From 3a926b9b5c0186742910ad81ab6a430f58f8a7fb Mon Sep 17 00:00:00 2001
From: Chandler Carruth <chandlerc@gmail.com>
Date: Tue, 30 Sep 2014 22:04:45 +0000
Subject: [PATCH] [x86] Update the exact FileCheck syntax of the 256-bit and
 512-bit shuffle tests to match that used in the script I posted and now used
 consistently in 128-bit tests.

Nothing interesting changing here, just using the label name as the
FileCheck label and a slightly more general comment marker consumption
strategy.

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@218709 91177308-0d34-0410-b5e6-96231b3b80d8
---
 test/CodeGen/X86/vector-shuffle-256-v16.ll | 868 +++++++++----------
 test/CodeGen/X86/vector-shuffle-256-v32.ll | 814 +++++++++---------
 test/CodeGen/X86/vector-shuffle-256-v4.ll  | 461 +++++-----
 test/CodeGen/X86/vector-shuffle-256-v8.ll  | 938 ++++++++++-----------
 test/CodeGen/X86/vector-shuffle-512-v8.ll  | 842 +++++++++---------
 5 files changed, 1962 insertions(+), 1961 deletions(-)

diff --git a/test/CodeGen/X86/vector-shuffle-256-v16.ll b/test/CodeGen/X86/vector-shuffle-256-v16.ll
index ad6eca3b926..0cb73521503 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v16.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v16.ll
@@ -4,15 +4,15 @@
 target triple = "x86_64-unknown-unknown"
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -20,21 +20,21 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufd {{.*}} # xmm0 = xmm0[0,1,0,3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm0[0,1,2,3,4,4,4,4]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,4,5,4]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm0[0,1,2,3,4,4,4,4]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,5,4]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # xmm0 = xmm0[0,1,0,3]
-; AVX2-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; AVX2-NEXT:    vpshufhw {{.*}} # xmm1 = xmm0[0,1,2,3,4,4,4,4]
-; AVX2-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,4,5,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,3]
+; AVX2-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX2-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm0[0,1,2,3,4,4,4,4]
+; AVX2-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,5,4]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -42,17 +42,17 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -60,17 +60,17 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -78,17 +78,17 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -96,17 +96,17 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -114,17 +114,17 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -132,17 +132,17 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -150,23 +150,23 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,0,1,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm2[0],xmm1[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,1,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,u,u,u,u,u,u,u,u,u,u,u,u,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,u,u,u,u,u,u,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -174,23 +174,23 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,3,0,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm2[0],xmm1[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,3,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,u,u,u,u,u,u,u,u,u,u,2,3,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,u,u,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,255,255,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,u,u,u,u,2,3,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,u,u,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,255,255,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 9, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -198,24 +198,24 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[0,2,2,3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,3,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm2[0],xmm1[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,3,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,u,u,u,u,u,u,u,u,4,5,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,u,u,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,255,255,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,u,u,4,5,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,u,u,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,255,255,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 10, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -223,24 +223,24 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[0,3,2,3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[3,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm2[0],xmm1[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[3,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm2[0],xmm1[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,u,u,u,u,u,u,6,7,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,u,u,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,255,255,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,6,7,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,u,u,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,255,255,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 11, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -248,24 +248,24 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[2,3,0,1]
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,0,1,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm1[0],xmm2[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,1,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,u,u,u,u,8,9,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,u,u,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,255,255,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,8,9,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,u,u,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,255,255,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 12, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -273,24 +273,24 @@ define <16 x i16> @shuffle_v16i16_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[2,3,0,1]
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,3,0,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm1[0],xmm2[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,3,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,u,u,10,11,u,u,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,u,u,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,255,255,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,10,11,u,u,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,u,u,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,255,255,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 13, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -298,25 +298,25 @@ define <16 x i16> @shuffle_v16i16_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[2,3,0,1]
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[0,2,2,3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,3,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm1[0],xmm2[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,3,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,12,13,u,u,u,u,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,u,u,0,1,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,255,255,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,12,13,u,u,u,u,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,u,u,0,1,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,255,255,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -324,25 +324,25 @@ define <16 x i16> @shuffle_v16i16_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[2,3,0,1]
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm1[0,3,2,3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[3,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpunpcklqdq {{.*}} # xmm1 = xmm1[0],xmm2[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[3,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm2[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[14,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,0,1,0,1,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[14,15,u,u,u,u,u,u,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,0,1,0,1,0,1,0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -350,127 +350,127 @@ define <16 x i16> @shuffle_v16i16_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15
+; AVX1-LABEL: shuffle_v16i16_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [14,15,14,15,14,15,14,15,14,15,14,15,14,15,14,15]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [14,15,14,15,14,15,14,15,14,15,14,15,14,15,14,15]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15
+; AVX2-LABEL: shuffle_v16i16_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[14,15,14,15,14,15,14,15,14,15,14,15,14,15,14,15,30,31,30,31,30,31,30,31,30,31,30,31,30,31,30,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[14,15,14,15,14,15,14,15,14,15,14,15,14,15,14,15,30,31,30,31,30,31,30,31,30,31,30,31,30,31,30,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm1[0,1,2,3,4,4,4,4]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,4,4,4]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,4,4,4]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,4,4]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,8,9,8,9,8,9,8,9,16,17,16,17,16,17,16,17,24,25,24,25,24,25,24,25]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,8,9,8,9,8,9,8,9,16,17,16,17,16,17,16,17,24,25,24,25,24,25,24,25]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4, i32 8, i32 8, i32 8, i32 8, i32 12, i32 12, i32 12, i32 12>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15
+; AVX1-LABEL: shuffle_v16i16_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm0[3,3,3,3,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm1[0,1,2,3,7,7,7,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[3,3,3,3,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,7,7,7,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[3,3,3,3,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,7,7,7,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[3,3,3,3,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,7,7,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15
+; AVX2-LABEL: shuffle_v16i16_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[6,7,6,7,6,7,6,7,14,15,14,15,14,15,14,15,22,23,22,23,22,23,22,23,30,31,30,31,30,31,30,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[6,7,6,7,6,7,6,7,14,15,14,15,14,15,14,15,22,23,22,23,22,23,22,23,30,31,30,31,30,31,30,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 3, i32 3, i32 3, i32 3, i32 7, i32 7, i32 7, i32 7, i32 11, i32 11, i32 11, i32 11, i32 15, i32 15, i32 15, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14
+; AVX1-LABEL: shuffle_v16i16_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm0[0,0,2,2,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm1[0,1,2,3,4,4,6,6]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[0,0,2,2,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,4,6,6]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[0,0,2,2,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,4,6,6]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,2,2,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,6,6]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14
+; AVX2-LABEL: shuffle_v16i16_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,4,5,4,5,8,9,8,9,12,13,12,13,16,17,16,17,20,21,20,21,24,25,24,25,28,29,28,29]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5,8,9,8,9,12,13,12,13,16,17,16,17,20,21,20,21,24,25,24,25,28,29,28,29]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6, i32 8, i32 8, i32 10, i32 10, i32 12, i32 12, i32 14, i32 14>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15
+; AVX1-LABEL: shuffle_v16i16_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm0[1,1,3,3,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm1[0,1,2,3,5,5,7,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[1,1,3,3,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,5,5,7,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[1,1,3,3,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,5,5,7,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[1,1,3,3,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,5,5,7,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15
+; AVX2-LABEL: shuffle_v16i16_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[2,3,2,3,6,7,6,7,10,11,10,11,14,15,14,15,18,19,18,19,22,23,22,23,26,27,26,27,30,31,30,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7,10,11,10,11,14,15,14,15,18,19,18,19,22,23,22,23,26,27,26,27,30,31,30,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7, i32 9, i32 9, i32 11, i32 11, i32 13, i32 13, i32 15, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -478,15 +478,15 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_01_00_00_00_00_00_00_00_01_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -494,15 +494,15 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_00_02_00_00_00_00_00_00_00_02_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -510,15 +510,15 @@ define <16 x i16> @shuffle_v16i16_00_00_00_00_03_00_00_00_00_00_00_00_03_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -526,15 +526,15 @@ define <16 x i16> @shuffle_v16i16_00_00_00_04_00_00_00_00_00_00_00_04_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -542,15 +542,15 @@ define <16 x i16> @shuffle_v16i16_00_00_05_00_00_00_00_00_00_00_05_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -558,15 +558,15 @@ define <16 x i16> @shuffle_v16i16_00_06_00_00_00_00_00_00_00_06_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -574,81 +574,81 @@ define <16 x i16> @shuffle_v16i16_07_00_00_00_00_00_00_00_07_00_00_00_00_00_00_0
 }
 
 define <16 x i16> @shuffle_v16i16_00_17_02_19_04_21_06_23_08_25_10_27_12_29_14_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_17_02_19_04_21_06_23_08_25_10_27_12_29_14_31
+; AVX1-LABEL: shuffle_v16i16_00_17_02_19_04_21_06_23_08_25_10_27_12_29_14_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_17_02_19_04_21_06_23_08_25_10_27_12_29_14_31
+; AVX2-LABEL: shuffle_v16i16_00_17_02_19_04_21_06_23_08_25_10_27_12_29_14_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpblendw {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
+; AVX2-NEXT:    vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_16_01_18_03_20_05_22_07_24_09_26_11_28_13_30_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_16_01_18_03_20_05_22_07_24_09_26_11_28_13_30_15
+; AVX1-LABEL: shuffle_v16i16_16_01_18_03_20_05_22_07_24_09_26_11_28_13_30_15:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3],xmm1[4],xmm0[5],xmm1[6],xmm0[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3],xmm1[4],xmm0[5],xmm1[6],xmm0[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_16_01_18_03_20_05_22_07_24_09_26_11_28_13_30_15
+; AVX2-LABEL: shuffle_v16i16_16_01_18_03_20_05_22_07_24_09_26_11_28_13_30_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpblendw {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7],ymm1[8],ymm0[9],ymm1[10],ymm0[11],ymm1[12],ymm0[13],ymm1[14],ymm0[15]
+; AVX2-NEXT:    vpblendw {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7],ymm1[8],ymm0[9],ymm1[10],ymm0[11],ymm1[12],ymm0[13],ymm1[14],ymm0[15]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 16, i32 1, i32 18, i32 3, i32 20, i32 5, i32 22, i32 7, i32 24, i32 9, i32 26, i32 11, i32 28, i32 13, i32 30, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_01_18_19_04_05_22_23_08_09_26_27_12_13_30_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_01_18_19_04_05_22_23_08_09_26_27_12_13_30_31
+; AVX1-LABEL: shuffle_v16i16_00_01_18_19_04_05_22_23_08_09_26_27_12_13_30_31:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_01_18_19_04_05_22_23_08_09_26_27_12_13_30_31
+; AVX2-LABEL: shuffle_v16i16_00_01_18_19_04_05_22_23_08_09_26_27_12_13_30_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 1, i32 18, i32 19, i32 4, i32 5, i32 22, i32 23, i32 8, i32 9, i32 26, i32 27, i32 12, i32 13, i32 30, i32 31>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_16_17_18_19_04_05_06_07_24_25_26_27_12_13_14_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_16_17_18_19_04_05_06_07_24_25_26_27_12_13_14_15
+; AVX1-LABEL: shuffle_v16i16_16_17_18_19_04_05_06_07_24_25_26_27_12_13_14_15:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_16_17_18_19_04_05_06_07_24_25_26_27_12_13_14_15
+; AVX2-LABEL: shuffle_v16i16_16_17_18_19_04_05_06_07_24_25_26_27_12_13_14_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 16, i32 17, i32 18, i32 19, i32 4, i32 5, i32 6, i32 7, i32 24, i32 25, i32 26, i32 27, i32 12, i32 13, i32 14, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14_31
+; AVX1-LABEL: shuffle_v16i16_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpblendw {{.*}} # xmm1 = xmm2[0,1,2,3,4,5,6],xmm1[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm2[0,1,2,3,4,5,6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14_31
+; AVX2-LABEL: shuffle_v16i16_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,0,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 31>
@@ -656,16 +656,16 @@ define <16 x i16> @shuffle_v16i16_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14_3
 }
 
 define <16 x i16> @shuffle_v16i16_16_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_16_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15
+; AVX1-LABEL: shuffle_v16i16_16_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpblendw {{.*}} # xmm1 = xmm1[0],xmm0[1,2,3,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm1 = xmm1[0],xmm0[1,2,3,4,5,6,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_16_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15
+; AVX2-LABEL: shuffle_v16i16_16_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 16, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15>
@@ -673,18 +673,18 @@ define <16 x i16> @shuffle_v16i16_16_01_02_03_04_05_06_07_08_09_10_11_12_13_14_1
 }
 
 define <16 x i16> @shuffle_v16i16_00_17_02_19_04_21_06_23_24_09_26_11_28_13_30_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_17_02_19_04_21_06_23_24_09_26_11_28_13_30_15
+; AVX1-LABEL: shuffle_v16i16_00_17_02_19_04_21_06_23_24_09_26_11_28_13_30_15:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_17_02_19_04_21_06_23_24_09_26_11_28_13_30_15
+; AVX2-LABEL: shuffle_v16i16_00_17_02_19_04_21_06_23_24_09_26_11_28_13_30_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0,0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 17, i32 2, i32 19, i32 4, i32 21, i32 6, i32 23, i32 24, i32 9, i32 26, i32 11, i32 28, i32 13, i32 30, i32 15>
@@ -692,18 +692,18 @@ define <16 x i16> @shuffle_v16i16_00_17_02_19_04_21_06_23_24_09_26_11_28_13_30_1
 }
 
 define <16 x i16> @shuffle_v16i16_16_01_18_03_20_05_22_07_08_25_10_27_12_29_14_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_16_01_18_03_20_05_22_07_08_25_10_27_12_29_14_31
+; AVX1-LABEL: shuffle_v16i16_16_01_18_03_20_05_22_07_08_25_10_27_12_29_14_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3],xmm1[4],xmm0[5],xmm1[6],xmm0[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0],xmm0[1],xmm1[2],xmm0[3],xmm1[4],xmm0[5],xmm1[6],xmm0[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_16_01_18_03_20_05_22_07_08_25_10_27_12_29_14_31
+; AVX2-LABEL: shuffle_v16i16_16_01_18_03_20_05_22_07_08_25_10_27_12_29_14_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,255,255,0,0,255,255,0,0,255,255,0,0,255,255,255,255,0,0,255,255,0,0,255,255,0,0,255,255,0,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 16, i32 1, i32 18, i32 3, i32 20, i32 5, i32 22, i32 7, i32 8, i32 25, i32 10, i32 27, i32 12, i32 29, i32 14, i32 31>
@@ -711,33 +711,33 @@ define <16 x i16> @shuffle_v16i16_16_01_18_03_20_05_22_07_08_25_10_27_12_29_14_3
 }
 
 define <16 x i16> @shuffle_v16i16_00_01_18_19_20_21_06_07_08_09_26_27_12_13_30_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_01_18_19_20_21_06_07_08_09_26_27_12_13_30_31
+; AVX1-LABEL: shuffle_v16i16_00_01_18_19_20_21_06_07_08_09_26_27_12_13_30_31:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2],ymm0[3,4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3,4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_01_18_19_20_21_06_07_08_09_26_27_12_13_30_31
+; AVX2-LABEL: shuffle_v16i16_00_01_18_19_20_21_06_07_08_09_26_27_12_13_30_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1,2],ymm0[3,4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3,4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 1, i32 18, i32 19, i32 20, i32 21, i32 6, i32 7, i32 8, i32 9, i32 26, i32 27, i32 12, i32 13, i32 30, i32 31>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_16_00_16_00_16_00_16_00_16_00_16_00_16_00_16(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_16_00_16_00_16_00_16_00_16_00_16_00_16_00_16
+; AVX1-LABEL: shuffle_v16i16_00_16_00_16_00_16_00_16_00_16_00_16_00_16_00_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm1[0,1,0,1,4,5,0,1,0,1,0,1,12,13,0,1]
-; AVX1-NEXT:    vpshufd {{.*}} # xmm0 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,1,0,1,4,5,0,1,0,1,0,1,12,13,0,1]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_16_00_16_00_16_00_16_00_16_00_16_00_16_00_16
+; AVX2-LABEL: shuffle_v16i16_00_16_00_16_00_16_00_16_00_16_00_16_00_16_00_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm1 = xmm1[0,1,0,1,4,5,0,1,0,1,0,1,12,13,0,1]
-; AVX2-NEXT:    vpshufd {{.*}} # xmm0 = xmm0[0,0,0,0]
-; AVX2-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,1,0,1,4,5,0,1,0,1,0,1,12,13,0,1]
+; AVX2-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; AVX2-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 0, i32 16>
@@ -745,540 +745,540 @@ define <16 x i16> @shuffle_v16i16_00_16_00_16_00_16_00_16_00_16_00_16_00_16_00_1
 }
 
