[Bug tree-optimization/102494] New: Failure to optimize out vector reduction properly especially when using OpenMP

["gabravier at gmail dot com" <gcc-bugzilla@gcc.gnu.org>]

https://gcc.gnu.org/bugzilla/show_bug.cgi?id=102494

            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 = 0;

#pragma omp simd reduction(+:r)
    for (size_t i = 0 ; i < (sizeof(a) / sizeof(a[0])) ; i++) {
      r += 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 =
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 = xmm0[2,3,2,3]
        paddw   xmm1, xmm0
        pshufd  xmm0, xmm1, 85                  # xmm0 = 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 improves
  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