From: Chandler Carruth <chandlerc@gmail.com>
Date: Wed, 4 Feb 2015 10:46:53 +0000 (+0000)
Subject: [x86] Mechanically update a bunch of tests' check lines using the latest
X-Git-Url: http://plrg.eecs.uci.edu/git/?a=commitdiff_plain;h=424a198c304955133a0d975f57c4b35890455834;p=oota-llvm.git

[x86] Mechanically update a bunch of tests' check lines using the latest
version of the script.

Changes include:
- Using the VEX prefix
- Skipping more detail when we have useful shuffle comments to match
- Matching more shuffle comments that have been added to the printer
  (yay!)
- Matching the destination registers of some AVX instructions
- Stripping trailing whitespace that crept in
- Fixing indentation issues

Nothing interesting going on here. I'm just trying really hard to ensure
these changes don't show up in the diffs with actual changes to the
backend.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@228132 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/test/CodeGen/X86/vector-blend.ll b/test/CodeGen/X86/vector-blend.ll
index f23b8288385..39b2192a4f2 100644
--- a/test/CodeGen/X86/vector-blend.ll
+++ b/test/CodeGen/X86/vector-blend.ll
@@ -38,13 +38,13 @@ entry:
 define <4 x float> @vsel_float2(<4 x float> %v1, <4 x float> %v2) {
 ; SSE2-LABEL: vsel_float2:
 ; SSE2:       # BB#0: # %entry
-; 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: vsel_float2:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movss %xmm0, %xmm1
+; SSSE3-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -55,7 +55,7 @@ define <4 x float> @vsel_float2(<4 x float> %v1, <4 x float> %v2) {
 ;
 ; AVX-LABEL: vsel_float2:
 ; AVX:       # BB#0: # %entry
-; AVX-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2,3]
+; AVX-NEXT:    vblendps {{.*#+}} xmm0 = xmm0[0],xmm1[1,2,3]
 ; AVX-NEXT:    retq
 entry:
   %vsel = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x float> %v1, <4 x float> %v2
@@ -167,13 +167,13 @@ entry:
 define <2 x double> @vsel_double(<2 x double> %v1, <2 x double> %v2) {
 ; SSE2-LABEL: vsel_double:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm0, %xmm1
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: vsel_double:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm0, %xmm1
+; SSSE3-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -194,13 +194,13 @@ entry:
 define <2 x i64> @vsel_i64(<2 x i64> %v1, <2 x i64> %v2) {
 ; SSE2-LABEL: vsel_i64:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm0, %xmm1
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSE2-NEXT:    movaps %xmm1, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: vsel_i64:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm0, %xmm1
+; SSSE3-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; SSSE3-NEXT:    movaps %xmm1, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -291,16 +291,16 @@ entry:
 define <8 x float> @vsel_float8(<8 x float> %v1, <8 x float> %v2) {
 ; SSE2-LABEL: vsel_float8:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movss %xmm0, %xmm2
-; SSE2-NEXT:    movss %xmm1, %xmm3
+; SSE2-NEXT:    movss {{.*#+}} xmm2 = xmm0[0],xmm2[1,2,3]
+; SSE2-NEXT:    movss {{.*#+}} xmm3 = xmm1[0],xmm3[1,2,3]
 ; SSE2-NEXT:    movaps %xmm2, %xmm0
 ; SSE2-NEXT:    movaps %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: vsel_float8:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movss %xmm0, %xmm2
-; SSSE3-NEXT:    movss %xmm1, %xmm3
+; SSSE3-NEXT:    movss {{.*#+}} xmm2 = xmm0[0],xmm2[1,2,3]
+; SSSE3-NEXT:    movss {{.*#+}} xmm3 = xmm1[0],xmm3[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm2, %xmm0
 ; SSSE3-NEXT:    movaps %xmm3, %xmm1
 ; SSSE3-NEXT:    retq
@@ -323,16 +323,16 @@ entry:
 define <8 x i32> @vsel_i328(<8 x i32> %v1, <8 x i32> %v2) {
 ; SSE2-LABEL: vsel_i328:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movss %xmm0, %xmm2
-; SSE2-NEXT:    movss %xmm1, %xmm3
+; SSE2-NEXT:    movss {{.*#+}} xmm2 = xmm0[0],xmm2[1,2,3]
+; SSE2-NEXT:    movss {{.*#+}} xmm3 = xmm1[0],xmm3[1,2,3]
 ; SSE2-NEXT:    movaps %xmm2, %xmm0
 ; SSE2-NEXT:    movaps %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: vsel_i328:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movss %xmm0, %xmm2
-; SSSE3-NEXT:    movss %xmm1, %xmm3
+; SSSE3-NEXT:    movss {{.*#+}} xmm2 = xmm0[0],xmm2[1,2,3]
+; SSSE3-NEXT:    movss {{.*#+}} xmm3 = xmm1[0],xmm3[1,2,3]
 ; SSSE3-NEXT:    movaps %xmm2, %xmm0
 ; SSSE3-NEXT:    movaps %xmm3, %xmm1
 ; SSSE3-NEXT:    retq
@@ -360,8 +360,8 @@ entry:
 define <8 x double> @vsel_double8(<8 x double> %v1, <8 x double> %v2) {
 ; SSE2-LABEL: vsel_double8:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm0, %xmm4
-; SSE2-NEXT:    movsd %xmm2, %xmm6
+; SSE2-NEXT:    movsd {{.*#+}} xmm4 = xmm0[0],xmm4[1]
+; SSE2-NEXT:    movsd {{.*#+}} xmm6 = xmm2[0],xmm6[1]
 ; SSE2-NEXT:    movaps %xmm4, %xmm0
 ; SSE2-NEXT:    movaps %xmm5, %xmm1
 ; SSE2-NEXT:    movaps %xmm6, %xmm2
@@ -370,8 +370,8 @@ define <8 x double> @vsel_double8(<8 x double> %v1, <8 x double> %v2) {
 ;
 ; SSSE3-LABEL: vsel_double8:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm0, %xmm4
-; SSSE3-NEXT:    movsd %xmm2, %xmm6
+; SSSE3-NEXT:    movsd {{.*#+}} xmm4 = xmm0[0],xmm4[1]
+; SSSE3-NEXT:    movsd {{.*#+}} xmm6 = xmm2[0],xmm6[1]
 ; SSSE3-NEXT:    movaps %xmm4, %xmm0
 ; SSSE3-NEXT:    movaps %xmm5, %xmm1
 ; SSSE3-NEXT:    movaps %xmm6, %xmm2
@@ -399,8 +399,8 @@ entry:
 define <8 x i64> @vsel_i648(<8 x i64> %v1, <8 x i64> %v2) {
 ; SSE2-LABEL: vsel_i648:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm0, %xmm4
-; SSE2-NEXT:    movsd %xmm2, %xmm6
+; SSE2-NEXT:    movsd {{.*#+}} xmm4 = xmm0[0],xmm4[1]
+; SSE2-NEXT:    movsd {{.*#+}} xmm6 = xmm2[0],xmm6[1]
 ; SSE2-NEXT:    movaps %xmm4, %xmm0
 ; SSE2-NEXT:    movaps %xmm5, %xmm1
 ; SSE2-NEXT:    movaps %xmm6, %xmm2
@@ -409,8 +409,8 @@ define <8 x i64> @vsel_i648(<8 x i64> %v1, <8 x i64> %v2) {
 ;
 ; SSSE3-LABEL: vsel_i648:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm0, %xmm4
-; SSSE3-NEXT:    movsd %xmm2, %xmm6
+; SSSE3-NEXT:    movsd {{.*#+}} xmm4 = xmm0[0],xmm4[1]
+; SSSE3-NEXT:    movsd {{.*#+}} xmm6 = xmm2[0],xmm6[1]
 ; SSSE3-NEXT:    movaps %xmm4, %xmm0
 ; SSSE3-NEXT:    movaps %xmm5, %xmm1
 ; SSSE3-NEXT:    movaps %xmm6, %xmm2
@@ -444,16 +444,16 @@ entry:
 define <4 x double> @vsel_double4(<4 x double> %v1, <4 x double> %v2) {
 ; SSE2-LABEL: vsel_double4:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm0, %xmm2
-; SSE2-NEXT:    movsd %xmm1, %xmm3
+; SSE2-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
+; SSE2-NEXT:    movsd {{.*#+}} xmm3 = xmm1[0],xmm3[1]
 ; SSE2-NEXT:    movaps %xmm2, %xmm0
 ; SSE2-NEXT:    movaps %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: vsel_double4:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm0, %xmm2
-; SSSE3-NEXT:    movsd %xmm1, %xmm3
+; SSSE3-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
+; SSSE3-NEXT:    movsd {{.*#+}} xmm3 = xmm1[0],xmm3[1]
 ; SSSE3-NEXT:    movaps %xmm2, %xmm0
 ; SSSE3-NEXT:    movaps %xmm3, %xmm1
 ; SSSE3-NEXT:    retq
@@ -556,14 +556,14 @@ entry:
 define <4 x double> @constant_blendvpd_avx(<4 x double> %xy, <4 x double> %ab) {
 ; SSE2-LABEL: constant_blendvpd_avx:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm1, %xmm3
+; SSE2-NEXT:    movsd {{.*#+}} xmm3 = xmm1[0],xmm3[1]
 ; SSE2-NEXT:    movaps %xmm2, %xmm0
 ; SSE2-NEXT:    movaps %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: constant_blendvpd_avx:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm1, %xmm3
+; SSSE3-NEXT:    movsd {{.*#+}} xmm3 = xmm1[0],xmm3[1]
 ; SSSE3-NEXT:    movaps %xmm2, %xmm0
 ; SSSE3-NEXT:    movaps %xmm3, %xmm1
 ; SSSE3-NEXT:    retq
@@ -709,7 +709,7 @@ entry:
 define <8 x float> @blend_shufflevector_8xfloat(<8 x float> %a, <8 x float> %b) {
 ; SSE2-LABEL: blend_shufflevector_8xfloat:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movss %xmm0, %xmm2
