diff --git a/llvm/test/CodeGen/X86/sse2.ll b/llvm/test/CodeGen/X86/sse2.ll
index b7db6cb56ef2..d670fdf6ca33 100644
--- a/llvm/test/CodeGen/X86/sse2.ll
+++ b/llvm/test/CodeGen/X86/sse2.ll
@@ -75,7 +75,7 @@ define <4 x i32> @test5(i8** %ptr) nounwind {
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; CHECK-NEXT:    movl (%eax), %eax
-; CHECK-NEXT:    movss (%eax), %xmm1
+; CHECK-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; CHECK-NEXT:    pxor %xmm0, %xmm0
 ; CHECK-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; CHECK-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
@@ -180,7 +180,7 @@ define void @test12() nounwind {
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    movapd 0, %xmm0
 ; CHECK-NEXT:    movaps {{.*#+}} xmm1 = [1.000000e+00,1.000000e+00,1.000000e+00,1.000000e+00]
-; CHECK-NEXT:    movsd %xmm0, %xmm1
+; CHECK-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; CHECK-NEXT:    xorpd %xmm2, %xmm2
 ; CHECK-NEXT:    unpckhpd {{.*#+}} xmm0 = xmm0[1],xmm2[1]
 ; CHECK-NEXT:    addps %xmm1, %xmm0
@@ -293,7 +293,7 @@ entry:
 define <2 x i64> @test_insert_64_zext(<2 x i64> %i) {
 ; CHECK-LABEL: test_insert_64_zext:
 ; CHECK:       ## BB#0:
-; CHECK-NEXT:    movq %xmm0, %xmm0
+; CHECK-NEXT:    movq {{.*#+}} xmm0 = xmm0[0],zero
 ; CHECK-NEXT:    retl
   %1 = shufflevector <2 x i64> %i, <2 x i64> <i64 0, i64 undef>, <2 x i32> <i32 0, i32 2>
   ret <2 x i64> %1
@@ -303,7 +303,7 @@ define <4 x i32> @PR19721(<4 x i32> %i) {
 ; CHECK-LABEL: PR19721:
 ; CHECK:       ## BB#0:
 ; CHECK-NEXT:    xorps %xmm1, %xmm1
-; CHECK-NEXT:    movss %xmm1, %xmm0
+; CHECK-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; CHECK-NEXT:    retl
   %bc = bitcast <4 x i32> %i to i128
   %insert = and i128 %bc, -4294967296
diff --git a/llvm/test/CodeGen/X86/sse41.ll b/llvm/test/CodeGen/X86/sse41.ll
index 187bdb63e4d2..4979b6ff767e 100644
--- a/llvm/test/CodeGen/X86/sse41.ll
+++ b/llvm/test/CodeGen/X86/sse41.ll
@@ -78,13 +78,13 @@ define <2 x i64> @pmovzxbq_1() nounwind {
 ; X32-LABEL: pmovzxbq_1:
 ; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    movl L_g16$non_lazy_ptr, %eax
-; X32-NEXT:    pmovzxbq (%eax), %xmm0
+; X32-NEXT:    pmovzxbq {{.*#+}} xmm0 = mem[0],zero,zero,zero,zero,zero,zero,zero,mem[1],zero,zero,zero,zero,zero,zero,zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: pmovzxbq_1:
 ; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    movq _g16@{{.*}}(%rip), %rax
-; X64-NEXT:    pmovzxbq (%rax), %xmm0
+; X64-NEXT:    pmovzxbq {{.*#+}} xmm0 = mem[0],zero,zero,zero,zero,zero,zero,zero,mem[1],zero,zero,zero,zero,zero,zero,zero
 ; X64-NEXT:    retq
 entry:
 	%0 = load i16* @g16, align 2		; <i16> [#uses=1]
@@ -202,7 +202,7 @@ declare <4 x float> @llvm.x86.sse41.insertps(<4 x float>, <4 x float>, i32) noun
 define <4 x float> @insertps_2(<4 x float> %t1, float %t2) nounwind {
 ; X32-LABEL: insertps_2:
 ; X32:       ## BB#0:
-; X32-NEXT:    insertps $0, {{[0-9]+}}(%esp), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = mem[0],xmm0[1,2,3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_2:
@@ -322,12 +322,12 @@ define <4 x float> @insertps_from_shufflevector_1(<4 x float> %a, <4 x float>* n
 ; X32-LABEL: insertps_from_shufflevector_1:
 ; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    insertps $48, (%eax), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_shufflevector_1:
 ; X64:       ## BB#0: ## %entry
-; X64-NEXT:    insertps $48, (%rdi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; X64-NEXT:    retq
 entry:
   %0 = load <4 x float>* %pb, align 16
@@ -356,12 +356,12 @@ define <4 x i32> @pinsrd_from_shufflevector_i32(<4 x i32> %a, <4 x i32>* nocaptu
 ; X32-LABEL: pinsrd_from_shufflevector_i32:
 ; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    insertps $48, (%eax), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: pinsrd_from_shufflevector_i32:
 ; X64:       ## BB#0: ## %entry
-; X64-NEXT:    insertps $48, (%rdi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; X64-NEXT:    retq
 entry:
   %0 = load <4 x i32>* %pb, align 16
@@ -388,12 +388,12 @@ define <4 x float> @insertps_from_load_ins_elt_undef(<4 x float> %a, float* %b)
 ; X32-LABEL: insertps_from_load_ins_elt_undef:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    insertps $16, (%eax), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_load_ins_elt_undef:
 ; X64:       ## BB#0:
-; X64-NEXT:    insertps $16, (%rdi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
 ; X64-NEXT:    retq
   %1 = load float* %b, align 4
   %2 = insertelement <4 x float> undef, float %1, i32 0
@@ -406,13 +406,13 @@ define <4 x i32> @insertps_from_load_ins_elt_undef_i32(<4 x i32> %a, i32* %b) {
 ; X32-LABEL: insertps_from_load_ins_elt_undef_i32:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movd (%eax), %xmm1
+; X32-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_load_ins_elt_undef_i32:
 ; X64:       ## BB#0:
-; X64-NEXT:    movd (%rdi), %xmm1
+; X64-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
 ; X64-NEXT:    retq
   %1 = load i32* %b, align 4
@@ -447,12 +447,12 @@ define <4 x float> @shuf_XYZ0(<4 x float> %x, <4 x float> %a) {
 define <4 x float> @shuf_XY00(<4 x float> %x, <4 x float> %a) {
 ; X32-LABEL: shuf_XY00:
 ; X32:       ## BB#0:
-; X32-NEXT:    movq %xmm0, %xmm0
+; X32-NEXT:    movq {{.*#+}} xmm0 = xmm0[0],zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: shuf_XY00:
 ; X64:       ## BB#0:
-; X64-NEXT:    movq %xmm0, %xmm0
+; X64-NEXT:    movq {{.*#+}} xmm0 = xmm0[0],zero
 ; X64-NEXT:    retq
   %vecext = extractelement <4 x float> %x, i32 0
   %vecinit = insertelement <4 x float> undef, float %vecext, i32 0
@@ -617,12 +617,12 @@ define <4 x i32> @i32_shuf_XYZ0(<4 x i32> %x, <4 x i32> %a) {
 define <4 x i32> @i32_shuf_XY00(<4 x i32> %x, <4 x i32> %a) {
 ; X32-LABEL: i32_shuf_XY00:
 ; X32:       ## BB#0:
-; X32-NEXT:    movq %xmm0, %xmm0
+; X32-NEXT:    movq {{.*#+}} xmm0 = xmm0[0],zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: i32_shuf_XY00:
 ; X64:       ## BB#0:
-; X64-NEXT:    movq %xmm0, %xmm0
+; X64-NEXT:    movq {{.*#+}} xmm0 = xmm0[0],zero
 ; X64-NEXT:    retq
   %vecext = extractelement <4 x i32> %x, i32 0
   %vecinit = insertelement <4 x i32> undef, i32 %vecext, i32 0
@@ -739,7 +739,7 @@ define <4 x i32> @i32_shuf_X00X(<4 x i32> %x, <4 x i32> %a) {
 define <4 x i32> @i32_shuf_X0YC(<4 x i32> %x, <4 x i32> %a) {