 define <16 x i16> @shuffle_v16i16_00_16_00_16_00_16_00_16_08_24_08_24_08_24_08_24(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_16_00_16_00_16_00_16_08_24_08_24_08_24_08_24
+; AVX1-LABEL: shuffle_v16i16_00_16_00_16_00_16_00_16_08_24_08_24_08_24_08_24:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = [0,1,0,1,4,5,0,1,0,1,0,1,12,13,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,1,0,1,4,5,0,1,0,1,0,1,12,13,0,1]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm4
-; AVX1-NEXT:    vpshufd {{.*}} # xmm4 = xmm4[0,0,0,0]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm4[0],xmm2[1],xmm4[2],xmm2[3],xmm4[4],xmm2[5],xmm4[6],xmm2[7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm4 = xmm4[0,0,0,0]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm4[0],xmm2[1],xmm4[2],xmm2[3],xmm4[4],xmm2[5],xmm4[6],xmm2[7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
-; AVX1-NEXT:    vpshufd {{.*}} # xmm0 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_16_00_16_00_16_00_16_08_24_08_24_08_24_08_24
+; AVX2-LABEL: shuffle_v16i16_00_16_00_16_00_16_00_16_08_24_08_24_08_24_08_24:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,0,1,u,u,0,1,u,u,0,1,u,u,0,1,u,u,16,17,u,u,16,17,u,u,16,17,u,u,16,17]
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,0,0,0,4,4,4,4]
-; AVX2-NEXT:    vpblendw {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,0,1,u,u,0,1,u,u,0,1,u,u,0,1,u,u,16,17,u,u,16,17,u,u,16,17,u,u,16,17]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4]
+; AVX2-NEXT:    vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 0, i32 16, i32 8, i32 24, i32 8, i32 24, i32 8, i32 24, i32 8, i32 24>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_16_16_16_16_04_05_06_07_24_24_24_24_12_13_14_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_16_16_16_16_04_05_06_07_24_24_24_24_12_13_14_15
+; AVX1-LABEL: shuffle_v16i16_16_16_16_16_04_05_06_07_24_24_24_24_12_13_14_15:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm3 = xmm3[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0,1,2,3],xmm2[4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0,1,2,3],xmm2[4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_16_16_16_16_04_05_06_07_24_24_24_24_12_13_14_15
+; AVX2-LABEL: shuffle_v16i16_16_16_16_16_04_05_06_07_24_24_24_24_12_13_14_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[0,1,0,1,0,1,0,1,u,u,u,u,u,u,u,u,16,17,16,17,16,17,16,17,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 16, i32 16, i32 16, i32 16, i32 4, i32 5, i32 6, i32 7, i32 24, i32 24, i32 24, i32 24, i32 12, i32 13, i32 14, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_19_18_17_16_07_06_05_04_27_26_25_24_15_14_13_12(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_19_18_17_16_07_06_05_04_27_26_25_24_15_14_13_12
+; AVX1-LABEL: shuffle_v16i16_19_18_17_16_07_06_05_04_27_26_25_24_15_14_13_12:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm2 = xmm2[0,1,2,3,7,6,5,4]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,7,6,5,4]
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm3
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm3 = xmm3[3,2,1,0,4,5,6,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0,1,2,3],xmm2[4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,7,6,5,4]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[3,2,1,0,4,5,6,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[3,2,1,0,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0,1,2,3],xmm2[4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,6,5,4]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[3,2,1,0,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_19_18_17_16_07_06_05_04_27_26_25_24_15_14_13_12
+; AVX2-LABEL: shuffle_v16i16_19_18_17_16_07_06_05_04_27_26_25_24_15_14_13_12:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,14,15,12,13,10,11,8,9,u,u,u,u,u,u,u,u,30,31,28,29,26,27,24,25]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[6,7,4,5,2,3,0,1,u,u,u,u,u,u,u,u,22,23,20,21,18,19,16,17,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,14,15,12,13,10,11,8,9,u,u,u,u,u,u,u,u,30,31,28,29,26,27,24,25]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[6,7,4,5,2,3,0,1,u,u,u,u,u,u,u,u,22,23,20,21,18,19,16,17,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 19, i32 18, i32 17, i32 16, i32 7, i32 6, i32 5, i32 4, i32 27, i32 26, i32 25, i32 24, i32 15, i32 14, i32 13, i32 12>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_19_18_17_16_03_02_01_00_27_26_25_24_11_10_09_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_19_18_17_16_03_02_01_00_27_26_25_24_11_10_09_08
+; AVX1-LABEL: shuffle_v16i16_19_18_17_16_03_02_01_00_27_26_25_24_11_10_09_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm2 = xmm2[3,2,1,0,4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm2 = xmm2[3,2,1,0,4,5,6,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpshufd {{.*}} # xmm3 = xmm3[0,1,0,1]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm3 = xmm3[0,1,2,3,7,6,5,4]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm2[0,1,2,3],xmm3[4,5,6,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[3,2,1,0,4,5,6,7]
-; AVX1-NEXT:    vpshufd {{.*}} # xmm0 = xmm0[0,1,0,1]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,7,6,5,4]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm3 = xmm3[0,1,0,1]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,7,6,5,4]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm2[0,1,2,3],xmm3[4,5,6,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[3,2,1,0,4,5,6,7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,6,5,4]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_19_18_17_16_03_02_01_00_27_26_25_24_11_10_09_08
+; AVX2-LABEL: shuffle_v16i16_19_18_17_16_03_02_01_00_27_26_25_24_11_10_09_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,6,7,4,5,2,3,0,1,u,u,u,u,u,u,u,u,22,23,20,21,18,19,16,17]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[6,7,4,5,2,3,0,1,u,u,u,u,u,u,u,u,22,23,20,21,18,19,16,17,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,6,7,4,5,2,3,0,1,u,u,u,u,u,u,u,u,22,23,20,21,18,19,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[6,7,4,5,2,3,0,1,u,u,u,u,u,u,u,u,22,23,20,21,18,19,16,17,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 19, i32 18, i32 17, i32 16, i32 3, i32 2, i32 1, i32 0, i32 27, i32 26, i32 25, i32 24, i32 11, i32 10, i32 9, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_01_00_08_08_08_08_08_08_09_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_01_00_08_08_08_08_08_08_09_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_08_08_08_08_08_08_09_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_01_00_08_08_08_08_08_08_09_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_08_08_08_08_08_08_09_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1,16,17,16,17,16,17,16,17,16,17,16,17,18,19,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1,16,17,16,17,16,17,16,17,16,17,16,17,18,19,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 9, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_08_08_08_10_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_08_08_08_10_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_08_08_08_10_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_08_08_08_10_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_08_08_08_10_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1,16,17,16,17,16,17,16,17,16,17,20,21,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1,16,17,16,17,16,17,16,17,16,17,20,21,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 10, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_08_11_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_08_11_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_08_11_08_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_08_11_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_08_11_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1,16,17,16,17,16,17,16,17,22,23,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1,16,17,16,17,16,17,16,17,22,23,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 11, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_12_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_12_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_12_08_08_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_12_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_12_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1,16,17,16,17,16,17,24,25,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1,16,17,16,17,16,17,24,25,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 12, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_13_08_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_13_08_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_13_08_08_08_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_13_08_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_13_08_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1,16,17,16,17,26,27,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1,16,17,16,17,26,27,16,17,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 13, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_06_00_00_00_00_00_00_08_14_08_08_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_06_00_00_00_00_00_00_08_14_08_08_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_08_14_08_08_08_08_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_06_00_00_00_00_00_00_08_14_08_08_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_08_14_08_08_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1,16,17,28,29,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1,16,17,28,29,16,17,16,17,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 14, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_07_00_00_00_00_00_00_00_15_08_08_08_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_07_00_00_00_00_00_00_00_15_08_08_08_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_15_08_08_08_08_08_08_08:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_07_00_00_00_00_00_00_00_15_08_08_08_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_15_08_08_08_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1,30,31,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1,30,31,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 15, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_16_01_17_02_18_03_19_08_24_09_25_10_26_11_27(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_16_01_17_02_18_03_19_08_24_09_25_10_26_11_27
+; AVX1-LABEL: shuffle_v16i16_00_16_01_17_02_18_03_19_08_24_09_25_10_26_11_27:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm2 = xmm2[0,0,1,1,2,2,3,3]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; AVX1-NEXT:    vpmovzxwd %xmm3, %xmm3
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm1[0,0,1,1,2,2,3,3]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3]
 ; AVX1-NEXT:    vpmovzxwd %xmm0, %xmm0
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_16_01_17_02_18_03_19_08_24_09_25_10_26_11_27
+; AVX2-LABEL: shuffle_v16i16_00_16_01_17_02_18_03_19_08_24_09_25_10_26_11_27:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpcklwd {{.*}} # ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11]
+; AVX2-NEXT:    vpunpcklwd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_04_20_05_21_06_22_07_23_12_28_13_29_14_30_15_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_04_20_05_21_06_22_07_23_12_28_13_29_14_30_15_31
+; AVX1-LABEL: shuffle_v16i16_04_20_05_21_06_22_07_23_12_28_13_29_14_30_15_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm2 = xmm2[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm2 = xmm2[4,4,5,5,6,6,7,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm3 = xmm3[4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm1 = xmm1[4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm3[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_04_20_05_21_06_22_07_23_12_28_13_29_14_30_15_31
+; AVX2-LABEL: shuffle_v16i16_04_20_05_21_06_22_07_23_12_28_13_29_14_30_15_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpckhwd {{.*}} # ymm0 = ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15]
+; AVX2-NEXT:    vpunpckhwd {{.*#+}} ymm0 = ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_16_01_17_02_18_03_19_12_28_13_29_14_30_15_31(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_16_01_17_02_18_03_19_12_28_13_29_14_30_15_31
+; AVX1-LABEL: shuffle_v16i16_00_16_01_17_02_18_03_19_12_28_13_29_14_30_15_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm2 = xmm2[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm2 = xmm2[4,4,5,5,6,6,7,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm3 = xmm3[4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm1 = xmm1[0,0,1,1,2,2,3,3]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm3 = xmm3[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3]
 ; AVX1-NEXT:    vpmovzxwd %xmm0, %xmm0
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_16_01_17_02_18_03_19_12_28_13_29_14_30_15_31
+; AVX2-LABEL: shuffle_v16i16_00_16_01_17_02_18_03_19_12_28_13_29_14_30_15_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,0,1,u,u,2,3,u,u,4,5,u,u,6,7,u,u,24,25,u,u,26,27,u,u,28,29,u,u,30,31]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,u,u,2,3,u,u,4,5,u,u,6,7,u,u,24,25,u,u,26,27,u,u,28,29,u,u,30,31,u,u]
-; AVX2-NEXT:    vpblendw {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,0,1,u,u,2,3,u,u,4,5,u,u,6,7,u,u,24,25,u,u,26,27,u,u,28,29,u,u,30,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,u,u,2,3,u,u,4,5,u,u,6,7,u,u,24,25,u,u,26,27,u,u,28,29,u,u,30,31,u,u]
+; AVX2-NEXT:    vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 12, i32 28, i32 13, i32 29, i32 14, i32 30, i32 15, i32 31>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_04_20_05_21_06_22_07_23_08_24_09_25_10_26_11_27(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_04_20_05_21_06_22_07_23_08_24_09_25_10_26_11_27
+; AVX1-LABEL: shuffle_v16i16_04_20_05_21_06_22_07_23_08_24_09_25_10_26_11_27:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vpunpcklwd {{.*}} # xmm2 = xmm2[0,0,1,1,2,2,3,3]
+; AVX1-NEXT:    vpunpcklwd {{.*#+}} xmm2 = xmm2[0,0,1,1,2,2,3,3]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
 ; AVX1-NEXT:    vpmovzxwd %xmm3, %xmm3
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm1 = xmm1[4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpunpckhwd {{.*}} # xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0],xmm2[1],xmm3[2],xmm2[3],xmm3[4],xmm2[5],xmm3[6],xmm2[7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm1 = xmm1[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0],xmm1[1],xmm0[2],xmm1[3],xmm0[4],xmm1[5],xmm0[6],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_04_20_05_21_06_22_07_23_08_24_09_25_10_26_11_27
+; AVX2-LABEL: shuffle_v16i16_04_20_05_21_06_22_07_23_08_24_09_25_10_26_11_27:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,u,8,9,u,u,10,11,u,u,12,13,u,u,14,15,u,u,16,17,u,u,18,19,u,u,20,21,u,u,22,23]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[8,9,u,u,10,11,u,u,12,13,u,u,14,15,u,u,16,17,u,u,18,19,u,u,20,21,u,u,22,23,u,u]
-; AVX2-NEXT:    vpblendw {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,8,9,u,u,10,11,u,u,12,13,u,u,14,15,u,u,16,17,u,u,18,19,u,u,20,21,u,u,22,23]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,u,u,10,11,u,u,12,13,u,u,14,15,u,u,16,17,u,u,18,19,u,u,20,21,u,u,22,23,u,u]
+; AVX2-NEXT:    vpblendw {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7],ymm0[8],ymm1[9],ymm0[10],ymm1[11],ymm0[12],ymm1[13],ymm0[14],ymm1[15]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23, i32 8, i32 24, i32 9, i32 25, i32 10, i32 26, i32 11, i32 27>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_00_01_00_08_09_08_08_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_00_01_00_08_09_08_08_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_08_09_08_08_08_08_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,2,3,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_00_01_00_08_09_08_08_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_00_01_00_08_09_08_08_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1,16,17,18,19,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,2,3,0,1,16,17,18,19,16,17,16,17,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 8, i32 9, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_10_08_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_10_08_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_10_08_08_08_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,4,5,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,4,5,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_10_08_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_00_02_00_00_08_08_10_08_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1,16,17,16,17,20,21,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,4,5,0,1,0,1,16,17,16,17,20,21,16,17,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 8, i32 8, i32 10, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_11_08_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_11_08_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_11_08_08_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,6,7,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,6,7,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_11_08_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_00_03_00_00_00_08_08_08_11_08_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1,16,17,16,17,16,17,22,23,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,6,7,0,1,0,1,0,1,16,17,16,17,16,17,22,23,16,17,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 11, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_08_12_08_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_08_12_08_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_08_12_08_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,8,9,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,8,9,0,1,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_08_12_08_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_00_04_00_00_00_00_08_08_08_08_12_08_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,24,25,16,17,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,8,9,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,24,25,16,17,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 12, i32 8, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_08_08_08_13_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_08_08_08_13_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_08_08_08_13_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,10,11,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,10,11,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_08_08_08_13_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_05_00_00_00_00_00_08_08_08_08_08_13_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,26,27,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,10,11,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,26,27,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 13, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_06_00_00_00_00_00_00_08_08_08_08_08_08_14_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_06_00_00_00_00_00_00_08_08_08_08_08_08_14_08
+; AVX1-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_08_08_08_08_08_08_14_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,12,13,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,12,13,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_06_00_00_00_00_00_00_08_08_08_08_08_08_14_08
+; AVX2-LABEL: shuffle_v16i16_00_06_00_00_00_00_00_00_08_08_08_08_08_08_14_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,28,29,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,12,13,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,28,29,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 14, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_07_00_00_00_00_00_00_00_08_08_08_08_08_08_08_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_07_00_00_00_00_00_00_00_08_08_08_08_08_08_08_15
+; AVX1-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_08_08_08_08_08_08_08_15:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,14,15]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,14,15]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_07_00_00_00_00_00_00_00_08_08_08_08_08_08_08_15
+; AVX2-LABEL: shuffle_v16i16_07_00_00_00_00_00_00_00_08_08_08_08_08_08_08_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,30,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[14,15,0,1,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,30,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_00_02_02_04_04_06_06_14_14_12_12_10_10_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_00_02_02_04_04_06_06_14_14_12_12_10_10_08_08
+; AVX1-LABEL: shuffle_v16i16_00_00_02_02_04_04_06_06_14_14_12_12_10_10_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm0[0,0,2,2,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm1[0,1,2,3,4,4,6,6]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[0,0,2,2,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,4,6,6]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[12,13,12,13,8,9,8,9,4,5,4,5,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,13,12,13,8,9,8,9,4,5,4,5,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_00_02_02_04_04_06_06_14_14_12_12_10_10_08_08
+; AVX2-LABEL: shuffle_v16i16_00_00_02_02_04_04_06_06_14_14_12_12_10_10_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,4,5,4,5,8,9,8,9,12,13,12,13,28,29,28,29,24,25,24,25,20,21,20,21,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5,8,9,8,9,12,13,12,13,28,29,28,29,24,25,24,25,20,21,20,21,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6, i32 14, i32 14, i32 12, i32 12, i32 10, i32 10, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_04_04_04_04_00_00_00_00_08_08_08_08_12_12_12_12(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_04_04_04_04_00_00_00_00_08_08_08_08_12_12_12_12
+; AVX1-LABEL: shuffle_v16i16_04_04_04_04_00_00_00_00_08_08_08_08_12_12_12_12:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[8,9,8,9,8,9,8,9,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[8,9,8,9,8,9,8,9,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,4,4,4]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,4,4]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_04_04_04_04_00_00_00_00_08_08_08_08_12_12_12_12
+; AVX2-LABEL: shuffle_v16i16_04_04_04_04_00_00_00_00_08_08_08_08_12_12_12_12:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[8,9,8,9,8,9,8,9,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,24,25,24,25,24,25,24,25]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,8,9,8,9,8,9,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,24,25,24,25,24,25,24,25]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 4, i32 4, i32 4, i32 4, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 12, i32 12, i32 12, i32 12>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_uu_uu_00_00_00_00_00_08_08_uu_uu_08_08_14_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_uu_uu_00_00_00_00_00_08_08_uu_uu_08_08_14_08
+; AVX1-LABEL: shuffle_v16i16_00_uu_uu_00_00_00_00_00_08_08_uu_uu_08_08_14_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,1,2,3,4,5,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,1,2,3,4,5,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,4,5,6,7,0,1,0,1,12,13,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,4,5,6,7,0,1,0,1,12,13,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_uu_uu_00_00_00_00_00_08_08_uu_uu_08_08_14_08
+; AVX2-LABEL: shuffle_v16i16_00_uu_uu_00_00_00_00_00_08_08_uu_uu_08_08_14_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,u,u,u,u,0,1,0,1,0,1,0,1,0,1,16,17,16,17,u,u,u,u,16,17,16,17,28,29,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,u,u,u,u,0,1,0,1,0,1,0,1,0,1,16,17,16,17,u,u,u,u,16,17,16,17,28,29,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 undef, i32 undef, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 undef, i32 undef, i32 8, i32 8, i32 14, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_07_uu_00_00_00_00_00_00_08_08_uu_uu_08_08_08_15(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_07_uu_00_00_00_00_00_00_08_08_uu_uu_08_08_08_15
+; AVX1-LABEL: shuffle_v16i16_07_uu_00_00_00_00_00_00_08_08_uu_uu_08_08_08_15:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[14,15,2,3,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[14,15,2,3,0,1,0,1,0,1,0,1,0,1,0,1]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,1,4,5,6,7,0,1,0,1,0,1,14,15]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,4,5,6,7,0,1,0,1,0,1,14,15]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_07_uu_00_00_00_00_00_00_08_08_uu_uu_08_08_08_15
+; AVX2-LABEL: shuffle_v16i16_07_uu_00_00_00_00_00_00_08_08_uu_uu_08_08_08_15:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[14,15,u,u,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,u,u,u,u,16,17,16,17,16,17,30,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[14,15,u,u,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,u,u,u,u,16,17,16,17,16,17,30,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 7, i32 undef, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 undef, i32 undef, i32 8, i32 8, i32 8, i32 15>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_00_uu_uu_02_04_04_uu_06_14_14_uu_12_10_10_08_08(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_00_uu_uu_02_04_04_uu_06_14_14_uu_12_10_10_08_08
+; AVX1-LABEL: shuffle_v16i16_00_uu_uu_02_04_04_uu_06_14_14_uu_12_10_10_08_08:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm0[0,1,2,2,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm1 = xmm1[0,1,2,3,4,4,6,6]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[0,1,2,2,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,4,6,6]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[12,13,12,13,12,13,8,9,4,5,4,5,0,1,0,1]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,13,12,13,12,13,8,9,4,5,4,5,0,1,0,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_00_uu_uu_02_04_04_uu_06_14_14_uu_12_10_10_08_08
+; AVX2-LABEL: shuffle_v16i16_00_uu_uu_02_04_04_uu_06_14_14_uu_12_10_10_08_08:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,u,u,u,u,4,5,8,9,8,9,u,u,12,13,28,29,28,29,u,u,24,25,20,21,20,21,16,17,16,17]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,u,u,u,u,4,5,8,9,8,9,u,u,12,13,28,29,28,29,u,u,24,25,20,21,20,21,16,17,16,17]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 0, i32 undef, i32 undef, i32 2, i32 4, i32 4, i32 undef, i32 6, i32 14, i32 14, i32 undef, i32 12, i32 10, i32 10, i32 8, i32 8>
   ret <16 x i16> %shuffle
 }
 
 define <16 x i16> @shuffle_v16i16_04_04_04_04_uu_uu_uu_uu_08_08_08_uu_uu_12_12_12(<16 x i16> %a, <16 x i16> %b) {
-; AVX1-LABEL: @shuffle_v16i16_04_04_04_04_uu_uu_uu_uu_08_08_08_uu_uu_12_12_12
+; AVX1-LABEL: shuffle_v16i16_04_04_04_04_uu_uu_uu_uu_08_08_08_uu_uu_12_12_12:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufd {{.*}} # xmm1 = xmm0[2,1,2,3]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpshufd {{.*#+}} xmm1 = xmm0[2,1,2,3]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm0 = xmm0[0,0,0,3,4,5,6,7]
-; AVX1-NEXT:    vpshufhw {{.*}} # xmm0 = xmm0[0,1,2,3,4,4,4,4]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,3,4,5,6,7]
+; AVX1-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,4,4]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v16i16_04_04_04_04_uu_uu_uu_uu_08_08_08_uu_uu_12_12_12
+; AVX2-LABEL: shuffle_v16i16_04_04_04_04_uu_uu_uu_uu_08_08_08_uu_uu_12_12_12:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[8,9,8,9,8,9,8,9,u,u,u,u,u,u,u,u,16,17,16,17,16,17,u,u,u,u,24,25,24,25,24,25]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,8,9,8,9,8,9,u,u,u,u,u,u,u,u,16,17,16,17,16,17,u,u,u,u,24,25,24,25,24,25]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <16 x i16> %a, <16 x i16> %b, <16 x i32> <i32 4, i32 4, i32 4, i32 4, i32 undef, i32 undef, i32 undef, i32 undef, i32 8, i32 8, i32 8, i32 undef, i32 undef, i32 12, i32 12, i32 12>
   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 338053ad32c..fab36b2b273 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v32.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v32.ll
@@ -4,14 +4,14 @@
 target triple = "x86_64-unknown-unknown"
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm0
@@ -22,19 +22,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -42,19 +42,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -62,19 +62,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_03_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,3,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -82,19 +82,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,4,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,4,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_04_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,4,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,4,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -102,19 +102,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,5,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,5,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_05_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,5,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,5,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -122,19 +122,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,6,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,6,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_06_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,6,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,6,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -142,19 +142,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -162,19 +162,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -182,19 +182,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,9,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,9,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_09_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,9,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,9,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 9, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -202,19 +202,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,10,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,10,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_10_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,10,0,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,10,0,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 10, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -222,19 +222,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,11,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,11,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_11_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,11,0,0,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,11,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 11, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -242,19 +242,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,12,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,12,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_12_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,12,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,12,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 12, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -262,19 +262,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,13,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,13,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_13_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,13,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,13,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 13, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -282,19 +282,19 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -302,7 +302,7 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    movl $15, %eax
 ; AVX1-NEXT:    vmovd %eax, %xmm1
@@ -312,7 +312,7 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    movl $15, %eax
 ; AVX2-NEXT:    vmovd %eax, %xmm1
@@ -326,24 +326,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0],zero
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm2
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm0
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm1, %ymm0, %ymm2, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -351,24 +351,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_17_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_17_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_17_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[1],zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_17_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_17_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,u,u,u,1,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,u,u,u,1,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 17, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -376,24 +376,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_17_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_18_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_18_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_18_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[2],zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[2],zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_18_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_18_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,u,u,2,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,255,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,u,u,2,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,255,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 18, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -401,24 +401,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_18_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_19_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_19_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_19_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[3],zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[3],zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_19_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_19_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,u,3,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,255,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,u,3,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,0,0,255,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 19, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -426,24 +426,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_19_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_20_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_20_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_20_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[4],zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[4],zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_20_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_20_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,4,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,0,255,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,u,4,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,0,255,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 20, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -451,24 +451,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_20_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_21_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_21_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_21_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[5],zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[5],zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_21_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_21_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,5,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,0,255,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,u,u,5,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,0,255,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 21, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -476,24 +476,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_21_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_22_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_22_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_22_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[6],zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm2[6],zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_22_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_22_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,u,6,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,0,255,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,u,6,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,0,255,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 22, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -501,24 +501,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_22_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_23_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_23_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_23_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[7],zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,zero,xmm2[7],zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_23_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_23_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,7,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,7,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 23, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -526,24 +526,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_23_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_24_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_24_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_24_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,zero,xmm2[8],zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,zero,xmm2[8],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_24_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_24_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,8,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,8,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,0,255,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 24, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -551,24 +551,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_24_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_25_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_25_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_25_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,zero,xmm2[9],zero,zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,zero,xmm2[9],zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_25_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_25_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,9,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,0,255,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,9,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,0,255,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 25, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -576,24 +576,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_25_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_26_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_26_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_26_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,zero,xmm2[10],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,zero,xmm2[10],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_26_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_26_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,10,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,0,255,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,10,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,0,255,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 26, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -601,24 +601,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_26_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_27_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_27_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_27_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,zero,xmm2[11],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,zero,xmm2[11],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_27_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_27_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,11,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,0,255,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,11,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,0,255,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 27, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -626,24 +626,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_27_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_28_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_28_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_28_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,zero,xmm2[12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,zero,xmm2[12],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_28_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_28_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,12,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,0,255,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,12,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,0,255,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 28, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -651,24 +651,24 @@ define <32 x i8> @shuffle_v32i8_00_00_00_28_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_29_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_29_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_29_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,xmm2[13],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,xmm2[13],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_29_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_29_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,13,u,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,0,255,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,13,u,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,0,255,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 29, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -676,24 +676,24 @@ define <32 x i8> @shuffle_v32i8_00_00_29_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_30_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_30_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_30_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,xmm2[14],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,xmm2[14],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0],zero,xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpor %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_30_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_30_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [0,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,14,u,u,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [0,255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 30, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -701,7 +701,7 @@ define <32 x i8> @shuffle_v32i8_00_30_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
@@ -709,21 +709,21 @@ define <32 x i8> @shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 ; AVX1-NEXT:    vmovd %eax, %xmm2
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[15],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
 ; AVX1-NEXT:    vpor %xmm0, %xmm2, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm1 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
 ; AVX2-NEXT:    movl $15, %eax
 ; AVX2-NEXT:    vmovd %eax, %xmm2
 ; AVX2-NEXT:    vpxor %ymm3, %ymm3, %ymm3
 ; AVX2-NEXT:    vinserti128 $0, %xmm2, %ymm3, %ymm2
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm3, %ymm0, %ymm0
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 31, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -731,7 +731,7 @@ define <32 x i8> @shuffle_v32i8_31_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
@@ -740,7 +740,7 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpshufb %ymm1, %ymm0, %ymm0
@@ -750,141 +750,141 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31
+; AVX1-LABEL: shuffle_v32i8_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31
+; AVX2-LABEL: shuffle_v32i8_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_15_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,15,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8,16,16,16,16,16,16,16,16,24,24,24,24,24,24,24,24]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8,16,16,16,16,16,16,16,16,24,24,24,24,24,24,24,24]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15_23_23_23_23_23_23_23_23_31_31_31_31_31_31_31_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15_23_23_23_23_23_23_23_23_31_31_31_31_31_31_31_31
+; AVX1-LABEL: shuffle_v32i8_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15_23_23_23_23_23_23_23_23_31_31_31_31_31_31_31_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [7,7,7,7,7,7,7,7,15,15,15,15,15,15,15,15]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [7,7,7,7,7,7,7,7,15,15,15,15,15,15,15,15]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15_23_23_23_23_23_23_23_23_31_31_31_31_31_31_31_31
+; AVX2-LABEL: shuffle_v32i8_07_07_07_07_07_07_07_07_15_15_15_15_15_15_15_15_23_23_23_23_23_23_23_23_31_31_31_31_31_31_31_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[7,7,7,7,7,7,7,7,15,15,15,15,15,15,15,15,23,23,23,23,23,23,23,23,31,31,31,31,31,31,31,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[7,7,7,7,7,7,7,7,15,15,15,15,15,15,15,15,23,23,23,23,23,23,23,23,31,31,31,31,31,31,31,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 7, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 15, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 23, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31, i32 31>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_16_16_16_16_20_20_20_20_24_24_24_24_28_28_28_28(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_16_16_16_16_20_20_20_20_24_24_24_24_28_28_28_28
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_16_16_16_16_20_20_20_20_24_24_24_24_28_28_28_28:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_16_16_16_16_20_20_20_20_24_24_24_24_28_28_28_28
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_16_16_16_16_20_20_20_20_24_24_24_24_28_28_28_28:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12,16,16,16,16,20,20,20,20,24,24,24,24,28,28,28,28]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12,16,16,16,16,20,20,20,20,24,24,24,24,28,28,28,28]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4, i32 8, i32 8, i32 8, i32 8, i32 12, i32 12, i32 12, i32 12, i32 16, i32 16, i32 16, i32 16, i32 20, i32 20, i32 20, i32 20, i32 24, i32 24, i32 24, i32 24, i32 28, i32 28, i32 28, i32 28>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15_19_19_19_19_23_23_23_23_27_27_27_27_31_31_31_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15_19_19_19_19_23_23_23_23_27_27_27_27_31_31_31_31
+; AVX1-LABEL: shuffle_v32i8_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15_19_19_19_19_23_23_23_23_27_27_27_27_31_31_31_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [3,3,3,3,7,7,7,7,11,11,11,11,15,15,15,15]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [3,3,3,3,7,7,7,7,11,11,11,11,15,15,15,15]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15_19_19_19_19_23_23_23_23_27_27_27_27_31_31_31_31
+; AVX2-LABEL: shuffle_v32i8_03_03_03_03_07_07_07_07_11_11_11_11_15_15_15_15_19_19_19_19_23_23_23_23_27_27_27_27_31_31_31_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[3,3,3,3,7,7,7,7,11,11,11,11,15,15,15,15,19,19,19,19,23,23,23,23,27,27,27,27,31,31,31,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[3,3,3,3,7,7,7,7,11,11,11,11,15,15,15,15,19,19,19,19,23,23,23,23,27,27,27,27,31,31,31,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 3, i32 3, i32 3, i32 3, i32 7, i32 7, i32 7, i32 7, i32 11, i32 11, i32 11, i32 11, i32 15, i32 15, i32 15, i32 15, i32 19, i32 19, i32 19, i32 19, i32 23, i32 23, i32 23, i32 23, i32 27, i32 27, i32 27, i32 27, i32 31, i32 31, i32 31, i32 31>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14_16_16_18_18_20_20_22_22_24_24_26_26_28_28_30_30(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14_16_16_18_18_20_20_22_22_24_24_26_26_28_28_30_30
+; AVX1-LABEL: shuffle_v32i8_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14_16_16_18_18_20_20_22_22_24_24_26_26_28_28_30_30:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14_16_16_18_18_20_20_22_22_24_24_26_26_28_28_30_30
+; AVX2-LABEL: shuffle_v32i8_00_00_02_02_04_04_06_06_08_08_10_10_12_12_14_14_16_16_18_18_20_20_22_22_24_24_26_26_28_28_30_30:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14,16,16,18,18,20,20,22,22,24,24,26,26,28,28,30,30]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6,8,8,10,10,12,12,14,14,16,16,18,18,20,20,22,22,24,24,26,26,28,28,30,30]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6, i32 8, i32 8, i32 10, i32 10, i32 12, i32 12, i32 14, i32 14, i32 16, i32 16, i32 18, i32 18, i32 20, i32 20, i32 22, i32 22, i32 24, i32 24, i32 26, i32 26, i32 28, i32 28, i32 30, i32 30>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15_17_17_19_19_21_21_23_23_25_25_27_27_29_29_31_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15_17_17_19_19_21_21_23_23_25_25_27_27_29_29_31_31
+; AVX1-LABEL: shuffle_v32i8_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15_17_17_19_19_21_21_23_23_25_25_27_27_29_29_31_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15_17_17_19_19_21_21_23_23_25_25_27_27_29_29_31_31
+; AVX2-LABEL: shuffle_v32i8_01_01_03_03_05_05_07_07_09_09_11_11_13_13_15_15_17_17_19_19_21_21_23_23_25_25_27_27_29_29_31_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15,17,17,19,19,21,21,23,23,25,25,27,27,29,29,31,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7,9,9,11,11,13,13,15,15,17,17,19,19,21,21,23,23,25,25,27,27,29,29,31,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7, i32 9, i32 9, i32 11, i32 11, i32 13, i32 13, i32 15, i32 15, i32 17, i32 17, i32 19, i32 19, i32 21, i32 21, i32 23, i32 23, i32 25, i32 25, i32 27, i32 27, i32 29, i32 29, i32 31, i32 31>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -892,15 +892,15 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -908,15 +908,15 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -924,15 +924,15 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -940,15 +940,15 @@ define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -956,7 +956,7 @@ define <32 x i8> @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX1-LABEL: shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    movl $15, %eax
 ; AVX1-NEXT:    vmovd %eax, %xmm1
@@ -964,7 +964,7 @@ define <32 x i8> @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00
+; AVX2-LABEL: shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    movl $15, %eax
 ; AVX2-NEXT:    vmovd %eax, %xmm1
@@ -976,24 +976,24 @@ define <32 x i8> @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 }
 