+; SSE2-NEXT:    movss {{.*#+}} xmm2 = xmm0[0],xmm2[1,2,3]
 ; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[2,0],xmm3[3,0]
 ; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[0,1],xmm1[0,2]
 ; SSE2-NEXT:    movaps %xmm2, %xmm0
@@ -718,7 +718,7 @@ define <8 x float> @blend_shufflevector_8xfloat(<8 x float> %a, <8 x float> %b)
 ;
 ; SSSE3-LABEL: blend_shufflevector_8xfloat:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movss %xmm0, %xmm2
+; SSSE3-NEXT:    movss {{.*#+}} xmm2 = xmm0[0],xmm2[1,2,3]
 ; SSSE3-NEXT:    shufps {{.*#+}} xmm1 = xmm1[2,0],xmm3[3,0]
 ; SSSE3-NEXT:    shufps {{.*#+}} xmm3 = xmm3[0,1],xmm1[0,2]
 ; SSSE3-NEXT:    movaps %xmm2, %xmm0
@@ -743,13 +743,13 @@ entry:
 define <4 x double> @blend_shufflevector_4xdouble(<4 x double> %a, <4 x double> %b) {
 ; SSE2-LABEL: blend_shufflevector_4xdouble:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm0, %xmm2
+; SSE2-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
 ; SSE2-NEXT:    movaps %xmm2, %xmm0
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: blend_shufflevector_4xdouble:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm0, %xmm2
+; SSSE3-NEXT:    movsd {{.*#+}} xmm2 = xmm0[0],xmm2[1]
 ; SSSE3-NEXT:    movaps %xmm2, %xmm0
 ; SSSE3-NEXT:    retq
 ;
@@ -770,13 +770,13 @@ entry:
 define <4 x i64> @blend_shufflevector_4xi64(<4 x i64> %a, <4 x i64> %b) {
 ; SSE2-LABEL: blend_shufflevector_4xi64:
 ; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    movsd %xmm2, %xmm0
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
 ; SSE2-NEXT:    movaps %xmm3, %xmm1
 ; SSE2-NEXT:    retq
 ;
 ; SSSE3-LABEL: blend_shufflevector_4xi64:
 ; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    movsd %xmm2, %xmm0
+; SSSE3-NEXT:    movsd {{.*#+}} xmm0 = xmm2[0],xmm0[1]
 ; SSSE3-NEXT:    movaps %xmm3, %xmm1
 ; SSSE3-NEXT:    retq
 ;
diff --git a/test/CodeGen/X86/vector-shuffle-128-v16.ll b/test/CodeGen/X86/vector-shuffle-128-v16.ll
index 74067304664..e22fb473b13 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v16.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v16.ll
@@ -719,7 +719,7 @@ define <16 x i8> @shuffle_v16i8_zz_zz_19_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz(
 ; AVX-LABEL: shuffle_v16i8_zz_zz_19_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
 ; AVX:       # BB#0:
 ; AVX-NEXT:    vmovd %edi, %xmm0
-; AVX-NEXT:    vpslld $24, %xmm0
+; AVX-NEXT:    vpslld $24, %xmm0, %xmm0
 ; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
 ; AVX-NEXT:    retq
   %a = insertelement <16 x i8> undef, i8 %i, i32 3
@@ -1197,7 +1197,7 @@ define <16 x i8> @shuffle_v16i8_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_14(
 ;
 ; AVX-LABEL: shuffle_v16i8_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_14:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsllw $8, %xmm0
+; AVX-NEXT:    vpsllw $8, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 16, i32 0, i32 16, i32 2, i32 16, i32 4, i32 16, i32 6, i32 16, i32 8, i32 16, i32 10, i32 16, i32 12, i32 16, i32 14>
   ret <16 x i8> %shuffle
@@ -1211,7 +1211,7 @@ define <16 x i8> @shuffle_v16i8_zz_zz_zz_00_zz_zz_zz_04_zz_zz_zz_08_zz_zz_zz_12(
 ;
 ; AVX-LABEL: shuffle_v16i8_zz_zz_zz_00_zz_zz_zz_04_zz_zz_zz_08_zz_zz_zz_12:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpslld $24, %xmm0
+; AVX-NEXT:    vpslld $24, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 16, i32 16, i32 16, i32 0, i32 16, i32 16, i32 16, i32 4, i32 16, i32 16, i32 16, i32 8, i32 16, i32 16, i32 16, i32 12>
   ret <16 x i8> %shuffle
@@ -1225,7 +1225,7 @@ define <16 x i8> @shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_00_zz_zz_zz_zz_zz_zz_zz_08(
 ;
 ; AVX-LABEL: shuffle_v16i8_zz_zz_zz_zz_zz_zz_zz_00_zz_zz_zz_zz_zz_zz_zz_08:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsllq $56, %xmm0
+; AVX-NEXT:    vpsllq $56, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 8>
   ret <16 x i8> %shuffle
@@ -1239,7 +1239,7 @@ define <16 x i8> @shuffle_v16i8_zz_00_uu_02_03_uu_05_06_zz_08_09_uu_11_12_13_14(
 ;
 ; AVX-LABEL: shuffle_v16i8_zz_00_uu_02_03_uu_05_06_zz_08_09_uu_11_12_13_14:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsllq $8, %xmm0
+; AVX-NEXT:    vpsllq $8, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 16, i32 0, i32 undef, i32 2, i32 3, i32 undef, i32 5, i32 6, i32 16, i32 8, i32 9, i32 undef, i32 11, i32 12, i32 13, i32 14>
   ret <16 x i8> %shuffle
@@ -1253,7 +1253,7 @@ define <16 x i8> @shuffle_v16i8_01_uu_uu_uu_uu_zz_uu_zz_uu_zz_11_zz_13_zz_15_zz(
 ;
 ; AVX-LABEL: shuffle_v16i8_01_uu_uu_uu_uu_zz_uu_zz_uu_zz_11_zz_13_zz_15_zz:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsrlw $8, %xmm0
+; AVX-NEXT:    vpsrlw $8, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 16, i32 undef, i32 16, i32 undef, i32 16, i32 11, i32 16, i32 13, i32 16, i32 15, i32 16>
   ret <16 x i8> %shuffle
@@ -1267,7 +1267,7 @@ define <16 x i8> @shuffle_v16i8_02_03_zz_zz_06_07_uu_uu_uu_uu_uu_uu_14_15_zz_zz(
 ;
 ; AVX-LABEL: shuffle_v16i8_02_03_zz_zz_06_07_uu_uu_uu_uu_uu_uu_14_15_zz_zz:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsrld $16, %xmm0
+; AVX-NEXT:    vpsrld $16, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 2, i32 3, i32 16, i32 16, i32 6, i32 7, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 14, i32 15, i32 16, i32 16>
   ret <16 x i8> %shuffle
@@ -1281,7 +1281,7 @@ define <16 x i8> @shuffle_v16i8_07_zz_zz_zz_zz_zz_uu_uu_15_uu_uu_uu_uu_uu_zz_zz(
 ;
 ; AVX-LABEL: shuffle_v16i8_07_zz_zz_zz_zz_zz_uu_uu_15_uu_uu_uu_uu_uu_zz_zz:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vpsrlq $56, %xmm0
+; AVX-NEXT:    vpsrlq $56, %xmm0, %xmm0
 ; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32><i32 7, i32 16, i32 16, i32 16, i32 16, i32 16, i32 undef, i32 undef, i32 15, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 16, i32 16>
   ret <16 x i8> %shuffle
diff --git a/test/CodeGen/X86/vector-shuffle-128-v2.ll b/test/CodeGen/X86/vector-shuffle-128-v2.ll
index 2d944166faf..710c9dd5f06 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v2.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v2.ll
@@ -1091,22 +1091,22 @@ define <2 x double> @insert_dup_mem_v2f64(double* %ptr) {
 ;
 ; SSE3-LABEL: insert_dup_mem_v2f64:
 ; SSE3:       # BB#0:
-; SSE3-NEXT:    movddup (%rdi), %xmm0
+; SSE3-NEXT:    movddup {{.*#+}} xmm0 = mem[0,0]
 ; SSE3-NEXT:    retq
 ;
 ; SSSE3-LABEL: insert_dup_mem_v2f64:
 ; SSSE3:       # BB#0:
-; SSSE3-NEXT:    movddup (%rdi), %xmm0
+; SSSE3-NEXT:    movddup {{.*#+}} xmm0 = mem[0,0]
 ; SSSE3-NEXT:    retq
 ;
 ; SSE41-LABEL: insert_dup_mem_v2f64:
 ; SSE41:       # BB#0:
-; SSE41-NEXT:    movddup (%rdi), %xmm0
+; SSE41-NEXT:    movddup {{.*#+}} xmm0 = mem[0,0]
 ; SSE41-NEXT:    retq
 ;
 ; AVX-LABEL: insert_dup_mem_v2f64:
 ; AVX:       # BB#0:
-; AVX-NEXT:    vmovddup (%rdi), %xmm0
+; AVX-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
 ; AVX-NEXT:    retq
   %a = load double* %ptr
   %v = insertelement <2 x double> undef, double %a, i32 0
diff --git a/test/CodeGen/X86/vector-shuffle-256-v16.ll b/test/CodeGen/X86/vector-shuffle-256-v16.ll
index b37447a707f..bdfaaa58608 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v16.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v16.ll
@@ -1383,7 +1383,7 @@ define <16 x i16> @shuffle_v16i16_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_1
 ;
 ; AVX2-LABEL: shuffle_v16i16_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_14:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpslld $16, %ymm0
+; AVX2-NEXT:    vpslld $16, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <16 x i32> <i32 16, i32 0, i32 16, i32 2, i32 16, i32 4, i32 16, i32 6, i32 16, i32 8, i32 16, i32 10, i32 16, i32 12, i32 16, i32 14>
   ret <16 x i16> %shuffle
@@ -1410,7 +1410,7 @@ define <16 x i16> @shuffle_v16i16_zz_zz_zz_00_zz_zz_zz_04_zz_zz_zz_08_zz_zz_zz_1