 ; X32-LABEL: i32_shuf_X0YC:
 ; X32:       ## BB#0:
-; X32-NEXT:    pmovzxdq %xmm0, %xmm2
+; X32-NEXT:    pmovzxdq {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero
 ; X32-NEXT:    insertps {{.*#+}} xmm2 = xmm2[0,1],xmm0[1],zero
 ; X32-NEXT:    insertps {{.*#+}} xmm2 = xmm2[0,1,2],xmm1[2]
 ; X32-NEXT:    movaps %xmm2, %xmm0
@@ -747,7 +747,7 @@ define <4 x i32> @i32_shuf_X0YC(<4 x i32> %x, <4 x i32> %a) {
 ;
 ; X64-LABEL: i32_shuf_X0YC:
 ; X64:       ## BB#0:
-; X64-NEXT:    pmovzxdq %xmm0, %xmm2
+; X64-NEXT:    pmovzxdq {{.*#+}} xmm2 = xmm0[0],zero,xmm0[1],zero
 ; X64-NEXT:    insertps {{.*#+}} xmm2 = xmm2[0,1],xmm0[1],zero
 ; X64-NEXT:    insertps {{.*#+}} xmm2 = xmm2[0,1,2],xmm1[2]
 ; X64-NEXT:    movaps %xmm2, %xmm0
@@ -812,12 +812,12 @@ define <4 x float> @insertps_from_vector_load(<4 x float> %a, <4 x float>* nocap
 ; X32-LABEL: insertps_from_vector_load:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    insertps $48, (%eax), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_vector_load:
 ; X64:       ## BB#0:
-; X64-NEXT:    insertps $48, (%rdi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],mem[0]
 ; X64-NEXT:    retq
   %1 = load <4 x float>* %pb, align 16
   %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 48)
@@ -830,12 +830,12 @@ define <4 x float> @insertps_from_vector_load_offset(<4 x float> %a, <4 x float>
 ; X32-LABEL: insertps_from_vector_load_offset:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    insertps $96, 4(%eax), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],mem[1],xmm0[3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_vector_load_offset:
 ; X64:       ## BB#0:
-; X64-NEXT:    insertps $96, 4(%rdi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],mem[1],xmm0[3]
 ; X64-NEXT:    retq
   %1 = load <4 x float>* %pb, align 16
   %2 = tail call <4 x float> @llvm.x86.sse41.insertps(<4 x float> %a, <4 x float> %1, i32 96)
@@ -849,13 +849,13 @@ define <4 x float> @insertps_from_vector_load_offset_2(<4 x float> %a, <4 x floa
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
 ; X32-NEXT:    shll $4, %ecx
-; X32-NEXT:    insertps $192, 12(%eax,%ecx), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = mem[3],xmm0[1,2,3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_vector_load_offset_2:
 ; X64:       ## BB#0:
 ; X64-NEXT:    shlq $4, %rsi
-; X64-NEXT:    insertps $192, 12(%rdi,%rsi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = mem[3],xmm0[1,2,3]
 ; X64-NEXT:    retq
   %1 = getelementptr inbounds <4 x float>* %pb, i64 %index
   %2 = load <4 x float>* %1, align 16
@@ -868,14 +868,14 @@ define <4 x float> @insertps_from_broadcast_loadf32(<4 x float> %a, float* nocap
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    movss (%ecx,%eax,4), %xmm1
+; X32-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; X32-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,0,0,0]
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_from_broadcast_loadf32:
 ; X64:       ## BB#0:
-; X64-NEXT:    movss (%rdi,%rsi,4), %xmm1
+; X64-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; X64-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,0,0,0]
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
 ; X64-NEXT:    retq
@@ -920,7 +920,7 @@ define <4 x float> @insertps_from_broadcast_multiple_use(<4 x float> %a, <4 x fl
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %ecx
-; X32-NEXT:    movss (%ecx,%eax,4), %xmm4
+; X32-NEXT:    movss {{.*#+}} xmm4 = mem[0],zero,zero,zero
 ; X32-NEXT:    shufps {{.*#+}} xmm4 = xmm4[0,0,0,0]
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm4[0]
 ; X32-NEXT:    insertps {{.*#+}} xmm1 = xmm1[0,1,2],xmm4[0]
@@ -933,7 +933,7 @@ define <4 x float> @insertps_from_broadcast_multiple_use(<4 x float> %a, <4 x fl
 ;
 ; X64-LABEL: insertps_from_broadcast_multiple_use:
 ; X64:       ## BB#0:
-; X64-NEXT:    movss (%rdi,%rsi,4), %xmm4
+; X64-NEXT:    movss {{.*#+}} xmm4 = mem[0],zero,zero,zero
 ; X64-NEXT:    shufps {{.*#+}} xmm4 = xmm4[0,0,0,0]
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm4[0]
 ; X64-NEXT:    insertps {{.*#+}} xmm1 = xmm1[0,1,2],xmm4[0]
@@ -963,14 +963,14 @@ define <4 x float> @insertps_with_undefs(<4 x float> %a, float* %b) {
 ; X32-LABEL: insertps_with_undefs:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    movss (%eax), %xmm1
+; X32-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; X32-NEXT:    insertps {{.*#+}} xmm1 = xmm1[0],zero,xmm0[0],xmm1[3]
 ; X32-NEXT:    movaps %xmm1, %xmm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_with_undefs:
 ; X64:       ## BB#0:
-; X64-NEXT:    movss (%rdi), %xmm1
+; X64-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; X64-NEXT:    insertps {{.*#+}} xmm1 = xmm1[0],zero,xmm0[0],xmm1[3]
 ; X64-NEXT:    movaps %xmm1, %xmm0
 ; X64-NEXT:    retq
@@ -986,12 +986,12 @@ define <4 x float> @pr20087(<4 x float> %a, <4 x float> *%ptr) {
 ; X32-LABEL: pr20087:
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
-; X32-NEXT:    insertps $178, 8(%eax), %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],mem[2]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: pr20087:
 ; X64:       ## BB#0:
-; X64-NEXT:    insertps $178, 8(%rdi), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],mem[2]
 ; X64-NEXT:    retq
   %load = load <4 x float> *%ptr
   %ret = shufflevector <4 x float> %load, <4 x float> %a, <4 x i32> <i32 4, i32 undef, i32 6, i32 2>
@@ -1004,14 +1004,14 @@ define void @insertps_pr20411(i32* noalias nocapture %RET) #1 {
 ; X32:       ## BB#0:
 ; X32-NEXT:    movl {{[0-9]+}}(%esp), %eax
 ; X32-NEXT:    movaps {{.*#+}} xmm0 = [3,3,3,3]
-; X32-NEXT:    insertps $220, LCPI49_1+12, %xmm0
+; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[3],zero,zero
 ; X32-NEXT:    movups %xmm0, (%eax)
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_pr20411:
 ; X64:       ## BB#0:
 ; X64-NEXT:    movaps {{.*#+}} xmm0 = [3,3,3,3]
-; X64-NEXT:    insertps $220, LCPI49_1+{{.*}}(%rip), %xmm0
+; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[3],zero,zero
 ; X64-NEXT:    movups %xmm0, (%rdi)
 ; X64-NEXT:    retq
   %gather_load = shufflevector <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>, <8 x i32> undef, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
@@ -1025,12 +1025,12 @@ define void @insertps_pr20411(i32* noalias nocapture %RET) #1 {
 
