[Bug target/46295] New: Missing vzeroupper

[Bug target/46295] New: Missing vzeroupper

[hjl.tools at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46295

           Summary: Missing vzeroupper
           Product: gcc
           Version: 4.6.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
        AssignedTo: unassigned@gcc.gnu.org
        ReportedBy: hjl.tools@gmail.com
                CC: ubizjak@gmail.com


[hjl@gnu-6 969]$ cat z.i 
typedef double VECTOR[3];
typedef double EXPRESS[5];
void Parse_Rel_Factor (EXPRESS Express,int *Terms);
void Parse_Vector (VECTOR Vector)
{
   EXPRESS Express;
   int Terms;
   for (Terms = 0; Terms < 5; Terms++)
     Express[Terms] = 0.0;
   Parse_Rel_Factor(Express,&Terms);
}
[hjl@gnu-6 969]$ make z.s
/export/build/gnu/gcc-avx256/build-x86_64-linux/gcc/xgcc
-B/export/build/gnu/gcc-avx256/build-x86_64-linux/gcc/ -O3 -funroll-loops
-ffast-math -mavx   -S z.i
[hjl@gnu-6 969]$ cat z.s
    .file    "z.i"
    .text
    .p2align 4,,15
    .globl    Parse_Vector
    .type    Parse_Vector, @function
Parse_Vector:
.LFB0:
    .cfi_startproc
    pushq    %rbp
    .cfi_def_cfa_offset 16
    .cfi_offset 6, -16
    vxorpd    %xmm0, %xmm0, %xmm0
    movq    %rsp, %rbp
    .cfi_def_cfa_register 6
    andq    $-32, %rsp
    subq    $64, %rsp
    leaq    60(%rsp), %rsi
    movq    %rsp, %rdi
    vmovapd    %ymm0, (%rsp)
    movq    $0, 32(%rsp)
    movl    $5, 60(%rsp)
    call    Parse_Rel_Factor
    leave
    .cfi_def_cfa 7, 8
    ret
    .cfi_endproc
.LFE0:
    .size    Parse_Vector, .-Parse_Vector
    .ident    "GCC: (GNU) 4.6.0 20101103 (experimental)"
    .section    .note.GNU-stack,"",@progbits
[hjl@gnu-6 969]$

[Bug target/46295] Missing vzeroupper

[hjl.tools at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46295

H.J. Lu <hjl.tools at gmail dot com> changed:

           What    |Removed                     |Added
----------------------------------------------------------------------------
                URL|                            |http://gcc.gnu.org/ml/gcc-p
                   |                            |atches/2010-11/msg00350.htm
                   |                            |l
   Target Milestone|---                         |4.6.0

--- Comment #1 from H.J. Lu <hjl.tools at gmail dot com> 2010-11-03 21:04:52 UTC ---
A patch is posted at

http://gcc.gnu.org/ml/gcc-patches/2010-11/msg00350.html

[Bug target/46295] Missing vzeroupper

[hjl at gcc dot gnu.org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46295

--- Comment #2 from hjl at gcc dot gnu.org <hjl at gcc dot gnu.org> 2010-11-03 21:16:40 UTC ---
Author: hjl
Date: Wed Nov  3 21:16:36 2010
New Revision: 166277

URL: http://gcc.gnu.org/viewcvs?root=gcc&view=rev&rev=166277
Log:
Set use_avx256_p if 256bit AVX register is used in vector move.

gcc/

2010-11-03  H.J. Lu  <hongjiu.lu@intel.com>

    PR target/46295
    * config/i386/i386.c (ix86_expand_vector_move): Set use_avx256_p
    if 256bit AVX register is used.

gcc/testsuite/

2010-11-03  H.J. Lu  <hongjiu.lu@intel.com>

    PR target/46295
    * gcc.target/i386/pr46295.c: New.

Added:
    trunk/gcc/testsuite/gcc.target/i386/pr46295.c
Modified:
    trunk/gcc/ChangeLog
    trunk/gcc/config/i386/i386.c
    trunk/gcc/testsuite/ChangeLog

[Bug target/46295] Missing vzeroupper

[hjl.tools at gmail dot com]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=46295

H.J. Lu <hjl.tools at gmail dot com> changed:

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

--- Comment #3 from H.J. Lu <hjl.tools at gmail dot com> 2010-11-04 12:01:20 UTC ---
Fixed.