 ;
 ; AVX2-LABEL: shuffle_v16i16_zz_zz_zz_00_zz_zz_zz_04_zz_zz_zz_08_zz_zz_zz_12:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsllq $48, %ymm0
+; AVX2-NEXT:    vpsllq $48, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <16 x i32> <i32 16, i32 16, i32 16, i32 0, i32 16, i32 16, i32 16, i32 4, i32 16, i32 16, i32 16, i32 8, i32 16, i32 16, i32 16, i32 12>
   ret <16 x i16> %shuffle
@@ -1432,7 +1432,7 @@ define <16 x i16> @shuffle_v16i16_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_z
 ;
 ; AVX2-LABEL: shuffle_v16i16_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrld $16, %ymm0
+; AVX2-NEXT:    vpsrld $16, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <16 x i32> <i32 1, i32 16, i32 3, i32 16, i32 5, i32 16, i32 7, i32 16, i32 9, i32 16, i32 11, i32 16, i32 13, i32 16, i32 15, i32 16>
   ret <16 x i16> %shuffle
@@ -1461,7 +1461,7 @@ define <16 x i16> @shuffle_v16i16_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_z
 ;
 ; AVX2-LABEL: shuffle_v16i16_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_zz:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlq $32, %ymm0
+; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> zeroinitializer, <16 x i32> <i32 2, i32 3, i32 16, i32 16, i32 6, i32 7, i32 16, i32 16, i32 10, i32 11, i32 16, i32 16, i32 14, i32 15, i32 16, i32 16>
   ret <16 x i16> %shuffle
diff --git a/test/CodeGen/X86/vector-shuffle-256-v32.ll b/test/CodeGen/X86/vector-shuffle-256-v32.ll
index f2e49262b2e..e0e3ade0bcf 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v32.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v32.ll
@@ -1667,7 +1667,7 @@ define <32 x i8> @shuffle_v32i8_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_14_
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpshuflw $0, %xmm3, %xmm3 # xmm3 = xmm3[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[0,0,0,0,4,5,6,7]
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm3[0],xmm0[0],xmm3[1],xmm0[1],xmm3[2],xmm0[2],xmm3[3],xmm0[3],xmm3[4],xmm0[4],xmm3[5],xmm0[5],xmm3[6],xmm0[6],xmm3[7],xmm0[7]
@@ -1676,7 +1676,7 @@ define <32 x i8> @shuffle_v32i8_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_14_
 ;
 ; AVX2-LABEL: shuffle_v32i8_zz_00_zz_02_zz_04_zz_06_zz_08_zz_10_zz_12_zz_14_zz_16_zz_18_zz_20_zz_22_zz_24_zz_26_zz_28_zz_30:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsllw $8, %ymm0
+; AVX2-NEXT:    vpsllw $8, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 32, i32 0, i32 32, i32 2, i32 32, i32 4, i32 32, i32 6, i32 32, i32 8, i32 32, i32 10, i32 32, i32 12, i32 32, i32 14, i32 32, i32 16, i32 32, i32 18, i32 32, i32 20, i32 32, i32 22, i32 32, i32 24, i32 32, i32 26, i32 32, i32 28, i32 32, i32 30>
   ret <32 x i8> %shuffle
@@ -1698,7 +1698,7 @@ define <32 x i8> @shuffle_v32i8_zz_zz_00_01_zz_zz_04_05_zz_zz_08_09_zz_zz_12_13_
 ;
 ; AVX2-LABEL: shuffle_v32i8_zz_zz_00_01_zz_zz_04_05_zz_zz_08_09_zz_zz_12_13_zz_zz_16_17_zz_zz_20_21_zz_zz_24_25_zz_zz_28_29:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpslld $16, %ymm0
+; AVX2-NEXT:    vpslld $16, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 32, i32 32, i32 0, i32 1, i32 32, i32 32, i32 4, i32 5, i32 32, i32 32, i32 8, i32 9, i32 32, i32 32, i32 12, i32 13, i32 32, i32 32, i32 16, i32 17, i32 32, i32 32, i32 20, i32 21, i32 32, i32 32, i32 24, i32 25, i32 32, i32 32, i32 28, i32 29>
   ret <32 x i8> %shuffle
@@ -1720,7 +1720,7 @@ define <32 x i8> @shuffle_v32i8_zz_zz_zz_zz_zz_zz_00_01_zz_zz_zz_zz_zz_zz_08_09_
 ;
 ; AVX2-LABEL: shuffle_v32i8_zz_zz_zz_zz_zz_zz_00_01_zz_zz_zz_zz_zz_zz_08_09_zz_zz_zz_zz_zz_zz_16_17_zz_zz_zz_zz_zz_zz_24_25:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsllq $48, %ymm0
+; AVX2-NEXT:    vpsllq $48, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 0, i32 1, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 8, i32 9, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 16, i32 17, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 24, i32 25>
   ret <32 x i8> %shuffle
@@ -1734,7 +1734,7 @@ define <32 x i8> @shuffle_v32i8_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpshuflw $0, %xmm3, %xmm3 # xmm3 = xmm3[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[0,0,0,0,4,5,6,7]
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0],xmm3[0],xmm1[1],xmm3[1],xmm1[2],xmm3[2],xmm1[3],xmm3[3],xmm1[4],xmm3[4],xmm1[5],xmm3[5],xmm1[6],xmm3[6],xmm1[7],xmm3[7]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
@@ -1743,7 +1743,7 @@ define <32 x i8> @shuffle_v32i8_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_
 ;
 ; AVX2-LABEL: shuffle_v32i8_01_zz_03_zz_05_zz_07_zz_09_zz_11_zz_13_zz_15_zz_17_zz_19_zz_21_zz_23_zz_25_zz_27_zz_29_zz_31_zz:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlw $8, %ymm0
+; AVX2-NEXT:    vpsrlw $8, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 1, i32 32, i32 3, i32 32, i32 5, i32 32, i32 7, i32 32, i32 9, i32 32, i32 11, i32 32, i32 13, i32 32, i32 15, i32 32, i32 17, i32 32, i32 19, i32 32, i32 21, i32 32, i32 23, i32 32, i32 25, i32 32, i32 27, i32 32, i32 29, i32 32, i32 31, i32 32>
   ret <32 x i8> %shuffle
@@ -1765,7 +1765,7 @@ define <32 x i8> @shuffle_v32i8_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_zz_
 ;
 ; AVX2-LABEL: shuffle_v32i8_02_03_zz_zz_06_07_zz_zz_10_11_zz_zz_14_15_zz_zz_18_19_zz_zz_22_23_zz_zz_26_27_zz_zz_30_31_zz_zz:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrld $16, %ymm0
+; AVX2-NEXT:    vpsrld $16, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 2, i32 3, i32 32, i32 32, i32 6, i32 7, i32 32, i32 32, i32 10, i32 11, i32 32, i32 32, i32 14, i32 15, i32 32, i32 32, i32 18, i32 19, i32 32, i32 32, i32 22, i32 23, i32 32, i32 32, i32 26, i32 27, i32 32, i32 32, i32 30, i32 31, i32 32, i32 32>
   ret <32 x i8> %shuffle
@@ -1791,7 +1791,7 @@ define <32 x i8> @shuffle_v32i8_07_zz_zz_zz_zz_zz_zz_zz_15_zz_zz_zz_zz_z_zz_zz_2
 ;
 ; AVX2-LABEL: shuffle_v32i8_07_zz_zz_zz_zz_zz_zz_zz_15_zz_zz_zz_zz_z_zz_zz_23_zz_zz_zz_zz_zz_zz_zz_31_zz_zz_zz_zz_zz_zz_zz:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlq $56, %ymm0
+; AVX2-NEXT:    vpsrlq $56, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> zeroinitializer, <32 x i32> <i32 7, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 15, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 23, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 31, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32>
   ret <32 x i8> %shuffle
@@ -1812,12 +1812,12 @@ define <32 x i8> @shuffle_v32i8_32_zz_zz_zz_zz_zz_zz_zz_33_zz_zz_zz_zz_zz_zz_zz_
 ; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
-
 ;
 ; AVX2-LABEL: shuffle_v32i8_32_zz_zz_zz_zz_zz_zz_zz_33_zz_zz_zz_zz_zz_zz_zz_34_zz_zz_zz_zz_zz_zz_zz_35_zz_zz_zz_zz_zz_zz_zz:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpmovzxbq {{.*#+}} ymm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,xmm0[1],zero,zero,zero,zero,zero,zero,zero,xmm0[2],zero,zero,zero,zero,zero,zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero
 ; AVX2-NEXT:    retq
+
   %shuffle = shufflevector <32 x i8> zeroinitializer, <32 x i8> %a, <32 x i32> <i32 32, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 33, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 34, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 35, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
   ret <32 x i8> %shuffle
 }
diff --git a/test/CodeGen/X86/vector-shuffle-256-v4.ll b/test/CodeGen/X86/vector-shuffle-256-v4.ll
index 5905db26c4d..11a9da1fe48 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v4.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v4.ll
@@ -749,21 +749,8 @@ define <4 x i64> @shuffle_v4i64_0415(<4 x i64> %a, <4 x i64> %b) {
 }
 