 define <4 x float> @insertps_4(<4 x float> %A, <4 x float> %B) {
 ; X32-LABEL: insertps_4:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[2],zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_4:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[2],zero
 ; X64-NEXT:    retq
 entry:
@@ -1045,12 +1045,12 @@ entry:
 
 define <4 x float> @insertps_5(<4 x float> %A, <4 x float> %B) {
 ; X32-LABEL: insertps_5:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],xmm1[1],zero,zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_5:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],xmm1[1],zero,zero
 ; X64-NEXT:    retq
 entry:
@@ -1065,12 +1065,12 @@ entry:
 
 define <4 x float> @insertps_6(<4 x float> %A, <4 x float> %B) {
 ; X32-LABEL: insertps_6:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = zero,xmm0[1],xmm1[2],zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_6:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = zero,xmm0[1],xmm1[2],zero
 ; X64-NEXT:    retq
 entry:
@@ -1084,12 +1084,12 @@ entry:
 
 define <4 x float> @insertps_7(<4 x float> %A, <4 x float> %B) {
 ; X32-LABEL: insertps_7:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[1],zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_7:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm1[1],zero
 ; X64-NEXT:    retq
 entry:
@@ -1104,12 +1104,12 @@ entry:
 
 define <4 x float> @insertps_8(<4 x float> %A, <4 x float> %B) {
 ; X32-LABEL: insertps_8:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],zero,zero
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_8:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],zero,zero
 ; X64-NEXT:    retq
 entry:
@@ -1124,13 +1124,13 @@ entry:
 
 define <4 x float> @insertps_9(<4 x float> %A, <4 x float> %B) {
 ; X32-LABEL: insertps_9:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    insertps {{.*#+}} xmm1 = zero,xmm0[0],xmm1[2],zero
 ; X32-NEXT:    movaps %xmm1, %xmm0
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: insertps_9:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    insertps {{.*#+}} xmm1 = zero,xmm0[0],xmm1[2],zero
 ; X64-NEXT:    movaps %xmm1, %xmm0
 ; X64-NEXT:    retq
@@ -1144,7 +1144,6 @@ entry:
 }
 
 define <4 x float> @insertps_10(<4 x float> %A)
-{
 ; X32-LABEL: insertps_10:
 ; X32:       ## BB#0:
 ; X32-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
@@ -1154,6 +1153,7 @@ define <4 x float> @insertps_10(<4 x float> %A)
 ; X64:       ## BB#0:
 ; X64-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0],zero
 ; X64-NEXT:    retq
+{
   %vecext = extractelement <4 x float> %A, i32 0
   %vecbuild1 = insertelement <4 x float> <float 0.000000e+00, float 0.000000e+00, float 0.000000e+00, float 0.000000e+00>, float %vecext, i32 0
   %vecbuild2 = insertelement <4 x float> %vecbuild1, float %vecext, i32 2
@@ -1162,13 +1162,13 @@ define <4 x float> @insertps_10(<4 x float> %A)
 
