark regression with
Linaro GCC 4.7 backport of vector alignment patch.
Mit freundlichen Gruessen / Best Regards
Ulrich Weigand
--
Dr. Ulrich Weigand | Phone: +49-7031/16-3727
STSM, GNU compiler and toolchain for Linux on System z and Cell/B.E.
IBM Deutschland Research & Development GmbH
Vorsitzender des Aufsichtsrats: Martin Jetter | Geschäftsführung: Dirk
Wittkopp
Sitz der Gesellschaft: Böblingen | Registergericht: Amtsgericht
Stuttgart, HRB 243294
== Progress ==
* Started Linaro ramp up process
* Lots of admin, paperwork, and PC setup
* Successfully built compilers from Linaro and upstream trees
* Out of office Friday 10
== Next Week ==
* Out of office Friday 17
* Attend appropriate Virtual Connect sessions
* Do the 2012.08 release of the Toolchain
* Start working on symbol_ref split benchmarking.
== Future ==
* Find a small patch to GCC to use to pipeclean the submission process
--
Matthew Gretton-Dann
Linaro Toolchain Working Group
matthew.gretton-dann(a)linaro.org
Hello,
I've had a look at the mp3player performance regressions (just with *some*
data sets) with the vector-alignment patch. Interestingly it turns out
that the patch basically does not change the generated code for the hot
spot (inv_mdct routine) at all. (The *only* change is which bits of the
incoming pointer the run-time alignment check generated by the vectorizer
tests for. But this has no practical consequences, since the check itself
is not hot, and the *decision* made by the check is the same anyway --
everything is in fact properly aligned at runtime.)
The other difference, outside of code, introduced by the vector-alignment
patch is that some global arrays used to be forcibly aligned to 16 bytes by
the vectorizer, and they are now only aligned to 8 bytes. To check whether
this makes a difference, I've modified the compiler as a hack to always
force all global arrays to be 16 byte aligned. And interestingly enough,
this appears to fix this particular performance regression ...
Any thoughts as to why this might be the case? What are the
recommendations on the ARM hardware side as to what alignment is prefered?
Mit freundlichen Gruessen / Best Regards
Ulrich Weigand
--
Dr. Ulrich Weigand | Phone: +49-7031/16-3727
STSM, GNU compiler and toolchain for Linux on System z and Cell/B.E.
IBM Deutschland Research & Development GmbH
Vorsitzende des Aufsichtsrats: Martina Koederitz | Geschäftsführung: Dirk
Wittkopp
Sitz der Gesellschaft: Böblingen | Registergericht: Amtsgericht
Stuttgart, HRB 243294
I have noticed gcc has a preference for generating UXTB instructions
when an AND with #255 would do the same thing. This is bad, because
on A9 UXTB has two cycles latency compared to one cycle for AND. On
A8 both instructions have one cycle latency.
--
Mans Rullgard / mru
== GCC ==
* Checked in patch to change vector alignment to 8
to GCC mainline.
* Started investigating benchmark regressions with
Linaro GCC 4.7 backport of vector alignment patch.
== GDB ==
* Checked in patch to fix hardware breakpoints on
non-4-byte aligned (Thumb) instructions.
* Checked in patch to properly report unsupported
watchpoint address/length combinations in gdbserver.
* Checked in patch to fix regression accessing /proc
files on older Linux kernels.
* Checked in 5 more patches to fix miscellaneous
test suite regressions.
* Re-tested GDB 7.5 pre-release on multiple platforms.
Mit freundlichen Gruessen / Best Regards
Ulrich Weigand
--
Dr. Ulrich Weigand | Phone: +49-7031/16-3727
STSM, GNU compiler and toolchain for Linux on System z and Cell/B.E.
IBM Deutschland Research & Development GmbH
Vorsitzender des Aufsichtsrats: Martin Jetter | Geschäftsführung: Dirk
Wittkopp
Sitz der Gesellschaft: Böblingen | Registergericht: Amtsgericht
Stuttgart, HRB 243294
[ Also posted to debian-arm; not cross-posted to avoid subscription
complaints... ]
Hi folks,
We're currently carrying patches in glibc in Debian (and Ubuntu) that
I wrote which are used to work out whether an ELF binary is hard-float
or soft-float. We're using these to allow us to do the right thing on
a multi-arch system, which is to pick a consistent set of binaries
(programs and libraries) at runtime; if you try to mix binaries using
different ABIs, you're prone to all kinds of weird and wonderful
results but generally badness occurs.
Upstream glibc have generally not been welcoming of these patches, and
I understand this; the approach taken (reading ARM-specific build
attributes) is far from clean and doesn't fit well in the design of
ld.so in particular. So, I've been looking into alternative methods
for achieving the goal of identifying ABI. After a couple of false
starts and discussion with some of the helpful toolchain and ABI folks
in ARM, I think we have a solution that will work well in the long
term. I just wish we'd thought about this *way* back when we first
started the armhf port, as it would have been much easier to work on
and standardise this back then. Modulo availability of time machines,
there's not much we can do on that front... :-)
What I'm proposing is to use two new values in the OSABI field in the
ELF header:
#define ELFOSABI_LINUX_ARM_AEABI_SF 65
#define ELFOSABI_LINUX_ARM_AEABI_HF 66
and use these values in the future for soft- and hard-float binaries
so that can unambiguously identify them.
There's already precedent for binaries using different values in this
field, with support in glibc for parsing and understanding
them. Adding more possible values is quite easy, assuming that the
maintainers are amenable. I'm about to post a similar message there.
I have a plan of attack for how to make a staged switch over,
deliberately to minimise any potential compatibility problems. See the
attached doc for that. It's deliberately not very specific in terms of
timeline, as that's something I'm hoping to get feedback
about. Comments very welcome; please point out if you think there are
problems with this approach, or if there are any more implementations
of toolchain / linker that will need to be addressed.
Cheers,
--
Steve McIntyre steve.mcintyre(a)linaro.org
<http://www.linaro.org/> Linaro.org | Open source software for ARM SoCs
For reference, if you see link time errors about a missing
'__dso_handle' symbol when building Android, then check if you're
using any global class instances in your multimedia libraries.
Each shared library has a __dso_handle symbol which is filled in on
load by the dynamic loader. Global class instances use this unique
value to make sure the destructor is called when the library is
unloaded. The symbol itself is defined in crtbegin_so.o, but the
multimedia rules forbid using this for an unknown reason. Either
create your global instances in a different way or change the
multimedia rules :)
-- Michael
