2) Don't try to insert an i64 value into the low part of a 
   vector with movq on an x86-32 target.  This allows us to 
   compile:

__m128i doload64(short x) {return _mm_set_epi16(0,0,0,0,0,0,0,1);}

into:

_doload64:
	movaps	LCPI1_0, %xmm0
	ret

instead of:

_doload64:
	subl	$28, %esp
	movl	$0, 4(%esp)
	movl	$1, (%esp)
	movq	(%esp), %xmm0
	addl	$28, %esp
	ret

llvm-svn: 48057