 define <4 x float> @build_vector_to_shuffle_1(<4 x float> %A) {
 ; X32-LABEL: build_vector_to_shuffle_1:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    xorps %xmm1, %xmm1
 ; X32-NEXT:    blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: build_vector_to_shuffle_1:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    xorps %xmm1, %xmm1
 ; X64-NEXT:    blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3]
 ; X64-NEXT:    retq
@@ -1182,13 +1182,13 @@ entry:
 
 define <4 x float> @build_vector_to_shuffle_2(<4 x float> %A) {
 ; X32-LABEL: build_vector_to_shuffle_2:
-; X32:       ## BB#0:
+; X32:       ## BB#0: ## %entry
 ; X32-NEXT:    xorps %xmm1, %xmm1
 ; X32-NEXT:    blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
 ; X32-NEXT:    retl
 ;
 ; X64-LABEL: build_vector_to_shuffle_2:
-; X64:       ## BB#0:
+; X64:       ## BB#0: ## %entry
 ; X64-NEXT:    xorps %xmm1, %xmm1
 ; X64-NEXT:    blendps {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
 ; X64-NEXT:    retq
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll b/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
index 371bf92c5b77..fbc269e91697 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
@@ -1386,7 +1386,7 @@ define <4 x i32> @shuffle_v4i32_z0zX(<4 x i32> %a) {
 ;
 ; AVX-LABEL: shuffle_v4i32_z0zX:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsllq $32, %xmm0
+; AVX-NEXT:    vpsllq $32, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32> <i32 4, i32 0, i32 4, i32 undef>
   ret <4 x i32> %shuffle
@@ -1400,7 +1400,7 @@ define <4 x i32> @shuffle_v4i32_1z3z(<4 x i32> %a) {
 ;
 ; AVX-LABEL: shuffle_v4i32_1z3z:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsrlq $32, %xmm0
+; AVX-NEXT:    vpsrlq $32, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <4 x i32> %a, <4 x i32> zeroinitializer, <4 x i32> <i32 1, i32 4, i32 3, i32 4>
   ret <4 x i32> %shuffle
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
index 109372c836b2..8261b89c3785 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining.ll
@@ -554,24 +554,24 @@ define <4 x i32> @combine_bitwise_ops_test2c(<4 x i32> %a, <4 x i32> %b, <4 x i3
 
 define <4 x i32> @combine_bitwise_ops_test3c(<4 x i32> %a, <4 x i32> %b, <4 x i32> %c) {
 ; SSE2-LABEL: combine_bitwise_ops_test3c:
-; SSE2:      # BB#0:
-; SSE2-NEXT:   xorps %xmm1, %xmm0
-; SSE2-NEXT:   xorps %xmm1, %xmm1
-; SSE2-NEXT:   shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[1,3]
-; SSE2-NEXT:   retq
+; SSE2:       # BB#0:
+; SSE2-NEXT:    xorps %xmm1, %xmm0
+; SSE2-NEXT:    xorps %xmm1, %xmm1
+; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[1,3]
+; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_bitwise_ops_test3c:
-; SSSE3:      # BB#0:
-; SSSE3-NEXT:   xorps %xmm1, %xmm0
-; SSSE3-NEXT:   xorps %xmm1, %xmm1
-; SSSE3-NEXT:   shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[1,3]
-; SSSE3-NEXT:   retq
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    xorps %xmm1, %xmm0
+; SSSE3-NEXT:    xorps %xmm1, %xmm1
+; SSSE3-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,2],xmm1[1,3]
+; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: combine_bitwise_ops_test3c:
-; SSE41:      # BB#0:
-; SSE41-NEXT:   xorps %xmm1, %xmm0
-; SSE41-NEXT:   insertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
-; SSE41-NEXT:   retq
+; SSE41:       # BB#0:
+; SSE41-NEXT:    xorps %xmm1, %xmm0
+; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,2],zero,zero
+; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: combine_bitwise_ops_test3c:
 ; AVX:       # BB#0:
@@ -1148,13 +1148,13 @@ define <4 x float> @combine_test1(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @combine_test2(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_test2:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movss %xmm0, %xmm1
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_test2:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movss %xmm0, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -1256,13 +1256,13 @@ define <4 x i32> @combine_test6(<4 x i32> %a, <4 x i32> %b) {
 define <4 x i32> @combine_test7(<4 x i32> %a, <4 x i32> %b) {
 ; SSE2-LABEL: combine_test7:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movss %xmm0, %xmm1
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_test7:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movss %xmm0, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -1368,13 +1368,13 @@ define <4 x float> @combine_test11(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @combine_test12(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_test12:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movss %xmm0, %xmm1
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_test12:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movss %xmm0, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -1467,13 +1467,13 @@ define <4 x i32> @combine_test16(<4 x i32> %a, <4 x i32> %b) {
 define <4 x i32> @combine_test17(<4 x i32> %a, <4 x i32> %b) {
 ; SSE2-LABEL: combine_test17:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movss %xmm0, %xmm1
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_test17:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movss %xmm0, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -1568,26 +1568,26 @@ define <4 x i32> @combine_test21(<8 x i32> %a, <4 x i32>* %ptr) {
 ; SSE-LABEL: combine_test21:
 ; SSE:       # BB#0:
 ; SSE-NEXT:    movdqa %xmm0, %xmm2
-; SSE-NEXT:    punpcklqdq  {{.*#+}} xmm2 = xmm2[0],xmm1[0]
-; SSE-NEXT:    punpckhqdq  {{.*#+}} xmm0 = xmm0[1],xmm1[1]
-; SSE-NEXT:    movdqa %xmm2,
+; SSE-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm1[0]
+; SSE-NEXT:    punpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
+; SSE-NEXT:    movdqa %xmm2, (%rdi)
 ; SSE-NEXT:    retq
 ;
 ; AVX1-LABEL: combine_test21:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpunpcklqdq  {{.*#+}} xmm2 = xmm0[0],xmm1[0]
-; AVX1-NEXT:    vpunpckhqdq  {{.*#+}} xmm0 = xmm0[1],xmm1[1]
-; AVX1-NEXT:    movdqa %xmm2,
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm0[0],xmm1[0]
+; AVX1-NEXT:    vpunpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
+; AVX1-NEXT:    vmovdqa %xmm2, (%rdi)
 ; AVX1-NEXT:    vzeroupper
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: combine_test21:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vextracti128 $1, %ymm0, %xmm1
-; AVX2-NEXT:    vpunpcklqdq  {{.*#+}} xmm2 = xmm0[0],xmm1[0]
-; AVX2-NEXT:    vpunpckhqdq  {{.*#+}} xmm0 = xmm0[1],xmm1[1]
-; AVX2-NEXT:    movdqa %xmm2,
+; AVX2-NEXT:    vpunpcklqdq {{.*#+}} xmm2 = xmm0[0],xmm1[0]
+; AVX2-NEXT:    vpunpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
+; AVX2-NEXT:    vmovdqa %xmm2, (%rdi)
 ; AVX2-NEXT:    vzeroupper
 ; AVX2-NEXT:    retq
   %1 = shufflevector <8 x i32> %a, <8 x i32> %a, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
@@ -1599,16 +1599,15 @@ define <4 x i32> @combine_test21(<8 x i32> %a, <4 x i32>* %ptr) {
 define <8 x float> @combine_test22(<2 x float>* %a, <2 x float>* %b) {
 ; SSE-LABEL: combine_test22:
 ; SSE:       # BB#0:
-; SSE-NEXT:    movq    (%rdi), %xmm0
-; SSE-NEXT:    movhpd  (%rsi), %xmm0
+; SSE-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
+; SSE-NEXT:    movhpd (%rsi), %xmm0
 ; SSE-NEXT:    retq
 ;
-; AVX1-LABEL: combine_test22:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovq    (%rdi), %xmm0
-; AVX1-NEXT:    vmovhpd  (%rsi), %xmm0, %xmm0
-; AVX1-NEXT:    retq
-;
+; AVX-LABEL: combine_test22:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovq {{.*#+}} xmm0 = mem[0],zero
+; AVX-NEXT:    vmovhpd (%rsi), %xmm0, %xmm0
+; AVX-NEXT:    retq
 ; Current AVX2 lowering of this is still awful, not adding a test case.
   %1 = load <2 x float>* %a, align 8
   %2 = load <2 x float>* %b, align 8
@@ -1641,23 +1640,23 @@ define <4 x float> @combine_test2b(<4 x float> %a, <4 x float> %b) {
 ; SSE2-NEXT:    movlhps {{.*#+}} xmm1 = xmm1[0,0]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
-;
-; SSSE3-LABEL: combine_test2b:
-; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm1[0,0]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: combine_test2b:
-; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm1[0,0]
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: combine_test2b:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm1[0,0]
-; AVX-NEXT:    retq
-  %1 = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
-  %2 = shufflevector <4 x float> %1, <4 x float> %b, <4 x i32> <i32 0, i32 5, i32 0, i32 5>
+;
+; SSSE3-LABEL: combine_test2b:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm1[0,0]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: combine_test2b:
+; SSE41:       # BB#0:
+; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm1[0,0]
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: combine_test2b:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm1[0,0]
+; AVX-NEXT:    retq
+  %1 = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
+  %2 = shufflevector <4 x float> %1, <4 x float> %b, <4 x i32> <i32 0, i32 5, i32 0, i32 5>
   ret <4 x float> %2
 }
 