 define <32 x i8> @shuffle_v32i8_00_33_02_35_04_37_06_39_08_41_10_43_12_45_14_47_16_49_18_51_20_53_22_55_24_57_26_59_28_61_30_63(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_33_02_35_04_37_06_39_08_41_10_43_12_45_14_47_16_49_18_51_20_53_22_55_24_57_26_59_28_61_30_63
+; AVX1-LABEL: shuffle_v32i8_00_33_02_35_04_37_06_39_08_41_10_43_12_45_14_47_16_49_18_51_20_53_22_55_24_57_26_59_28_61_30_63:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm4
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm0, %xmm0
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_33_02_35_04_37_06_39_08_41_10_43_12_45_14_47_16_49_18_51_20_53_22_55_24_57_26_59_28_61_30_63
+; AVX2-LABEL: shuffle_v32i8_00_33_02_35_04_37_06_39_08_41_10_43_12_45_14_47_16_49_18_51_20_53_22_55_24_57_26_59_28_61_30_63:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 33, i32 2, i32 35, i32 4, i32 37, i32 6, i32 39, i32 8, i32 41, i32 10, i32 43, i32 12, i32 45, i32 14, i32 47, i32 16, i32 49, i32 18, i32 51, i32 20, i32 53, i32 22, i32 55, i32 24, i32 57, i32 26, i32 59, i32 28, i32 61, i32 30, i32 63>
@@ -1001,24 +1001,24 @@ define <32 x i8> @shuffle_v32i8_00_33_02_35_04_37_06_39_08_41_10_43_12_45_14_47_
 }
 
 define <32 x i8> @shuffle_v32i8_32_01_34_03_36_05_38_07_40_09_42_11_44_13_46_15_48_17_50_19_52_21_54_23_56_25_58_27_60_29_62_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_32_01_34_03_36_05_38_07_40_09_42_11_44_13_46_15_48_17_50_19_52_21_54_23_56_25_58_27_60_29_62_31
+; AVX1-LABEL: shuffle_v32i8_32_01_34_03_36_05_38_07_40_09_42_11_44_13_46_15_48_17_50_19_52_21_54_23_56_25_58_27_60_29_62_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <1,3,5,7,9,11,13,15,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm5 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm1, %xmm1
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = 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]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = 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]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_32_01_34_03_36_05_38_07_40_09_42_11_44_13_46_15_48_17_50_19_52_21_54_23_56_25_58_27_60_29_62_31
+; AVX2-LABEL: shuffle_v32i8_32_01_34_03_36_05_38_07_40_09_42_11_44_13_46_15_48_17_50_19_52_21_54_23_56_25_58_27_60_29_62_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 32, i32 1, i32 34, i32 3, i32 36, i32 5, i32 38, i32 7, i32 40, i32 9, i32 42, i32 11, i32 44, i32 13, i32 46, i32 15, i32 48, i32 17, i32 50, i32 19, i32 52, i32 21, i32 54, i32 23, i32 56, i32 25, i32 58, i32 27, i32 60, i32 29, i32 62, i32 31>
@@ -1026,21 +1026,21 @@ define <32 x i8> @shuffle_v32i8_32_01_34_03_36_05_38_07_40_09_42_11_44_13_46_15_
 }
 
 define <32 x i8> @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32
+; AVX1-LABEL: shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32
+; AVX2-LABEL: shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm2, %xmm2, %xmm2
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX2-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
-; AVX2-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX2-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX2-NEXT:    vinserti128 $1, %xmm0, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32>
@@ -1048,26 +1048,26 @@ define <32 x i8> @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_
 }
 
 define <32 x i8> @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_16_48_16_48_16_48_16_48_16_48_16_48_16_48_16_48(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_16_48_16_48_16_48_16_48_16_48_16_48_16_48_16_48
+; AVX1-LABEL: shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_16_48_16_48_16_48_16_48_16_48_16_48_16_48_16_48:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
 ; AVX1-NEXT:    vpxor %xmm3, %xmm3, %xmm3
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm4
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm4, %xmm4
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_16_48_16_48_16_48_16_48_16_48_16_48_16_48_16_48
+; AVX2-LABEL: shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_16_48_16_48_16_48_16_48_16_48_16_48_16_48_16_48:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm2, %ymm2, %ymm2
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1,16,17,16,17,16,17,16,17,16,17,16,17,16,17,16,17]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 0, i32 32, i32 16, i32 48, i32 16, i32 48, i32 16, i32 48, i32 16, i32 48, i32 16, i32 48, i32 16, i32 48, i32 16, i32 48, i32 16, i32 48>
@@ -1075,173 +1075,173 @@ define <32 x i8> @shuffle_v32i8_00_32_00_32_00_32_00_32_00_32_00_32_00_32_00_32_
 }
 
 define <32 x i8> @shuffle_v32i8_32_32_32_32_32_32_32_32_08_09_10_11_12_13_14_15_48_48_48_48_48_48_48_48_24_25_26_27_28_29_30_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_32_32_32_32_32_32_32_32_08_09_10_11_12_13_14_15_48_48_48_48_48_48_48_48_24_25_26_27_28_29_30_31
+; AVX1-LABEL: shuffle_v32i8_32_32_32_32_32_32_32_32_08_09_10_11_12_13_14_15_48_48_48_48_48_48_48_48_24_25_26_27_28_29_30_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %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 {{.*}} # xmm3 = xmm3[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm3[0,1,2,3],xmm2[4,5,6,7]
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,0,0,4,5,6,7]
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm3 = xmm3[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm3 = xmm3[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm3[0,1,2,3],xmm2[4,5,6,7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_32_32_32_32_32_32_32_32_08_09_10_11_12_13_14_15_48_48_48_48_48_48_48_48_24_25_26_27_28_29_30_31
+; AVX2-LABEL: shuffle_v32i8_32_32_32_32_32_32_32_32_08_09_10_11_12_13_14_15_48_48_48_48_48_48_48_48_24_25_26_27_28_29_30_31:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm2, %ymm2, %ymm2
 ; AVX2-NEXT:    vpshufb %ymm2, %ymm1, %ymm1
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 32, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 48, i32 48, i32 48, i32 48, i32 48, i32 48, i32 48, i32 48, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_39_38_37_36_35_34_33_32_15_14_13_12_11_10_09_08_55_54_53_52_51_50_49_48_31_30_29_28_27_26_25_24(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_39_38_37_36_35_34_33_32_15_14_13_12_11_10_09_08_55_54_53_52_51_50_49_48_31_30_29_28_27_26_25_24
+; AVX1-LABEL: shuffle_v32i8_39_38_37_36_35_34_33_32_15_14_13_12_11_10_09_08_55_54_53_52_51_50_49_48_31_30_29_28_27_26_25_24:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <u,u,u,u,u,u,u,u,15,14,13,12,11,10,9,8>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <u,u,u,u,u,u,u,u,15,14,13,12,11,10,9,8>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm5 = <7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm5 = <7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm4[0,1,2,3],xmm2[4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm4[0,1,2,3],xmm2[4,5,6,7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm1, %xmm1
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_39_38_37_36_35_34_33_32_15_14_13_12_11_10_09_08_55_54_53_52_51_50_49_48_31_30_29_28_27_26_25_24
+; AVX2-LABEL: shuffle_v32i8_39_38_37_36_35_34_33_32_15_14_13_12_11_10_09_08_55_54_53_52_51_50_49_48_31_30_29_28_27_26_25_24:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,15,14,13,12,11,10,9,8,u,u,u,u,u,u,u,u,31,30,29,28,27,26,25,24]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u,23,22,21,20,19,18,17,16,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,15,14,13,12,11,10,9,8,u,u,u,u,u,u,u,u,31,30,29,28,27,26,25,24]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u,23,22,21,20,19,18,17,16,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 15, i32 14, i32 13, i32 12, i32 11, i32 10, i32 9, i32 8, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 31, i32 30, i32 29, i32 28, i32 27, i32 26, i32 25, i32 24>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_39_38_37_36_35_34_33_32_07_06_05_04_03_02_01_00_55_54_53_52_51_50_49_48_23_22_21_20_19_18_17_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_39_38_37_36_35_34_33_32_07_06_05_04_03_02_01_00_55_54_53_52_51_50_49_48_23_22_21_20_19_18_17_16
+; AVX1-LABEL: shuffle_v32i8_39_38_37_36_35_34_33_32_07_06_05_04_03_02_01_00_55_54_53_52_51_50_49_48_23_22_21_20_19_18_17_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <u,u,u,u,u,u,u,u,7,6,5,4,3,2,1,0>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <u,u,u,u,u,u,u,u,7,6,5,4,3,2,1,0>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm5 = <7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm5 = <7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm4, %xmm4
-; AVX1-NEXT:    vpblendw {{.*}} # xmm2 = xmm4[0,1,2,3],xmm2[4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm2 = xmm4[0,1,2,3],xmm2[4,5,6,7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm5, %xmm1, %xmm1
-; AVX1-NEXT:    vpblendw {{.*}} # xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_39_38_37_36_35_34_33_32_07_06_05_04_03_02_01_00_55_54_53_52_51_50_49_48_23_22_21_20_19_18_17_16
+; AVX2-LABEL: shuffle_v32i8_39_38_37_36_35_34_33_32_07_06_05_04_03_02_01_00_55_54_53_52_51_50_49_48_23_22_21_20_19_18_17_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,u,u,u,u,u,u,7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u,23,22,21,20,19,18,17,16]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u,23,22,21,20,19,18,17,16,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u,23,22,21,20,19,18,17,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[7,6,5,4,3,2,1,0,u,u,u,u,u,u,u,u,23,22,21,20,19,18,17,16,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 39, i32 38, i32 37, i32 36, i32 35, i32 34, i32 33, i32 32, i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0, i32 55, i32 54, i32 53, i32 52, i32 51, i32 50, i32 49, i32 48, i32 23, i32 22, i32 21, i32 20, i32 19, i32 18, i32 17, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_17_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_17_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_17_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_17_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_17_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,16,16,16,16,16,16,16,16,16,16,16,16,16,16,17,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,16,16,16,16,16,16,16,16,16,16,16,16,16,16,17,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 17, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_18_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_18_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_18_16_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_18_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_18_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0,16,16,16,16,16,16,16,16,16,16,16,16,16,18,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0,16,16,16,16,16,16,16,16,16,16,16,16,16,18,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 18, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,23,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,23,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 23, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,24,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,24,16,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 24, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_30_16_16_16_16_16_16_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_30_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_30_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = [0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_30_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_30_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0,16,30,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0,16,30,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 30, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_31_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_31_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_31_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    movl $15, %eax
 ; AVX1-NEXT:    vmovd %eax, %xmm1
@@ -1251,80 +1251,80 @@ define <32 x i8> @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_31_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_31_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[15,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,31,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[15,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,31,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 31, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55
+; AVX1-LABEL: shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vpmovzxbw %xmm2, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3],xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1],xmm2[2],xmm4[2],xmm2[3],xmm4[3],xmm2[4],xmm4[4],xmm2[5],xmm4[5],xmm2[6],xmm4[6],xmm2[7],xmm4[7]
 ; AVX1-NEXT:    vpmovzxbw %xmm0, %xmm0
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55
+; AVX2-LABEL: shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpcklbw {{.*}} # ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
+; AVX2-NEXT:    vpunpcklbw {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63
+; AVX1-LABEL: shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <8,9,10,11,12,13,14,15,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <8,9,10,11,12,13,14,15,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm4
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm4, %xmm4
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63
+; AVX2-LABEL: shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpckhbw {{.*}} # ymm0 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
+; AVX2-NEXT:    vpunpckhbw {{.*#+}} ymm0 = ymm0[8],ymm1[8],ymm0[9],ymm1[9],ymm0[10],ymm1[10],ymm0[11],ymm1[11],ymm0[12],ymm1[12],ymm0[13],ymm1[13],ymm0[14],ymm1[14],ymm0[15],ymm1[15],ymm0[24],ymm1[24],ymm0[25],ymm1[25],ymm0[26],ymm1[26],ymm0[27],ymm1[27],ymm0[28],ymm1[28],ymm0[29],ymm1[29],ymm0[30],ymm1[30],ymm0[31],ymm1[31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63
+; AVX1-LABEL: shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm2
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm3 = <8,9,10,11,12,13,14,15,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = <8,9,10,11,12,13,14,15,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm2, %xmm2
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm4
 ; AVX1-NEXT:    vpshufb %xmm3, %xmm4, %xmm3
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
 ; AVX1-NEXT:    vpmovzxbw %xmm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63
+; AVX2-LABEL: shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_24_56_25_57_26_58_27_59_28_60_29_61_30_62_31_63:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,u,1,u,2,u,3,u,4,u,5,u,6,u,7,u,24,u,25,u,26,u,27,u,28,u,29,u,30,u,31,u]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,0,u,1,u,2,u,3,u,4,u,5,u,6,u,7,u,24,u,25,u,26,u,27,u,28,u,29,u,30,u,31]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,u,1,u,2,u,3,u,4,u,5,u,6,u,7,u,24,u,25,u,26,u,27,u,28,u,29,u,30,u,31,u]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,0,u,1,u,2,u,3,u,4,u,5,u,6,u,7,u,24,u,25,u,26,u,27,u,28,u,29,u,30,u,31]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 24, i32 56, i32 25, i32 57, i32 26, i32 58, i32 27, i32 59, i32 28, i32 60, i32 29, i32 61, i32 30, i32 62, i32 31, i32 63>
@@ -1332,25 +1332,25 @@ define <32 x i8> @shuffle_v32i8_00_32_01_33_02_34_03_35_04_36_05_37_06_38_07_39_
 }
 
