diff --git a/test/CodeGen/X86/vector-shuffle-128-v16.ll b/test/CodeGen/X86/vector-shuffle-128-v16.ll
index fc4ffa6eaf2..306ef8a220f 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v16.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v16.ll
@@ -1,6 +1,8 @@
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSSE3
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE41
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-unknown"
@@ -33,6 +35,12 @@ define <16 x i8> @shuffle_v16i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00(
 ; SSE41-NEXT:    pxor %xmm1, %xmm1
 ; SSE41-NEXT:    pshufb %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00_00:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX-NEXT:    vpshufb %xmm1, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %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>
   ret <16 x i8> %shuffle
 }
@@ -55,6 +63,11 @@ define <16 x i8> @shuffle_v16i8_00_00_00_00_00_00_00_00_01_01_01_01_01_01_01_01(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_00_00_00_00_00_00_00_01_01_01_01_01_01_01_01:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,1,1,1,1,1,1,1,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1, i32 1>
   ret <16 x i8> %shuffle
 }
@@ -78,26 +91,43 @@ define <16 x i8> @shuffle_v16i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_00_00_00_00_00_00_00_08_08_08_08_08_08_08_08:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,0,0,0,0,8,8,8,8,8,8,8,8]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %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 i8> %shuffle
 }
 
 define <16 x i8> @shuffle_v16i8_00_00_00_00_01_01_01_01_02_02_02_02_03_03_03_03(<16 x i8> %a, <16 x i8> %b) {
-; ALL-LABEL: shuffle_v16i8_00_00_00_00_01_01_01_01_02_02_02_02_03_03_03_03:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v16i8_00_00_00_00_01_01_01_01_02_02_02_02_03_03_03_03:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_00_00_00_01_01_01_01_02_02_02_02_03_03_03_03:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1, i32 2, i32 2, i32 2, i32 2, i32 3, i32 3, i32 3, i32 3>
   ret <16 x i8> %shuffle
 }
 
 define <16 x i8> @shuffle_v16i8_04_04_04_04_05_05_05_05_06_06_06_06_07_07_07_07(<16 x i8> %a, <16 x i8> %b) {
-; ALL-LABEL: shuffle_v16i8_04_04_04_04_05_05_05_05_06_06_06_06_07_07_07_07:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; ALL-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v16i8_04_04_04_04_05_05_05_05_06_06_06_06_07_07_07_07:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; SSE-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_04_04_04_04_05_05_05_05_06_06_06_06_07_07_07_07:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 4, i32 4, i32 4, i32 4, i32 5, i32 5, i32 5, i32 5, i32 6, i32 6, i32 6, i32 6, i32 7, i32 7, i32 7, i32 7>
   ret <16 x i8> %shuffle
 }
@@ -122,15 +152,25 @@ define <16 x i8> @shuffle_v16i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_00_00_00_04_04_04_04_08_08_08_08_12_12_12_12:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,0,0,0,4,4,4,4,8,8,8,8,12,12,12,12]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %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 i8> %shuffle
 }
 
 define <16 x i8> @shuffle_v16i8_00_00_01_01_02_02_03_03_04_04_05_05_06_06_07_07(<16 x i8> %a, <16 x i8> %b) {
-; ALL-LABEL: shuffle_v16i8_00_00_01_01_02_02_03_03_04_04_05_05_06_06_07_07:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v16i8_00_00_01_01_02_02_03_03_04_04_05_05_06_06_07_07:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_00_01_01_02_02_03_03_04_04_05_05_06_06_07_07:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 0, i32 1, i32 1, i32 2, i32 2, i32 3, i32 3, i32 4, i32 4, i32 5, i32 5, i32 6, i32 6, i32 7, i32 7>
   ret <16 x i8> %shuffle
 }
@@ -159,27 +199,44 @@ define <16 x i8> @shuffle_v16i8_0101010101010101(<16 x i8> %a, <16 x i8> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_0101010101010101:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1, i32 0, i32 1>
   ret <16 x i8> %shuffle
 }
 
 define <16 x i8> @shuffle_v16i8_00_16_01_17_02_18_03_19_04_20_05_21_06_22_07_23(<16 x i8> %a, <16 x i8> %b) {
-; ALL-LABEL: shuffle_v16i8_00_16_01_17_02_18_03_19_04_20_05_21_06_22_07_23:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklbw {{.*#+}} 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]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v16i8_00_16_01_17_02_18_03_19_04_20_05_21_06_22_07_23:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklbw {{.*#+}} 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]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_16_01_17_02_18_03_19_04_20_05_21_06_22_07_23:
+; AVX:       # BB#0:
+; AVX-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]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
   ret <16 x i8> %shuffle
 }
 
 define <16 x i8> @shuffle_v16i8_16_00_16_01_16_02_16_03_16_04_16_05_16_06_16_07(<16 x i8> %a, <16 x i8> %b) {
-; ALL-LABEL: shuffle_v16i8_16_00_16_01_16_02_16_03_16_04_16_05_16_06_16_07:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
-; ALL-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
-; ALL-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
-; ALL-NEXT:    movdqa %xmm1, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v16i8_16_00_16_01_16_02_16_03_16_04_16_05_16_06_16_07:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; SSE-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; SSE-NEXT:    movdqa %xmm1, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_16_00_16_01_16_02_16_03_16_04_16_05_16_06_16_07:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; AVX-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]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 16, i32 0, i32 16, i32 1, i32 16, i32 2, i32 16, i32 3, i32 16, i32 4, i32 16, i32 5, i32 16, i32 6, i32 16, i32 7>
   ret <16 x i8> %shuffle
 }
@@ -207,6 +264,11 @@ define <16 x i8> @shuffle_v16i8_03_02_01_00_07_06_05_04_11_10_09_08_15_14_13_12(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_03_02_01_00_07_06_05_04_11_10_09_08_15_14_13_12:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4,11,10,9,8,15,14,13,12]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 11, i32 10, i32 9, i32 8, i32 15, i32 14, i32 13, i32 12>
   ret <16 x i8> %shuffle
 }
@@ -237,6 +299,13 @@ define <16 x i8> @shuffle_v16i8_03_02_01_00_07_06_05_04_19_18_17_16_23_22_21_20(
