[Bug target/50962] New: Additional opportunity for AGU stall avoidance optimization for Atom processor

[Bug target/50962] New: Additional opportunity for AGU stall avoidance optimization for Atom processor

[izamyatin at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

             Bug #: 50962
           Summary: Additional opportunity for AGU stall avoidance
                    optimization for Atom processor
    Classification: Unclassified
           Product: gcc
           Version: 4.7.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: izamyatin@gmail.com


We have now following code for attached testcase:

foo:
.LFB0:
        .cfi_startproc
        movl    4(%esp), %eax
        testl   %eax, %eax
        je      .L4
        xorl    %ecx, %ecx
        jmp     .L3
        .p2align 4,,7
        .p2align 3
.L5:
        movl    %eax, %ecx
        movl    %edx, %eax
.L3:
        movl    (%eax), %edx <--- AGU stall here on Atom since eax produced on
previous cycle. We should use lea in previous instruction.
        movl    %ecx, (%eax)
        testl   %edx, %edx
        jne     .L5
        ret
.L4:
        xorl    %eax, %eax
        ret
        .cfi_endproc

 So we can use lea before movl (%eax), %edx which is better for Atom.

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[izamyatin at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

--- Comment #1 from Igor Zamyatin <izamyatin at gmail dot com> 2011-11-02 12:00:55 UTC ---
Created attachment 25688
  --> http://gcc.gnu.org/bugzilla/attachment.cgi?id=25688
testcase

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[enkovich.gnu at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

--- Comment #2 from Ilya Enkovich <enkovich.gnu at gmail dot com> 2011-11-02 13:05:46 UTC ---
Created attachment 25689
  --> http://gcc.gnu.org/bugzilla/attachment.cgi?id=25689
Proposed patch

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[enkovich.gnu at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

Ilya Enkovich <enkovich.gnu at gmail dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                 CC|                            |enkovich.gnu at gmail dot
                   |                            |com

--- Comment #3 from Ilya Enkovich <enkovich.gnu at gmail dot com> 2011-11-02 13:06:07 UTC ---
Current optimization use only splits to transform arithmetic into lea and vice
versa. It does not work for move because corresponding lea template will be
equal. We can check if lea is required during instruction emit. 

I have a patch to fix it. Bootstrap and make check passed. I'm currently
checking performance changes.

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[kyukhin at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

--- Comment #4 from Kirill Yukhin <kyukhin at gcc dot gnu.org> 2011-11-07 08:47:18 UTC ---
Author: kyukhin
Date: Mon Nov  7 08:47:15 2011
New Revision: 181077

URL: http://gcc.gnu.org/viewcvs?root=gcc&view=rev&rev=181077
Log:
gcc/
    PR target/50962
    * config/i386/i386-protos.h (ix86_use_lea_for_mov): New.
    * config/i386/i386.c (ix86_use_lea_for_mov): Likewise.
    * config/i386/i386.md (movsi_internal): Emit lea if profitable.
    (movdi_internal_rex64): Likewise.


Modified:
    trunk/gcc/config/i386/i386-protos.h
    trunk/gcc/config/i386/i386.c
    trunk/gcc/config/i386/i386.md
    trunk/gcc/testsuite/ChangeLog

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[pinskia at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

--- Comment #5 from Andrew Pinski <pinskia at gcc dot gnu.org> 2011-12-15 00:22:03 UTC ---
Has this been fixed now?

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[izamyatin at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

Igor Zamyatin <izamyatin at gmail dot com> changed:

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

--- Comment #6 from Igor Zamyatin <izamyatin at gmail dot com> 2011-12-15 04:48:30 UTC ---
Fixed.

[Bug target/50962] Additional opportunity for AGU stall avoidance optimization for Atom processor

[dirtyepic at gentoo dot org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=50962

--- Comment #7 from Ryan Hill <dirtyepic at gentoo dot org> ---
This caused PR56707.