[Bug target/32951] New: missed memcpy -> movdqa optimization.

[pluto at agmk dot net]

#include <emmintrin.h>

typedef char const* __attribute__((aligned(16))) aligned_byte_buffer;

__m128i load_1( aligned_byte_buffer buf )
{
        return *((__m128i*)buf);
}

__m128i load_2( aligned_byte_buffer buf )
{
        __m128i m;
        __builtin_memcpy( &m, buf, sizeof( m ) );
        return m;
}

gcc-4.2.1 produces unoptimal load_2 code:

load_1:
        movdqa  (%rdi), %xmm0
        ret

load_2:
        movq    (%rdi), %rax
        movq    %rax, -24(%rsp)
        movq    8(%rdi), %rax
        movq    %rax, -16(%rsp)
        movdqa  -24(%rsp), %xmm0
        ret


-- 
           Summary: missed memcpy -> movdqa optimization.
           Product: gcc
           Version: 4.2.1
            Status: UNCONFIRMED
          Severity: normal
          Priority: P3
         Component: target
        AssignedTo: unassigned at gcc dot gnu dot org
        ReportedBy: pluto at agmk dot net
GCC target triplet: x86_64-linux


http://gcc.gnu.org/bugzilla/show_bug.cgi?id=32951