[Bug target/101495] New: Unnecessary vzeroupper

[Bug target/101495] New: Unnecessary vzeroupper

[hjl.tools at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101495

            Bug ID: 101495
           Summary: Unnecessary vzeroupper
           Product: gcc
           Version: 11.1.1
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: hjl.tools at gmail dot com
                CC: crazylht at gmail dot com
  Target Milestone: ---
            Target: i386,x86-64

[hjl@gnu-cfl-2 pr101456]$ cat y.c
#include <x86intrin.h>

extern __m256d x;

extern __m256d bar (void);

__m256d
foo (void)
{
  x = _mm256_setzero_pd ();
  return bar ();
}
[hjl@gnu-cfl-2 pr101456]$ gcc -S -O2 -mavx2 y.c
[hjl@gnu-cfl-2 pr101456]$ cat y.s
        .file   "y.c"
        .text
        .p2align 4
        .globl  foo
        .type   foo, @function
foo:
.LFB5667:
        .cfi_startproc
        vxorpd  %xmm0, %xmm0, %xmm0
        vmovapd %ymm0, x(%rip)
        vzeroupper
        jmp     bar
        .cfi_endproc
.LFE5667:
        .size   foo, .-foo
        .ident  "GCC: (GNU) 11.1.1 20210531 (Red Hat 11.1.1-3)"
        .section        .note.GNU-stack,"",@progbits
[hjl@gnu-cfl-2 pr101456]$ 

Since bar returns __m256d, it must be compiled with AVX and there is no
need for vzeroupper.

[Bug target/101495] Unnecessary vzeroupper

[cvs-commit at gcc dot gnu.org]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101495

--- Comment #1 from CVS Commits <cvs-commit at gcc dot gnu.org> ---
The master branch has been updated by H.J. Lu <hjl@gcc.gnu.org>:

https://gcc.gnu.org/g:5586e7e85de381f3df843091494889f8ad8e3e1f

commit r12-2385-g5586e7e85de381f3df843091494889f8ad8e3e1f
Author: H.J. Lu <hjl.tools@gmail.com>
Date:   Sun Jul 18 06:12:29 2021 -0700

    x86: Don't issue vzeroupper if callee returns AVX register

    Don't issue vzeroupper before function call if callee returns AVX
    register since callee must be compiled with AVX.

    gcc/

            PR target/101495
            * config/i386/i386.c (ix86_check_avx_upper_stores): Moved before
            ix86_avx_u128_mode_needed.
            (ix86_avx_u128_mode_needed): Return AVX_U128_DIRTY if callee
            returns AVX register.

    gcc/testsuite/

            PR target/101495
            * gcc.target/i386/avx-vzeroupper-28.c: New test.

[Bug target/101495] Unnecessary vzeroupper

[hjl.tools at gmail dot com]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101495

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

           What    |Removed                     |Added
----------------------------------------------------------------------------
   Target Milestone|---                         |12.0
             Status|UNCONFIRMED                 |RESOLVED
         Resolution|---                         |FIXED

--- Comment #2 from H.J. Lu <hjl.tools at gmail dot com> ---
Fixed for GCC 12.