@@ -1705,44 +1704,44 @@ define <4 x float> @combine_test4b(<4 x float> %a, <4 x float> %b) {
 define <4 x i8> @combine_test1c(<4 x i8>* %a, <4 x i8>* %b) {
 ; SSE2-LABEL: combine_test1c:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movd (%rdi), %xmm1
+; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSE2-NEXT:    movd (%rsi), %xmm0
+; SSE2-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSE2-NEXT:    movss %xmm1, %xmm0
+; SSE2-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_test1c:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movd (%rdi), %xmm1
+; SSSE3-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSSE3-NEXT:    movd (%rsi), %xmm0
+; SSSE3-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSSE3-NEXT:    movss %xmm1, %xmm0
+; SSSE3-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: combine_test1c:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    pmovzxbd (%rdi), %xmm1
-; SSE41-NEXT:    pmovzxbd (%rsi), %xmm0
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3,4,5,6,7]
 ; SSE41-NEXT:    retq
 ;
 ; AVX1-LABEL: combine_test1c:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpmovzxbd (%rdi), %xmm0
-; AVX1-NEXT:    vpmovzxbd (%rsi), %xmm1
+; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3,4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: combine_test1c:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmovzxbd (%rdi), %xmm0
-; AVX2-NEXT:    vpmovzxbd (%rsi), %xmm1
+; AVX2-NEXT:    vpmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; AVX2-NEXT:    vpmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0],xmm1[1,2,3]
 ; AVX2-NEXT:    retq
   %A = load <4 x i8>* %a
@@ -1755,10 +1754,10 @@ define <4 x i8> @combine_test1c(<4 x i8>* %a, <4 x i8>* %b) {
 define <4 x i8> @combine_test2c(<4 x i8>* %a, <4 x i8>* %b) {
 ; SSE2-LABEL: combine_test2c:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movd (%rdi), %xmm0
+; SSE2-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSE2-NEXT:    movd (%rsi), %xmm1
+; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
 ; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
@@ -1766,10 +1765,10 @@ define <4 x i8> @combine_test2c(<4 x i8>* %a, <4 x i8>* %b) {
 ;
 ; SSSE3-LABEL: combine_test2c:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movd (%rdi), %xmm0
+; SSSE3-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; SSSE3-NEXT:    movd (%rsi), %xmm1
+; SSSE3-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
 ; SSSE3-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
@@ -1777,15 +1776,15 @@ define <4 x i8> @combine_test2c(<4 x i8>* %a, <4 x i8>* %b) {
 ;
 ; SSE41-LABEL: combine_test2c:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    pmovzxbd (%rdi), %xmm0
-; SSE41-NEXT:    pmovzxbd (%rsi), %xmm1
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: combine_test2c:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpmovzxbd (%rdi), %xmm0
-; AVX-NEXT:    vpmovzxbd (%rsi), %xmm1
+; AVX-NEXT:    vpmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; AVX-NEXT:    vpmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
 ; AVX-NEXT:    retq
   %A = load <4 x i8>* %a
@@ -1798,10 +1797,10 @@ define <4 x i8> @combine_test2c(<4 x i8>* %a, <4 x i8>* %b) {
 define <4 x i8> @combine_test3c(<4 x i8>* %a, <4 x i8>* %b) {
 ; SSE2-LABEL: combine_test3c:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movd (%rdi), %xmm1
+; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSE2-NEXT:    movd (%rsi), %xmm0
+; SSE2-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
 ; SSE2-NEXT:    punpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
@@ -1809,10 +1808,10 @@ define <4 x i8> @combine_test3c(<4 x i8>* %a, <4 x i8>* %b) {
 ;
 ; SSSE3-LABEL: combine_test3c:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movd (%rdi), %xmm1
+; SSSE3-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSSE3-NEXT:    movd (%rsi), %xmm0
+; SSSE3-NEXT:    movd {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
 ; SSSE3-NEXT:    punpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
@@ -1820,15 +1819,15 @@ define <4 x i8> @combine_test3c(<4 x i8>* %a, <4 x i8>* %b) {
 ;
 ; SSE41-LABEL: combine_test3c:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    pmovzxbd (%rdi), %xmm1
-; SSE41-NEXT:    pmovzxbd (%rsi), %xmm0
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; SSE41-NEXT:    punpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: combine_test3c:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpmovzxbd (%rdi), %xmm0
-; AVX-NEXT:    vpmovzxbd (%rsi), %xmm1
+; AVX-NEXT:    vpmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; AVX-NEXT:    vpmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; AVX-NEXT:    vpunpckhqdq {{.*#+}} xmm0 = xmm1[1],xmm0[1]
 ; AVX-NEXT:    retq
   %A = load <4 x i8>* %a
@@ -1841,10 +1840,10 @@ define <4 x i8> @combine_test3c(<4 x i8>* %a, <4 x i8>* %b) {
 define <4 x i8> @combine_test4c(<4 x i8>* %a, <4 x i8>* %b) {
 ; SSE2-LABEL: combine_test4c:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movd (%rdi), %xmm1
+; SSE2-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSE2-NEXT:    movd (%rsi), %xmm2
+; SSE2-NEXT:    movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
 ; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
 ; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
 ; SSE2-NEXT:    movdqa %xmm2, %xmm0
@@ -1856,10 +1855,10 @@ define <4 x i8> @combine_test4c(<4 x i8>* %a, <4 x i8>* %b) {