 define <4 x i64> @stress_test1(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: stress_test1:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm1[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*#+}} ymm2 = ymm0[1,0,3,2]
-; AVX1-NEXT:    vblendpd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2,3]
-; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,3,2]
-; AVX1-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: stress_test1:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm1[3,1,1,0]
-; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[3,3,1,3]
-; AVX2-NEXT:    vpunpckhqdq {{.*#+}} ymm0 = ymm1[1],ymm0[1],ymm1[3],ymm0[3]
-; AVX2-NEXT:    retq
+; ALL-LABEL: stress_test1:
+; ALL:         retq
   %c = shufflevector <4 x i64> %b, <4 x i64> undef, <4 x i32> <i32 3, i32 1, i32 1, i32 0>
   %d = shufflevector <4 x i64> %c, <4 x i64> undef, <4 x i32> <i32 3, i32 undef, i32 2, i32 undef>
   %e = shufflevector <4 x i64> %b, <4 x i64> undef, <4 x i32> <i32 3, i32 3, i32 1, i32 undef>
@@ -847,7 +834,7 @@ define <4 x double> @splat_mem_v4f64(double* %ptr) {
 define <4 x i64> @splat_mem_v4i64(i64* %ptr) {
 ; AVX1-LABEL: splat_mem_v4i64:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovddup (%rdi), %xmm0
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
diff --git a/test/CodeGen/X86/vector-shuffle-256-v8.ll b/test/CodeGen/X86/vector-shuffle-256-v8.ll
index 06a6b68b808..ffbec325b85 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v8.ll
@@ -1862,7 +1862,7 @@ define <8 x i32> @shuffle_v8i32_z0U2zUz6(<8 x i32> %a) {
 ;
 ; AVX2-LABEL: shuffle_v8i32_z0U2zUz6:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsllq $32, %ymm0
+; AVX2-NEXT:    vpsllq $32, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> zeroinitializer, <8 x i32> <i32 8, i32 0, i32 undef, i32 2, i32 8, i32 undef, i32 8, i32 6>
   ret <8 x i32> %shuffle
@@ -1878,7 +1878,7 @@ define <8 x i32> @shuffle_v8i32_1U3z5zUU(<8 x i32> %a) {
 ;
 ; AVX2-LABEL: shuffle_v8i32_1U3z5zUU:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpsrlq $32, %ymm0
+; AVX2-NEXT:    vpsrlq $32, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> zeroinitializer, <8 x i32> <i32 1, i32 undef, i32 3, i32 8, i32 5, i32 8, i32 undef, i32 undef>
   ret <8 x i32> %shuffle
diff --git a/test/CodeGen/X86/vector-shuffle-512-v8.ll b/test/CodeGen/X86/vector-shuffle-512-v8.ll
index f3c64da044f..20cbbaef17e 100644
--- a/test/CodeGen/X86/vector-shuffle-512-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-512-v8.ll
@@ -6,7 +6,7 @@ target triple = "x86_64-unknown-unknown"
 define <8 x double> @shuffle_v8f64_00000000(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vbroadcastsd %xmm0, %zmm0 
+; ALL-NEXT:    vbroadcastsd %xmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
   ret <8 x double> %shuffle
@@ -48,7 +48,7 @@ define <8 x double> @shuffle_v8f64_00003000(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_00040000(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00040000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vbroadcastsd %xmm1, %ymm1
 ; ALL-NEXT:    vbroadcastsd %xmm0, %ymm0
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm0[0,1,2],ymm1[3]
@@ -61,7 +61,7 @@ define <8 x double> @shuffle_v8f64_00040000(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_00500000(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00500000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,1,1,3]
 ; ALL-NEXT:    vbroadcastsd %xmm0, %ymm0
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm0[0,1],ymm1[2],ymm0[3]
@@ -74,7 +74,7 @@ define <8 x double> @shuffle_v8f64_00500000(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_06000000(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_06000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; ALL-NEXT:    vbroadcastsd %xmm0, %ymm0
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm0[0],ymm1[1],ymm0[2,3]
@@ -87,7 +87,7 @@ define <8 x double> @shuffle_v8f64_06000000(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_70000000(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_70000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[3,1,2,3]
 ; ALL-NEXT:    vbroadcastsd %xmm0, %ymm0
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm1[0],ymm0[1,2,3]
@@ -100,7 +100,7 @@ define <8 x double> @shuffle_v8f64_70000000(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_01014545(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_01014545:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
 ; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
@@ -134,8 +134,8 @@ define <8 x double> @shuffle_v8f64_00001111(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_81a3c5e7(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_81a3c5e7:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2 
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
@@ -159,9 +159,9 @@ define <8 x double> @shuffle_v8f64_08080808(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_08084c4c(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_08084c4c:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
 ; ALL-NEXT:    vinsertf128 $1, %xmm2, %ymm2, %ymm2
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vbroadcastsd %xmm3, %ymm3
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm2[0],ymm3[1],ymm2[2],ymm3[3]
 ; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
@@ -176,8 +176,8 @@ define <8 x double> @shuffle_v8f64_08084c4c(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_8823cc67(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_8823cc67:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2 
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vbroadcastsd %xmm3, %ymm3
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3]
 ; ALL-NEXT:    vbroadcastsd %xmm1, %ymm1
@@ -221,9 +221,9 @@ define <8 x double> @shuffle_v8f64_9810dc54(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_08194c5d(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_08194c5d:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,0,2,1]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm3[0,1,1,3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,0,2,1]
@@ -238,9 +238,9 @@ define <8 x double> @shuffle_v8f64_08194c5d(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_2a3b6e7f(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_2a3b6e7f:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,2,2,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm3[2,1,3,3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
@@ -284,7 +284,7 @@ define <8 x double> @shuffle_v8f64_08991abb(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_091b2d3f(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_091b2d3f:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm0[2,1,3,3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
@@ -298,7 +298,7 @@ define <8 x double> @shuffle_v8f64_091b2d3f(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_09ab1def(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_09ab1def:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm3 = ymm0[1,0,2,2]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1,2,3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