 define <32 x i8> @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55
+; AVX1-LABEL: shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovdqa {{.*}} # xmm2 = <8,9,10,11,12,13,14,15,u,u,u,u,u,u,u,u>
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = <8,9,10,11,12,13,14,15,u,u,u,u,u,u,u,u>
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm3
 ; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm2
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm2 = xmm2[0],xmm3[0],xmm2[1],xmm3[1],xmm2[2],xmm3[2],xmm2[3],xmm3[3],xmm2[4],xmm3[4],xmm2[5],xmm3[5],xmm2[6],xmm3[6],xmm2[7],xmm3[7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
 ; AVX1-NEXT:    vpmovzxbw %xmm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
-; AVX1-NEXT:    vpunpcklbw {{.*}} # xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3],xmm0[4],xmm1[4],xmm0[5],xmm1[5],xmm0[6],xmm1[6],xmm0[7],xmm1[7]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55
+; AVX2-LABEL: shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_16_48_17_49_18_50_19_51_20_52_21_53_22_54_23_55:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[8,u,9,u,10,u,11,u,12,u,13,u,14,u,15,u,16,u,17,u,18,u,19,u,20,u,21,u,22,u,23,u]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[u,8,u,9,u,10,u,11,u,12,u,13,u,14,u,15,u,16,u,17,u,18,u,19,u,20,u,21,u,22,u,23]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,u,9,u,10,u,11,u,12,u,13,u,14,u,15,u,16,u,17,u,18,u,19,u,20,u,21,u,22,u,23,u]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,8,u,9,u,10,u,11,u,12,u,13,u,14,u,15,u,16,u,17,u,18,u,19,u,20,u,21,u,22,u,23]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 8, i32 40, i32 9, i32 41, i32 10, i32 42, i32 11, i32 43, i32 12, i32 44, i32 13, i32 45, i32 14, i32 46, i32 15, i32 47, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50, i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
@@ -1358,249 +1358,249 @@ define <32 x i8> @shuffle_v32i8_08_40_09_41_10_42_11_43_12_44_13_45_14_46_15_47_
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_17_16_16_16_16_16_16_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_17_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_17_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_17_16_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_01_00_16_17_16_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,16,17,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,1,0,16,17,16,16,16,16,16,16,16,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0, i32 16, i32 17, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_18_16_16_16_16_16_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_18_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_18_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,2,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_18_16_16_16_16_16_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_00_00_00_00_00_02_00_00_16_16_18_16_16_16_16_16_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0,16,16,18,16,16,16,16,16,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,0,0,0,0,0,2,0,0,16,16,18,16,16,16,16,16,16,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0, i32 16, i32 16, i32 18, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,7,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,7,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_00_07_00_00_00_00_00_00_00_16_16_16_16_16_16_16_23_16_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0,16,16,16,16,16,16,16,23,16,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,0,7,0,0,0,0,0,0,0,16,16,16,16,16,16,16,23,16,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 23, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,8,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,8,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_00_00_00_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_16_16_16_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,24,16,16,16,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,0,0,0,8,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,24,16,16,16,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 24, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_30_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_30_16
+; AVX1-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_30_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,14,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,14,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_30_16
+; AVX2-LABEL: shuffle_v32i8_00_14_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_30_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,16,16,16,16,16,16,30,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,14,0,0,0,0,0,0,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,16,16,16,16,16,16,30,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 14, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 30, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_31(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_31
+; AVX1-LABEL: shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_31:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    movl $15, %eax
 ; AVX1-NEXT:    vmovd %eax, %xmm1
 ; AVX1-NEXT:    vpshufb %xmm1, %xmm0, %xmm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,15]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,15]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_31
+; AVX2-LABEL: shuffle_v32i8_15_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_16_16_16_16_16_16_16_31:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[15,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,31]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[15,0,0,0,0,0,0,0,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,16,16,16,16,16,16,16,31]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 15, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 31>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_28_28_28_28_24_24_24_24_20_20_20_20_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_28_28_28_28_24_24_24_24_20_20_20_20_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_28_28_28_28_24_24_24_24_20_20_20_20_16_16_16_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[12,12,12,12,8,8,8,8,4,4,4,4,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,12,12,12,8,8,8,8,4,4,4,4,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_28_28_28_28_24_24_24_24_20_20_20_20_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12_28_28_28_28_24_24_24_24_20_20_20_20_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12,28,28,28,28,24,24,24,24,20,20,20,20,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12,28,28,28,28,24,24,24,24,20,20,20,20,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4, i32 8, i32 8, i32 8, i32 8, i32 12, i32 12, i32 12, i32 12, i32 28, i32 28, i32 28, i32 28, i32 24, i32 24, i32 24, i32 24, i32 20, i32 20, i32 20, i32 20, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_08_08_08_08_08_08_08_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_08_08_08_08_08_08_08_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24
+; AVX1-LABEL: shuffle_v32i8_08_08_08_08_08_08_08_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[8,8,8,8,8,8,8,8,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[8,8,8,8,8,8,8,8,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_08_08_08_08_08_08_08_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24
+; AVX2-LABEL: shuffle_v32i8_08_08_08_08_08_08_08_08_00_00_00_00_00_00_00_00_16_16_16_16_16_16_16_16_24_24_24_24_24_24_24_24:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[8,8,8,8,8,8,8,8,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,24,24,24,24,24,24,24,24]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,8,8,8,8,8,8,8,0,0,0,0,0,0,0,0,16,16,16,16,16,16,16,16,24,24,24,24,24,24,24,24]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_16_uu_uu_uu_uu_uu_16_16_16_16_16_30_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_16_uu_uu_uu_uu_uu_16_16_16_16_16_30_16
+; AVX1-LABEL: shuffle_v32i8_00_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_16_uu_uu_uu_uu_uu_16_16_16_16_16_30_16:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm1[0,0,0,0,u,u,u,u,u,0,0,0,0,0,14,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,0,0,0,u,u,u,u,u,0,0,0,0,0,14,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_16_uu_uu_uu_uu_uu_16_16_16_16_16_30_16
+; AVX2-LABEL: shuffle_v32i8_00_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_16_uu_uu_uu_uu_uu_16_16_16_16_16_30_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,u,u,u,u,u,16,16,16,16,16,30,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,16,16,16,16,u,u,u,u,u,16,16,16,16,16,30,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 16, i32 16, i32 16, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 16, i32 16, i32 16, i32 16, i32 16, i32 30, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_uu_14_uu_uu_00_00_00_00_00_00_00_00_00_00_00_00_16_16_uu_16_uu_uu_uu_uu_16_16_16_16_16_16_30_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_uu_14_uu_uu_00_00_00_00_00_00_00_00_00_00_00_00_16_16_uu_16_uu_uu_uu_uu_16_16_16_16_16_16_30_16
+; AVX1-LABEL: shuffle_v32i8_uu_14_uu_uu_00_00_00_00_00_00_00_00_00_00_00_00_16_16_uu_16_uu_uu_uu_uu_16_16_16_16_16_16_30_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[14,14,1,1,0,0,0,0,0,0,0,0,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[14,14,1,1,0,0,0,0,0,0,0,0,0,0,0,0]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,u,0,u,u,u,u,0,0,0,0,0,0,14,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,u,0,u,u,u,u,0,0,0,0,0,0,14,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_uu_14_uu_uu_00_00_00_00_00_00_00_00_00_00_00_00_16_16_uu_16_uu_uu_uu_uu_16_16_16_16_16_16_30_16
+; AVX2-LABEL: shuffle_v32i8_uu_14_uu_uu_00_00_00_00_00_00_00_00_00_00_00_00_16_16_uu_16_uu_uu_uu_uu_16_16_16_16_16_16_30_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,14,u,u,0,0,0,0,0,0,0,0,0,0,0,0,16,16,u,16,u,u,u,u,16,16,16,16,16,16,30,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,14,u,u,0,0,0,0,0,0,0,0,0,0,0,0,16,16,u,16,u,u,u,u,16,16,16,16,16,16,30,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 undef, i32 14, i32 undef, i32 undef, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 16, i32 16, i32 undef, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 16, i32 16, i32 16, i32 16, i32 16, i32 16, i32 30, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_00_00_00_uu_uu_uu_04_uu_08_08_08_08_uu_uu_12_uu_28_28_28_28_uu_uu_uu_24_20_20_20_20_16_16_16_16(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_00_00_00_uu_uu_uu_04_uu_08_08_08_08_uu_uu_12_uu_28_28_28_28_uu_uu_uu_24_20_20_20_20_16_16_16_16
+; AVX1-LABEL: shuffle_v32i8_00_00_00_uu_uu_uu_04_uu_08_08_08_08_uu_uu_12_uu_28_28_28_28_uu_uu_uu_24_20_20_20_20_16_16_16_16:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[12,12,12,12,8,8,8,8,4,4,4,4,0,0,0,0]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,12,12,12,8,8,8,8,4,4,4,4,0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_00_00_00_uu_uu_uu_04_uu_08_08_08_08_uu_uu_12_uu_28_28_28_28_uu_uu_uu_24_20_20_20_20_16_16_16_16
+; AVX2-LABEL: shuffle_v32i8_00_00_00_uu_uu_uu_04_uu_08_08_08_08_uu_uu_12_uu_28_28_28_28_uu_uu_uu_24_20_20_20_20_16_16_16_16:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[0,0,0,u,u,u,4,u,8,8,8,8,u,u,12,u,28,28,28,28,u,u,u,24,20,20,20,20,16,16,16,16]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[0,0,0,u,u,u,4,u,8,8,8,8,u,u,12,u,28,28,28,28,u,u,u,24,20,20,20,20,16,16,16,16]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 0, i32 0, i32 0, i32 undef, i32 undef, i32 undef, i32 4, i32 undef, i32 8, i32 8, i32 8, i32 8, i32 undef, i32 undef, i32 12, i32 undef, i32 28, i32 28, i32 28, i32 28, i32 undef, i32 undef, i32 undef, i32 24, i32 20, i32 20, i32 20, i32 20, i32 16, i32 16, i32 16, i32 16>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_08_08_08_08_08_08_08_08_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_uu_uu_uu_uu_uu_uu_uu_24_24_24_24_24_24(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_08_08_08_08_08_08_08_08_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_uu_uu_uu_uu_uu_uu_uu_24_24_24_24_24_24
+; AVX1-LABEL: shuffle_v32i8_08_08_08_08_08_08_08_08_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_uu_uu_uu_uu_uu_uu_uu_24_24_24_24_24_24:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpunpckhbw {{.*}} # xmm1 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
-; AVX1-NEXT:    vpshuflw {{.*}} # xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; AVX1-NEXT:    vpunpckhbw {{.*#+}} xmm1 = xmm0[8,8,9,9,10,10,11,11,12,12,13,13,14,14,15,15]
+; AVX1-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[0,0,0,0,8,8,9,9,8,8,8,8,8,8,8,8]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,8,8,9,9,8,8,8,8,8,8,8,8]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_08_08_08_08_08_08_08_08_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_uu_uu_uu_uu_uu_uu_uu_24_24_24_24_24_24
+; AVX2-LABEL: shuffle_v32i8_08_08_08_08_08_08_08_08_uu_uu_uu_uu_uu_uu_uu_uu_16_16_16_uu_uu_uu_uu_uu_uu_uu_24_24_24_24_24_24:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u,16,16,16,u,u,u,u,u,u,u,24,24,24,24,24,24]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,8,8,8,8,8,8,8,u,u,u,u,u,u,u,u,16,16,16,u,u,u,u,u,u,u,24,24,24,24,24,24]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 16, i32 16, i32 16, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 24, i32 24, i32 24, i32 24, i32 24, i32 24>
   ret <32 x i8> %shuffle
 }
 
 define <32 x i8> @shuffle_v32i8_42_45_12_13_35_35_60_40_17_22_29_44_33_12_48_51_20_19_52_19_49_54_37_32_48_42_59_07_36_34_36_39(<32 x i8> %a, <32 x i8> %b) {
-; AVX1-LABEL: @shuffle_v32i8_42_45_12_13_35_35_60_40_17_22_29_44_33_12_48_51_20_19_52_19_49_54_37_32_48_42_59_07_36_34_36_39
+; AVX1-LABEL: shuffle_v32i8_42_45_12_13_35_35_60_40_17_22_29_44_33_12_48_51_20_19_52_19_49_54_37_32_48_42_59_07_36_34_36_39:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = zero,zero,xmm0[u],zero,xmm0[u,u,u,u,u,u,u,7,u,u,u,u]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = zero,zero,xmm0[u],zero,xmm0[u,u,u,u,u,u,u,7,u,u,u,u]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm3
-; AVX1-NEXT:    vpshufb {{.*}} # xmm4 = xmm3[4,3,u,3,u,u,u,u,u,u,u],zero,xmm3[u,u,u,u]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm4 = xmm3[4,3,u,3,u,u,u,u,u,u,u],zero,xmm3[u,u,u,u]
 ; AVX1-NEXT:    vpor %xmm2, %xmm4, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm2 = xmm2[0,1],zero,xmm2[3],zero,zero,zero,zero,zero,zero,zero,xmm2[11],zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[0,1],zero,xmm2[3],zero,zero,zero,zero,zero,zero,zero,xmm2[11],zero,zero,zero,zero
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
-; AVX1-NEXT:    vpshufb {{.*}} # xmm5 = xmm4[u,u,4,u,1,6],zero,zero,xmm4[0],zero,xmm4[11,u],zero,zero,zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm6 = xmm1[u,u],zero,xmm1[u],zero,zero,xmm1[5,0],zero,xmm1[10],zero,xmm1[u,4,2,4,7]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm5 = xmm4[u,u,4,u,1,6],zero,zero,xmm4[0],zero,xmm4[11,u],zero,zero,zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm6 = xmm1[u,u],zero,xmm1[u],zero,zero,xmm1[5,0],zero,xmm1[10],zero,xmm1[u,4,2,4,7]
 ; AVX1-NEXT:    vpor %xmm5, %xmm6, %xmm5
-; AVX1-NEXT:    vpshufb {{.*}} # xmm5 = zero,zero,xmm5[2],zero,xmm5[4,5,6,7,8,9,10],zero,xmm5[12,13,14,15]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm5 = zero,zero,xmm5[2],zero,xmm5[4,5,6,7,8,9,10],zero,xmm5[12,13,14,15]
 ; AVX1-NEXT:    vpor %xmm2, %xmm5, %xmm2
-; AVX1-NEXT:    vpshufb {{.*}} # xmm3 = xmm3[u,u],zero,zero,xmm3[u,u,u,u,1,6,13,u,u],zero,xmm3[u,u]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = xmm0[u,u,12,13,u,u,u,u],zero,zero,zero,xmm0[u,u,12,u,u]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm3 = xmm3[u,u],zero,zero,xmm3[u,u,u,u,1,6,13,u,u],zero,xmm3[u,u]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[u,u,12,13,u,u,u,u],zero,zero,zero,xmm0[u,u,12,u,u]
 ; AVX1-NEXT:    vpor %xmm3, %xmm0, %xmm0
-; AVX1-NEXT:    vpshufb {{.*}} # xmm0 = zero,zero,xmm0[2,3],zero,zero,zero,zero,xmm0[8,9,10],zero,zero,xmm0[13],zero,zero
-; AVX1-NEXT:    vpshufb {{.*}} # xmm3 = zero,zero,xmm4[u,u],zero,zero,xmm4[12],zero,xmm4[u,u,u],zero,zero,xmm4[u,0,3]
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm1[10,13,u,u,3,3],zero,xmm1[8,u,u,u,12,1,u],zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm0 = zero,zero,xmm0[2,3],zero,zero,zero,zero,xmm0[8,9,10],zero,zero,xmm0[13],zero,zero
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm3 = zero,zero,xmm4[u,u],zero,zero,xmm4[12],zero,xmm4[u,u,u],zero,zero,xmm4[u,0,3]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[10,13,u,u,3,3],zero,xmm1[8,u,u,u,12,1,u],zero,zero
 ; AVX1-NEXT:    vpor %xmm3, %xmm1, %xmm1
-; AVX1-NEXT:    vpshufb {{.*}} # xmm1 = xmm1[0,1],zero,zero,xmm1[4,5,6,7],zero,zero,zero,xmm1[11,12],zero,xmm1[14,15]
+; AVX1-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,1],zero,zero,xmm1[4,5,6,7],zero,zero,zero,xmm1[11,12],zero,xmm1[14,15]
 ; AVX1-NEXT:    vpor %xmm0, %xmm1, %xmm0
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v32i8_42_45_12_13_35_35_60_40_17_22_29_44_33_12_48_51_20_19_52_19_49_54_37_32_48_42_59_07_36_34_36_39
+; AVX2-LABEL: shuffle_v32i8_42_45_12_13_35_35_60_40_17_22_29_44_33_12_48_51_20_19_52_19_49_54_37_32_48_42_59_07_36_34_36_39:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm2 = ymm1[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm2 = ymm2[u,u,u,u,u,u,12,u,u,u,u,u,u,u,0,3,u,u,u,u,u,u,21,16,u,26,u,u,20,18,20,23]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm1 = ymm1[10,13,u,u,3,3,u,8,u,u,u,12,1,u,u,u,u,u,20,u,17,22,u,u,16,u,27,u,u,u,u,u]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm3 = <255,255,u,u,255,255,0,255,u,u,u,255,255,u,0,0,u,u,255,u,255,255,0,0,255,0,255,u,0,0,0,0>
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm2 = ymm1[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm2 = ymm2[u,u,u,u,u,u,12,u,u,u,u,u,u,u,0,3,u,u,u,u,u,u,21,16,u,26,u,u,20,18,20,23]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[10,13,u,u,3,3,u,8,u,u,u,12,1,u,u,u,u,u,20,u,17,22,u,u,16,u,27,u,u,u,u,u]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm3 = <255,255,u,u,255,255,0,255,u,u,u,255,255,u,0,0,u,u,255,u,255,255,0,0,255,0,255,u,0,0,0,0>
 ; AVX2-NEXT:    vpblendvb %ymm3, %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vperm2i128 {{.*}} # ymm2 = ymm0[2,3,0,1]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm2 = ymm2[u,u,u,u,u,u,u,u,1,6,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,23,u,u,u,u]
-; AVX2-NEXT:    vpshufb {{.*}} # ymm0 = ymm0[u,u,12,13,u,u,u,u,u,u,u,u,u,12,u,u,20,19,u,19,u,u,u,u,u,u,u,u,u,u,u,u]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm2[2],ymm0[3,4,5],ymm2[6],ymm0[7]
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = [255,255,0,0,255,255,255,255,0,0,0,255,255,0,255,255,0,0,255,0,255,255,255,255,255,255,255,0,255,255,255,255]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm2 = ymm2[u,u,u,u,u,u,u,u,1,6,13,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,u,23,u,u,u,u]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,12,13,u,u,u,u,u,u,u,u,u,12,u,u,20,19,u,19,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm2[2],ymm0[3,4,5],ymm2[6],ymm0[7]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,255,0,0,255,255,255,255,0,0,0,255,255,0,255,255,0,0,255,0,255,255,255,255,255,255,255,0,255,255,255,255]
 ; AVX2-NEXT:    vpblendvb %ymm2, %ymm1, %ymm0, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <32 x i8> %a, <32 x i8> %b, <32 x i32> <i32 42, i32 45, i32 12, i32 13, i32 35, i32 35, i32 60, i32 40, i32 17, i32 22, i32 29, i32 44, i32 33, i32 12, i32 48, i32 51, i32 20, i32 19, i32 52, i32 19, i32 49, i32 54, i32 37, i32 32, i32 48, i32 42, i32 59, i32 7, i32 36, i32 34, i32 36, i32 39>
diff --git a/test/CodeGen/X86/vector-shuffle-256-v4.ll b/test/CodeGen/X86/vector-shuffle-256-v4.ll
index 717c7cddba7..74662ac82e4 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v4.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v4.ll
@@ -4,661 +4,661 @@
 target triple = "x86_64-unknown-unknown"
 