 ;
 ; SSSE3-LABEL: combine_test4c:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movd (%rdi), %xmm1
+; SSSE3-NEXT:    movd {{.*#+}} xmm1 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; SSSE3-NEXT:    movd (%rsi), %xmm2
+; SSSE3-NEXT:    movd {{.*#+}} xmm2 = mem[0],zero,zero,zero
 ; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
 ; SSSE3-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
 ; SSSE3-NEXT:    movdqa %xmm2, %xmm0
@@ -1871,22 +1870,22 @@ define <4 x i8> @combine_test4c(<4 x i8>* %a, <4 x i8>* %b) {
 ;
 ; SSE41-LABEL: combine_test4c:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    pmovzxbd (%rdi), %xmm1
-; SSE41-NEXT:    pmovzxbd (%rsi), %xmm0
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; SSE41-NEXT:    pmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3],xmm0[4,5,6,7]
 ; SSE41-NEXT:    retq
 ;
 ; AVX1-LABEL: combine_test4c:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpmovzxbd (%rdi), %xmm0
-; AVX1-NEXT:    vpmovzxbd (%rsi), %xmm1
+; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; AVX1-NEXT:    vpmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3],xmm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: combine_test4c:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpmovzxbd (%rdi), %xmm0
-; AVX2-NEXT:    vpmovzxbd (%rsi), %xmm1
+; AVX2-NEXT:    vpmovzxbd {{.*#+}} xmm0 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
+; AVX2-NEXT:    vpmovzxbd {{.*#+}} xmm1 = mem[0],zero,zero,zero,mem[1],zero,zero,zero,mem[2],zero,zero,zero,mem[3],zero,zero,zero
 ; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2,3]
 ; AVX2-NEXT:    retq
   %A = load <4 x i8>* %a
@@ -1929,12 +1928,12 @@ define <4 x i8> @combine_test4c(<4 x i8>* %a, <4 x i8>* %b) {
 define <4 x float> @combine_blend_01(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_blend_01:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movsd %xmm1, %xmm0
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_blend_01:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movsd %xmm1, %xmm0
+; SSSE3-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: combine_blend_01:
@@ -1954,14 +1953,14 @@ define <4 x float> @combine_blend_01(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @combine_blend_02(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_blend_02:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movss %xmm1, %xmm0
+; SSE2-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[3,0]
 ; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_blend_02:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movss %xmm1, %xmm0
+; SSSE3-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; SSSE3-NEXT:    shufps {{.*#+}} xmm1 = xmm1[2,0],xmm0[3,0]
 ; SSSE3-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0,2]
 ; SSSE3-NEXT:    retq
@@ -1983,13 +1982,13 @@ define <4 x float> @combine_blend_02(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @combine_blend_123(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_blend_123:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movss %xmm0, %xmm1
+; SSE2-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_blend_123:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movss %xmm0, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -2063,12 +2062,12 @@ define <4 x i32> @combine_test_movhl_3(<4 x i32> %a, <4 x i32> %b) {
 define <4 x float> @combine_undef_input_test1(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_undef_input_test1:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movsd %xmm1, %xmm0
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_undef_input_test1:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movsd %xmm1, %xmm0
+; SSSE3-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: combine_undef_input_test1:
@@ -2134,13 +2133,13 @@ define <4 x float> @combine_undef_input_test4(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @combine_undef_input_test5(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_undef_input_test5:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movsd %xmm0, %xmm1
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_undef_input_test5:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movsd %xmm0, %xmm1
+; SSSE3-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -2176,23 +2175,23 @@ define <4 x float> @combine_undef_input_test7(<4 x float> %a) {
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0,0]
 ; SSE2-NEXT:    retq
-;
-; SSSE3-LABEL: combine_undef_input_test7:
-; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: combine_undef_input_test7:
-; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: combine_undef_input_test7:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
-; AVX-NEXT:    retq
-  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 6, i32 0, i32 1, i32 7>
-  %2 = shufflevector <4 x float> %1, <4 x float> %a, <4 x i32> <i32 1, i32 2, i32 4, i32 5>
+;
+; SSSE3-LABEL: combine_undef_input_test7:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: combine_undef_input_test7:
+; SSE41:       # BB#0:
+; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: combine_undef_input_test7:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX-NEXT:    retq
+  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 6, i32 0, i32 1, i32 7>
+  %2 = shufflevector <4 x float> %1, <4 x float> %a, <4 x i32> <i32 1, i32 2, i32 4, i32 5>
   ret <4 x float> %2
 }
 