@@ -312,7 +312,7 @@ define <8 x double> @shuffle_v8f64_00014445(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00014445:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,1]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -324,7 +324,7 @@ define <8 x double> @shuffle_v8f64_00204464(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00204464:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,2,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -336,7 +336,7 @@ define <8 x double> @shuffle_v8f64_03004744(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_03004744:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,3,0,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -348,7 +348,7 @@ define <8 x double> @shuffle_v8f64_10005444(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_10005444:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[1,0,0,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -360,7 +360,7 @@ define <8 x double> @shuffle_v8f64_22006644(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_22006644:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,0,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -372,7 +372,7 @@ define <8 x double> @shuffle_v8f64_33307774(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_33307774:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,3,3,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -384,7 +384,7 @@ define <8 x double> @shuffle_v8f64_32107654(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_32107654:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,2,1,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -396,7 +396,7 @@ define <8 x double> @shuffle_v8f64_00234467(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00234467:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -404,15 +404,15 @@ define <8 x double> @shuffle_v8f64_00234467(<8 x double> %a, <8 x double> %b) {
   ret <8 x double> %shuffle
 }
 
-define <8 x double> @shuffle_v8f64_00224466(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: shuffle_v8f64_00224466:
-; ALL:       # BB#0:
-; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
-; ALL-NEXT:    vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
-; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
-; ALL-NEXT:    retq
-  %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
+define <8 x double> @shuffle_v8f64_00224466(<8 x double> %a, <8 x double> %b) {
+; ALL-LABEL: shuffle_v8f64_00224466:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
+; ALL-NEXT:    vmovddup {{.*#+}} ymm0 = ymm0[0,0,2,2]
+; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
+; ALL-NEXT:    retq
+  %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   ret <8 x double> %shuffle
 }
 
@@ -420,7 +420,7 @@ define <8 x double> @shuffle_v8f64_10325476(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_10325476:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,3,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -432,7 +432,7 @@ define <8 x double> @shuffle_v8f64_11335577(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_11335577:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,1,3,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,3,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -444,7 +444,7 @@ define <8 x double> @shuffle_v8f64_10235467(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_10235467:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,2,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -456,7 +456,7 @@ define <8 x double> @shuffle_v8f64_10225466(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_10225466:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,2,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -468,7 +468,7 @@ define <8 x double> @shuffle_v8f64_00015444(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00015444:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,1]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -480,7 +480,7 @@ define <8 x double> @shuffle_v8f64_00204644(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00204644:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,2,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,2,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -492,7 +492,7 @@ define <8 x double> @shuffle_v8f64_03004474(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_03004474:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,3,0,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,3,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -504,7 +504,7 @@ define <8 x double> @shuffle_v8f64_10004444(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_10004444:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[1,0,0,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vbroadcastsd %xmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -516,7 +516,7 @@ define <8 x double> @shuffle_v8f64_22006446(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_22006446:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,0,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,0,0,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -528,7 +528,7 @@ define <8 x double> @shuffle_v8f64_33307474(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_33307474:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,3,3,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,3,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -540,7 +540,7 @@ define <8 x double> @shuffle_v8f64_32104567(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_32104567:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,2,1,0]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 4, i32 5, i32 6, i32 7>
@@ -551,7 +551,7 @@ define <8 x double> @shuffle_v8f64_00236744(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00236744:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,3,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -559,13 +559,13 @@ define <8 x double> @shuffle_v8f64_00236744(<8 x double> %a, <8 x double> %b) {
   ret <8 x double> %shuffle
 }
 
-define <8 x double> @shuffle_v8f64_00226644(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: shuffle_v8f64_00226644:
-; ALL:       # BB#0:
-; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
-; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,0,0]
-; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
+define <8 x double> @shuffle_v8f64_00226644(<8 x double> %a, <8 x double> %b) {
+; ALL-LABEL: shuffle_v8f64_00226644:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,0,0]
+; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 6, i32 6, i32 4, i32 4>
   ret <8 x double> %shuffle
@@ -575,7 +575,7 @@ define <8 x double> @shuffle_v8f64_10324567(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_10324567:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,3,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 6, i32 7>
@@ -586,7 +586,7 @@ define <8 x double> @shuffle_v8f64_11334567(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_11334567:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,1,3,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 4, i32 5, i32 6, i32 7>
@@ -596,7 +596,7 @@ define <8 x double> @shuffle_v8f64_11334567(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_01235467(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_01235467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -607,7 +607,7 @@ define <8 x double> @shuffle_v8f64_01235467(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_01235466(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_01235466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -615,13 +615,13 @@ define <8 x double> @shuffle_v8f64_01235466(<8 x double> %a, <8 x double> %b) {
   ret <8 x double> %shuffle
 }
 
-define <8 x double> @shuffle_v8f64_002u6u44(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: shuffle_v8f64_002u6u44:
-; ALL:       # BB#0:
-; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
-; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,1,0,0]
-; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
+define <8 x double> @shuffle_v8f64_002u6u44(<8 x double> %a, <8 x double> %b) {
+; ALL-LABEL: shuffle_v8f64_002u6u44:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,1,0,0]
+; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 undef, i32 6, i32 undef, i32 4, i32 4>
   ret <8 x double> %shuffle
