From mboxrd@z Thu Jan  1 00:00:00 1970
Return-Path: <gcc-bugzilla@gcc.gnu.org>
Received: by sourceware.org (Postfix, from userid 48)
 id 4E67D3877034; Mon, 27 Sep 2021 00:52:19 +0000 (GMT)
DKIM-Filter: OpenDKIM Filter v2.11.0 sourceware.org 4E67D3877034
From: "gabravier at gmail dot com" <gcc-bugzilla@gcc.gnu.org>
To: gcc-bugs@gcc.gnu.org
Subject: [Bug tree-optimization/102494] New: Failure to optimize out vector
 reduction properly especially when using OpenMP
Date: Mon, 27 Sep 2021 00:52:19 +0000
X-Bugzilla-Reason: CC
X-Bugzilla-Type: new
X-Bugzilla-Watch-Reason: None
X-Bugzilla-Product: gcc
X-Bugzilla-Component: tree-optimization
X-Bugzilla-Version: 12.0
X-Bugzilla-Keywords: 
X-Bugzilla-Severity: normal
X-Bugzilla-Who: gabravier at gmail dot com
X-Bugzilla-Status: UNCONFIRMED
X-Bugzilla-Resolution: 
X-Bugzilla-Priority: P3
X-Bugzilla-Assigned-To: unassigned at gcc dot gnu.org
X-Bugzilla-Target-Milestone: ---
X-Bugzilla-Flags: 
X-Bugzilla-Changed-Fields: bug_id short_desc product version bug_status
 bug_severity priority component assigned_to reporter target_milestone
Message-ID: <bug-102494-4@http.gcc.gnu.org/bugzilla/>
Content-Type: text/plain; charset="UTF-8"
Content-Transfer-Encoding: quoted-printable
X-Bugzilla-URL: http://gcc.gnu.org/bugzilla/
Auto-Submitted: auto-generated
MIME-Version: 1.0
X-BeenThere: gcc-bugs@gcc.gnu.org
X-Mailman-Version: 2.1.29
Precedence: list
List-Id: Gcc-bugs mailing list <gcc-bugs.gcc.gnu.org>
List-Unsubscribe: <https://gcc.gnu.org/mailman/options/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=unsubscribe>
List-Archive: <https://gcc.gnu.org/pipermail/gcc-bugs/>
List-Post: <mailto:gcc-bugs@gcc.gnu.org>
List-Help: <mailto:gcc-bugs-request@gcc.gnu.org?subject=help>
List-Subscribe: <https://gcc.gnu.org/mailman/listinfo/gcc-bugs>,
 <mailto:gcc-bugs-request@gcc.gnu.org?subject=subscribe>
X-List-Received-Date: Mon, 27 Sep 2021 00:52:19 -0000

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=3D102494

            Bug ID: 102494
           Summary: Failure to optimize out vector reduction properly
                    especially when using OpenMP
           Product: gcc
           Version: 12.0
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: tree-optimization
          Assignee: unassigned at gcc dot gnu.org
          Reporter: gabravier at gmail dot com
  Target Milestone: ---

#include <stdint.h>
#include <stddef.h>

typedef int8_t simde_int8x8_t __attribute__((__vector_size__(8)));

int16_t
simde_vaddlv_s8(simde_int8x8_t a) {
    int16_t r =3D 0;

#pragma omp simd reduction(+:r)
    for (size_t i =3D 0 ; i < (sizeof(a) / sizeof(a[0])) ; i++) {
      r +=3D a[i];
    }

    return r;
}

Compiled with -O3 -fopenmp-simd, this is the output on AMD64:

simde_vaddlv_s8(signed char __vector(8)):
        pxor    xmm1, xmm1
        movdqa  xmm2, xmm0
        pcmpgtb xmm1, xmm0
        punpcklbw       xmm0, xmm1
        punpcklbw       xmm2, xmm1
        pshufd  xmm0, xmm0, 78
        movq    QWORD PTR [rsp-24], xmm2
        movq    QWORD PTR [rsp-16], xmm0
        movdqa  xmm0, XMMWORD PTR [rsp-24]
        psrldq  xmm0, 8
        paddw   xmm0, XMMWORD PTR [rsp-24]
        movdqa  xmm1, xmm0
        psrldq  xmm1, 4
        paddw   xmm0, xmm1
        movdqa  xmm1, xmm0
        psrldq  xmm1, 2
        paddw   xmm0, xmm1
        pextrw  eax, xmm0, 0
        ret

This is what Clang manages:

simde_vaddlv_s8(signed char __vector(8)):
        punpcklbw       xmm0, xmm0              # xmm0 =3D
xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
        psraw   xmm0, 8
        pshufd  xmm1, xmm0, 238                 # xmm1 =3D xmm0[2,3,2,3]
        paddw   xmm1, xmm0
        pshufd  xmm0, xmm1, 85                  # xmm0 =3D xmm1[1,1,1,1]
        paddw   xmm0, xmm1
        movdqa  xmm1, xmm0
        psrld   xmm1, 16
        paddw   xmm1, xmm0
        movd    eax, xmm1
        ret

Weirdly enough, removing the `#pragma omp simd reduction(+r)` slightly impr=
oves
  GCC's output to this:

simde_vaddlv_s8(signed char __vector(8)):
        pxor    xmm1, xmm1
        movdqa  xmm2, xmm0
        pcmpgtb xmm1, xmm0
        punpcklbw       xmm0, xmm1
        punpcklbw       xmm2, xmm1
        pshufd  xmm0, xmm0, 78
        paddw   xmm0, xmm2
        pextrw  edx, xmm0, 1
        pextrw  eax, xmm0, 0
        add     eax, edx
        pextrw  edx, xmm0, 2
        add     eax, edx
        pextrw  edx, xmm0, 3
        add     eax, edx
        ret=