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4],zero,zero,zero,zero,zero,zero,zero,zero
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_03_02_01_00_07_06_05_04_19_18_17_16_23_22_21_20:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[3,2,1,0,7,6,5,4]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0,7,6,5,4],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT:    vpor %xmm1, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 7, i32 6, i32 5, i32 4, i32 19, i32 18, i32 17, i32 16, i32 23, i32 22, i32 21, i32 20>
   ret <16 x i8> %shuffle
 }
@@ -273,6 +342,13 @@ define <16 x i8> @shuffle_v16i8_03_02_01_00_31_30_29_28_11_10_09_08_23_22_21_20(
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[3,2,1,0],zero,zero,zero,zero,xmm0[11,10,9,8],zero,zero,zero,zero
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_03_02_01_00_31_30_29_28_11_10_09_08_23_22_21_20:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = zero,zero,zero,zero,xmm1[15,14,13,12],zero,zero,zero,zero,xmm1[7,6,5,4]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[3,2,1,0],zero,zero,zero,zero,xmm0[11,10,9,8],zero,zero,zero,zero
+; AVX-NEXT:    vpor %xmm1, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 3, i32 2, i32 1, i32 0, i32 31, i32 30, i32 29, i32 28, i32 11, i32 10, i32 9, i32 8, i32 23, i32 22, i32 21, i32 20>
   ret <16 x i8> %shuffle
 }
@@ -294,6 +370,11 @@ define <16 x i8> @trunc_v4i32_shuffle(<16 x i8> %a) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: trunc_v4i32_shuffle:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,4,8,12,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> undef, <16 x i32> <i32 0, i32 4, i32 8, i32 12, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <16 x i8> %shuffle
 }
@@ -371,6 +452,14 @@ define <16 x i8> @PR20540(<8 x i8> %a) {
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: PR20540:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = zero,zero,zero,zero,zero,zero,zero,zero,xmm1[0,0,0,0,0,0,0,0]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT:    vpor %xmm1, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i8> %a, <8 x i8> zeroinitializer, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8, i32 8>
   ret <16 x i8> %shuffle
 }
@@ -399,6 +488,15 @@ define <16 x i8> @shuffle_v16i8_16_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz(
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_16_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovd %edi, %xmm0
+; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = zero,xmm1[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT:    vpor %xmm0, %xmm1, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <16 x i8> undef, i8 %i, i32 0
   %shuffle = shufflevector <16 x i8> zeroinitializer, <16 x i8> %a, <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>
   ret <16 x i8> %shuffle
@@ -429,6 +527,15 @@ define <16 x i8> @shuffle_v16i8_zz_zz_zz_zz_zz_16_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz(
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,xmm0[0],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_zz_zz_zz_zz_zz_16_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovd %edi, %xmm0
+; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,0,0,0,0],zero,xmm1[0,0,0,0,0,0,0,0,0,0]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,xmm0[0],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT:    vpor %xmm0, %xmm1, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <16 x i8> undef, i8 %i, i32 0
   %shuffle = shufflevector <16 x i8> zeroinitializer, <16 x i8> %a, <16 x i32> <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>
   ret <16 x i8> %shuffle
@@ -459,6 +566,15 @@ define <16 x i8> @shuffle_v16i8_zz_uu_uu_zz_uu_uu_zz_zz_zz_zz_zz_zz_zz_zz_zz_16(
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = zero,xmm0[u,u],zero,xmm0[u,u],zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[0]
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_zz_uu_uu_zz_uu_uu_zz_zz_zz_zz_zz_zz_zz_zz_zz_16:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovd %edi, %xmm0
+; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,u,u,3,u,u,6,7,8,9,10,11,12,13,14],zero
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = zero,xmm0[u,u],zero,xmm0[u,u],zero,zero,zero,zero,zero,zero,zero,zero,zero,xmm0[0]
+; AVX-NEXT:    vpor %xmm0, %xmm1, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <16 x i8> undef, i8 %i, i32 0
   %shuffle = shufflevector <16 x i8> zeroinitializer, <16 x i8> %a, <16 x i32> <i32 0, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 16>
   ret <16 x i8> %shuffle
@@ -491,6 +607,16 @@ define <16 x i8> @shuffle_v16i8_zz_zz_19_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz(
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
 ; SSE41-NEXT:    por %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_zz_zz_19_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz_zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vmovd %edi, %xmm0
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[13,14,15,0,1,2,3,4,5,6,7,8,9,10,11,12]
+; AVX-NEXT:    vpxor %xmm1, %xmm1, %xmm1
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[0,1],zero,xmm1[3,4,5,6,7,8,9,10,11,12,13,14,15]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = zero,zero,xmm0[3],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX-NEXT:    vpor %xmm0, %xmm1, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <16 x i8> undef, i8 %i, i32 3
   %shuffle = shufflevector <16 x i8> zeroinitializer, <16 x i8> %a, <16 x i32> <i32 0, i32 1, i32 19, 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>
   ret <16 x i8> %shuffle
@@ -541,6 +667,11 @@ define <16 x i8> @shuffle_v16i8_31_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm1[15],xmm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_31_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[15],xmm0[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 31, 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>
   ret <16 x i8> %shuffle
 }
@@ -587,6 +718,11 @@ define <16 x i8> @shuffle_v16i8_15_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[15,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_15_00_01_02_03_04_05_06_07_08_09_10_11_12_13_14:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[15,0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 15, 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>
   ret <16 x i8> %shuffle
 }