@@ -631,7 +631,7 @@ define <8 x double> @shuffle_v8f64_00uu66uu(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_00uu66uu:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vbroadcastsd %xmm0, %ymm1
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -643,7 +643,7 @@ define <8 x double> @shuffle_v8f64_103245uu(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_103245uu:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,3,2]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 undef, i32 undef>
@@ -654,7 +654,7 @@ define <8 x double> @shuffle_v8f64_1133uu67(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_1133uu67:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,1,3,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 undef, i32 undef, i32 6, i32 7>
@@ -664,7 +664,7 @@ define <8 x double> @shuffle_v8f64_1133uu67(<8 x double> %a, <8 x double> %b) {
 define <8 x double> @shuffle_v8f64_0uu354uu(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_0uu354uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -673,22 +673,22 @@ define <8 x double> @shuffle_v8f64_0uu354uu(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_uuu3uu66(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: shuffle_v8f64_uuu3uu66:
-; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1 
-; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm1[0,0,2,2]
-; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
-; ALL-NEXT:    retq
-  %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 6>
+; ALL-LABEL: shuffle_v8f64_uuu3uu66:
+; ALL:       # BB#0:
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
+; ALL-NEXT:    vmovddup {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
+; ALL-NEXT:    retq
+  %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 6>
   ret <8 x double> %shuffle
 }
 
 define <8 x double> @shuffle_v8f64_c348cda0(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_c348cda0:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
 ; ALL-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[0,1],ymm2[0,1]
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vbroadcastsd %xmm1, %ymm4
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm4 = ymm3[0,1,2],ymm4[3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm4[0],ymm2[1,2],ymm4[3]
@@ -705,14 +705,14 @@ define <8 x double> @shuffle_v8f64_f511235a(<8 x double> %a, <8 x double> %b) {
 ; ALL-LABEL: shuffle_v8f64_f511235a:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
-; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3 
-; ALL-NEXT:    vpermpd {{.*#+}} ymm4 = ymm3[0,1,1,3]
-; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3]
-; ALL-NEXT:    vmovddup {{.*#+}} ymm4 = ymm1[0,0,2,2]
-; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm2[0,1,2],ymm4[3]
-; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,1]
-; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm3[1],ymm0[2,3]
-; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm1 
+; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3
+; ALL-NEXT:    vpermpd {{.*#+}} ymm4 = ymm3[0,1,1,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm2[0,1],ymm4[2],ymm2[3]
+; ALL-NEXT:    vmovddup {{.*#+}} ymm4 = ymm1[0,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm2[0,1,2],ymm4[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,1]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm3[1],ymm0[2,3]
+; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm1
 ; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[3,1,2,3]
 ; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
@@ -766,7 +766,7 @@ define <8 x i64> @shuffle_v8i64_00003000(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_00040000(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00040000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpbroadcastq %xmm1, %ymm1
 ; ALL-NEXT:    vpbroadcastq %xmm0, %ymm0
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm0[0,1,2,3,4,5],ymm1[6,7]
@@ -779,7 +779,7 @@ define <8 x i64> @shuffle_v8i64_00040000(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_00500000(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00500000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,1,3]
 ; ALL-NEXT:    vpbroadcastq %xmm0, %ymm0
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
@@ -792,7 +792,7 @@ define <8 x i64> @shuffle_v8i64_00500000(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_06000000(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_06000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
 ; ALL-NEXT:    vpbroadcastq %xmm0, %ymm0
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
@@ -805,7 +805,7 @@ define <8 x i64> @shuffle_v8i64_06000000(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_70000000(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_70000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[3,1,2,3]
 ; ALL-NEXT:    vpbroadcastq %xmm0, %ymm0
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm0[2,3,4,5,6,7]
@@ -818,7 +818,7 @@ define <8 x i64> @shuffle_v8i64_70000000(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_01014545(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_01014545:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vinserti128 $1, %xmm1, %ymm1, %ymm1
 ; ALL-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
@@ -852,8 +852,8 @@ define <8 x i64> @shuffle_v8i64_00001111(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_81a3c5e7(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_81a3c5e7:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2 
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
@@ -877,9 +877,9 @@ define <8 x i64> @shuffle_v8i64_08080808(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_08084c4c(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_08084c4c:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2
 ; ALL-NEXT:    vinserti128 $1, %xmm2, %ymm2, %ymm2
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vpbroadcastq %xmm3, %ymm3
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm2[0,1],ymm3[2,3],ymm2[4,5],ymm3[6,7]
 ; ALL-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
@@ -894,8 +894,8 @@ define <8 x i64> @shuffle_v8i64_08084c4c(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_8823cc67(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_8823cc67:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2 
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vpbroadcastq %xmm3, %ymm3
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
 ; ALL-NEXT:    vpbroadcastq %xmm1, %ymm1
@@ -939,9 +939,9 @@ define <8 x i64> @shuffle_v8i64_9810dc54(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_08194c5d(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_08194c5d:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,0,2,1]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm3 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm3
 ; ALL-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,1,1,3]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,0,2,1]
@@ -956,9 +956,9 @@ define <8 x i64> @shuffle_v8i64_08194c5d(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_2a3b6e7f(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_2a3b6e7f:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm3 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm3
 ; ALL-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[2,1,3,3]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
@@ -1002,7 +1002,7 @@ define <8 x i64> @shuffle_v8i64_08991abb(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_091b2d3f(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_091b2d3f:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpermq {{.*#+}} ymm3 = ymm0[2,1,3,3]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,3]
