[Bug target/59539] Missed optimisation: VEX-prefixed operations don't need aligned data

[thiago at kde dot org]

http://gcc.gnu.org/bugzilla/show_bug.cgi?id=59539

--- Comment #13 from Thiago Macieira <thiago at kde dot org> ---
I can't confirm. trunk@206091:

$ ~/gcc4.9/bin/gcc -mavx -S -o - -O3 -xc - <<<'#include <immintrin.h>
int f(void *p1, void *p2)
{
    __m128i d1 = _mm_loadu_si128((__m128i*)p1);
    __m128i d2 = _mm_loadu_si128((__m128i*)p2);
    __m128i result = _mm_cmpeq_epi16(d1, d2);
    return _mm_movemask_epi8(result);
}
'
        .file   ""
        .section        .text.unlikely,"ax",@progbits
.LCOLDB0:
        .text
.LHOTB0:
        .p2align 4,,15
        .globl  f
        .type   f, @function
f:
.LFB1073:
        .cfi_startproc
        vmovdqu (%rdi), %xmm0
        vmovdqu (%rsi), %xmm1
        vpcmpeqw        %xmm1, %xmm0, %xmm0
        vpmovmskb       %xmm0, %eax
        ret
        .cfi_endproc
.LFE1073:
        .size   f, .-f
        .section        .text.unlikely
.LCOLDE0:
        .text
.LHOTE0:
        .ident  "GCC: (GNU) 4.9.0 20131121 (experimental)"
        .section        .note.GNU-stack,"",@progbits