@@ -636,6 +772,11 @@ define <16 x i8> @shuffle_v16i8_17_18_19_20_21_22_23_24_25_26_27_28_29_30_31_00(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm1[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],xmm0[0]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_17_18_19_20_21_22_23_24_25_26_27_28_29_30_31_00:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],xmm0[0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31, i32 0>
   ret <16 x i8> %shuffle
 }
@@ -687,6 +828,11 @@ define <16 x i8> @shuffle_v16i8_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15_16(
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],xmm1[0]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15_16:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15],xmm1[0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <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, i32 16>
   ret <16 x i8> %shuffle
 }
@@ -733,6 +879,11 @@ define <16 x i8> @shuffle_v16i8_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15_00(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,0]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_01_02_03_04_05_06_07_08_09_10_11_12_13_14_15_00:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[1,2,3,4,5,6,7,8,9,10,11,12,13,14,15,0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <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, i32 0>
   ret <16 x i8> %shuffle
 }
@@ -784,6 +935,11 @@ define <16 x i8> @shuffle_v16i8_15_16_17_18_19_20_21_22_23_24_25_26_27_28_29_30(
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[15],xmm1[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_15_16_17_18_19_20_21_22_23_24_25_26_27_28_29_30:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[15],xmm1[0,1,2,3,4,5,6,7,8,9,10,11,12,13,14]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30>
   ret <16 x i8> %shuffle
 }
@@ -805,6 +961,11 @@ define <16 x i8> @shuffle_v16i8_00_uu_uu_uu_uu_uu_uu_uu_01_uu_uu_uu_uu_uu_uu_uu(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxbq %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_uu_uu_uu_uu_uu_uu_uu_01_uu_uu_uu_uu_uu_uu_uu:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxbq %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <16 x i8> %shuffle
 }
@@ -827,6 +988,11 @@ define <16 x i8> @shuffle_v16i8_00_zz_zz_zz_zz_zz_zz_zz_01_zz_zz_zz_zz_zz_zz_zz(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxbq %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_zz_zz_zz_zz_zz_zz_zz_01_zz_zz_zz_zz_zz_zz_zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxbq %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 1, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 31>
   ret <16 x i8> %shuffle
 }
@@ -848,6 +1014,11 @@ define <16 x i8> @shuffle_v16i8_00_uu_uu_uu_01_uu_uu_uu_02_uu_uu_uu_03_uu_uu_uu(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxbd %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_uu_uu_uu_01_uu_uu_uu_02_uu_uu_uu_03_uu_uu_uu:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxbd %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 1, i32 undef, i32 undef, i32 undef, i32 2, i32 undef, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 undef>
   ret <16 x i8> %shuffle
 }
@@ -871,6 +1042,11 @@ define <16 x i8> @shuffle_v16i8_00_zz_zz_zz_01_zz_zz_zz_02_zz_zz_zz_03_zz_zz_zz(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxbd %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_zz_zz_zz_01_zz_zz_zz_02_zz_zz_zz_03_zz_zz_zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxbd %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 17, i32 18, i32 19, i32 1, i32 21, i32 22, i32 23, i32 2, i32 25, i32 26, i32 27, i32 3, i32 29, i32 30, i32 31>
   ret <16 x i8> %shuffle
 }
@@ -890,6 +1066,11 @@ define <16 x i8> @shuffle_v16i8_00_uu_01_uu_02_uu_03_uu_04_uu_05_uu_06_uu_07_uu(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxbw %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_uu_01_uu_02_uu_03_uu_04_uu_05_uu_06_uu_07_uu:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxbw %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 undef, i32 1, i32 undef, i32 2, i32 undef, i32 3, i32 undef, i32 4, i32 undef, i32 5, i32 undef, i32 6, i32 undef, i32 7, i32 undef>
   ret <16 x i8> %shuffle
 }
@@ -911,6 +1092,11 @@ define <16 x i8> @shuffle_v16i8_00_zz_01_zz_02_zz_03_zz_04_zz_05_zz_06_zz_07_zz(
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxbw %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_00_zz_01_zz_02_zz_03_zz_04_zz_05_zz_06_zz_07_zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxbw %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> zeroinitializer, <16 x i32> <i32 0, i32 17, i32 1, i32 19, i32 2, i32 21, i32 3, i32 23, i32 4, i32 25, i32 5, i32 27, i32 6, i32 29, i32 7, i32 31>
   ret <16 x i8> %shuffle
 }
@@ -976,6 +1162,15 @@ define <16 x i8> @shuffle_v16i8_uu_10_02_07_22_14_07_02_18_03_01_14_18_09_11_00(
 ; SSE41-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3],xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v16i8_uu_10_02_07_22_14_07_02_18_03_01_14_18_09_11_00:
+; AVX:       # BB#0: # %entry
+; AVX-NEXT:    vpshufb {{.*#+}} xmm2 = xmm0[2,7,1,11,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm1 = xmm1[6,6,2,2,2,2,3,3,4,4,5,5,6,6,7,7]
+; AVX-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0],xmm2[0],xmm1[1],xmm2[1],xmm1[2],xmm2[2],xmm1[3],xmm2[3],xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[10,7,14,2,3,14,9,0,u,u,u,u,u,u,u,u]
+; AVX-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]
+; AVX-NEXT:    retq
 entry:
   %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 undef, i32 10, i32 2, i32 7, i32 22, i32 14, i32 7, i32 2, i32 18, i32 3, i32 1, i32 14, i32 18, i32 9, i32 11, i32 0>
 
@@ -983,197 +1178,9 @@ entry:
 }
 
 define <16 x i8> @stress_test2(<16 x i8> %s.0.0, <16 x i8> %s.0.1, <16 x i8> %s.0.2) {
-; SSE2-LABEL: stress_test2:
-; SSE2:       # BB#0: # %entry
-; SSE2-NEXT:    pxor %xmm8, %xmm8
-; SSE2-NEXT:    movdqa %xmm0, %xmm4
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm8[0],xmm4[1],xmm8[1],xmm4[2],xmm8[2],xmm4[3],xmm8[3],xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7]
-; SSE2-NEXT:    punpckhbw {{.*#+}} xmm0 = xmm0[8],xmm8[8],xmm0[9],xmm8[9],xmm0[10],xmm8[10],xmm0[11],xmm8[11],xmm0[12],xmm8[12],xmm0[13],xmm8[13],xmm0[14],xmm8[14],xmm0[15],xmm8[15]
-; SSE2-NEXT:    movdqa %xmm0, %xmm5
