[Bug target/105493] New: [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[Bug target/105493] New: [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[lili.cui at intel dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

            Bug ID: 105493
           Summary: [12/13 Regression] x86_64 538.imagick_r 6% regressions
                    and 2% 525.x264_r regressions on Alder Lake after
                    r12-7319-g90d693bdc9d718
           Product: gcc
           Version: 13.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: lili.cui at intel dot com
  Target Milestone: ---

Similar issue with https://gcc.gnu.org/bugzilla/show_bug.cgi?id=104762
they are all caused by the same commit 90d693bdc9d71841f51d68826ffa5bd685d7f0bc

options: -march=native -Ofast -lto

Alder Lake single copy:

            after Vs. before this commit
525.x264_r           -9.09%
538.imagick_r        -25.00%

Alder Lake multicopy:

            after Vs. before this commit
525.x264_r           -2.00%
538.imagick_r        -6.7%

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

Richard Biener <rguenth at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
           Keywords|                            |missed-optimization
                 CC|                            |jamborm at gcc dot gnu.org
             Target|                            |x86_64-*-*
             Blocks|                            |26163
   Target Milestone|---                         |12.0

--- Comment #1 from Richard Biener <rguenth at gcc dot gnu.org> ---
Martin is currently re-benchmarking GCC 12 on AMD, so let's see if there's
anything left on those.


Referenced Bugs:

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=26163
[Bug 26163] [meta-bug] missed optimization in SPEC (2k17, 2k and 2k6 and 95)

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[lili.cui at intel dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

--- Comment #2 from cuilili <lili.cui at intel dot com> ---
(In reply to Richard Biener from comment #1)
> Martin is currently re-benchmarking GCC 12 on AMD, so let's see if there's
> anything left on those.

AMD may not have this issue, Richard fixed AMD regression with this commit
r12-7612-g69619acd8d9b5856f5af6e5323d9c7c4ec9ad08f, but intel wasn't fixed
because they use different costs.

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[jakub at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

Jakub Jelinek <jakub at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|12.0                        |12.2

--- Comment #3 from Jakub Jelinek <jakub at gcc dot gnu.org> ---
GCC 12.1 is being released, retargeting bugs to GCC 12.2.

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[marxin at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

Martin Liška <marxin at gcc dot gnu.org> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
             Status|UNCONFIRMED                 |NEW
   Last reconfirmed|                            |2022-05-09
                 CC|                            |marxin at gcc dot gnu.org
     Ever confirmed|0                           |1

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

--- Comment #4 from Hongtao.liu <crazylht at gmail dot com> ---
regarding 525, it's pr101929.

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[jamborm at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

--- Comment #5 from Martin Jambor <jamborm at gcc dot gnu.org> ---
I can confirm that an Intel Cascade Lake Xeon, using -Ofast -flto
-march=native, 538.imagick_r produced by GCC 12.1 is almost 20% slower
than the benchmark built with GCC 11.2 and the same options (on Zen2
or 3 I can see only smaller regressios at -O2 and with PGO)

I do not see the 525.x264_r regression using the same compilers and
options on this machine.

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[cvs-commit at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

--- Comment #6 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by hongtao Liu <liuhongt@gcc.gnu.org>:

https://gcc.gnu.org/g:269edf4e5e6ab489730038f7e3495550623179fe

commit r13-1021-g269edf4e5e6ab489730038f7e3495550623179fe
Author: Cui,Lili <lili.cui@intel.com>
Date:   Wed Jun 8 11:25:57 2022 +0800

    Update {skylake,icelake,alderlake}_cost to add a bit preference to vector
store.

    Since the interger vector construction cost has changed, we need to adjust
the
    load and store costs for intel processers.

    With the patch applied
    538.imagic_r:gets ~6% improvement on ADL for multicopy.
    525.x264_r  :gets ~2% improvement on ADL and ICX for multicopy.
    with no measurable changes for other benchmarks.

    gcc/ChangeLog

            PR target/105493
            * config/i386/x86-tune-costs.h (skylake_cost): Raise the gpr load
cost
            from 4 to 6 and gpr store cost from 6 to 8. Change SSE loads and
            unaligned loads cost from {6, 6, 6, 10, 20} to {8, 8, 8, 8, 16}.
            (icelake_cost): Ditto.
            (alderlake_cost): Raise the gpr store cost from 6 to 8 and SSE
loads,
            stores and unaligned stores cost from {6, 6, 6, 10, 15} to
            {8, 8, 8, 10, 15}.

    gcc/testsuite/

            PR target/105493
            * gcc.target/i386/pr91446.c: Adjust to expect vectorization
            * gcc.target/i386/pr99881.c: XFAIL.
            * gcc.target/i386/pr105493.c: New.
            * g++.target/i386/pr105638.C: Use other sequence checks
            instead of vpxor, because code generation changed.

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[rguenth at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

--- Comment #7 from Richard Biener <rguenth at gcc dot gnu.org> ---
Can this be considered fixed on trunk?

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[crazylht at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

--- Comment #8 from Hongtao.liu <crazylht at gmail dot com> ---
(In reply to Richard Biener from comment #7)
> Can this be considered fixed on trunk?

Yes.

[Bug target/105493] [12/13 Regression] x86_64 538.imagick_r 6% regressions and 2% 525.x264_r regressions on Alder Lake after r12-7319-g90d693bdc9d718

[lili.cui at intel dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=105493

cuilili <lili.cui at intel dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
         Resolution|---                         |FIXED
             Status|NEW                         |RESOLVED

--- Comment #9 from cuilili <lili.cui at intel dot com> ---
This regression was fixed by commit
r13-1021-g269edf4e5e6ab489730038f7e3495550623179fe, now close this ticket.