when we see a unaligned load from an insufficiently aligned global or
alloca, increase the alignment of the load, turning it into an aligned load.
This allows us to compile:
#include <xmmintrin.h>
__m128i foo(__m128i x){
static const unsigned int c_0[4] = { 0, 0, 0, 0 };
__m128i v_Zero = _mm_loadu_si128((__m128i*)c_0);
x = _mm_unpacklo_epi8(x, v_Zero);
return x;
}
into:
_foo:
punpcklbw _c_0.5944, %xmm0
ret
.data
.lcomm _c_0.5944,16,4 # c_0.5944
instead of:
_foo:
movdqu _c_0.5944, %xmm1
punpcklbw %xmm1, %xmm0
ret
.data
.lcomm _c_0.5944,16,2 # c_0.5944
llvm-svn: 40971
a8e4b4bc7b