; CHECK-NEXT: pmovzxwq %xmm0, %xmm0
; CHECK-NEXT: retq
entry:
- %2 = load <4 x i32>* %0, align 16
+ %2 = load <4 x i32>, <4 x i32>* %0, align 16
%3 = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %2, <4 x i32> <i32 127, i32 127, i32 127, i32 127>)
%4 = extractelement <4 x i32> %3, i32 0
%5 = extractelement <4 x i32> %3, i32 1
; CHECK: # BB#0: # %entry
; CHECK-NEXT: movdqa (%rdi), %xmm0
; CHECK-NEXT: pminud {{.*}}(%rip), %xmm0
-; CHECK-NEXT: pextrd $1, %xmm0, %eax
-; CHECK-NEXT: movd %eax, %xmm0
-; CHECK-NEXT: pmovzxwq %xmm0, %xmm0
+; CHECK-NEXT: pshufd {{.*#+}} xmm0 = xmm0[1,1,2,3]
+; CHECK-NEXT: pmovzxwq {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[1],zero,zero,zero
; CHECK-NEXT: retq
entry:
- %2 = load <4 x i32>* %0, align 16
+ %2 = load <4 x i32>, <4 x i32>* %0, align 16
%3 = call <4 x i32> @llvm.x86.sse41.pminud(<4 x i32> %2, <4 x i32> <i32 127, i32 127, i32 127, i32 127>)
%4 = extractelement <4 x i32> %3, i32 0
%5 = extractelement <4 x i32> %3, i32 1