-; SSE2-NEXT:    punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm4[4],xmm5[5],xmm4[5],xmm5[6],xmm4[6],xmm5[7],xmm4[7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm5 = xmm5[3,1,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm5 = xmm5[0,1,0,3,4,5,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm6 = xmm4[1,2,2,3]
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm6 = xmm6[0],xmm5[0]
-; SSE2-NEXT:    movdqa %xmm1, %xmm5
-; SSE2-NEXT:    punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm8[8],xmm5[9],xmm8[9],xmm5[10],xmm8[10],xmm5[11],xmm8[11],xmm5[12],xmm8[12],xmm5[13],xmm8[13],xmm5[14],xmm8[14],xmm5[15],xmm8[15]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm7 = xmm5[2,1,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm7 = xmm7[0,1,2,3,6,4,6,7]
-; SSE2-NEXT:    movdqa %xmm6, %xmm3
-; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[3,0],xmm7[2,0]
-; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[2,0],xmm7[2,3]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm6 = xmm6[0],xmm7[0],xmm6[1],xmm7[1],xmm6[2],xmm7[2],xmm6[3],xmm7[3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm6 = xmm6[2,1,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm6 = xmm6[0,1,2,3,4,6,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm6 = xmm6[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm6 = xmm6[1,0,2,3,4,5,6,7]
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm6 = xmm6[0],xmm3[0]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm0[0],xmm4[1],xmm0[1],xmm4[2],xmm0[2],xmm4[3],xmm0[3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm4[2,1,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,0,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,7,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm0[3,1,2,3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm5[3,1,2,3]
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1],xmm1[2],xmm8[2],xmm1[3],xmm8[3],xmm1[4],xmm8[4],xmm1[5],xmm8[5],xmm1[6],xmm8[6],xmm1[7],xmm8[7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm7 = xmm0[0,3,2,3,4,5,6,7]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm7[0],xmm4[1],xmm7[1],xmm4[2],xmm7[2],xmm4[3],xmm7[3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm4[0,3,2,1]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm4 = xmm4[0,1,2,3,4,7,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm4 = xmm4[0,1,3,2,4,5,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm7 = xmm5[2,1,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm7 = xmm7[1,1,2,3,4,5,6,7]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm7 = xmm7[0],xmm4[0],xmm7[1],xmm4[1],xmm7[2],xmm4[2],xmm7[3],xmm4[3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm4 = xmm7[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm4 = xmm4[0,2,2,3,4,5,6,7]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm4[0,3,2,1]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,6,5,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm4 = xmm3[0,3,2,1,4,5,6,7]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm3 = xmm7[3,1,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,7,5,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[1,0,3,2,4,5,6,7]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
-; SSE2-NEXT:    packuswb %xmm6, %xmm4
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm5[0,1,2,0]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,7,6,7]
-; SSE2-NEXT:    punpckhwd {{.*#+}} xmm3 = xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[0,2,3,3,4,5,6,7]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[1,3,1,3,4,5,6,7]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3]
-; SSE2-NEXT:    movdqa %xmm2, %xmm3
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm8[0],xmm3[1],xmm8[1],xmm3[2],xmm8[2],xmm3[3],xmm8[3],xmm3[4],xmm8[4],xmm3[5],xmm8[5],xmm3[6],xmm8[6],xmm3[7],xmm8[7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm3[0,1,0,3]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,5,5,6]
-; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[3,0],xmm0[2,0]
-; SSE2-NEXT:    shufps {{.*#+}} xmm0 = xmm0[0,1],xmm3[2,0]
-; SSE2-NEXT:    packuswb %xmm0, %xmm0
-; SSE2-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,1,1,3]
-; SSE2-NEXT:    punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm5[4],xmm1[5],xmm5[5],xmm1[6],xmm5[6],xmm1[7],xmm5[7]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,1,2,0,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,5,4,7]
-; SSE2-NEXT:    punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm8[8],xmm2[9],xmm8[9],xmm2[10],xmm8[10],xmm2[11],xmm8[11],xmm2[12],xmm8[12],xmm2[13],xmm8[13],xmm2[14],xmm8[14],xmm2[15],xmm8[15]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,5,4,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,3,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[3,0,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,5,7,6,7]
-; SSE2-NEXT:    movdqa %xmm1, %xmm3
-; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[3,0],xmm2[2,0]
-; SSE2-NEXT:    shufps {{.*#+}} xmm3 = xmm3[2,0],xmm2[2,3]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm1 = xmm2[0,2,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,7,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm1[0,2,2,3]
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm3[0]
-; SSE2-NEXT:    packuswb %xmm0, %xmm2
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3],xmm2[4],xmm0[4],xmm2[5],xmm0[5],xmm2[6],xmm0[6],xmm2[7],xmm0[7]
-; SSE2-NEXT:    movdqa %xmm2, %xmm1
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm1 = xmm1[0],xmm8[0],xmm1[1],xmm8[1],xmm1[2],xmm8[2],xmm1[3],xmm8[3],xmm1[4],xmm8[4],xmm1[5],xmm8[5],xmm1[6],xmm8[6],xmm1[7],xmm8[7]
-; SSE2-NEXT:    punpckhbw {{.*#+}} xmm2 = xmm2[8],xmm8[8],xmm2[9],xmm8[9],xmm2[10],xmm8[10],xmm2[11],xmm8[11],xmm2[12],xmm8[12],xmm2[13],xmm8[13],xmm2[14],xmm8[14],xmm2[15],xmm8[15]
-; SSE2-NEXT:    movdqa %xmm2, %xmm0
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,1,2,1,4,5,6,7]
-; SSE2-NEXT:    punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[2,1,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[1,1,0,0,4,5,6,7]
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm2 = xmm2[0],xmm0[0]
-; SSE2-NEXT:    movdqa %xmm4, %xmm3
-; SSE2-NEXT:    punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm8[8],xmm3[9],xmm8[9],xmm3[10],xmm8[10],xmm3[11],xmm8[11],xmm3[12],xmm8[12],xmm3[13],xmm8[13],xmm3[14],xmm8[14],xmm3[15],xmm8[15]
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm8[0],xmm4[1],xmm8[1],xmm4[2],xmm8[2],xmm4[3],xmm8[3],xmm4[4],xmm8[4],xmm4[5],xmm8[5],xmm4[6],xmm8[6],xmm4[7],xmm8[7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm4[0,1,0,1]
