3 files changed, 8 insertions, 28 deletions
diff --git a/llvm/test/CodeGen/X86/insertps-combine.ll b/llvm/test/CodeGen/X86/insertps-combine.ll
index f2596b6347b..690707b6870 100644
--- a/llvm/test/CodeGen/X86/insertps-combine.ll
+++ b/llvm/test/CodeGen/X86/insertps-combine.ll
@@ -6,16 +6,12 @@
 define <4 x float> @shuffle_v4f32_0z27(<4 x float> %x, <4 x float> %a) {
 ; SSE-LABEL: shuffle_v4f32_0z27:
 ; SSE:       # BB#0:
-; SSE-NEXT:    xorps %xmm2, %xmm2
-; SSE-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2,3]
-; SSE-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[2]
+; SSE-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],xmm1[2]
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: shuffle_v4f32_0z27:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vxorps %xmm2, %xmm2, %xmm2
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2,3]
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[2]
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],xmm1[2]
 ; AVX-NEXT:    retq
   %vecext = extractelement <4 x float> %x, i32 0
   %vecinit = insertelement <4 x float> undef, float %vecext, i32 0
@@ -50,16 +46,12 @@ define <4 x float> @shuffle_v4f32_0zz4(<4 x float> %xyzw, <4 x float> %abcd) {
 define <4 x float> @shuffle_v4f32_0z24(<4 x float> %xyzw, <4 x float> %abcd) {
 ; SSE-LABEL: shuffle_v4f32_0z24:
 ; SSE:       # BB#0:
-; SSE-NEXT:    xorps %xmm2, %xmm2
-; SSE-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2,3]
-; SSE-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
+; SSE-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],xmm1[0]
 ; SSE-NEXT:    retq
 ;
 ; AVX-LABEL: shuffle_v4f32_0z24:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vxorps %xmm2, %xmm2, %xmm2
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm2[1],xmm0[2,3]
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1,2],xmm1[0]
+; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],xmm1[0]
 ; AVX-NEXT:    retq
   %vecext = extractelement <4 x float> %xyzw, i32 0
   %vecinit = insertelement <4 x float> undef, float %vecext, i32 0
diff --git a/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll b/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
index 2d6d3b6a0fb..5c6efe6eb2c 100644
--- a/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
+++ b/llvm/test/CodeGen/X86/merge-consecutive-loads-128.ll
@@ -159,15 +159,13 @@ define <4 x float> @merge_4f32_f32_012u(float* %ptr) nounwind uwtable noinline s
 ;
 ; SSE41-LABEL: merge_4f32_f32_012u:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
+; SSE41-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: merge_4f32_f32_012u:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
+; AVX-NEXT:    vmovq {{.*#+}} xmm0 = mem[0],zero
 ; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
 ; AVX-NEXT:    retq
   %ptr0 = getelementptr inbounds float, float* %ptr, i64 0
@@ -195,15 +193,13 @@ define <4 x float> @merge_4f32_f32_019u(float* %ptr) nounwind uwtable noinline s
 ;
 ; SSE41-LABEL: merge_4f32_f32_019u:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    movss {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
+; SSE41-NEXT:    movq {{.*#+}} xmm0 = mem[0],zero
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: merge_4f32_f32_019u:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovss {{.*#+}} xmm0 = mem[0],zero,zero,zero
-; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],mem[0],xmm0[2,3]
+; AVX-NEXT:    vmovq {{.*#+}} xmm0 = mem[0],zero
 ; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0,1],mem[0],xmm0[3]
 ; AVX-NEXT:    retq
   %ptr0 = getelementptr inbounds float, float* %ptr, i64 0
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll b/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
index 53dbb32235a..9187f3513d6 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-128-v4.ll
@@ -1080,15 +1080,11 @@ define <4 x float> @shuffle_v4f32_0zz6(<4 x float> %a, <4 x float> %b) {
 ; SSE41-LABEL: shuffle_v4f32_0zz6:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,zero,xmm1[2]
-; SSE41-NEXT:    xorps %xmm1, %xmm1
-; SSE41-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2],xmm0[3]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: shuffle_v4f32_0zz6:
 ; AVX:       # BB#0:
 ; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],zero,zero,xmm1[2]
-; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2],xmm0[3]
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 undef, i32 undef, i32 6>
   %shuffle1 = shufflevector <4 x float> zeroinitializer, <4 x float> %shuffle, <4 x i32> <i32 4, i32 1, i32 2, i32 7>
@@ -1129,15 +1125,11 @@ define <4 x float> @shuffle_v4f32_0z24(<4 x float> %a, <4 x float> %b) {
 ; SSE41-LABEL: shuffle_v4f32_0z24:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    insertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],xmm1[0]
-; SSE41-NEXT:    xorps %xmm1, %xmm1
-; SSE41-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: shuffle_v4f32_0z24:
 ; AVX:       # BB#0:
 ; AVX-NEXT:    vinsertps {{.*#+}} xmm0 = xmm0[0],zero,xmm0[2],xmm1[0]
-; AVX-NEXT:    vxorps %xmm1, %xmm1, %xmm1
-; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2,3]
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <4 x float> %a, <4 x float> %b, <4 x i32> <i32 0, i32 undef, i32 2, i32 4>
   %shuffle1 = shufflevector <4 x float> zeroinitializer, <4 x float> %shuffle, <4 x i32> <i32 4, i32 1, i32 6, i32 7>