@@ -1016,7 +1016,7 @@ define <8 x i64> @shuffle_v8i64_091b2d3f(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_09ab1def(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_09ab1def:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2 
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm3 = ymm0[2,3,2,3,6,7,6,7]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3,4,5,6,7]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
@@ -1030,7 +1030,7 @@ define <8 x i64> @shuffle_v8i64_00014445(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00014445:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,1]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1042,7 +1042,7 @@ define <8 x i64> @shuffle_v8i64_00204464(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00204464:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1054,7 +1054,7 @@ define <8 x i64> @shuffle_v8i64_03004744(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_03004744:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,3,0,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1066,7 +1066,7 @@ define <8 x i64> @shuffle_v8i64_10005444(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_10005444:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,0,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1078,7 +1078,7 @@ define <8 x i64> @shuffle_v8i64_22006644(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_22006644:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[2,2,0,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1090,7 +1090,7 @@ define <8 x i64> @shuffle_v8i64_33307774(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_33307774:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,3,3,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1102,7 +1102,7 @@ define <8 x i64> @shuffle_v8i64_32107654(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_32107654:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,2,1,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1114,7 +1114,7 @@ define <8 x i64> @shuffle_v8i64_00234467(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00234467:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,3]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1126,7 +1126,7 @@ define <8 x i64> @shuffle_v8i64_00224466(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00224466:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1138,7 +1138,7 @@ define <8 x i64> @shuffle_v8i64_10325476(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_10325476:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1150,7 +1150,7 @@ define <8 x i64> @shuffle_v8i64_11335577(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_11335577:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,2,3,6,7,6,7]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1162,7 +1162,7 @@ define <8 x i64> @shuffle_v8i64_10235467(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_10235467:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,2,3]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1174,7 +1174,7 @@ define <8 x i64> @shuffle_v8i64_10225466(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_10225466:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,2,2]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,2,2]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1186,7 +1186,7 @@ define <8 x i64> @shuffle_v8i64_00015444(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00015444:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,1]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1198,7 +1198,7 @@ define <8 x i64> @shuffle_v8i64_00204644(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00204644:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1210,7 +1210,7 @@ define <8 x i64> @shuffle_v8i64_03004474(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_03004474:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,3,0,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,3,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1222,7 +1222,7 @@ define <8 x i64> @shuffle_v8i64_10004444(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_10004444:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,0,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpbroadcastq %xmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1234,7 +1234,7 @@ define <8 x i64> @shuffle_v8i64_22006446(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_22006446:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[2,2,0,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,0,0,2]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1246,7 +1246,7 @@ define <8 x i64> @shuffle_v8i64_33307474(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_33307474:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,3,3,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,0,3,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1258,7 +1258,7 @@ define <8 x i64> @shuffle_v8i64_32104567(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_32104567:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,2,1,0]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 4, i32 5, i32 6, i32 7>
@@ -1269,7 +1269,7 @@ define <8 x i64> @shuffle_v8i64_00236744(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00236744:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,3]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,3,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1281,7 +1281,7 @@ define <8 x i64> @shuffle_v8i64_00226644(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00226644:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1293,7 +1293,7 @@ define <8 x i64> @shuffle_v8i64_10324567(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_10324567:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 6, i32 7>
@@ -1304,7 +1304,7 @@ define <8 x i64> @shuffle_v8i64_11334567(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_11334567:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,2,3,6,7,6,7]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 4, i32 5, i32 6, i32 7>
@@ -1314,7 +1314,7 @@ define <8 x i64> @shuffle_v8i64_11334567(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_01235467(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_01235467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[1,0,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -1325,7 +1325,7 @@ define <8 x i64> @shuffle_v8i64_01235467(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_01235466(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_01235466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[1,0,2,2]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -1337,7 +1337,7 @@ define <8 x i64> @shuffle_v8i64_002u6u44(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_002u6u44:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,1,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1349,7 +1349,7 @@ define <8 x i64> @shuffle_v8i64_00uu66uu(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_00uu66uu:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpbroadcastq %xmm0, %ymm1
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1361,7 +1361,7 @@ define <8 x i64> @shuffle_v8i64_103245uu(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_103245uu:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 undef, i32 undef>
@@ -1372,7 +1372,7 @@ define <8 x i64> @shuffle_v8i64_1133uu67(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_1133uu67:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,2,3,6,7,6,7]
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 undef, i32 undef, i32 6, i32 7>