-; SSE2-NEXT:    movdqa %xmm3, %xmm5
-; SSE2-NEXT:    punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm0[4],xmm5[5],xmm0[5],xmm5[6],xmm0[6],xmm5[7],xmm0[7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm5[0,1,2,1]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,7,4,6,7]
-; SSE2-NEXT:    movdqa %xmm2, %xmm5
-; SSE2-NEXT:    shufps {{.*#+}} xmm5 = xmm5[3,0],xmm0[2,0]
-; SSE2-NEXT:    shufps {{.*#+}} xmm5 = xmm5[2,0],xmm0[2,3]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm2 = xmm2[0],xmm0[0],xmm2[1],xmm0[1],xmm2[2],xmm0[2],xmm2[3],xmm0[3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm0 = xmm2[0,3,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; SSE2-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm5[0]
-; SSE2-NEXT:    packuswb %xmm0, %xmm0
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm4[3,1,2,3,4,5,6,7]
-; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[1,0],xmm2[0,0]
-; SSE2-NEXT:    shufps {{.*#+}} xmm1 = xmm1[2,0],xmm2[2,3]
-; SSE2-NEXT:    packuswb %xmm0, %xmm1
-; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm3[2,1,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[1,1,2,3,4,5,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm3 = xmm4[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm3 = xmm3[2,1,2,3,4,5,6,7]
-; SSE2-NEXT:    punpcklwd {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm3[0,3,2,1]
-; SSE2-NEXT:    pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,6,5,6,7]
-; SSE2-NEXT:    pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
-; SSE2-NEXT:    pshuflw {{.*#+}} xmm2 = xmm2[2,0,3,1,4,5,6,7]
-; SSE2-NEXT:    packuswb %xmm0, %xmm2
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm2 = xmm2[0],xmm1[0],xmm2[1],xmm1[1],xmm2[2],xmm1[2],xmm2[3],xmm1[3],xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
-; SSE2-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
-; SSE2-NEXT:    retq
-;
-; SSSE3-LABEL: stress_test2:
-; SSSE3:       # BB#0: # %entry
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = zero,zero,xmm0[2],zero,zero,zero,xmm0[11],zero,zero,xmm0[3,4,5],zero,zero,xmm0[15,5]
-; SSSE3-NEXT:    movdqa %xmm1, %xmm3
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm3 = xmm3[13,14],zero,xmm3[0,10,5],zero,xmm3[10,10],zero,zero,zero,xmm3[14,12],zero,zero
-; SSSE3-NEXT:    por %xmm0, %xmm3
-; SSSE3-NEXT:    movdqa %xmm2, %xmm0
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,xmm0[1,6,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    movdqa %xmm1, %xmm4
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm4 = xmm4[1,12,5,9,1,5],zero,zero,xmm4[u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    por %xmm0, %xmm4
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm1 = zero,zero,zero,xmm1[2],zero,zero,xmm1[6,15,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm2 = xmm2[15,8,12],zero,xmm2[13,15],zero,zero,xmm2[u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    por %xmm1, %xmm2
-; SSSE3-NEXT:    punpcklbw {{.*#+}} 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]
-; SSSE3-NEXT:    movdqa %xmm2, %xmm1
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[6],zero,xmm1[14,14],zero,zero,xmm1[11,0,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    movdqa %xmm3, %xmm0
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm0 = zero,xmm0[12],zero,zero,xmm0[1,14],zero,zero,xmm0[u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    por %xmm1, %xmm0
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm2 = zero,xmm2[u,2,3,u,u,u,u,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    movdqa %xmm3, %xmm1
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[3,u],zero,zero,xmm1[u,u,u,u,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    por %xmm2, %xmm1
-; SSSE3-NEXT:    pshufb {{.*#+}} xmm3 = xmm3[1,4,10,13,u,u,u,u,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
-; SSSE3-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
-; SSSE3-NEXT:    retq
-;
-; SSE41-LABEL: stress_test2:
-; SSE41:       # BB#0: # %entry
-; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = zero,zero,xmm0[2],zero,zero,zero,xmm0[11],zero,zero,xmm0[3,4,5],zero,zero,xmm0[15,5]
-; SSE41-NEXT:    movdqa %xmm1, %xmm3
-; SSE41-NEXT:    pshufb {{.*#+}} xmm3 = xmm3[13,14],zero,xmm3[0,10,5],zero,xmm3[10,10],zero,zero,zero,xmm3[14,12],zero,zero
-; SSE41-NEXT:    por %xmm0, %xmm3
-; SSE41-NEXT:    movdqa %xmm2, %xmm0
-; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = zero,zero,zero,zero,zero,zero,xmm0[1,6,u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    movdqa %xmm1, %xmm4
-; SSE41-NEXT:    pshufb {{.*#+}} xmm4 = xmm4[1,12,5,9,1,5],zero,zero,xmm4[u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    por %xmm0, %xmm4
-; SSE41-NEXT:    pshufb {{.*#+}} xmm1 = zero,zero,zero,xmm1[2],zero,zero,xmm1[6,15,u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    pshufb {{.*#+}} xmm2 = xmm2[15,8,12],zero,xmm2[13,15],zero,zero,xmm2[u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    por %xmm1, %xmm2
-; SSE41-NEXT:    punpcklbw {{.*#+}} 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]
-; SSE41-NEXT:    movdqa %xmm2, %xmm1
-; SSE41-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[6],zero,xmm1[14,14],zero,zero,xmm1[11,0,u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    movdqa %xmm3, %xmm0
-; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = zero,xmm0[12],zero,zero,xmm0[1,14],zero,zero,xmm0[u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    por %xmm1, %xmm0
-; SSE41-NEXT:    pshufb {{.*#+}} xmm2 = zero,xmm2[u,2,3,u,u,u,u,u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    movdqa %xmm3, %xmm1
-; SSE41-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[3,u],zero,zero,xmm1[u,u,u,u,u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    por %xmm2, %xmm1
-; SSE41-NEXT:    pshufb {{.*#+}} xmm3 = xmm3[1,4,10,13,u,u,u,u,u,u,u,u,u,u,u,u]
-; SSE41-NEXT:    punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm1[0],xmm3[1],xmm1[1],xmm3[2],xmm1[2],xmm3[3],xmm1[3],xmm3[4],xmm1[4],xmm3[5],xmm1[5],xmm3[6],xmm1[6],xmm3[7],xmm1[7]
-; SSE41-NEXT:    punpcklbw {{.*#+}} xmm0 = xmm0[0],xmm3[0],xmm0[1],xmm3[1],xmm0[2],xmm3[2],xmm0[3],xmm3[3],xmm0[4],xmm3[4],xmm0[5],xmm3[5],xmm0[6],xmm3[6],xmm0[7],xmm3[7]
-; SSE41-NEXT:    retq
+; Nothing interesting to test here. Just make sure we didn't crashe.
