(cc'd to linaro-toolchain to archive)
Hi Matt. I've had a look at the manual builds you tried to spawn.
Here's what I did to run cbuild locally to test it:
* cd linaro
* bzr branch lp:cbuild
* cd cbuild/slaves
* cp -a example `hostname`
* cd `hostname`
* make -f ../../lib/build.mk final/gcc-4.8+svn190558.stamp
I'm not proud of the whole 'slaves/$hostname' setup, but it is what it is.
Results are in $version, such as gcc-4.8+svn190558. The build tree is
in $version/gcc/default/build. Nuke using rm -rf final results
$version. See lib/common.mk and override the email address etc in
local.mk to stop build results going out You should put a proxy in
$http_proxy or ~/.wgetrc to reduce the download cost. Please add to
the cbuild README.
A nit: we use the Debian versioning scheme so the version should be
4.8~svn190558, i.e. a SVN checkout leading up to 4.8. Compare with
4.7+svn1234, which is a SVN checkout of the 4.7 branch.
The tarballs look generally good. I've spawned them into the a9hf
queue as that's what we benchmark on. Note that they're low priority
due to not having 'linaro' in the name.
-- Michael
Zhenqiang's been working on the later split 2 patch which causes more
constants to be built using a movw/movt instead of a constant pool
load. There was an unexpected ~10 % regression in one benchmark which
seems to be due to function alignment. I think we've tracked down the
reason but not the action.
Compared to the baseline, the split2 branch took 113 % of the time to
run, i.e. 13 % longer. Adding an explicit 16 byte alignment to the
function changed this to 97 % of the time, i.e. 3 % faster. The
reason Zhenqiang and I got different results was the build-id. He
used the binary build scripts to make the cross compiler, which turn
on the build ID, which added an extra 20 bytes ahead of .text, which
happened to align the function to 16 bytes. cbuild doesn't use the
build-id (although it should) which happened to align the function to
an 8 byte boundary.
The disassembly is identical so I assume the regression is cache or
fast loop related. I'm not sure what to do, so let's talk about this
at the next performance call.
-- Michael
All,
I have updated the minutes from today's Performance Call here:
https://wiki.linaro.org/WorkingGroups/ToolChain/Meetings/2012-08-21
The following are the actions from the meeting:
* michaelh to folow-up and ping Mans on getting a hold of his benchmark runs
* michaelh to investigate regression with movw/movt patch by hand
* mgrettondann to run current symbol ref splitting patch over SPEC
against FSF trunk
* michaelh to point mgrettondann to existing cards
* michaelh and mgrettondann to start writing card for PGO work
* mgrettondann to pick up Hot/Cold Partitioning patch from ramana,
cross-test against SPEC for correctness, and then do a benchmarking
run
* ramana to create a Blueprint for min-idion in middle-end and
update Todo list with link
* mgrettondann to update todo list with changes in 2012.08 release.
* zchen to work on shrink-wrapping
* clyon to update his vext patch
The next meeting is on 4 September and a proposed Agenda is here:
https://wiki.linaro.org/WorkingGroups/ToolChain/Meetings/2012-09-04
Please add any items you wish to discuss to the agenda.
Thanks,
Matt
--
Matthew Gretton-Dann
Linaro Toolchain Working Group
matthew.gretton-dann(a)linaro.org
On 18 August 2012 12:06, Ramana Radhakrishnan
<ramana.radhakrishnan(a)linaro.org> wrote:
> This should have been fixed by this patch . I'm a bit surprised that
> we are seeing these failures still ?
>
> ../ports/sysdeps/unix/sysv/linux/arm/ldsodefs.h:41:0: warning:
> "MORE_ELF_HEADER_DATA" redefined [enabled by default]
>
> http://permalink.gmane.org/gmane.comp.lib.glibc.ports/1428
>
> which should have made it back to eglibc 2.16 ?
Well, that's embarrassing. The eglibc script is used to both build
eglibc and to use a fixed eglibc to test GCC. The latter was winning
so every snapshot build was actually building eglibc 2.12.
Fixed and testing,
-- 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 || || || ||
== 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