 define <4 x double> @shuffle_v4f64_0000(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_0000
+; AVX1-LABEL: shuffle_v4f64_0000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_0000
+; AVX2-LABEL: shuffle_v4f64_0000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0001(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_0001
+; AVX1-LABEL: shuffle_v4f64_0001:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm0[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_0001
+; AVX2-LABEL: shuffle_v4f64_0001:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,1]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,1]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0020(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_0020
+; AVX1-LABEL: shuffle_v4f64_0020:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0],xmm0[0]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_0020
+; AVX2-LABEL: shuffle_v4f64_0020:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,2,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,2,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0300(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_0300
+; AVX1-LABEL: shuffle_v4f64_0300:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,1,2,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[0,1,2,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_0300
+; AVX2-LABEL: shuffle_v4f64_0300:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,3,0,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,3,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 3, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1000(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_1000
+; AVX1-LABEL: shuffle_v4f64_1000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm0[1,0]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_1000
+; AVX2-LABEL: shuffle_v4f64_1000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[1,0,0,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_2200(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_2200
+; AVX1-LABEL: shuffle_v4f64_2200:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,2]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_2200
+; AVX2-LABEL: shuffle_v4f64_2200:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,2,0,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 2, i32 2, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_3330(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_3330
+; AVX1-LABEL: shuffle_v4f64_3330:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,1,2,2]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,3,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2],ymm1[3]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,1,2,2]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,3,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_3330
+; AVX2-LABEL: shuffle_v4f64_3330:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,3,3,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,3,3,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_3210(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_3210
+; AVX1-LABEL: shuffle_v4f64_3210:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,3,2]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_3210
+; AVX2-LABEL: shuffle_v4f64_3210:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,2,1,0]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,2,1,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0023(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0023
+; ALL-LABEL: shuffle_v4f64_0023:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0022(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0022
+; ALL-LABEL: shuffle_v4f64_0022:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,2]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 2>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1032(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_1032
+; ALL-LABEL: shuffle_v4f64_1032:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1133(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_1133
+; ALL-LABEL: shuffle_v4f64_1133:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,1,3,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,3,3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 1, i32 3, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1023(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_1023
+; ALL-LABEL: shuffle_v4f64_1023:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 0, i32 2, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1022(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_1022
+; ALL-LABEL: shuffle_v4f64_1022:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,2]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 0, i32 2, i32 2>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0423(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0423
+; ALL-LABEL: shuffle_v4f64_0423:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0462(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0462
+; ALL-LABEL: shuffle_v4f64_0462:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,0,2,2]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2],ymm0[3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 6, i32 2>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0426(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0426
+; ALL-LABEL: shuffle_v4f64_0426:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpcklpd {{.*}} # ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
+; ALL-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[2],ymm1[2]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 6>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1537(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_1537
+; ALL-LABEL: shuffle_v4f64_1537:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpckhpd {{.*}} # ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
+; ALL-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm0[1],ymm1[1],ymm0[3],ymm1[3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 5, i32 3, i32 7>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_4062(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_4062
+; ALL-LABEL: shuffle_v4f64_4062:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpcklpd {{.*}} # ymm0 = ymm1[0],ymm0[0],ymm1[2],ymm0[2]
+; ALL-NEXT:    vunpcklpd {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[2],ymm0[2]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 4, i32 0, i32 6, i32 2>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_5173(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_5173
+; ALL-LABEL: shuffle_v4f64_5173:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpckhpd {{.*}} # ymm0 = ymm1[1],ymm0[1],ymm1[3],ymm0[3]
+; ALL-NEXT:    vunpckhpd {{.*#+}} ymm0 = ymm1[1],ymm0[1],ymm1[3],ymm0[3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 5, i32 1, i32 7, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_5163(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_5163
+; ALL-LABEL: shuffle_v4f64_5163:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vshufpd {{.*}} # ymm0 = ymm1[1],ymm0[1],ymm1[2],ymm0[3]
+; ALL-NEXT:    vshufpd {{.*#+}} ymm0 = ymm1[1],ymm0[1],ymm1[2],ymm0[3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 5, i32 1, i32 6, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0527(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0527
+; ALL-LABEL: shuffle_v4f64_0527:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 5, i32 2, i32 7>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_4163(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_4163
+; ALL-LABEL: shuffle_v4f64_4163:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 4, i32 1, i32 6, i32 3>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0145(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_0145
+; AVX1-LABEL: shuffle_v4f64_0145:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_0145
+; AVX2-LABEL: shuffle_v4f64_0145:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,1,0,1]
-; AVX2-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,1,0,1]
+; AVX2-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_4501(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: @shuffle_v4f64_4501
+; AVX1-LABEL: shuffle_v4f64_4501:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4f64_4501
+; AVX2-LABEL: shuffle_v4f64_4501:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,0,1]
-; AVX2-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX2-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0167(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0167
+; ALL-LABEL: shuffle_v4f64_0167:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 1, i32 6, i32 7>
   ret <4 x double> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0000(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0000
+; AVX1-LABEL: shuffle_v4i64_0000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0000
+; AVX2-LABEL: shuffle_v4i64_0000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0001(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0001
+; AVX1-LABEL: shuffle_v4i64_0001:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm0[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0001
+; AVX2-LABEL: shuffle_v4i64_0001:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,1]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,1]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0020(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0020
+; AVX1-LABEL: shuffle_v4i64_0020:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0],xmm0[0]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0020
+; AVX2-LABEL: shuffle_v4i64_0020:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,2,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,2,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0112(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0112
+; AVX1-LABEL: shuffle_v4i64_0112:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; AVX1-NEXT:    vshufpd {{.*}} # xmm1 = xmm0[1],xmm1[0]
+; AVX1-NEXT:    vshufpd {{.*#+}} xmm1 = xmm0[1],xmm1[0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0112
+; AVX2-LABEL: shuffle_v4i64_0112:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,1,2]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,2]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 1, i32 2>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0300(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0300
+; AVX1-LABEL: shuffle_v4i64_0300:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,1,2,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[0,1,2,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0300
+; AVX2-LABEL: shuffle_v4i64_0300:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,3,0,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,3,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 3, i32 0, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_1000(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_1000
+; AVX1-LABEL: shuffle_v4i64_1000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm0[1,0]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm0[1,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_1000
+; AVX2-LABEL: shuffle_v4i64_1000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,0,0,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_2200(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_2200
+; AVX1-LABEL: shuffle_v4i64_2200:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,2]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_2200
+; AVX2-LABEL: shuffle_v4i64_2200:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,2,0,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 2, i32 2, i32 0, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_3330(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_3330
+; AVX1-LABEL: shuffle_v4i64_3330:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,1,2,2]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,3,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2],ymm1[3]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,1,2,2]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,3,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_3330
+; AVX2-LABEL: shuffle_v4i64_3330:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,3,3,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,3,3,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_3210(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_3210
+; AVX1-LABEL: shuffle_v4i64_3210:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,3,2]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_3210
+; AVX2-LABEL: shuffle_v4i64_3210:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,2,1,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0124(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0124
+; AVX1-LABEL: shuffle_v4i64_0124:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm1 = xmm1[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1,2],ymm1[3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0124
+; AVX2-LABEL: shuffle_v4i64_0124:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,2,0]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,2,0]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 2, i32 4>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0142(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0142
+; AVX1-LABEL: shuffle_v4i64_0142:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,1,2,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,1,2,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0142
+; AVX2-LABEL: shuffle_v4i64_0142:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,0,3]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,2,2]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,0,3]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,2,2]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 2>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0412(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0412
+; AVX1-LABEL: shuffle_v4i64_0412:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vshufpd {{.*}} # xmm2 = xmm0[1],xmm2[0]
+; AVX1-NEXT:    vshufpd {{.*#+}} xmm2 = xmm0[1],xmm2[0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,0,2,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0412
+; AVX2-LABEL: shuffle_v4i64_0412:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[0,1,0,1,4,5,4,5]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,1,2]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,2]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 2>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_4012(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_4012
+; AVX1-LABEL: shuffle_v4i64_4012:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vshufpd {{.*}} # xmm2 = xmm0[1],xmm2[0]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vshufpd {{.*#+}} xmm2 = xmm0[1],xmm2[0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm0 = xmm0[0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_4012
+; AVX2-LABEL: shuffle_v4i64_4012:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,1,2]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,1,2]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 4, i32 0, i32 1, i32 2>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0145(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0145
+; AVX1-LABEL: shuffle_v4i64_0145:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0145
+; AVX2-LABEL: shuffle_v4i64_0145:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,0,1]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,0,1]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_0451(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_0451
+; AVX1-LABEL: shuffle_v4i64_0451:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm2 = xmm1[0,0]
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm1[1,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm2 = xmm1[0,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2],ymm0[3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2],ymm0[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_0451
+; AVX2-LABEL: shuffle_v4i64_0451:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,0,1,3]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,2,1]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3,4,5],ymm0[6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,0,1,3]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,2,1]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 5, i32 1>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_4501(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_4501
+; AVX1-LABEL: shuffle_v4i64_4501:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_4501
+; AVX2-LABEL: shuffle_v4i64_4501:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,0,1]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_4015(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_4015
+; AVX1-LABEL: shuffle_v4i64_4015:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm2 = xmm0[0,0]
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm0 = xmm0[1,0]
+; AVX1-NEXT:    vunpcklpd {{.*#+}} xmm2 = xmm0[0,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1,2],ymm1[3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_4015
+; AVX2-LABEL: shuffle_v4i64_4015:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,2,1]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,1,3]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3,4,5],ymm1[6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,2,1]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,1,3]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5],ymm1[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 4, i32 0, i32 1, i32 5>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_2u35(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_2u35
+; AVX1-LABEL: shuffle_v4i64_2u35:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm2 = xmm0[1,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm0[1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1,2],ymm1[3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_2u35
+; AVX2-LABEL: shuffle_v4i64_2u35:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,2,1]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,1,3,3]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,2,1]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,1,3,3]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3,4,5],ymm1[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 2, i32 undef, i32 3, i32 5>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @shuffle_v4i64_1251(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @shuffle_v4i64_1251
+; AVX1-LABEL: shuffle_v4i64_1251:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm2 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vshufpd {{.*}} # ymm0 = ymm0[1],ymm2[0],ymm0[2],ymm2[3]
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm1[1,0]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vshufpd {{.*#+}} ymm0 = ymm0[1],ymm2[0],ymm0[2],ymm2[3]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v4i64_1251
+; AVX2-LABEL: shuffle_v4i64_1251:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,1,3]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,2,2,1]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,1,3]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,2,2,1]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 2, i32 5, i32 1>
   ret <4 x i64> %shuffle
 }
 
 define <4 x i64> @stress_test1(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: @stress_test1
+; 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:    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:    vextractf128 $1, %ymm1, %xmm1
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm1[1,0]
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,1,3,2]
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm2 = xmm1[1,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm1 = xmm1[1,0]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,3,2]
+; AVX1-NEXT:    vpermilpd {{.*#+}} xmm2 = xmm1[1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,2,2]
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,2]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @stress_test1
+; AVX2-LABEL: stress_test1:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm1[3,1,1,0]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,1,2,3]
-; AVX2-NEXT:    vpermq {{.*}} # ymm1 = ymm1[3,3,1,3]
-; AVX2-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[2,3,2,3,6,7,6,7]
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,1,0]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm1[3,1,1,0]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,1,2,3]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[3,3,1,3]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[2,3,2,3,6,7,6,7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,0]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3,4,5,6,7]
 ; AVX2-NEXT:    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>
@@ -669,18 +669,18 @@ define <4 x i64> @stress_test1(<4 x i64> %a, <4 x i64> %b) {
 }
 
 define <4 x i64> @insert_reg_and_zero_v4i64(i64 %a) {
-; AVX1-LABEL: @insert_reg_and_zero_v4i64
+; AVX1-LABEL: insert_reg_and_zero_v4i64:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vmovq %rdi, %xmm0
 ; AVX1-NEXT:    vxorpd %ymm1, %ymm1, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @insert_reg_and_zero_v4i64
+; AVX2-LABEL: insert_reg_and_zero_v4i64:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vmovq %rdi, %xmm0
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
 ; AVX2-NEXT:    retq
   %v = insertelement <4 x i64> undef, i64 %a, i64 0
   %shuffle = shufflevector <4 x i64> %v, <4 x i64> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
@@ -688,18 +688,18 @@ define <4 x i64> @insert_reg_and_zero_v4i64(i64 %a) {
 }
 
 define <4 x i64> @insert_mem_and_zero_v4i64(i64* %ptr) {
-; AVX1-LABEL: @insert_mem_and_zero_v4i64
+; AVX1-LABEL: insert_mem_and_zero_v4i64:
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vmovq (%rdi), %xmm0
 ; AVX1-NEXT:    vxorpd %ymm1, %ymm1, %ymm1
-; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @insert_mem_and_zero_v4i64
+; AVX2-LABEL: insert_mem_and_zero_v4i64:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vmovq (%rdi), %xmm0
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
 ; AVX2-NEXT:    retq
   %a = load i64* %ptr
   %v = insertelement <4 x i64> undef, i64 %a, i64 0
@@ -708,10 +708,11 @@ define <4 x i64> @insert_mem_and_zero_v4i64(i64* %ptr) {
 }
 
 define <4 x double> @insert_reg_and_zero_v4f64(double %a) {
-; ALL-LABEL: @insert_reg_and_zero_v4f64
+; ALL-LABEL: insert_reg_and_zero_v4f64:
 ; ALL:       # BB#0:
-; ALL:         vxorpd %ymm1, %ymm1, %ymm1
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; ALL-NEXT:   # kill: XMM0<def> XMM0<kill> YMM0<def>
+; ALL-NEXT:    vxorpd %ymm1, %ymm1, %ymm1
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; ALL-NEXT:    retq
   %v = insertelement <4 x double> undef, double %a, i32 0
   %shuffle = shufflevector <4 x double> %v, <4 x double> zeroinitializer, <4 x i32> <i32 0, i32 5, i32 6, i32 7>
@@ -719,11 +720,11 @@ define <4 x double> @insert_reg_and_zero_v4f64(double %a) {
 }
 
 define <4 x double> @insert_mem_and_zero_v4f64(double* %ptr) {
-; ALL-LABEL: @insert_mem_and_zero_v4f64
+; ALL-LABEL: insert_mem_and_zero_v4f64:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vmovsd (%rdi), %xmm0
 ; ALL-NEXT:    vxorpd %ymm1, %ymm1, %ymm1
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; ALL-NEXT:    retq
   %a = load double* %ptr
   %v = insertelement <4 x double> undef, double %a, i32 0
diff --git a/test/CodeGen/X86/vector-shuffle-256-v8.ll b/test/CodeGen/X86/vector-shuffle-256-v8.ll
index eec968eec2a..b9a2de0298b 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v8.ll
@@ -4,13 +4,13 @@
 target triple = "x86_64-unknown-unknown"
 
 define <8 x float> @shuffle_v8f32_00000000(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00000000
+; AVX1-LABEL: shuffle_v8f32_00000000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00000000
+; AVX2-LABEL: shuffle_v8f32_00000000:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vxorps %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
@@ -20,16 +20,16 @@ define <8 x float> @shuffle_v8f32_00000000(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_00000010(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00000010
+; AVX1-LABEL: shuffle_v8f32_00000010:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,0,1,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00000010
+; AVX2-LABEL: shuffle_v8f32_00000010:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,0,0,0,0,1,0]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,0,0,0,0,1,0]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -37,16 +37,16 @@ define <8 x float> @shuffle_v8f32_00000010(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_00000200(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00000200
+; AVX1-LABEL: shuffle_v8f32_00000200:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,2,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00000200
+; AVX2-LABEL: shuffle_v8f32_00000200:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,0,0,0,2,0,0]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,0,0,0,2,0,0]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -54,16 +54,16 @@ define <8 x float> @shuffle_v8f32_00000200(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_00003000(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00003000
+; AVX1-LABEL: shuffle_v8f32_00003000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[3,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00003000
+; AVX2-LABEL: shuffle_v8f32_00003000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,0,0,3,0,0,0]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,0,0,3,0,0,0]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -71,17 +71,17 @@ define <8 x float> @shuffle_v8f32_00003000(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_00040000(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00040000
+; AVX1-LABEL: shuffle_v8f32_00040000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[0,0,0,0,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,3,4,4,4,7]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[0,0,0,0,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,3,4,4,4,7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00040000
+; AVX2-LABEL: shuffle_v8f32_00040000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,0,4,0,0,0,0]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,0,4,0,0,0,0]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -89,17 +89,17 @@ define <8 x float> @shuffle_v8f32_00040000(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_00500000(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00500000
+; AVX1-LABEL: shuffle_v8f32_00500000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[u,u,1,u,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,0,4,4,6,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0,1],ymm1[2],ymm0[3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[u,u,1,u,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,0,4,4,6,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3],ymm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00500000
+; AVX2-LABEL: shuffle_v8f32_00500000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,5,0,0,0,0,0]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,5,0,0,0,0,0]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -107,17 +107,17 @@ define <8 x float> @shuffle_v8f32_00500000(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_06000000(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_06000000
+; AVX1-LABEL: shuffle_v8f32_06000000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[u,2,u,u,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,0,0,4,5,4,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[u,2,u,u,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,0,0,4,5,4,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_06000000
+; AVX2-LABEL: shuffle_v8f32_06000000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,6,0,0,0,0,0,0]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,6,0,0,0,0,0,0]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -125,15 +125,15 @@ define <8 x float> @shuffle_v8f32_06000000(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_70000000(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_70000000
+; AVX1-LABEL: shuffle_v8f32_70000000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[3,u,u,u,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,0,4,4,4,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[3,u,u,u,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_70000000
+; AVX2-LABEL: shuffle_v8f32_70000000:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    movl $7, %eax
@@ -147,25 +147,25 @@ define <8 x float> @shuffle_v8f32_70000000(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_01014545(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_01014545
+; ALL-LABEL: shuffle_v8f32_01014545:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 4, i32 5, i32 4, i32 5>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00112233(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00112233
+; AVX1-LABEL: shuffle_v8f32_00112233:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklps {{.*}} # xmm1 = xmm0[0,0,1,1]
-; AVX1-NEXT:    vunpckhps {{.*}} # xmm0 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vunpcklps {{.*#+}} xmm1 = xmm0[0,0,1,1]
+; AVX1-NEXT:    vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00112233
+; AVX2-LABEL: shuffle_v8f32_00112233:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,1,1,2,2,3,3]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,1,1,2,2,3,3]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 1, i32 1, i32 2, i32 2, i32 3, i32 3>
@@ -173,16 +173,16 @@ define <8 x float> @shuffle_v8f32_00112233(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_00001111(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_00001111
+; AVX1-LABEL: shuffle_v8f32_00001111:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_00001111
+; AVX2-LABEL: shuffle_v8f32_00001111:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm1 = [0,0,0,0,1,1,1,1]
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm1 = [0,0,0,0,1,1,1,1]
 ; AVX2-NEXT:    vpermps %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
@@ -190,517 +190,517 @@ define <8 x float> @shuffle_v8f32_00001111(<8 x float> %a, <8 x float> %b) {
 }
 
 define <8 x float> @shuffle_v8f32_81a3c5e7(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_81a3c5e7
+; ALL-LABEL: shuffle_v8f32_81a3c5e7:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7]
+; ALL-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 5, i32 14, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_08080808(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_08080808
+; AVX1-LABEL: shuffle_v8f32_08080808:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm1[0,0,2,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,1,0,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,1,0,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_08080808
+; AVX2-LABEL: shuffle_v8f32_08080808:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vxorps %ymm2, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermps %ymm1, %ymm2, %ymm1
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_08084c4c(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_08084c4c
+; ALL-LABEL: shuffle_v8f32_08084c4c:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vshufps {{.*}} # ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
-; ALL-NEXT:    vshufps {{.*}} # ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
+; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 4, i32 12, i32 4, i32 12>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_8823cc67(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_8823cc67
+; ALL-LABEL: shuffle_v8f32_8823cc67:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vshufps {{.*}} # ymm0 = ymm1[0,0],ymm0[2,3],ymm1[4,4],ymm0[6,7]
+; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,0],ymm0[2,3],ymm1[4,4],ymm0[6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 8, i32 8, i32 2, i32 3, i32 12, i32 12, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_9832dc76(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_9832dc76
+; ALL-LABEL: shuffle_v8f32_9832dc76:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vshufps {{.*}} # ymm0 = ymm1[1,0],ymm0[3,2],ymm1[5,4],ymm0[7,6]
+; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[1,0],ymm0[3,2],ymm1[5,4],ymm0[7,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 9, i32 8, i32 3, i32 2, i32 13, i32 12, i32 7, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_9810dc54(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_9810dc54
+; ALL-LABEL: shuffle_v8f32_9810dc54:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vshufps {{.*}} # ymm0 = ymm1[1,0],ymm0[1,0],ymm1[5,4],ymm0[5,4]
+; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[1,0],ymm0[1,0],ymm1[5,4],ymm0[5,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 9, i32 8, i32 1, i32 0, i32 13, i32 12, i32 5, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_08194c5d(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_08194c5d
+; ALL-LABEL: shuffle_v8f32_08194c5d:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpcklps {{.*}} # ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; ALL-NEXT:    vunpcklps {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_2a3b6e7f(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_2a3b6e7f
+; ALL-LABEL: shuffle_v8f32_2a3b6e7f:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vunpckhps {{.*}} # ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; ALL-NEXT:    vunpckhps {{.*#+}} ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_08192a3b(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_08192a3b
+; AVX1-LABEL: shuffle_v8f32_08192a3b:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm1[0,0,2,1]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm1[0,2,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[0,0,2,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[2,1,3,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_08192a3b
+; AVX2-LABEL: shuffle_v8f32_08192a3b:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <u,0,u,1,u,2,u,3>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <u,0,u,1,u,2,u,3>
 ; AVX2-NEXT:    vpermps %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <0,u,1,u,2,u,3,u>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <0,u,1,u,2,u,3,u>
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_08991abb(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_08991abb
+; AVX1-LABEL: shuffle_v8f32_08991abb:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[1,1,2,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vunpcklps {{.*}} # xmm2 = xmm1[0,0,1,1]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm1[0,2,3,3]
+; AVX1-NEXT:    vunpcklps {{.*#+}} xmm2 = xmm1[0,0,1,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_08991abb
+; AVX2-LABEL: shuffle_v8f32_08991abb:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <0,u,u,u,1,u,u,u>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <u,0,1,1,u,2,3,3>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <u,0,1,1,u,2,3,3>
 ; AVX2-NEXT:    vpermps %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 9, i32 1, i32 10, i32 11, i32 11>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_091b2d3f(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_091b2d3f
+; AVX1-LABEL: shuffle_v8f32_091b2d3f:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[2,1,3,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_091b2d3f
+; AVX2-LABEL: shuffle_v8f32_091b2d3f:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <0,u,1,u,2,u,3,u>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <0,u,1,u,2,u,3,u>
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 9, i32 1, i32 11, i32 2, i32 13, i32 3, i32 15>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_09ab1def(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_09ab1def
+; AVX1-LABEL: shuffle_v8f32_09ab1def:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[1,1,2,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_09ab1def
+; AVX2-LABEL: shuffle_v8f32_09ab1def:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <0,u,u,u,1,u,u,u>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00014445(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00014445
+; ALL-LABEL: shuffle_v8f32_00014445:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,1,4,4,4,5]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,1,4,4,4,5]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 4, i32 4, i32 4, i32 5>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00204464(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00204464
+; ALL-LABEL: shuffle_v8f32_00204464:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,0,4,4,6,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,0,4,4,6,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 0, i32 4, i32 4, i32 6, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_03004744(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_03004744
+; ALL-LABEL: shuffle_v8f32_03004744:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,3,0,0,4,7,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,3,0,0,4,7,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 3, i32 0, i32 0, i32 4, i32 7, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_10005444(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_10005444
+; ALL-LABEL: shuffle_v8f32_10005444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,0,0,5,4,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,0,0,5,4,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_22006644(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_22006644
+; ALL-LABEL: shuffle_v8f32_22006644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[2,2,0,0,6,6,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,2,0,0,6,6,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 6, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_33307774(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_33307774
+; ALL-LABEL: shuffle_v8f32_33307774:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,3,3,0,7,7,7,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,3,3,0,7,7,7,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 3, i32 3, i32 0, i32 7, i32 7, i32 7, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_32107654(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_32107654
+; ALL-LABEL: shuffle_v8f32_32107654:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00234467(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00234467
+; ALL-LABEL: shuffle_v8f32_00234467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,3,4,4,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,3,4,4,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 3, i32 4, i32 4, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00224466(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00224466
+; ALL-LABEL: shuffle_v8f32_00224466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,2,4,4,6,6]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_10325476(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_10325476
+; ALL-LABEL: shuffle_v8f32_10325476:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,3,2,5,4,7,6]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_11335577(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_11335577
+; ALL-LABEL: shuffle_v8f32_11335577:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,1,3,3,5,5,7,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_10235467(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_10235467
+; ALL-LABEL: shuffle_v8f32_10235467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,2,3,5,4,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,2,3,5,4,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 2, i32 3, i32 5, i32 4, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_10225466(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_10225466
+; ALL-LABEL: shuffle_v8f32_10225466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,2,2,5,4,6,6]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,2,2,5,4,6,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 2, i32 2, i32 5, i32 4, i32 6, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00015444(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00015444
+; ALL-LABEL: shuffle_v8f32_00015444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,1,5,4,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,1,5,4,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 5, i32 4, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00204644(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00204644
+; ALL-LABEL: shuffle_v8f32_00204644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,0,4,6,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,0,4,6,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 0, i32 4, i32 6, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_03004474(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_03004474
+; ALL-LABEL: shuffle_v8f32_03004474:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,3,0,0,4,4,7,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,3,0,0,4,4,7,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 3, i32 0, i32 0, i32 4, i32 4, i32 7, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_10004444(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_10004444
+; ALL-LABEL: shuffle_v8f32_10004444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,0,0,4,4,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,0,0,4,4,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_22006446(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_22006446
+; ALL-LABEL: shuffle_v8f32_22006446:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[2,2,0,0,6,4,4,6]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,2,0,0,6,4,4,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 4, i32 4, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_33307474(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_33307474
+; ALL-LABEL: shuffle_v8f32_33307474:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,3,3,0,7,4,7,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,3,3,0,7,4,7,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 3, i32 3, i32 0, i32 7, i32 4, i32 7, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_32104567(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_32104567
+; ALL-LABEL: shuffle_v8f32_32104567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,2,1,0,4,5,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,4,5,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 4, i32 5, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00236744(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00236744
+; ALL-LABEL: shuffle_v8f32_00236744:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,3,6,7,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,3,6,7,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 3, i32 6, i32 7, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00226644(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00226644
+; ALL-LABEL: shuffle_v8f32_00226644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,2,6,6,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,2,6,6,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 6, i32 6, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_10324567(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_10324567
+; ALL-LABEL: shuffle_v8f32_10324567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,3,2,4,5,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,3,2,4,5,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_11334567(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_11334567
+; ALL-LABEL: shuffle_v8f32_11334567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,1,3,3,4,5,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,1,3,3,4,5,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 4, i32 5, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_01235467(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_01235467
+; ALL-LABEL: shuffle_v8f32_01235467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,2,3,5,4,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,2,3,5,4,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_01235466(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_01235466
+; ALL-LABEL: shuffle_v8f32_01235466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,2,3,5,4,6,6]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,2,3,5,4,6,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_002u6u44(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_002u6u44
+; ALL-LABEL: shuffle_v8f32_002u6u44:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,u,6,u,4,4]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,u,6,u,4,4]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 undef, i32 6, i32 undef, i32 4, i32 4>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_00uu66uu(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_00uu66uu
+; ALL-LABEL: shuffle_v8f32_00uu66uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,u,u,6,6,u,u]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,u,u,6,6,u,u]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 undef, i32 undef, i32 6, i32 6, i32 undef, i32 undef>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_103245uu(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_103245uu
+; ALL-LABEL: shuffle_v8f32_103245uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,3,2,4,5,u,u]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,3,2,4,5,u,u]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 undef, i32 undef>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_1133uu67(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_1133uu67
+; ALL-LABEL: shuffle_v8f32_1133uu67:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,1,3,3,u,u,6,7]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,1,3,3,u,u,6,7]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 undef, i32 undef, i32 6, i32 7>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_0uu354uu(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_0uu354uu
+; ALL-LABEL: shuffle_v8f32_0uu354uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,u,u,3,5,4,u,u]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,u,u,3,5,4,u,u]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 undef, i32 undef, i32 3, i32 5, i32 4, i32 undef, i32 undef>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_uuu3uu66(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: @shuffle_v8f32_uuu3uu66
+; ALL-LABEL: shuffle_v8f32_uuu3uu66:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[u,u,u,3,u,u,6,6]
+; ALL-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[u,u,u,3,u,u,6,6]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 6>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_c348cda0(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_c348cda0
+; AVX1-LABEL: shuffle_v8f32_c348cda0:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm2 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vshufps {{.*}} # ymm0 = ymm0[0,3],ymm2[0,0],ymm0[4,7],ymm2[4,4]
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm2 = ymm1[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[0,1,2,0,4,5,6,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm1 = ymm2[0],ymm1[1,2,3,4,5],ymm2[6],ymm1[7]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6],ymm0[7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,3],ymm2[0,0],ymm0[4,7],ymm2[4,4]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[0,1,2,0,4,5,6,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm1 = ymm2[0],ymm1[1,2,3,4,5],ymm2[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6],ymm0[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_c348cda0
+; AVX2-LABEL: shuffle_v8f32_c348cda0:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <u,3,4,u,u,u,u,0>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <u,3,4,u,u,u,u,0>
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <4,u,u,0,4,5,2,u>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <4,u,u,0,4,5,2,u>
 ; AVX2-NEXT:    vpermps %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6],ymm0[7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6],ymm0[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 12, i32 3, i32 4, i32 8, i32 12, i32 13, i32 10, i32 0>
   ret <8 x float> %shuffle
 }
 