@@ -1382,7 +1382,7 @@ define <8 x i64> @shuffle_v8i64_1133uu67(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_0uu354uu(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_0uu354uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -1393,7 +1393,7 @@ define <8 x i64> @shuffle_v8i64_0uu354uu(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_uuu3uu66(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_uuu3uu66:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
 ; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
@@ -1404,9 +1404,9 @@ define <8 x i64> @shuffle_v8i64_uuu3uu66(<8 x i64> %a, <8 x i64> %b) {
 define <8 x i64> @shuffle_v8i64_6caa87e5(<8 x i64> %a, <8 x i64> %b) {
 ; ALL-LABEL: shuffle_v8i64_6caa87e5:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0 
+; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vperm2i128 {{.*#+}} ymm2 = ymm0[0,1,0,1]
-; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3 
+; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm4 = ymm1[0,1,2,3],ymm3[4,5],ymm1[6,7]
 ; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm4[0,1],ymm2[2,3],ymm4[4,5],ymm2[6,7]
 ; ALL-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
diff --git a/test/CodeGen/X86/vselect-2.ll b/test/CodeGen/X86/vselect-2.ll
index 0991bdacd9c..8ea7580d76f 100644
--- a/test/CodeGen/X86/vselect-2.ll
+++ b/test/CodeGen/X86/vselect-2.ll
@@ -2,13 +2,13 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mattr=+sse4.1 | FileCheck %s --check-prefix=SSE41
 
 define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) {
-; SSE2-LABEL: test1
-; SSE2:        # BB#0:
-; SSE2-NEXT:     movsd %xmm0, %xmm1
-; SSE2-NEXT:     movaps %xmm1, %xmm0
-; SSE2-NEXT:     retq
+; SSE2-LABEL: test1:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
+; SSE2-NEXT:    movaps %xmm1, %xmm0
+; SSE2-NEXT:    retq
 ;
-; SSE41-LABEL: test1
+; SSE41-LABEL: test1:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
 ; SSE41-NEXT:    retq
@@ -17,12 +17,12 @@ define <4 x i32> @test1(<4 x i32> %A, <4 x i32> %B) {
 }
 
 define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) {
-; SSE2-LABEL: test2
-; SSE2:        # BB#0:
-; SSE2-NEXT:     movsd %xmm1, %xmm0
-; SSE2-NEXT:     retq
+; SSE2-LABEL: test2:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
+; SSE2-NEXT:    retq
 ;
-; SSE41-LABEL: test2
+; SSE41-LABEL: test2:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; SSE41-NEXT:    retq
@@ -31,13 +31,13 @@ define <4 x i32> @test2(<4 x i32> %A, <4 x i32> %B) {
 }
 
 define <4 x float> @test3(<4 x float> %A, <4 x float> %B) {
-; SSE2-LABEL: test3
-; SSE2:        # BB#0:
-; SSE2-NEXT:     movsd %xmm0, %xmm1
-; SSE2-NEXT:     movaps %xmm1, %xmm0
-; SSE2-NEXT:     retq
+; SSE2-LABEL: test3:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
+; SSE2-NEXT:    movaps %xmm1, %xmm0
+; SSE2-NEXT:    retq
 ;
-; SSE41-LABEL: test3
+; SSE41-LABEL: test3:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    blendpd {{.*#+}} xmm0 = xmm0[0],xmm1[1]
 ; SSE41-NEXT:    retq
@@ -46,12 +46,12 @@ define <4 x float> @test3(<4 x float> %A, <4 x float> %B) {
 }
 
 define <4 x float> @test4(<4 x float> %A, <4 x float> %B) {
-; SSE2-LABEL: test4
-; SSE2:        # BB#0:
-; SSE2-NEXT:     movsd %xmm1, %xmm0
-; SSE2-NEXT:     retq
+; SSE2-LABEL: test4:
+; SSE2:       # BB#0:
+; SSE2-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
+; SSE2-NEXT:    retq
 ;
-; SSE41-LABEL: test4
+; SSE41-LABEL: test4:
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    blendpd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; SSE41-NEXT:    retq
diff --git a/test/CodeGen/X86/vselect.ll b/test/CodeGen/X86/vselect.ll
index ad734100f7b..e8e4cc25e69 100644
--- a/test/CodeGen/X86/vselect.ll
+++ b/test/CodeGen/X86/vselect.ll
@@ -17,7 +17,7 @@ define <4 x float> @test1(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @test2(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: test2:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd %xmm0, %xmm1
+; CHECK-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; CHECK-NEXT:    movaps %xmm1, %xmm0
 ; CHECK-NEXT:    retq
   %1 = select <4 x i1> <i1 true, i1 true, i1 false, i1 false>, <4 x float> %a, <4 x float> %b
@@ -27,7 +27,7 @@ define <4 x float> @test2(<4 x float> %a, <4 x float> %b) {
 define <4 x float> @test3(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: test3:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd %xmm1, %xmm0
+; CHECK-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; CHECK-NEXT:    retq
   %1 = select <4 x i1> <i1 false, i1 false, i1 true, i1 true>, <4 x float> %a, <4 x float> %b
   ret <4 x float> %1
@@ -169,7 +169,7 @@ define <8 x i16> @test17(<8 x i16> %a, <8 x i16> %b) {
 define <4 x float> @test18(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: test18:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movss %xmm1, %xmm0
+; CHECK-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; CHECK-NEXT:    retq
   %1 = select <4 x i1> <i1 false, i1 true, i1 true, i1 true>, <4 x float> %a, <4 x float> %b
   ret <4 x float> %1
@@ -178,7 +178,7 @@ define <4 x float> @test18(<4 x float> %a, <4 x float> %b) {
 define <4 x i32> @test19(<4 x i32> %a, <4 x i32> %b) {
 ; CHECK-LABEL: test19:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movss %xmm1, %xmm0
+; CHECK-NEXT:    movss {{.*#+}} xmm0 = xmm1[0],xmm0[1,2,3]
 ; CHECK-NEXT:    retq
   %1 = select <4 x i1> <i1 false, i1 true, i1 true, i1 true>, <4 x i32> %a, <4 x i32> %b
   ret <4 x i32> %1
@@ -187,7 +187,7 @@ define <4 x i32> @test19(<4 x i32> %a, <4 x i32> %b) {
 define <2 x double> @test20(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: test20:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd %xmm1, %xmm0
+; CHECK-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; CHECK-NEXT:    retq
   %1 = select <2 x i1> <i1 false, i1 true>, <2 x double> %a, <2 x double> %b
   ret <2 x double> %1
@@ -196,7 +196,7 @@ define <2 x double> @test20(<2 x double> %a, <2 x double> %b) {
 define <2 x i64> @test21(<2 x i64> %a, <2 x i64> %b) {
 ; CHECK-LABEL: test21:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd %xmm1, %xmm0
+; CHECK-NEXT:    movsd {{.*#+}} xmm0 = xmm1[0],xmm0[1]
 ; CHECK-NEXT:    retq
   %1 = select <2 x i1> <i1 false, i1 true>, <2 x i64> %a, <2 x i64> %b
   ret <2 x i64> %1
@@ -205,7 +205,7 @@ define <2 x i64> @test21(<2 x i64> %a, <2 x i64> %b) {
 define <4 x float> @test22(<4 x float> %a, <4 x float> %b) {
 ; CHECK-LABEL: test22:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movss %xmm0, %xmm1
+; CHECK-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; CHECK-NEXT:    movaps %xmm1, %xmm0
 ; CHECK-NEXT:    retq
   %1 = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x float> %a, <4 x float> %b
@@ -215,7 +215,7 @@ define <4 x float> @test22(<4 x float> %a, <4 x float> %b) {
 define <4 x i32> @test23(<4 x i32> %a, <4 x i32> %b) {
 ; CHECK-LABEL: test23:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movss %xmm0, %xmm1
+; CHECK-NEXT:    movss {{.*#+}} xmm1 = xmm0[0],xmm1[1,2,3]
 ; CHECK-NEXT:    movaps %xmm1, %xmm0
 ; CHECK-NEXT:    retq
   %1 = select <4 x i1> <i1 true, i1 false, i1 false, i1 false>, <4 x i32> %a, <4 x i32> %b
@@ -225,7 +225,7 @@ define <4 x i32> @test23(<4 x i32> %a, <4 x i32> %b) {
 define <2 x double> @test24(<2 x double> %a, <2 x double> %b) {
 ; CHECK-LABEL: test24:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd %xmm0, %xmm1
+; CHECK-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; CHECK-NEXT:    movaps %xmm1, %xmm0
 ; CHECK-NEXT:    retq
   %1 = select <2 x i1> <i1 true, i1 false>, <2 x double> %a, <2 x double> %b
@@ -235,7 +235,7 @@ define <2 x double> @test24(<2 x double> %a, <2 x double> %b) {
 define <2 x i64> @test25(<2 x i64> %a, <2 x i64> %b) {
 ; CHECK-LABEL: test25:
 ; CHECK:       # BB#0:
-; CHECK-NEXT:    movsd %xmm0, %xmm1
+; CHECK-NEXT:    movsd {{.*#+}} xmm1 = xmm0[0],xmm1[1]
 ; CHECK-NEXT:    movaps %xmm1, %xmm0
 ; CHECK-NEXT:    retq
   %1 = select <2 x i1> <i1 true, i1 false>, <2 x i64> %a, <2 x i64> %b