insertp[sd] $0, which is a noop.  Before:

_f32:                                   ## @f32
	pshufd	$1, %xmm1, %xmm2
	pshufd	$1, %xmm0, %xmm3
	addss	%xmm2, %xmm3
	addss	%xmm1, %xmm0
                                        ## kill: XMM0<def> XMM0<kill> XMM0<def>
	insertps	$0, %xmm0, %xmm0
	insertps	$16, %xmm3, %xmm0
	ret

after:

_f32:                                   ## @f32
	movdqa	%xmm0, %xmm2
	addss	%xmm1, %xmm2
	pshufd	$1, %xmm1, %xmm1
	pshufd	$1, %xmm0, %xmm3
	addss	%xmm1, %xmm3
	movdqa	%xmm2, %xmm0
	insertps	$16, %xmm3, %xmm0
	ret

The extra movs are due to a random (poor) scheduling decision.

llvm-svn: 112379