 define <8 x float> @shuffle_v8f32_f511235a(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: @shuffle_v8f32_f511235a
+; AVX1-LABEL: shuffle_v8f32_f511235a:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm2 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm2 = ymm2[u,1,u,u,6,7,u,u]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,1,1,4,5,5,5]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm2[1],ymm0[2,3],ymm2[4,5],ymm0[6,7]
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm1[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[3,1,2,2,7,5,6,6]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm2 = ymm2[u,1,u,u,6,7,u,u]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,1,1,4,5,5,5]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm2[1],ymm0[2,3],ymm2[4,5],ymm0[6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm1[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[3,1,2,2,7,5,6,6]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8f32_f511235a
+; AVX2-LABEL: shuffle_v8f32_f511235a:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <7,u,u,u,u,u,u,2>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <7,u,u,u,u,u,u,2>
 ; AVX2-NEXT:    vpermps %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vmovaps {{.*}} # ymm2 = <u,5,1,1,2,3,5,u>
+; AVX2-NEXT:    vmovaps {{.*#+}} ymm2 = <u,5,1,1,2,3,5,u>
 ; AVX2-NEXT:    vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
+; AVX2-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 15, i32 5, i32 1, i32 1, i32 2, i32 3, i32 5, i32 10>
   ret <8 x float> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00000000
+; AVX1-LABEL: shuffle_v8i32_00000000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00000000
+; AVX2-LABEL: shuffle_v8i32_00000000:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm1, %ymm1, %ymm1
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
@@ -710,16 +710,16 @@ define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00000010
+; AVX1-LABEL: shuffle_v8i32_00000010:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,0,1,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00000010
+; AVX2-LABEL: shuffle_v8i32_00000010:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,0,0,0,1,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,0,0,0,1,0]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -727,16 +727,16 @@ define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00000200
+; AVX1-LABEL: shuffle_v8i32_00000200:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,2,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,2,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00000200
+; AVX2-LABEL: shuffle_v8i32_00000200:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,0,0,2,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,0,0,2,0,0]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -744,16 +744,16 @@ define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00003000(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00003000
+; AVX1-LABEL: shuffle_v8i32_00003000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[3,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[3,0,0,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00003000
+; AVX2-LABEL: shuffle_v8i32_00003000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,0,3,0,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,0,3,0,0,0]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -761,17 +761,17 @@ define <8 x i32> @shuffle_v8i32_00003000(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00040000(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00040000
+; AVX1-LABEL: shuffle_v8i32_00040000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[0,0,0,0,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,3,4,4,4,7]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[0,0,0,0,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,3,4,4,4,7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0,1,2],ymm1[3,4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00040000
+; AVX2-LABEL: shuffle_v8i32_00040000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,4,0,0,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,4,0,0,0,0]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -779,17 +779,17 @@ define <8 x i32> @shuffle_v8i32_00040000(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00500000(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00500000
+; AVX1-LABEL: shuffle_v8i32_00500000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[u,u,1,u,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,0,4,4,6,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0,1],ymm1[2],ymm0[3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[u,u,1,u,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,0,4,4,6,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0,1],ymm1[2],ymm0[3],ymm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00500000
+; AVX2-LABEL: shuffle_v8i32_00500000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,5,0,0,0,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,5,0,0,0,0,0]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -797,17 +797,17 @@ define <8 x i32> @shuffle_v8i32_00500000(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_06000000(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_06000000
+; AVX1-LABEL: shuffle_v8i32_06000000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[u,2,u,u,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,0,0,4,5,4,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[u,2,u,u,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,0,0,4,5,4,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3],ymm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_06000000
+; AVX2-LABEL: shuffle_v8i32_06000000:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,6,0,0,0,0,0,0]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,6,0,0,0,0,0,0]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -815,15 +815,15 @@ define <8 x i32> @shuffle_v8i32_06000000(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_70000000(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_70000000
+; AVX1-LABEL: shuffle_v8i32_70000000:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm1 = ymm1[3,u,u,u,4,4,4,4]
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,0,4,4,4,4]
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4,5,6,7]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm1 = ymm1[3,u,u,u,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_70000000
+; AVX2-LABEL: shuffle_v8i32_70000000:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %xmm1, %xmm1, %xmm1
 ; AVX2-NEXT:    movl $7, %eax
@@ -837,30 +837,30 @@ define <8 x i32> @shuffle_v8i32_70000000(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_01014545(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_01014545
+; AVX1-LABEL: shuffle_v8i32_01014545:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,2]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_01014545
+; AVX2-LABEL: shuffle_v8i32_01014545:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,1,0,1,4,5,4,5]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 4, i32 5, i32 4, i32 5>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00112233
+; AVX1-LABEL: shuffle_v8i32_00112233:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklps {{.*}} # xmm1 = xmm0[0,0,1,1]
-; AVX1-NEXT:    vunpckhps {{.*}} # xmm0 = xmm0[2,2,3,3]
+; AVX1-NEXT:    vunpcklps {{.*#+}} xmm1 = xmm0[0,0,1,1]
+; AVX1-NEXT:    vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00112233
+; AVX2-LABEL: shuffle_v8i32_00112233:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,1,1,2,2,3,3]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,1,1,2,2,3,3]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 1, i32 1, i32 2, i32 2, i32 3, i32 3>
@@ -868,16 +868,16 @@ define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00001111(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00001111
+; AVX1-LABEL: shuffle_v8i32_00001111:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00001111
+; AVX2-LABEL: shuffle_v8i32_00001111:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,0,1,1,1,1]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,0,1,1,1,1]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
@@ -885,407 +885,407 @@ define <8 x i32> @shuffle_v8i32_00001111(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_81a3c5e7(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_81a3c5e7
+; AVX1-LABEL: shuffle_v8i32_81a3c5e7:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_81a3c5e7
+; AVX2-LABEL: shuffle_v8i32_81a3c5e7:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1],ymm1[2],ymm0[3],ymm1[4],ymm0[5],ymm1[6],ymm0[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 5, i32 14, i32 7>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_08080808(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_08080808
+; AVX1-LABEL: shuffle_v8i32_08080808:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm1[0,0,2,0]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,1,0,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,1,0,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_08080808
+; AVX2-LABEL: shuffle_v8i32_08080808:
 ; AVX2:       # BB#0:
 ; AVX2-NEXT:    vpxor %ymm2, %ymm2, %ymm2
 ; AVX2-NEXT:    vpermd %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_08084c4c(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_08084c4c
+; AVX1-LABEL: shuffle_v8i32_08084c4c:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vshufps {{.*}} # ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
-; AVX1-NEXT:    vshufps {{.*}} # ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_08084c4c
+; AVX2-LABEL: shuffle_v8i32_08084c4c:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[0,0,2,0,4,4,6,4]
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,1,0,1,4,5,4,5]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,0,2,0,4,4,6,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 4, i32 12, i32 4, i32 12>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_8823cc67(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_8823cc67
+; AVX1-LABEL: shuffle_v8i32_8823cc67:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vshufps {{.*}} # ymm0 = ymm1[0,0],ymm0[2,3],ymm1[4,4],ymm0[6,7]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,0],ymm0[2,3],ymm1[4,4],ymm0[6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_8823cc67
+; AVX2-LABEL: shuffle_v8i32_8823cc67:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[0,0,2,3,4,4,6,7]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,0,2,3,4,4,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 8, i32 8, i32 2, i32 3, i32 12, i32 12, i32 6, i32 7>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_9832dc76(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_9832dc76
+; AVX1-LABEL: shuffle_v8i32_9832dc76:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vshufps {{.*}} # ymm0 = ymm1[1,0],ymm0[3,2],ymm1[5,4],ymm0[7,6]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[1,0],ymm0[3,2],ymm1[5,4],ymm0[7,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_9832dc76
+; AVX2-LABEL: shuffle_v8i32_9832dc76:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,1,3,2,4,5,7,6]
-; AVX2-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[1,0,2,3,5,4,6,7]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,1,3,2,4,5,7,6]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[1,0,2,3,5,4,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 9, i32 8, i32 3, i32 2, i32 13, i32 12, i32 7, i32 6>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_9810dc54(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_9810dc54
+; AVX1-LABEL: shuffle_v8i32_9810dc54:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vshufps {{.*}} # ymm0 = ymm1[1,0],ymm0[1,0],ymm1[5,4],ymm0[5,4]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[1,0],ymm0[1,0],ymm1[5,4],ymm0[5,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_9810dc54
+; AVX2-LABEL: shuffle_v8i32_9810dc54:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,1,1,0,4,5,5,4]
-; AVX2-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[1,0,2,3,5,4,6,7]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,1,1,0,4,5,5,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[1,0,2,3,5,4,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 9, i32 8, i32 1, i32 0, i32 13, i32 12, i32 5, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_08194c5d(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_08194c5d
+; AVX1-LABEL: shuffle_v8i32_08194c5d:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpcklps {{.*}} # ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; AVX1-NEXT:    vunpcklps {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_08194c5d
+; AVX2-LABEL: shuffle_v8i32_08194c5d:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpckldq {{.*}} # ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
+; AVX2-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[4],ymm1[4],ymm0[5],ymm1[5]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_2a3b6e7f(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_2a3b6e7f
+; AVX1-LABEL: shuffle_v8i32_2a3b6e7f:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vunpckhps {{.*}} # ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; AVX1-NEXT:    vunpckhps {{.*#+}} ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_2a3b6e7f
+; AVX2-LABEL: shuffle_v8i32_2a3b6e7f:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpunpckhdq {{.*}} # ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
+; AVX2-NEXT:    vpunpckhdq {{.*#+}} ymm0 = ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[6],ymm1[6],ymm0[7],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_08192a3b(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_08192a3b
+; AVX1-LABEL: shuffle_v8i32_08192a3b:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm1[0,0,2,1]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm1[0,2,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm1[0,0,2,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,2,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[2,1,3,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_08192a3b
+; AVX2-LABEL: shuffle_v8i32_08192a3b:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <u,0,u,1,u,2,u,3>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <u,0,u,1,u,2,u,3>
 ; AVX2-NEXT:    vpermd %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <0,u,1,u,2,u,3,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <0,u,1,u,2,u,3,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_08991abb(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_08991abb
+; AVX1-LABEL: shuffle_v8i32_08991abb:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[1,1,2,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vunpcklps {{.*}} # xmm2 = xmm1[0,0,1,1]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm1 = xmm1[0,2,3,3]
+; AVX1-NEXT:    vunpcklps {{.*#+}} xmm2 = xmm1[0,0,1,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm1 = xmm1[0,2,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_08991abb
+; AVX2-LABEL: shuffle_v8i32_08991abb:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <0,u,u,u,1,u,u,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <u,0,1,1,u,2,3,3>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <u,0,1,1,u,2,3,3>
 ; AVX2-NEXT:    vpermd %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 9, i32 1, i32 10, i32 11, i32 11>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_091b2d3f(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_091b2d3f
+; AVX1-LABEL: shuffle_v8i32_091b2d3f:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[2,1,3,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_091b2d3f
+; AVX2-LABEL: shuffle_v8i32_091b2d3f:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <0,u,1,u,2,u,3,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <0,u,1,u,2,u,3,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 9, i32 1, i32 11, i32 2, i32 13, i32 3, i32 15>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_09ab1def(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_09ab1def
+; AVX1-LABEL: shuffle_v8i32_09ab1def:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[1,1,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[1,1,2,3]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_09ab1def
+; AVX2-LABEL: shuffle_v8i32_09ab1def:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <0,u,u,u,1,u,u,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm2, %ymm0
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00014445(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00014445
+; AVX1-LABEL: shuffle_v8i32_00014445:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,1,4,4,4,5]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,1,4,4,4,5]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00014445
+; AVX2-LABEL: shuffle_v8i32_00014445:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,0,0,1,4,4,4,5]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,0,0,1,4,4,4,5]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 4, i32 4, i32 4, i32 5>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00204464(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00204464
+; AVX1-LABEL: shuffle_v8i32_00204464:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,0,4,4,6,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,0,4,4,6,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00204464
+; AVX2-LABEL: shuffle_v8i32_00204464:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,0,2,0,4,4,6,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,0,2,0,4,4,6,4]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 0, i32 4, i32 4, i32 6, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_03004744(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_03004744
+; AVX1-LABEL: shuffle_v8i32_03004744:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,3,0,0,4,7,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,3,0,0,4,7,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_03004744
+; AVX2-LABEL: shuffle_v8i32_03004744:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,3,0,0,4,7,4,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,3,0,0,4,7,4,4]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 3, i32 0, i32 0, i32 4, i32 7, i32 4, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_10005444(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_10005444
+; AVX1-LABEL: shuffle_v8i32_10005444:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,0,0,5,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,0,0,5,4,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_10005444
+; AVX2-LABEL: shuffle_v8i32_10005444:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[1,0,0,0,5,4,4,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[1,0,0,0,5,4,4,4]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_22006644(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_22006644
+; AVX1-LABEL: shuffle_v8i32_22006644:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[2,2,0,0,6,6,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,2,0,0,6,6,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_22006644
+; AVX2-LABEL: shuffle_v8i32_22006644:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[2,2,0,0,6,6,4,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,2,0,0,6,6,4,4]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 6, i32 4, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_33307774(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_33307774
+; AVX1-LABEL: shuffle_v8i32_33307774:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,3,3,0,7,7,7,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,3,3,0,7,7,7,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_33307774
+; AVX2-LABEL: shuffle_v8i32_33307774:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[3,3,3,0,7,7,7,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[3,3,3,0,7,7,7,4]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 3, i32 3, i32 0, i32 7, i32 7, i32 7, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_32107654(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_32107654
+; AVX1-LABEL: shuffle_v8i32_32107654:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_32107654
+; AVX2-LABEL: shuffle_v8i32_32107654:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00234467(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00234467
+; AVX1-LABEL: shuffle_v8i32_00234467:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,3,4,4,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,3,4,4,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00234467
+; AVX2-LABEL: shuffle_v8i32_00234467:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,0,2,3,4,4,6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,0,2,3,4,4,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 3, i32 4, i32 4, i32 6, i32 7>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00224466(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00224466
+; AVX1-LABEL: shuffle_v8i32_00224466:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,2,4,4,6,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00224466
+; AVX2-LABEL: shuffle_v8i32_00224466:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,0,2,2,4,4,6,6]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,0,2,2,4,4,6,6]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_10325476(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_10325476
+; AVX1-LABEL: shuffle_v8i32_10325476:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,3,2,5,4,7,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_10325476
+; AVX2-LABEL: shuffle_v8i32_10325476:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[1,0,3,2,5,4,7,6]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[1,0,3,2,5,4,7,6]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_11335577(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_11335577
+; AVX1-LABEL: shuffle_v8i32_11335577:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,1,3,3,5,5,7,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_11335577
+; AVX2-LABEL: shuffle_v8i32_11335577:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[1,1,3,3,5,5,7,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[1,1,3,3,5,5,7,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 5, i32 5, i32 7, i32 7>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_10235467(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_10235467
+; AVX1-LABEL: shuffle_v8i32_10235467:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,2,3,5,4,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,2,3,5,4,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_10235467
+; AVX2-LABEL: shuffle_v8i32_10235467:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[1,0,2,3,5,4,6,7]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[1,0,2,3,5,4,6,7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 2, i32 3, i32 5, i32 4, i32 6, i32 7>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_10225466(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_10225466
+; AVX1-LABEL: shuffle_v8i32_10225466:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,2,2,5,4,6,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,2,2,5,4,6,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_10225466
+; AVX2-LABEL: shuffle_v8i32_10225466:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[1,0,2,2,5,4,6,6]
+; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[1,0,2,2,5,4,6,6]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 2, i32 2, i32 5, i32 4, i32 6, i32 6>
   ret <8 x i32> %shuffle
 }
 