@@ -2201,23 +2200,23 @@ define <4 x float> @combine_undef_input_test8(<4 x float> %a) {
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0,0]
 ; SSE2-NEXT:    retq
-;
-; SSSE3-LABEL: combine_undef_input_test8:
-; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: combine_undef_input_test8:
-; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: combine_undef_input_test8:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
-; AVX-NEXT:    retq
-  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 0, i32 5, i32 1, i32 7>
-  %2 = shufflevector <4 x float> %1, <4 x float> %a, <4 x i32> <i32 0, i32 2, i32 4, i32 1>
+;
+; SSSE3-LABEL: combine_undef_input_test8:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: combine_undef_input_test8:
+; SSE41:       # BB#0:
+; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: combine_undef_input_test8:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX-NEXT:    retq
+  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 0, i32 5, i32 1, i32 7>
+  %2 = shufflevector <4 x float> %1, <4 x float> %a, <4 x i32> <i32 0, i32 2, i32 4, i32 1>
   ret <4 x float> %2
 }
 
@@ -2248,12 +2247,12 @@ define <4 x float> @combine_undef_input_test10(<4 x float> %a) {
 define <4 x float> @combine_undef_input_test11(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_undef_input_test11:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movsd %xmm1, %xmm0
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_undef_input_test11:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movsd %xmm1, %xmm0
+; SSSE3-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: combine_undef_input_test11:
@@ -2319,13 +2318,13 @@ define <4 x float> @combine_undef_input_test14(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @combine_undef_input_test15(<4 x float> %a, <4 x float> %b) {
 ; SSE2-LABEL: combine_undef_input_test15:
 ; SSE2:       # BB#0:
-; SSE2-NEXT:    movsd %xmm0, %xmm1
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: combine_undef_input_test15:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movsd %xmm0, %xmm1
+; SSSE3-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -2367,23 +2366,23 @@ define <4 x float> @combine_undef_input_test17(<4 x float> %a) {
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0,0]
 ; SSE2-NEXT:    retq
-;
-; SSSE3-LABEL: combine_undef_input_test17:
-; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: combine_undef_input_test17:
-; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: combine_undef_input_test17:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
-; AVX-NEXT:    retq
-  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 6, i32 0, i32 1, i32 7>
-  %2 = shufflevector <4 x float> %a, <4 x float> %1, <4 x i32> <i32 5, i32 6, i32 0, i32 1>
+;
+; SSSE3-LABEL: combine_undef_input_test17:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: combine_undef_input_test17:
+; SSE41:       # BB#0:
+; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: combine_undef_input_test17:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX-NEXT:    retq
+  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 6, i32 0, i32 1, i32 7>
+  %2 = shufflevector <4 x float> %a, <4 x float> %1, <4 x i32> <i32 5, i32 6, i32 0, i32 1>
   ret <4 x float> %2
 }
 
@@ -2392,23 +2391,23 @@ define <4 x float> @combine_undef_input_test18(<4 x float> %a) {
 ; SSE2:       # BB#0:
 ; SSE2-NEXT:    movlhps {{.*#+}} xmm0 = xmm0[0,0]
 ; SSE2-NEXT:    retq
-;
-; SSSE3-LABEL: combine_undef_input_test18:
-; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: combine_undef_input_test18:
-; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
-; SSE41-NEXT:    retq
-;
-; AVX-LABEL: combine_undef_input_test18:
-; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
-; AVX-NEXT:    retq
-  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 0, i32 5, i32 1, i32 7>
-  %2 = shufflevector <4 x float> %a, <4 x float> %1, <4 x i32> <i32 4, i32 6, i32 0, i32 5>
+;
+; SSSE3-LABEL: combine_undef_input_test18:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSSE3-NEXT:    retq
+;
+; SSE41-LABEL: combine_undef_input_test18:
+; SSE41:       # BB#0:
+; SSE41-NEXT:    movddup {{.*#+}} xmm0 = xmm0[0,0]
+; SSE41-NEXT:    retq
+;
+; AVX-LABEL: combine_undef_input_test18:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX-NEXT:    retq
+  %1 = shufflevector <4 x float> %a, <4 x float> undef, <4 x i32> <i32 0, i32 5, i32 1, i32 7>
+  %2 = shufflevector <4 x float> %a, <4 x float> %1, <4 x i32> <i32 4, i32 6, i32 0, i32 5>
   ret <4 x float> %2
 }
 