+; ALL-LABEL: stress_test2:
+; ALL:         retq
 entry:
   %s.1.0 = shufflevector <16 x i8> %s.0.0, <16 x i8> %s.0.1, <16 x i32> <i32 29, i32 30, i32 2, i32 16, i32 26, i32 21, i32 11, i32 26, i32 26, i32 3, i32 4, i32 5, i32 30, i32 28, i32 15, i32 5>
   %s.1.1 = shufflevector <16 x i8> %s.0.1, <16 x i8> %s.0.2, <16 x i32> <i32 31, i32 1, i32 24, i32 12, i32 28, i32 5, i32 2, i32 9, i32 29, i32 1, i32 31, i32 5, i32 6, i32 17, i32 15, i32 22>
diff --git a/test/CodeGen/X86/vector-shuffle-128-v2.ll b/test/CodeGen/X86/vector-shuffle-128-v2.ll
index f1ae3612f5d..6f891c12505 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v2.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v2.ll
@@ -3,6 +3,7 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-unknown"
@@ -309,10 +310,15 @@ define <2 x i64> @shuffle_v2i64_03(<2 x i64> %a, <2 x i64> %b) {
 ; SSE41-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: shuffle_v2i64_03:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v2i64_03:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm0[0,1,2,3],xmm1[4,5,6,7]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v2i64_03:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm0[0,1],xmm1[2,3]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 0, i32 3>
   ret <2 x i64> %shuffle
 }
@@ -341,10 +347,15 @@ define <2 x i64> @shuffle_v2i64_03_copy(<2 x i64> %nonce, <2 x i64> %a, <2 x i64
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: shuffle_v2i64_03_copy:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm2[4,5,6,7]
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v2i64_03_copy:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm2[4,5,6,7]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v2i64_03_copy:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm2[2,3]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 0, i32 3>
   ret <2 x i64> %shuffle
 }
@@ -490,10 +501,15 @@ define <2 x i64> @shuffle_v2i64_21(<2 x i64> %a, <2 x i64> %b) {
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: shuffle_v2i64_21:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v2i64_21:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm1[0,1,2,3],xmm0[4,5,6,7]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v2i64_21:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm1[0,1],xmm0[2,3]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 2, i32 1>
   ret <2 x i64> %shuffle
 }
@@ -522,10 +538,15 @@ define <2 x i64> @shuffle_v2i64_21_copy(<2 x i64> %nonce, <2 x i64> %a, <2 x i64
 ; SSE41-NEXT:    movdqa %xmm2, %xmm0
 ; SSE41-NEXT:    retq
 ;
-; AVX-LABEL: shuffle_v2i64_21_copy:
-; AVX:       # BB#0:
-; AVX-NEXT:    vpblendw {{.*#+}} xmm0 = xmm2[0,1,2,3],xmm1[4,5,6,7]
-; AVX-NEXT:    retq
+; AVX1-LABEL: shuffle_v2i64_21_copy:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpblendw {{.*#+}} xmm0 = xmm2[0,1,2,3],xmm1[4,5,6,7]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: shuffle_v2i64_21_copy:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpblendd {{.*#+}} xmm0 = xmm2[0,1],xmm1[2,3]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <2 x i64> %a, <2 x i64> %b, <2 x i32> <i32 2, i32 1>
   ret <2 x i64> %shuffle
 }
diff --git a/test/CodeGen/X86/vector-shuffle-128-v4.ll b/test/CodeGen/X86/vector-shuffle-128-v4.ll
index c4c97f6b73e..080cd439476 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v4.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v4.ll
@@ -3,6 +3,7 @@
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
 ; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-unknown"
diff --git a/test/CodeGen/X86/vector-shuffle-128-v8.ll b/test/CodeGen/X86/vector-shuffle-128-v8.ll
index a3ca88c927b..d0c4a3f9d36 100644
--- a/test/CodeGen/X86/vector-shuffle-128-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-128-v8.ll
@@ -1,23 +1,35 @@
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSSE3
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE41
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSSE3
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+sse4.1 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 -x86-experimental-vector-shuffle-lowering | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
 
 target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128"
 target triple = "x86_64-unknown-unknown"
 
 define <8 x i16> @shuffle_v8i16_01012323(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_01012323:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_01012323:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_01012323:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 0, i32 1, i32 2, i32 3, i32 2, i32 3>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_67452301(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_67452301:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_67452301:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_67452301:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 6, i32 7, i32 4, i32 5, i32 2, i32 3, i32 0, i32 1>
   ret <8 x i16> %shuffle
 }
@@ -38,6 +50,11 @@ define <8 x i16> @shuffle_v8i16_456789AB(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_456789AB:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11>
   ret <8 x i16> %shuffle
 }
@@ -59,40 +76,67 @@ define <8 x i16> @shuffle_v8i16_00000000(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_00000000:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,0,1,0,1,0,1,0,1,0,1,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 0>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_00004444(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_00004444:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
-; ALL-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,4,4]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_00004444:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; SSE-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,4,4]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_00004444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,0,0,4,5,6,7]
+; AVX-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,4,4,4]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_u0u1u2u3(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_u0u1u2u3:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_u0u1u2u3:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u0u1u2u3:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0,0,1,1,2,2,3,3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 0, i32 undef, i32 1, i32 undef, i32 2, i32 undef, i32 3>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_u4u5u6u7(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_u4u5u6u7:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_u4u5u6u7:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u4u5u6u7:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm0[4,4,5,5,6,6,7,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 4, i32 undef, i32 5, i32 undef, i32 6, i32 undef, i32 7>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_31206745(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_31206745:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,0,4,5,6,7]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_31206745:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[3,1,2,0,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_31206745:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[3,1,2,0,4,5,6,7]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 3, i32 1, i32 2, i32 0, i32 6, i32 7, i32 4, i32 5>
   ret <8 x i16> %shuffle
 }