 define <8 x i32> @shuffle_v8i32_00015444(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00015444
+; AVX1-LABEL: shuffle_v8i32_00015444:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,0,1,5,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,1,5,4,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00015444
+; AVX2-LABEL: shuffle_v8i32_00015444:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,0,1,5,4,4,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,0,1,5,4,4,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 5, i32 4, i32 4, i32 4>
@@ -1293,14 +1293,14 @@ define <8 x i32> @shuffle_v8i32_00015444(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00204644(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00204644
+; AVX1-LABEL: shuffle_v8i32_00204644:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,0,4,6,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,0,4,6,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00204644
+; AVX2-LABEL: shuffle_v8i32_00204644:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,2,0,4,6,4,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,2,0,4,6,4,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 0, i32 4, i32 6, i32 4, i32 4>
@@ -1308,14 +1308,14 @@ define <8 x i32> @shuffle_v8i32_00204644(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_03004474(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_03004474
+; AVX1-LABEL: shuffle_v8i32_03004474:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,3,0,0,4,4,7,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,3,0,0,4,4,7,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_03004474
+; AVX2-LABEL: shuffle_v8i32_03004474:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,3,0,0,4,4,7,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,3,0,0,4,4,7,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 3, i32 0, i32 0, i32 4, i32 4, i32 7, i32 4>
@@ -1323,14 +1323,14 @@ define <8 x i32> @shuffle_v8i32_03004474(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_10004444(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_10004444
+; AVX1-LABEL: shuffle_v8i32_10004444:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,0,0,4,4,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,0,0,4,4,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_10004444
+; AVX2-LABEL: shuffle_v8i32_10004444:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [1,0,0,0,4,4,4,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,0,0,0,4,4,4,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
@@ -1338,14 +1338,14 @@ define <8 x i32> @shuffle_v8i32_10004444(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_22006446(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_22006446
+; AVX1-LABEL: shuffle_v8i32_22006446:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[2,2,0,0,6,4,4,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[2,2,0,0,6,4,4,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_22006446
+; AVX2-LABEL: shuffle_v8i32_22006446:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [2,2,0,0,6,4,4,6]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [2,2,0,0,6,4,4,6]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 4, i32 4, i32 6>
@@ -1353,14 +1353,14 @@ define <8 x i32> @shuffle_v8i32_22006446(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_33307474(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_33307474
+; AVX1-LABEL: shuffle_v8i32_33307474:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,3,3,0,7,4,7,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,3,3,0,7,4,7,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_33307474
+; AVX2-LABEL: shuffle_v8i32_33307474:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [3,3,3,0,7,4,7,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [3,3,3,0,7,4,7,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 3, i32 3, i32 0, i32 7, i32 4, i32 7, i32 4>
@@ -1368,14 +1368,14 @@ define <8 x i32> @shuffle_v8i32_33307474(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_32104567(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_32104567
+; AVX1-LABEL: shuffle_v8i32_32104567:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[3,2,1,0,4,5,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_32104567
+; AVX2-LABEL: shuffle_v8i32_32104567:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [3,2,1,0,4,5,6,7]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [3,2,1,0,4,5,6,7]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 4, i32 5, i32 6, i32 7>
@@ -1383,14 +1383,14 @@ define <8 x i32> @shuffle_v8i32_32104567(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00236744(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00236744
+; AVX1-LABEL: shuffle_v8i32_00236744:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,3,6,7,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,3,6,7,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00236744
+; AVX2-LABEL: shuffle_v8i32_00236744:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,2,3,6,7,4,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,2,3,6,7,4,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 3, i32 6, i32 7, i32 4, i32 4>
@@ -1398,14 +1398,14 @@ define <8 x i32> @shuffle_v8i32_00236744(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00226644(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00226644
+; AVX1-LABEL: shuffle_v8i32_00226644:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,2,6,6,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,2,6,6,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00226644
+; AVX2-LABEL: shuffle_v8i32_00226644:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,0,2,2,6,6,4,4]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,0,2,2,6,6,4,4]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 6, i32 6, i32 4, i32 4>
@@ -1413,14 +1413,14 @@ define <8 x i32> @shuffle_v8i32_00226644(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_10324567(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_10324567
+; AVX1-LABEL: shuffle_v8i32_10324567:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,3,2,4,5,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,3,2,4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_10324567
+; AVX2-LABEL: shuffle_v8i32_10324567:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [1,0,3,2,4,5,6,7]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,0,3,2,4,5,6,7]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 6, i32 7>
@@ -1428,14 +1428,14 @@ define <8 x i32> @shuffle_v8i32_10324567(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_11334567(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_11334567
+; AVX1-LABEL: shuffle_v8i32_11334567:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,1,3,3,4,5,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,1,3,3,4,5,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_11334567
+; AVX2-LABEL: shuffle_v8i32_11334567:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [1,1,3,3,4,5,6,7]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [1,1,3,3,4,5,6,7]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 4, i32 5, i32 6, i32 7>
@@ -1443,14 +1443,14 @@ define <8 x i32> @shuffle_v8i32_11334567(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_01235467(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_01235467
+; AVX1-LABEL: shuffle_v8i32_01235467:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,2,3,5,4,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,2,3,5,4,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_01235467
+; AVX2-LABEL: shuffle_v8i32_01235467:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,1,2,3,5,4,6,7]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3,5,4,6,7]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 7>
@@ -1458,14 +1458,14 @@ define <8 x i32> @shuffle_v8i32_01235467(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_01235466(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_01235466
+; AVX1-LABEL: shuffle_v8i32_01235466:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,1,2,3,5,4,6,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,1,2,3,5,4,6,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_01235466
+; AVX2-LABEL: shuffle_v8i32_01235466:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = [0,1,2,3,5,4,6,6]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = [0,1,2,3,5,4,6,6]
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 6>
@@ -1473,14 +1473,14 @@ define <8 x i32> @shuffle_v8i32_01235466(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_002u6u44(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_002u6u44
+; AVX1-LABEL: shuffle_v8i32_002u6u44:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,2,u,6,u,4,4]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,2,u,6,u,4,4]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_002u6u44
+; AVX2-LABEL: shuffle_v8i32_002u6u44:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = <0,0,2,u,6,u,4,4>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = <0,0,2,u,6,u,4,4>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 undef, i32 6, i32 undef, i32 4, i32 4>
@@ -1488,14 +1488,14 @@ define <8 x i32> @shuffle_v8i32_002u6u44(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_00uu66uu(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_00uu66uu
+; AVX1-LABEL: shuffle_v8i32_00uu66uu:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,0,u,u,6,6,u,u]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,0,u,u,6,6,u,u]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_00uu66uu
+; AVX2-LABEL: shuffle_v8i32_00uu66uu:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = <0,0,u,u,6,6,u,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = <0,0,u,u,6,6,u,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 undef, i32 undef, i32 6, i32 6, i32 undef, i32 undef>
@@ -1503,14 +1503,14 @@ define <8 x i32> @shuffle_v8i32_00uu66uu(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_103245uu(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_103245uu
+; AVX1-LABEL: shuffle_v8i32_103245uu:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,0,3,2,4,5,u,u]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,0,3,2,4,5,u,u]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_103245uu
+; AVX2-LABEL: shuffle_v8i32_103245uu:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = <1,0,3,2,4,5,u,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = <1,0,3,2,4,5,u,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 4, i32 5, i32 undef, i32 undef>
@@ -1518,14 +1518,14 @@ define <8 x i32> @shuffle_v8i32_103245uu(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_1133uu67(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_1133uu67
+; AVX1-LABEL: shuffle_v8i32_1133uu67:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[1,1,3,3,u,u,6,7]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[1,1,3,3,u,u,6,7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_1133uu67
+; AVX2-LABEL: shuffle_v8i32_1133uu67:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = <1,1,3,3,u,u,6,7>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = <1,1,3,3,u,u,6,7>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 1, i32 1, i32 3, i32 3, i32 undef, i32 undef, i32 6, i32 7>
@@ -1533,14 +1533,14 @@ define <8 x i32> @shuffle_v8i32_1133uu67(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_0uu354uu(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_0uu354uu
+; AVX1-LABEL: shuffle_v8i32_0uu354uu:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[0,u,u,3,5,4,u,u]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[0,u,u,3,5,4,u,u]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_0uu354uu
+; AVX2-LABEL: shuffle_v8i32_0uu354uu:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = <0,u,u,3,5,4,u,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = <0,u,u,3,5,4,u,u>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 undef, i32 undef, i32 3, i32 5, i32 4, i32 undef, i32 undef>
@@ -1548,14 +1548,14 @@ define <8 x i32> @shuffle_v8i32_0uu354uu(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_uuu3uu66(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_uuu3uu66
+; AVX1-LABEL: shuffle_v8i32_uuu3uu66:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilps {{.*}} # ymm0 = ymm0[u,u,u,3,u,u,6,6]
+; AVX1-NEXT:    vpermilps {{.*#+}} ymm0 = ymm0[u,u,u,3,u,u,6,6]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_uuu3uu66
+; AVX2-LABEL: shuffle_v8i32_uuu3uu66:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm1 = <u,u,u,3,u,u,6,6>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm1 = <u,u,u,3,u,u,6,6>
 ; AVX2-NEXT:    vpermd %ymm0, %ymm1, %ymm0
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 6>
@@ -1563,23 +1563,23 @@ define <8 x i32> @shuffle_v8i32_uuu3uu66(<8 x i32> %a, <8 x i32> %b) {
 }
 
