https://gcc.gnu.org/bugzilla/show_bug.cgi?id=101989

            Bug ID: 101989
           Summary: Fail to optimize (a & b) | (c & ~b) to vpternlog
                    instruction.
           Product: gcc
           Version: 12.0
            Status: UNCONFIRMED
          Keywords: missed-optimization
          Severity: normal
          Priority: P3
         Component: target
          Assignee: unassigned at gcc dot gnu.org
          Reporter: crazylht at gmail dot com
  Target Milestone: ---
              Host: x86_64-pc-linux-gnu
            Target: x86_64-*-* i?86-*-*

cat test.c

__m128i foo (__m128i src1, __m128i src2, __m128i src3)
{
  return (src2 & ~src1) | (src3 & src1);
}

__m128i foo1 (__m128i src1, __m128i src2, __m128i src3)
{
  return (src2 & src1) | (src3 & ~src1);
}

gcc -O2 -march=cascadelake  generates

foo(long long __vector(2), long long __vector(2), long long __vector(2)):
        vpxor   %xmm2, %xmm1, %xmm2
        vpand   %xmm0, %xmm2, %xmm2
        vpxor   %xmm1, %xmm2, %xmm0
        ret
foo1(long long __vector(2), long long __vector(2), long long __vector(2)):
        vpxor   %xmm2, %xmm1, %xmm1
        vpand   %xmm0, %xmm1, %xmm1
        vpxor   %xmm2, %xmm1, %xmm0
        ret


icx generates

foo(long long __vector(2), long long __vector(2), long long __vector(2)):      
                 # 
        vpternlogq      xmm0, xmm2, xmm1, 202
        ret
foo1(long long __vector(2), long long __vector(2), long long __vector(2)):     
                 # 
        vpternlogq      xmm0, xmm1, xmm2, 202
        ret

Guess we need a post_reload splitter to match

Failed to match this instruction:
(set (reg:V2DI 88)
    (xor:V2DI (and:V2DI (xor:V2DI (reg:V2DI 92)
                (reg/v:V2DI 87 [ src3 ]))
            (reg:V2DI 91))
        (reg/v:V2DI 87 [ src3 ])))
Failed to match this instruction:

Reply via email to