https://gcc.gnu.org/bugzilla/show_bug.cgi?id=66866

--- Comment #2 from Richard Biener <rguenth at gcc dot gnu.org> ---
More reduced, fails at -O1:

extern "C" void abort (void);
typedef long long __m128i __attribute__ ((__vector_size__ (16),
__may_alias__));
typedef short A __attribute__((__may_alias__));
__m128i __attribute__((noinline))
shuf(const __m128i v)
{
  __m128i r;
  reinterpret_cast<A *>(&r)[5] = reinterpret_cast<const A *>(&v)[4];
  return r;
}
int main()
{
  __attribute__((aligned(16))) short mem[8] = { 0, 1, 2, 3, 4, 5, 6, 7 };
  *reinterpret_cast<__m128i *>(mem) = shuf (*reinterpret_cast<__m128i *>(mem));
  if (mem[5] != 4)
    abort ();
  return 0;
}


_Z4shufDv2_x:
.LFB527:
        .cfi_startproc
        movaps  %xmm0, -24(%rsp)
        pxor    %xmm0, %xmm0
        pinsrw  $5, -24(%rsp), %xmm0
        ret

Reply via email to