 define <8 x i32> @shuffle_v8i32_6caa87e5(<8 x i32> %a, <8 x i32> %b) {
-; AVX1-LABEL: @shuffle_v8i32_6caa87e5
+; AVX1-LABEL: shuffle_v8i32_6caa87e5:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vperm2f128 {{.*}} # ymm2 = ymm1[2,3,0,1]
-; AVX1-NEXT:    vshufps {{.*}} # ymm1 = ymm2[0,0],ymm1[2,2],ymm2[4,4],ymm1[6,6]
+; AVX1-NEXT:    vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,0,1]
+; AVX1-NEXT:    vshufps {{.*#+}} ymm1 = ymm2[0,0],ymm1[2,2],ymm2[4,4],ymm1[6,6]
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT:    vpermilps {{.*}} # xmm2 = xmm0[2,1,2,3]
-; AVX1-NEXT:    vpermilps {{.*}} # xmm0 = xmm0[0,3,2,1]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm2 = xmm0[2,1,2,3]
+; AVX1-NEXT:    vpermilps {{.*#+}} xmm0 = xmm0[0,3,2,1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
-; AVX1-NEXT:    vblendps {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7]
+; AVX1-NEXT:    vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7]
 ; AVX1-NEXT:    retq
 ;
-; AVX2-LABEL: @shuffle_v8i32_6caa87e5
+; AVX2-LABEL: shuffle_v8i32_6caa87e5:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vmovdqa {{.*}} # ymm2 = <u,4,2,2,0,u,6,u>
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = <u,4,2,2,0,u,6,u>
 ; AVX2-NEXT:    vpermd %ymm1, %ymm2, %ymm1
-; AVX2-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,1,3,2]
-; AVX2-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7]
+; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,1,3,2]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 6, i32 12, i32 10, i32 10, i32 8, i32 7, i32 14, i32 5>
   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 06097d970e6..09dde3132dd 100644
--- a/test/CodeGen/X86/vector-shuffle-512-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-512-v8.ll
@@ -4,9 +4,9 @@
 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-LABEL: shuffle_v8f64_00000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm0, %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>
@@ -14,10 +14,10 @@ define <8 x double> @shuffle_v8f64_00000000(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00000010(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00000010
+; ALL-LABEL: shuffle_v8f64_00000010:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,1,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,1,0]
 ; 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 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -25,10 +25,10 @@ define <8 x double> @shuffle_v8f64_00000010(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00000200(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00000200
+; ALL-LABEL: shuffle_v8f64_00000200:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,2,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,2,0,0]
 ; 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 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -36,10 +36,10 @@ define <8 x double> @shuffle_v8f64_00000200(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00003000(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00003000
+; ALL-LABEL: shuffle_v8f64_00003000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,0,0]
 ; 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 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -47,13 +47,13 @@ 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-LABEL: shuffle_v8f64_00040000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,1,2,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm0[0,0,0,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm1 = ymm2[0,1,2],ymm1[3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,1,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm0[0,0,0,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm2[0,1,2],ymm1[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; 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 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -61,13 +61,13 @@ 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-LABEL: shuffle_v8f64_00500000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,1,1,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm0[0,0,2,0]
-; ALL-NEXT:    vblendpd {{.*}} # ymm1 = ymm2[0,1],ymm1[2],ymm2[3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,1,1,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm0[0,0,2,0]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm2[0,1],ymm1[2],ymm2[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; 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 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -75,13 +75,13 @@ 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-LABEL: shuffle_v8f64_06000000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,2,2,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm0[0,1,0,0]
-; ALL-NEXT:    vblendpd {{.*}} # ymm1 = ymm2[0],ymm1[1],ymm2[2,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm0[0,1,0,0]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm2[0],ymm1[1],ymm2[2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; 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 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -89,12 +89,12 @@ 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-LABEL: shuffle_v8f64_70000000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[3,1,2,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
-; ALL-NEXT:    vblendpd {{.*}} # ymm1 = ymm1[0],ymm0[1,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[3,1,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm1[0],ymm0[1,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -102,11 +102,11 @@ 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-LABEL: shuffle_v8f64_01014545:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,1,0,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,1,0,1]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,0,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,1]
 ; 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 1, i32 0, i32 1, i32 4, i32 5, i32 4, i32 5>
@@ -114,10 +114,10 @@ define <8 x double> @shuffle_v8f64_01014545(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00112233(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00112233
+; ALL-LABEL: shuffle_v8f64_00112233:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,1,1]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,2,3,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,1,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,3,3]
 ; 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 1, i32 1, i32 2, i32 2, i32 3, i32 3>
@@ -125,10 +125,10 @@ define <8 x double> @shuffle_v8f64_00112233(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00001111(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00001111
+; ALL-LABEL: shuffle_v8f64_00001111:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[1,1,1,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[1,1,1,1]
 ; 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 0, i32 0, i32 1, i32 1, i32 1, i32 1>
@@ -136,12 +136,12 @@ 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-LABEL: shuffle_v8f64_81a3c5e7:
 ; ALL:       # BB#0:
 ; 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:    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
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 5, i32 14, i32 7>
@@ -149,11 +149,11 @@ define <8 x double> @shuffle_v8f64_81a3c5e7(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_08080808(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_08080808
+; ALL-LABEL: shuffle_v8f64_08080808:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,0,2,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,0,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,0,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8>
@@ -161,16 +161,16 @@ 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-LABEL: shuffle_v8f64_08084c4c:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm2[0,0,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,0,2,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm3
-; ALL-NEXT:    vpermpd {{.*}} # ymm3 = ymm3[0,1,0,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,0,2,0]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,0,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm3[0,1,0,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,0,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,0,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 4, i32 12, i32 4, i32 12>
@@ -178,14 +178,14 @@ 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-LABEL: shuffle_v8f64_8823cc67:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpermilpd {{.*}} # ymm3 = ymm3[0,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm3[0,1],ymm2[2,3]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm3 = ymm3[0,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 8, i32 8, i32 2, i32 3, i32 12, i32 12, i32 6, i32 7>
@@ -193,16 +193,16 @@ define <8 x double> @shuffle_v8f64_8823cc67(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_9832dc76(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_9832dc76
+; ALL-LABEL: shuffle_v8f64_9832dc76:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vpermilpd {{.*}} # ymm2 = ymm2[0,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm2 = ymm2[0,0,3,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpermilpd {{.*}} # ymm3 = ymm3[1,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm3[0,1],ymm2[2,3]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,3,2]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm3 = ymm3[1,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 9, i32 8, i32 3, i32 2, i32 13, i32 12, i32 7, i32 6>
@@ -210,16 +210,16 @@ define <8 x double> @shuffle_v8f64_9832dc76(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_9810dc54(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_9810dc54
+; ALL-LABEL: shuffle_v8f64_9810dc54:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm2[0,1,1,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,1,1,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpermilpd {{.*}} # ymm3 = ymm3[1,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm3[0,1],ymm2[2,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,1,0]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm3 = ymm3[1,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,0]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 9, i32 8, i32 1, i32 0, i32 13, i32 12, i32 5, i32 4>
@@ -227,16 +227,16 @@ 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-LABEL: shuffle_v8f64_08194c5d:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm2[0,0,2,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,0,2,1]
 ; 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]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,1,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; 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]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
@@ -244,16 +244,16 @@ 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-LABEL: shuffle_v8f64_2a3b6e7f:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm2[0,2,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; 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]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,1,3,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; 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]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,1,3,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
@@ -261,14 +261,14 @@ define <8 x double> @shuffle_v8f64_2a3b6e7f(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_08192a3b(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_08192a3b
-; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm1[0,2,2,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm3 = ymm0[2,1,3,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,0,2,1]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,1,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; ALL-LABEL: shuffle_v8f64_08192a3b:
+; ALL:       # BB#0:
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm1[0,2,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm0[2,1,3,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0],ymm2[1],ymm3[2],ymm2[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,0,2,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
@@ -276,13 +276,13 @@ define <8 x double> @shuffle_v8f64_08192a3b(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_08991abb(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_08991abb
+; ALL-LABEL: shuffle_v8f64_08991abb:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm2 = ymm0[1,0,2,2]
-; ALL-NEXT:    vpermpd {{.*}} # ymm3 = ymm1[0,2,3,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm2[0],ymm3[1,2,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,0,1,1]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm2 = ymm0[1,0,2,2]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm1[0,2,3,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm2[0],ymm3[1,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm1[0,0,1,1]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 9, i32 1, i32 10, i32 11, i32 11>
@@ -290,13 +290,13 @@ 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-LABEL: shuffle_v8f64_091b2d3f:
 ; ALL:       # BB#0:
 ; 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]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
+; 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]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 9, i32 1, i32 11, i32 2, i32 13, i32 3, i32 15>
@@ -304,12 +304,12 @@ 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-LABEL: shuffle_v8f64_09ab1def:
 ; ALL:       # BB#0:
 ; 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]
+; 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]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
@@ -317,11 +317,11 @@ define <8 x double> @shuffle_v8f64_09ab1def(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00014445(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00014445
+; ALL-LABEL: shuffle_v8f64_00014445:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,0,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,1]
 ; 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 0, i32 1, i32 4, i32 4, i32 4, i32 5>
@@ -329,11 +329,11 @@ define <8 x double> @shuffle_v8f64_00014445(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00204464(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00204464
+; ALL-LABEL: shuffle_v8f64_00204464:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,2,0]
 ; 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 0, i32 4, i32 4, i32 6, i32 4>
@@ -341,11 +341,11 @@ define <8 x double> @shuffle_v8f64_00204464(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_03004744(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_03004744
+; ALL-LABEL: shuffle_v8f64_03004744:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,3,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,3,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,3,0,0]
 ; 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 3, i32 0, i32 0, i32 4, i32 7, i32 4, i32 4>
@@ -353,11 +353,11 @@ define <8 x double> @shuffle_v8f64_03004744(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_10005444(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_10005444
+; ALL-LABEL: shuffle_v8f64_10005444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 0, i32 0, i32 0, i32 5, i32 4, i32 4, i32 4>
@@ -365,11 +365,11 @@ define <8 x double> @shuffle_v8f64_10005444(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_22006644(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_22006644
+; ALL-LABEL: shuffle_v8f64_22006644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[2,2,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,2,0,0]
+; 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 2, i32 2, i32 0, i32 0, i32 6, i32 6, i32 4, i32 4>
@@ -377,11 +377,11 @@ define <8 x double> @shuffle_v8f64_22006644(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_33307774(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_33307774
+; ALL-LABEL: shuffle_v8f64_33307774:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[3,3,3,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,3,3,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 3, i32 3, i32 3, i32 0, i32 7, i32 7, i32 7, i32 4>
@@ -389,11 +389,11 @@ define <8 x double> @shuffle_v8f64_33307774(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_32107654(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_32107654
+; ALL-LABEL: shuffle_v8f64_32107654:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[3,2,1,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,2,1,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4>
@@ -401,11 +401,11 @@ define <8 x double> @shuffle_v8f64_32107654(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00234467(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00234467
+; ALL-LABEL: shuffle_v8f64_00234467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[0,0,2,3]
 ; 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 3, i32 4, i32 4, i32 6, i32 7>
@@ -413,11 +413,11 @@ define <8 x double> @shuffle_v8f64_00234467(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00224466(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00224466
+; ALL-LABEL: shuffle_v8f64_00224466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} 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>
@@ -425,11 +425,11 @@ define <8 x double> @shuffle_v8f64_00224466(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_10325476(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_10325476
+; ALL-LABEL: shuffle_v8f64_10325476:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,3,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 0, i32 3, i32 2, i32 5, i32 4, i32 7, i32 6>
@@ -437,11 +437,11 @@ define <8 x double> @shuffle_v8f64_10325476(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_11335577(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_11335577
+; ALL-LABEL: shuffle_v8f64_11335577:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,1,3,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,1,3,3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,1,3,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,3,3]
 ; 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 5, i32 5, i32 7, i32 7>
@@ -449,11 +449,11 @@ define <8 x double> @shuffle_v8f64_11335577(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_10235467(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_10235467
+; ALL-LABEL: shuffle_v8f64_10235467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,2,3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,3]
 ; 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 2, i32 3, i32 5, i32 4, i32 6, i32 7>
@@ -461,11 +461,11 @@ define <8 x double> @shuffle_v8f64_10235467(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_10225466(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_10225466
+; ALL-LABEL: shuffle_v8f64_10225466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,2,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,2,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 0, i32 2, i32 2, i32 5, i32 4, i32 6, i32 6>
@@ -473,11 +473,11 @@ define <8 x double> @shuffle_v8f64_10225466(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00015444(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00015444
+; ALL-LABEL: shuffle_v8f64_00015444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,0,1]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; 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 0, i32 1, i32 5, i32 4, i32 4, i32 4>
@@ -485,11 +485,11 @@ define <8 x double> @shuffle_v8f64_00015444(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00204644(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00204644
+; ALL-LABEL: shuffle_v8f64_00204644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,2,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,2,0,0]
 ; 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 0, i32 4, i32 6, i32 4, i32 4>
@@ -497,11 +497,11 @@ define <8 x double> @shuffle_v8f64_00204644(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_03004474(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_03004474
+; ALL-LABEL: shuffle_v8f64_03004474:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[0,3,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,3,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,3,0]
 ; 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 3, i32 0, i32 0, i32 4, i32 4, i32 7, i32 4>
@@ -509,11 +509,11 @@ define <8 x double> @shuffle_v8f64_03004474(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_10004444(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_10004444
+; ALL-LABEL: shuffle_v8f64_10004444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 1, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
@@ -521,11 +521,11 @@ define <8 x double> @shuffle_v8f64_10004444(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_22006446(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_22006446
+; ALL-LABEL: shuffle_v8f64_22006446:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[2,2,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,0,0,2]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,0,0,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 4, i32 4, i32 6>
@@ -533,11 +533,11 @@ define <8 x double> @shuffle_v8f64_22006446(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_33307474(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_33307474
+; ALL-LABEL: shuffle_v8f64_33307474:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[3,3,3,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,0,3,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[3,0,3,0]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 3, i32 3, i32 3, i32 0, i32 7, i32 4, i32 7, i32 4>
@@ -545,9 +545,9 @@ define <8 x double> @shuffle_v8f64_33307474(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_32104567(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_32104567
+; ALL-LABEL: shuffle_v8f64_32104567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermpd {{.*}} # ymm1 = ymm0[3,2,1,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm1 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -556,11 +556,11 @@ define <8 x double> @shuffle_v8f64_32104567(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00236744(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00236744
+; ALL-LABEL: shuffle_v8f64_00236744:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,3,0,0]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,3,0,0]
 ; 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 3, i32 6, i32 7, i32 4, i32 4>
@@ -568,11 +568,11 @@ define <8 x double> @shuffle_v8f64_00236744(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00226644(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00226644
+; ALL-LABEL: shuffle_v8f64_00226644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,2,0,0]
+; 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>
@@ -580,9 +580,9 @@ define <8 x double> @shuffle_v8f64_00226644(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_10324567(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_10324567
+; ALL-LABEL: shuffle_v8f64_10324567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,3,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -591,9 +591,9 @@ define <8 x double> @shuffle_v8f64_10324567(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_11334567(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_11334567
+; ALL-LABEL: shuffle_v8f64_11334567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,1,3,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,1,3,3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -602,10 +602,10 @@ 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-LABEL: shuffle_v8f64_01235467:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,0,2,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 7>
@@ -613,10 +613,10 @@ 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-LABEL: shuffle_v8f64_01235466:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 6>
@@ -624,11 +624,11 @@ define <8 x double> @shuffle_v8f64_01235466(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_002u6u44(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_002u6u44
+; ALL-LABEL: shuffle_v8f64_002u6u44:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,1,0,0]
+; 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>
@@ -636,11 +636,11 @@ define <8 x double> @shuffle_v8f64_002u6u44(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_00uu66uu(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_00uu66uu
+; ALL-LABEL: shuffle_v8f64_00uu66uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[0,0,2,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,2,2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[2,2,2,3]
 ; 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 undef, i32 undef, i32 6, i32 6, i32 undef, i32 undef>
@@ -648,9 +648,9 @@ define <8 x double> @shuffle_v8f64_00uu66uu(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_103245uu(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_103245uu
+; ALL-LABEL: shuffle_v8f64_103245uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,0,3,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,0,3,2]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -659,9 +659,9 @@ define <8 x double> @shuffle_v8f64_103245uu(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_1133uu67(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_1133uu67
+; ALL-LABEL: shuffle_v8f64_1133uu67:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm0[1,1,3,3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm0[1,1,3,3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -670,10 +670,10 @@ 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-LABEL: shuffle_v8f64_0uu354uu:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm1 = ymm1[1,0,2,2]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 0, i32 undef, i32 undef, i32 3, i32 5, i32 4, i32 undef, i32 undef>
@@ -681,10 +681,10 @@ 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-LABEL: shuffle_v8f64_uuu3uu66:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,0,2,2]
+; ALL-NEXT:    vpermilpd {{.*#+}} 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>
@@ -692,19 +692,19 @@ define <8 x double> @shuffle_v8f64_uuu3uu66(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_c348cda0(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_c348cda0
+; ALL-LABEL: shuffle_v8f64_c348cda0:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vpermpd {{.*}} # ymm2 = ymm2[0,1,0,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm3 = ymm0[0,3,2,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm3[0,1],ymm2[2],ymm3[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm2 = ymm2[0,1,0,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm0[0,3,2,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2],ymm3[3]
 ; ALL-NEXT:    vextractf64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpermpd {{.*}} # ymm4 = ymm1[0,1,2,0]
-; ALL-NEXT:    vblendpd {{.*}} # ymm4 = ymm3[0,1,2],ymm4[3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm2 = ymm4[0],ymm2[1,2],ymm4[3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm1 = ymm3[0,1],ymm1[2],ymm3[3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,2,0]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1,2],ymm0[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm4 = ymm1[0,1,2,0]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm4 = ymm3[0,1,2],ymm4[3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm2 = ymm4[0],ymm2[1,2],ymm4[3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm1 = ymm3[0,1],ymm1[2],ymm3[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,2,0]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0,1,2],ymm0[3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm0, %zmm2, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 12, i32 3, i32 4, i32 8, i32 12, i32 13, i32 10, i32 0>
@@ -712,19 +712,19 @@ define <8 x double> @shuffle_v8f64_c348cda0(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x double> @shuffle_v8f64_f511235a(<8 x double> %a, <8 x double> %b) {
-; ALL-LABEL: @shuffle_v8f64_f511235a
+; ALL-LABEL: shuffle_v8f64_f511235a:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextractf64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vpermpd {{.*}} # ymm3 = ymm2[0,1,1,3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm4 = ymm0[2,3,2,3]
-; ALL-NEXT:    vblendpd {{.*}} # ymm3 = ymm4[0,1],ymm3[2],ymm4[3]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm4 = ymm1[0,0,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm3 = ymm3[0,1,2],ymm4[3]
-; ALL-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,1,1]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm2[1],ymm0[2,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm3 = ymm2[0,1,1,3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm4 = ymm0[2,3,2,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm3 = ymm4[0,1],ymm3[2],ymm4[3]
+; ALL-NEXT:    vpermilpd {{.*#+}} ymm4 = ymm1[0,0,2,2]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm3 = ymm3[0,1,2],ymm4[3]
+; ALL-NEXT:    vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,1]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm2[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:    vpermpd {{.*#+}} ymm1 = ymm1[3,1,2,3]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3]
 ; ALL-NEXT:    vinsertf64x4 $1, %ymm3, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x double> %a, <8 x double> %b, <8 x i32> <i32 15, i32 5, i32 1, i32 1, i32 2, i32 3, i32 5, i32 10>
@@ -732,9 +732,9 @@ define <8 x double> @shuffle_v8f64_f511235a(<8 x double> %a, <8 x double> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00000000(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00000000
+; ALL-LABEL: shuffle_v8i64_00000000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -742,10 +742,10 @@ define <8 x i64> @shuffle_v8i64_00000000(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00000010(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00000010
+; ALL-LABEL: shuffle_v8i64_00000010:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,1,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,1,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
@@ -753,10 +753,10 @@ define <8 x i64> @shuffle_v8i64_00000010(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00000200(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00000200
+; ALL-LABEL: shuffle_v8i64_00000200:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,2,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
@@ -764,10 +764,10 @@ define <8 x i64> @shuffle_v8i64_00000200(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00003000(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00003000
+; ALL-LABEL: shuffle_v8i64_00003000:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
@@ -775,13 +775,13 @@ 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-LABEL: shuffle_v8i64_00040000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,2,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm0[0,0,0,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm1 = ymm2[0,1,2,3,4,5],ymm1[6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm0[0,0,0,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm2[0,1,2,3,4,5],ymm1[6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 4, i32 0, i32 0, i32 0, i32 0>
@@ -789,13 +789,13 @@ 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-LABEL: shuffle_v8i64_00500000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,1,1,3]
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm0[0,0,2,0]
-; ALL-NEXT:    vpblendd {{.*}} # ymm1 = ymm2[0,1,2,3],ymm1[4,5],ymm2[6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,1,1,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm2[0,1,2,3],ymm1[4,5],ymm2[6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 5, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -803,13 +803,13 @@ 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-LABEL: shuffle_v8i64_06000000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,2,2,3]
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm0[0,1,0,0]
-; ALL-NEXT:    vpblendd {{.*}} # ymm1 = ymm2[0,1],ymm1[2,3],ymm2[4,5,6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,2,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm0[0,1,0,0]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm2[0,1],ymm1[2,3],ymm2[4,5,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 6, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -817,12 +817,12 @@ 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-LABEL: shuffle_v8i64_70000000:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[3,1,2,3]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpblendd {{.*}} # ymm1 = ymm1[0,1],ymm0[2,3,4,5,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[3,1,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm0[2,3,4,5,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 7, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
@@ -830,11 +830,11 @@ 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-LABEL: shuffle_v8i64_01014545:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,1,0,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,1,0,1]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,0,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,0,1]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 4, i32 5, i32 4, i32 5>
@@ -842,10 +842,10 @@ define <8 x i64> @shuffle_v8i64_01014545(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00112233(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00112233
+; ALL-LABEL: shuffle_v8i64_00112233:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,1,1]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,2,3,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,1,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,3,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 1, i32 1, i32 2, i32 2, i32 3, i32 3>
@@ -853,10 +853,10 @@ define <8 x i64> @shuffle_v8i64_00112233(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00001111(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00001111
+; ALL-LABEL: shuffle_v8i64_00001111:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,0,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,1,1,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,1,1,1]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
@@ -864,12 +864,12 @@ 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-LABEL: shuffle_v8i64_81a3c5e7:
 ; ALL:       # BB#0:
 ; 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:    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
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 8, i32 1, i32 10, i32 3, i32 12, i32 5, i32 14, i32 7>
@@ -877,11 +877,11 @@ define <8 x i64> @shuffle_v8i64_81a3c5e7(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_08080808(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_08080808
+; ALL-LABEL: shuffle_v8i64_08080808:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,0,2,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,0,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,0,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,0,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8>
@@ -889,16 +889,16 @@ 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-LABEL: shuffle_v8i64_08084c4c:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm2[0,0,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,0,2,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm3
-; ALL-NEXT:    vpermq {{.*}} # ymm3 = ymm3[0,1,0,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,0,2,0]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,0,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm3 = ymm3[0,1,0,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1],ymm2[2,3],ymm3[4,5],ymm2[6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,0,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,0,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 4, i32 12, i32 4, i32 12>
@@ -906,14 +906,14 @@ 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-LABEL: shuffle_v8i64_8823cc67:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpshufd {{.*}} # ymm3 = ymm3[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 8, i32 8, i32 2, i32 3, i32 12, i32 12, i32 6, i32 7>
@@ -921,16 +921,16 @@ define <8 x i64> @shuffle_v8i64_8823cc67(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_9832dc76(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_9832dc76
+; ALL-LABEL: shuffle_v8i64_9832dc76:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vpshufd {{.*}} # ymm2 = ymm2[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpshufd {{.*}} # ymm3 = ymm3[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
-; ALL-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 9, i32 8, i32 3, i32 2, i32 13, i32 12, i32 7, i32 6>
@@ -938,16 +938,16 @@ define <8 x i64> @shuffle_v8i64_9832dc76(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_9810dc54(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_9810dc54
+; ALL-LABEL: shuffle_v8i64_9810dc54:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm2
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm2[0,1,1,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,1,1,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm3
-; ALL-NEXT:    vpshufd {{.*}} # ymm3 = ymm3[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,1,0]
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[2,3,0,1,6,7,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm3 = ymm3[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm3[0,1,2,3],ymm2[4,5,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,0]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0,1,2,3],ymm0[4,5,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 9, i32 8, i32 1, i32 0, i32 13, i32 12, i32 5, i32 4>
@@ -955,16 +955,16 @@ 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-LABEL: shuffle_v8i64_08194c5d:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm2[0,0,2,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,0,2,1]
 ; 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]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,1,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; 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]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 4, i32 12, i32 5, i32 13>
@@ -972,16 +972,16 @@ 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-LABEL: shuffle_v8i64_2a3b6e7f:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm2[0,2,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm2[0,2,2,3]
 ; 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]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,1,3,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; 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]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,1,3,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 2, i32 10, i32 3, i32 11, i32 6, i32 14, i32 7, i32 15>
@@ -989,14 +989,14 @@ define <8 x i64> @shuffle_v8i64_2a3b6e7f(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_08192a3b(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_08192a3b
-; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm2 = ymm1[0,2,2,3]
-; 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 {{.*}} # ymm1 = ymm1[0,0,2,1]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,1,1,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; ALL-LABEL: shuffle_v8i64_08192a3b:
+; ALL:       # BB#0:
+; ALL-NEXT:    vpermq {{.*#+}} ymm2 = ymm1[0,2,2,3]
+; 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 {{.*#+}} ymm1 = ymm1[0,0,2,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
@@ -1004,13 +1004,13 @@ define <8 x i64> @shuffle_v8i64_08192a3b(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_08991abb(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_08991abb
+; ALL-LABEL: shuffle_v8i64_08991abb:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm2 = ymm0[2,3,2,3,6,7,6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm3 = ymm1[0,2,3,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm2 = ymm2[0,1],ymm3[2,3,4,5,6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[0,0,1,1]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm2 = ymm0[2,3,2,3,6,7,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm3 = ymm1[0,2,3,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm2 = ymm2[0,1],ymm3[2,3,4,5,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[0,0,1,1]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 9, i32 1, i32 10, i32 11, i32 11>
@@ -1018,13 +1018,13 @@ 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-LABEL: shuffle_v8i64_091b2d3f:
 ; ALL:       # BB#0:
 ; 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]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
+; 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]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5],ymm1[6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 9, i32 1, i32 11, i32 2, i32 13, i32 3, i32 15>
@@ -1032,12 +1032,12 @@ 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-LABEL: shuffle_v8i64_09ab1def:
 ; ALL:       # BB#0:
 ; 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]
+; 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]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm2, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
@@ -1045,11 +1045,11 @@ define <8 x i64> @shuffle_v8i64_09ab1def(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00014445(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00014445
+; ALL-LABEL: shuffle_v8i64_00014445:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,0,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 4, i32 4, i32 4, i32 5>
@@ -1057,11 +1057,11 @@ define <8 x i64> @shuffle_v8i64_00014445(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00204464(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00204464
+; ALL-LABEL: shuffle_v8i64_00204464:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 0, i32 4, i32 4, i32 6, i32 4>
@@ -1069,11 +1069,11 @@ define <8 x i64> @shuffle_v8i64_00204464(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_03004744(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_03004744
+; ALL-LABEL: shuffle_v8i64_03004744:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,3,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,3,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 3, i32 0, i32 0, i32 4, i32 7, i32 4, i32 4>
@@ -1081,11 +1081,11 @@ define <8 x i64> @shuffle_v8i64_03004744(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_10005444(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_10005444
+; ALL-LABEL: shuffle_v8i64_10005444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; 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 0, i32 0, i32 5, i32 4, i32 4, i32 4>
@@ -1093,11 +1093,11 @@ define <8 x i64> @shuffle_v8i64_10005444(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_22006644(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_22006644
+; ALL-LABEL: shuffle_v8i64_22006644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[2,2,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,2,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 6, i32 4, i32 4>
@@ -1105,11 +1105,11 @@ define <8 x i64> @shuffle_v8i64_22006644(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_33307774(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_33307774
+; ALL-LABEL: shuffle_v8i64_33307774:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[3,3,3,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,3,3,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,3,3,0]
 ; 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 3, i32 3, i32 0, i32 7, i32 7, i32 7, i32 4>
@@ -1117,11 +1117,11 @@ define <8 x i64> @shuffle_v8i64_33307774(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_32107654(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_32107654
+; ALL-LABEL: shuffle_v8i64_32107654:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[3,2,1,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,2,1,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0]
 ; 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 7, i32 6, i32 5, i32 4>
@@ -1129,11 +1129,11 @@ define <8 x i64> @shuffle_v8i64_32107654(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00234467(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00234467
+; ALL-LABEL: shuffle_v8i64_00234467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 3, i32 4, i32 4, i32 6, i32 7>
@@ -1141,11 +1141,11 @@ define <8 x i64> @shuffle_v8i64_00234467(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00224466(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00224466
+; ALL-LABEL: shuffle_v8i64_00224466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 4, i32 4, i32 6, i32 6>
@@ -1153,11 +1153,11 @@ define <8 x i64> @shuffle_v8i64_00224466(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_10325476(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_10325476
+; ALL-LABEL: shuffle_v8i64_10325476:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5]
 ; 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 5, i32 4, i32 7, i32 6>
@@ -1165,11 +1165,11 @@ define <8 x i64> @shuffle_v8i64_10325476(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_11335577(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_11335577
+; ALL-LABEL: shuffle_v8i64_11335577:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[2,3,2,3,6,7,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,2,3,6,7,6,7]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpshufd {{.*}} # ymm0 = ymm0[2,3,2,3,6,7,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7]
 ; 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 5, i32 5, i32 7, i32 7>
@@ -1177,11 +1177,11 @@ define <8 x i64> @shuffle_v8i64_11335577(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_10235467(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_10235467
+; ALL-LABEL: shuffle_v8i64_10235467:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[1,0,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,2,3]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,0,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,2,3]
 ; 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 2, i32 3, i32 5, i32 4, i32 6, i32 7>
@@ -1189,11 +1189,11 @@ define <8 x i64> @shuffle_v8i64_10235467(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_10225466(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_10225466
+; ALL-LABEL: shuffle_v8i64_10225466:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[1,0,2,2]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,2,2]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,0,2,2]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,2,2]
 ; 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 2, i32 2, i32 5, i32 4, i32 6, i32 6>
@@ -1201,11 +1201,11 @@ define <8 x i64> @shuffle_v8i64_10225466(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00015444(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00015444
+; ALL-LABEL: shuffle_v8i64_00015444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,0,1]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,0,1]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 1, i32 5, i32 4, i32 4, i32 4>
@@ -1213,11 +1213,11 @@ define <8 x i64> @shuffle_v8i64_00015444(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00204644(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00204644
+; ALL-LABEL: shuffle_v8i64_00204644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,2,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,2,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 0, i32 4, i32 6, i32 4, i32 4>
@@ -1225,11 +1225,11 @@ define <8 x i64> @shuffle_v8i64_00204644(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_03004474(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_03004474
+; ALL-LABEL: shuffle_v8i64_03004474:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,3,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,3,0,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,3,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,3,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 3, i32 0, i32 0, i32 4, i32 4, i32 7, i32 4>
@@ -1237,11 +1237,11 @@ define <8 x i64> @shuffle_v8i64_03004474(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_10004444(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_10004444
+; ALL-LABEL: shuffle_v8i64_10004444:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[1,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[1,0,0,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[0,0,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,0,0,0]
 ; 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 0, i32 0, i32 4, i32 4, i32 4, i32 4>
@@ -1249,11 +1249,11 @@ define <8 x i64> @shuffle_v8i64_10004444(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_22006446(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_22006446
+; ALL-LABEL: shuffle_v8i64_22006446:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[2,2,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,0,0,2]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,0,0,2]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 2, i32 2, i32 0, i32 0, i32 6, i32 4, i32 4, i32 6>
@@ -1261,11 +1261,11 @@ define <8 x i64> @shuffle_v8i64_22006446(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_33307474(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_33307474
+; ALL-LABEL: shuffle_v8i64_33307474:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[3,3,3,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,3,3,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[3,0,3,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,0,3,0]
 ; 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 3, i32 3, i32 0, i32 7, i32 4, i32 7, i32 4>
@@ -1273,9 +1273,9 @@ define <8 x i64> @shuffle_v8i64_33307474(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_32104567(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_32104567
+; ALL-LABEL: shuffle_v8i64_32104567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[3,2,1,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[3,2,1,0]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1284,11 +1284,11 @@ define <8 x i64> @shuffle_v8i64_32104567(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00236744(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00236744
+; ALL-LABEL: shuffle_v8i64_00236744:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm0[0,0,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm0[0,0,2,3]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,3,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,3,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 3, i32 6, i32 7, i32 4, i32 4>
@@ -1296,11 +1296,11 @@ define <8 x i64> @shuffle_v8i64_00236744(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00226644(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00226644
+; ALL-LABEL: shuffle_v8i64_00226644:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,2,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 2, i32 6, i32 6, i32 4, i32 4>
@@ -1308,9 +1308,9 @@ define <8 x i64> @shuffle_v8i64_00226644(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_10324567(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_10324567
+; ALL-LABEL: shuffle_v8i64_10324567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1319,9 +1319,9 @@ define <8 x i64> @shuffle_v8i64_10324567(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_11334567(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_11334567
+; ALL-LABEL: shuffle_v8i64_11334567:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[2,3,2,3,6,7,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,2,3,6,7,6,7]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1330,10 +1330,10 @@ 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-LABEL: shuffle_v8i64_01235467:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[1,0,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[1,0,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 7>
@@ -1341,10 +1341,10 @@ 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-LABEL: shuffle_v8i64_01235466:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpermq {{.*}} # ymm1 = ymm1[1,0,2,2]
+; ALL-NEXT:    vpermq {{.*#+}} ymm1 = ymm1[1,0,2,2]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 3, i32 5, i32 4, i32 6, i32 6>
@@ -1352,11 +1352,11 @@ define <8 x i64> @shuffle_v8i64_01235466(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_002u6u44(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_002u6u44
+; ALL-LABEL: shuffle_v8i64_002u6u44:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,1,0,0]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,1,0,0]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 2, i32 undef, i32 6, i32 undef, i32 4, i32 4>
@@ -1364,11 +1364,11 @@ define <8 x i64> @shuffle_v8i64_002u6u44(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_00uu66uu(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_00uu66uu
+; ALL-LABEL: shuffle_v8i64_00uu66uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,2,2,3]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,2,2,3]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 0, i32 undef, i32 undef, i32 6, i32 6, i32 undef, i32 undef>
@@ -1376,9 +1376,9 @@ define <8 x i64> @shuffle_v8i64_00uu66uu(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_103245uu(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_103245uu
+; ALL-LABEL: shuffle_v8i64_103245uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1387,9 +1387,9 @@ define <8 x i64> @shuffle_v8i64_103245uu(<8 x i64> %a, <8 x i64> %b) {
 }
 
 define <8 x i64> @shuffle_v8i64_1133uu67(<8 x i64> %a, <8 x i64> %b) {
-; ALL-LABEL: @shuffle_v8i64_1133uu67
+; ALL-LABEL: shuffle_v8i64_1133uu67:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm0[2,3,2,3,6,7,6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm0[2,3,2,3,6,7,6,7]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
 ; ALL-NEXT:    vinserti64x4 $1, %ymm0, %zmm1, %zmm0
 ; ALL-NEXT:    retq
@@ -1398,10 +1398,10 @@ 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-LABEL: shuffle_v8i64_0uu354uu:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[2,3,0,1,6,7,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[2,3,0,1,6,7,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 0, i32 undef, i32 undef, i32 3, i32 5, i32 4, i32 undef, i32 undef>
@@ -1409,10 +1409,10 @@ 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-LABEL: shuffle_v8i64_uuu3uu66:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm1
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm1, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 6>
@@ -1420,18 +1420,18 @@ 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-LABEL: shuffle_v8i64_6caa87e5:
 ; ALL:       # BB#0:
 ; ALL-NEXT:    vextracti64x4 $1, %zmm1, %ymm2
-; ALL-NEXT:    vpblendd {{.*}} # ymm3 = ymm1[0,1,2,3],ymm2[4,5],ymm1[6,7]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm3 = ymm1[0,1,2,3],ymm2[4,5],ymm1[6,7]
 ; ALL-NEXT:    vextracti64x4 $1, %zmm0, %ymm0
-; ALL-NEXT:    vpermq {{.*}} # ymm4 = ymm0[0,3,2,1]
-; ALL-NEXT:    vpblendd {{.*}} # ymm3 = ymm3[0,1],ymm4[2,3],ymm3[4,5],ymm4[6,7]
-; ALL-NEXT:    vpshufd {{.*}} # ymm2 = ymm2[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vpshufd {{.*}} # ymm1 = ymm1[0,1,0,1,4,5,4,5]
-; ALL-NEXT:    vpblendd {{.*}} # ymm1 = ymm1[0,1],ymm2[2,3],ymm1[4,5,6,7]
-; ALL-NEXT:    vpermq {{.*}} # ymm0 = ymm0[2,1,2,3]
-; ALL-NEXT:    vpblendd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm4 = ymm0[0,3,2,1]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm3 = ymm3[0,1],ymm4[2,3],ymm3[4,5],ymm4[6,7]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm2 = ymm2[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpshufd {{.*#+}} ymm1 = ymm1[0,1,0,1,4,5,4,5]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm1 = ymm1[0,1],ymm2[2,3],ymm1[4,5,6,7]
+; ALL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[2,1,2,3]
+; ALL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3,4,5,6,7]
 ; ALL-NEXT:    vinserti64x4 $1, %ymm3, %zmm0, %zmm0
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <8 x i64> %a, <8 x i64> %b, <8 x i32> <i32 6, i32 12, i32 10, i32 10, i32 8, i32 7, i32 14, i32 5>
-- 
2.34.1