@@ -113,32 +157,54 @@ define <8 x i16> @shuffle_v8i16_44440000(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,8,9,0,1,0,1,0,1,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_44440000:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,8,9,0,1,0,1,0,1,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 4, i32 4, i32 4, i32 0, i32 0, i32 0, i32 0>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_23016745(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_23016745:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,0,3,2]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_23016745:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,0,3,2]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_23016745:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,0,3,2]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 3, i32 0, i32 1, i32 6, i32 7, i32 4, i32 5>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_23026745(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_23026745:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[2,3,0,2,4,5,6,7]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_23026745:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[2,3,0,2,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_23026745:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[2,3,0,2,4,5,6,7]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,3,2]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 3, i32 0, i32 2, i32 6, i32 7, i32 4, i32 5>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_23016747(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_23016747:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,0,2,3]
-; ALL-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,4,7]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_23016747:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[1,0,2,3]
+; SSE-NEXT:    pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,4,7]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_23016747:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[1,0,2,3]
+; AVX-NEXT:    vpshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,6,7,4,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 3, i32 0, i32 1, i32 6, i32 7, i32 4, i32 7>
   ret <8 x i16> %shuffle
 }
@@ -159,6 +225,11 @@ define <8 x i16> @shuffle_v8i16_75643120(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[14,15,10,11,12,13,8,9,6,7,2,3,4,5,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_75643120:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[14,15,10,11,12,13,8,9,6,7,2,3,4,5,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 7, i32 5, i32 6, i32 4, i32 3, i32 1, i32 2, i32 0>
   ret <8 x i16> %shuffle
 }
@@ -180,6 +251,11 @@ define <8 x i16> @shuffle_v8i16_10545410(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[2,3,0,1,10,11,8,9,10,11,8,9,2,3,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_10545410:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[2,3,0,1,10,11,8,9,10,11,8,9,2,3,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 0, i32 5, i32 4, i32 5, i32 4, i32 1, i32 0>
   ret <8 x i16> %shuffle
 }
@@ -200,6 +276,11 @@ define <8 x i16> @shuffle_v8i16_54105410(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[10,11,8,9,2,3,0,1,10,11,8,9,2,3,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_54105410:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[10,11,8,9,2,3,0,1,10,11,8,9,2,3,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 5, i32 4, i32 1, i32 0, i32 5, i32 4, i32 1, i32 0>
   ret <8 x i16> %shuffle
 }
@@ -220,6 +301,11 @@ define <8 x i16> @shuffle_v8i16_54101054(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[10,11,8,9,2,3,0,1,2,3,0,1,10,11,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_54101054:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[10,11,8,9,2,3,0,1,2,3,0,1,10,11,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 5, i32 4, i32 1, i32 0, i32 1, i32 0, i32 5, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -240,6 +326,11 @@ define <8 x i16> @shuffle_v8i16_04400440(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,0,1,8,9,8,9,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_04400440:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,0,1,8,9,8,9,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 4, i32 4, i32 0, i32 0, i32 4, i32 4, i32 0>
   ret <8 x i16> %shuffle
 }
@@ -260,6 +351,11 @@ define <8 x i16> @shuffle_v8i16_40044004(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[8,9,0,1,0,1,8,9,8,9,0,1,0,1,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_40044004:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,0,1,0,1,8,9,8,9,0,1,0,1,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 0, i32 0, i32 4, i32 4, i32 0, i32 0, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -283,6 +379,11 @@ define <8 x i16> @shuffle_v8i16_26405173(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[4,5,12,13,8,9,0,1,10,11,2,3,14,15,6,7]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_26405173:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[4,5,12,13,8,9,0,1,10,11,2,3,14,15,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 6, i32 4, i32 0, i32 5, i32 1, i32 7, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -305,6 +406,11 @@ define <8 x i16> @shuffle_v8i16_20645173(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[4,5,0,1,12,13,8,9,10,11,2,3,14,15,6,7]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_20645173:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[4,5,0,1,12,13,8,9,10,11,2,3,14,15,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 0, i32 6, i32 4, i32 5, i32 1, i32 7, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -326,6 +432,11 @@ define <8 x i16> @shuffle_v8i16_26401375(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[4,5,12,13,8,9,0,1,2,3,6,7,14,15,10,11]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_26401375:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[4,5,12,13,8,9,0,1,2,3,6,7,14,15,10,11]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 2, i32 6, i32 4, i32 0, i32 1, i32 3, i32 7, i32 5>
   ret <8 x i16> %shuffle
 }
@@ -349,6 +460,11 @@ define <8 x i16> @shuffle_v8i16_66751643(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[12,13,12,13,14,15,10,11,2,3,12,13,8,9,6,7]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_66751643:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,13,12,13,14,15,10,11,2,3,12,13,8,9,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 6, i32 6, i32 7, i32 5, i32 1, i32 6, i32 4, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -371,6 +487,11 @@ define <8 x i16> @shuffle_v8i16_60514754(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[12,13,0,1,10,11,2,3,8,9,14,15,10,11,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_60514754:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,13,0,1,10,11,2,3,8,9,14,15,10,11,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> undef, <8 x i32> <i32 6, i32 0, i32 5, i32 1, i32 4, i32 7, i32 5, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -392,6 +513,11 @@ define <8 x i16> @shuffle_v8i16_00444444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,8,9,8,9,8,9,8,9,8,9,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_00444444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,0,1,8,9,8,9,8,9,8,9,8,9,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 0, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -412,6 +538,11 @@ define <8 x i16> @shuffle_v8i16_44004444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,0,1,0,1,8,9,8,9,8,9,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_44004444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,0,1,0,1,8,9,8,9,8,9,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 4, i32 0, i32 0, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -432,6 +563,11 @@ define <8 x i16> @shuffle_v8i16_04404444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,8,9,8,9,8,9,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_04404444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,8,9,8,9,8,9,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 4, i32 4, i32 0, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -452,15 +588,26 @@ define <8 x i16> @shuffle_v8i16_04400000(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,0,1,0,1,0,1,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_04400000:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,0,1,0,1,0,1,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 4, i32 4, i32 0, i32 0, i32 0, i32 0, i32 0>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_04404567(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_04404567:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