@@ -2497,6 +2496,26 @@ define <8 x i32> @combine_unneeded_subvector2(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <4 x float> @combine_insertps1(<4 x float> %a, <4 x float> %b) {
+; SSE2-LABEL: combine_insertps1:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movaps %xmm0, %xmm2
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[2,0]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,2],xmm0[1,3]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSE2-NEXT:    movaps %xmm2, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: combine_insertps1:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movaps %xmm0, %xmm2
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[2,0]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[1,2],xmm0[1,3]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSSE3-NEXT:    movaps %xmm2, %xmm0
+; SSSE3-NEXT:    retq
+;
 ; SSE41-LABEL: combine_insertps1:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm1[2],xmm0[1,2,3]
@@ -2513,6 +2532,20 @@ define <4 x float> @combine_insertps1(<4 x float> %a, <4 x float> %b) {
 }
 
 define <4 x float> @combine_insertps2(<4 x float> %a, <4 x float> %b) {
+; SSE2-LABEL: combine_insertps2:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
+; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,2],xmm0[2,3]
+; SSE2-NEXT:    movaps %xmm1, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: combine_insertps2:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,2],xmm0[2,3]
+; SSSE3-NEXT:    movaps %xmm1, %xmm0
+; SSSE3-NEXT:    retq
+;
 ; SSE41-LABEL: combine_insertps2:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],xmm1[2],xmm0[2,3]
@@ -2529,6 +2562,26 @@ define <4 x float> @combine_insertps2(<4 x float> %a, <4 x float> %b) {
 }
 
 define <4 x float> @combine_insertps3(<4 x float> %a, <4 x float> %b) {
+; SSE2-LABEL: combine_insertps3:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movaps %xmm0, %xmm2
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[0,1]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,1],xmm0[1,3]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSE2-NEXT:    movaps %xmm2, %xmm0
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: combine_insertps3:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movaps %xmm0, %xmm2
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[0,1]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,1],xmm0[1,3]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSSE3-NEXT:    movaps %xmm2, %xmm0
+; SSSE3-NEXT:    retq
+;
 ; SSE41-LABEL: combine_insertps3:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],xmm1[0],xmm0[3]
@@ -2545,6 +2598,24 @@ define <4 x float> @combine_insertps3(<4 x float> %a, <4 x float> %b) {
 }
 
 define <4 x float> @combine_insertps4(<4 x float> %a, <4 x float> %b) {
+; SSE2-LABEL: combine_insertps4:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movaps %xmm0, %xmm2
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[0,1]
+; SSE2-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,0],xmm2[0,0]
+; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[2,0],xmm2[2,1]
+; SSE2-NEXT:    retq
+;
+; SSSE3-LABEL: combine_insertps4:
+; SSSE3:       # BB#0:
+; SSSE3-NEXT:    movaps %xmm0, %xmm2
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2],xmm1[0,1]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm2 = xmm2[0,2,1,3]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm0 = xmm0[1,0],xmm2[0,0]
+; SSSE3-NEXT:    shufps {{.*#+}} xmm0 = xmm0[2,0],xmm2[2,1]
+; SSSE3-NEXT:    retq
+;
 ; SSE41-LABEL: combine_insertps4:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll b/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll
index ef60272b6c35..3dbf510dae66 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-sse1.ll
@@ -95,7 +95,7 @@ define <4 x float> @shuffle_v4f32_4zzz(<4 x float> %a) {
 ; SSE1-LABEL: shuffle_v4f32_4zzz:
 ; SSE1:       # BB#0:
 ; SSE1-NEXT:    xorps %xmm1, %xmm1
-; SSE1-NEXT:    movss %xmm0, %xmm1
+; SSE1-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE1-NEXT:    movaps %xmm1, %xmm0
 ; SSE1-NEXT:    retq
   %shuffle = shufflevector <4 x float> zeroinitializer, <4 x float> %a, <4 x i32> <i32 4, i32 1, i32 2, i32 3>
@@ -163,7 +163,7 @@ define <4 x float> @insert_reg_and_zero_v4f32(float %a) {
 ; SSE1-LABEL: insert_reg_and_zero_v4f32:
 ; SSE1:       # BB#0:
 ; SSE1-NEXT:    xorps %xmm1, %xmm1
-; SSE1-NEXT:    movss %xmm0, %xmm1
+; SSE1-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSE1-NEXT:    movaps %xmm1, %xmm0
 ; SSE1-NEXT:    retq
   %v = insertelement <4 x float> undef, float %a, i32 0
@@ -174,7 +174,7 @@ define <4 x float> @insert_reg_and_zero_v4f32(float %a) {
 define <4 x float> @insert_mem_and_zero_v4f32(float* %ptr) {
 ; SSE1-LABEL: insert_mem_and_zero_v4f32:
 ; SSE1:       # BB#0:
-; SSE1-NEXT:    movss (%rdi), %xmm0
+; SSE1-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
 ; SSE1-NEXT:    retq
   %a = load float* %ptr
   %v = insertelement <4 x float> undef, float %a, i32 0
@@ -189,8 +189,8 @@ define <4 x float> @insert_mem_lo_v4f32(<2 x float>* %ptr, <4 x float> %b) {
 ; SSE1-NEXT:    movl %eax, -{{[0-9]+}}(%rsp)
 ; SSE1-NEXT:    shrq $32, %rax
 ; SSE1-NEXT:    movl %eax, -{{[0-9]+}}(%rsp)
-; SSE1-NEXT:    movss -{{[0-9]+}}(%rsp), %xmm1
-; SSE1-NEXT:    movss -{{[0-9]+}}(%rsp), %xmm2
+; SSE1-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; SSE1-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
 ; SSE1-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE1-NEXT:    xorps %xmm2, %xmm2
 ; SSE1-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,1],xmm2[0,1]
@@ -210,8 +210,8 @@ define <4 x float> @insert_mem_hi_v4f32(<2 x float>* %ptr, <4 x float> %b) {
 ; SSE1-NEXT:    movl %eax, -{{[0-9]+}}(%rsp)
 ; SSE1-NEXT:    shrq $32, %rax
 ; SSE1-NEXT:    movl %eax, -{{[0-9]+}}(%rsp)
-; SSE1-NEXT:    movss -{{[0-9]+}}(%rsp), %xmm1
-; SSE1-NEXT:    movss -{{[0-9]+}}(%rsp), %xmm2
+; SSE1-NEXT:    movss {{.*#+}} xmm1 = mem[0],zero,zero,zero
+; SSE1-NEXT:    movss {{.*#+}} xmm2 = mem[0],zero,zero,zero
 ; SSE1-NEXT:    unpcklps {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1]
 ; SSE1-NEXT:    xorps %xmm2, %xmm2
 ; SSE1-NEXT:    shufps {{.*#+}} xmm1 = xmm1[0,1],xmm2[0,1]