-; ALL-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,0,4,5,6,7]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_04404567:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,2,0,4,5,6,7]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_04404567:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,2,2,3]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,2,2,0,4,5,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 4, i32 4, i32 0, i32 4, i32 5, i32 6, i32 7>
   ret <8 x i16> %shuffle
 }
@@ -482,6 +629,11 @@ define <8 x i16> @shuffle_v8i16_0X444444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,8,9,8,9,8,9,8,9,8,9,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0X444444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,8,9,8,9,8,9,8,9,8,9,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 undef, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -502,6 +654,11 @@ define <8 x i16> @shuffle_v8i16_44X04444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,0,1,8,9,8,9,8,9,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_44X04444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,8,9,8,9,0,1,8,9,8,9,8,9,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 4, i32 undef, i32 0, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -522,6 +679,11 @@ define <8 x i16> @shuffle_v8i16_X4404444(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,8,9,8,9,8,9,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_X4404444:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,8,9,8,9,0,1,8,9,8,9,8,9,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 4, i32 4, i32 0, i32 4, i32 4, i32 4, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -543,6 +705,11 @@ define <8 x i16> @shuffle_v8i16_0127XXXX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,14,15,4,5,14,15,12,13,14,15]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0127XXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,14,15,4,5,14,15,12,13,14,15]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 7, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -564,6 +731,11 @@ define <8 x i16> @shuffle_v8i16_XXXX4563(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[12,13,6,7,4,5,6,7,8,9,10,11,12,13,6,7]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_XXXX4563:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[12,13,6,7,4,5,6,7,8,9,10,11,12,13,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 4, i32 5, i32 6, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -585,6 +757,11 @@ define <8 x i16> @shuffle_v8i16_4563XXXX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,6,7,8,9,10,11,0,1,2,3]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_4563XXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,6,7,8,9,10,11,0,1,2,3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -606,6 +783,11 @@ define <8 x i16> @shuffle_v8i16_01274563(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,14,15,8,9,10,11,12,13,6,7]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_01274563:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,14,15,8,9,10,11,12,13,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 7, i32 4, i32 5, i32 6, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -627,6 +809,11 @@ define <8 x i16> @shuffle_v8i16_45630127(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,6,7,0,1,2,3,4,5,14,15]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_45630127:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[8,9,10,11,12,13,6,7,0,1,2,3,4,5,14,15]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 5, i32 6, i32 3, i32 0, i32 1, i32 2, i32 7>
   ret <8 x i16> %shuffle
 }
@@ -651,114 +838,186 @@ define <8 x i16> @shuffle_v8i16_37102735(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[6,7,14,15,2,3,0,1,4,5,14,15,6,7,10,11]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_37102735:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[6,7,14,15,2,3,0,1,4,5,14,15,6,7,10,11]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 3, i32 7, i32 1, i32 0, i32 2, i32 7, i32 3, i32 5>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_08192a3b(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_08192a3b:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_08192a3b:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_08192a3b:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 2, i32 10, i32 3, i32 11>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_0c1d2e3f(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_0c1d2e3f:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_0c1d2e3f:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0c1d2e3f:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 12, i32 1, i32 13, i32 2, i32 14, i32 3, i32 15>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_4c5d6e7f(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_4c5d6e7f:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_4c5d6e7f:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_4c5d6e7f:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 12, i32 5, i32 13, i32 6, i32 14, i32 7, i32 15>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_48596a7b(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_48596a7b:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_48596a7b:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_48596a7b:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 8, i32 5, i32 9, i32 6, i32 10, i32 7, i32 11>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_08196e7f(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_08196e7f:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_08196e7f:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_08196e7f:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 8, i32 1, i32 9, i32 6, i32 14, i32 7, i32 15>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_0c1d6879(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_0c1d6879:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,0,2,3]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_0c1d6879:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,0,2,3]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0c1d6879:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,0,2,3]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,3,2,3]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 12, i32 1, i32 13, i32 6, i32 8, i32 7, i32 9>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_109832ba(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_109832ba:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
-; ALL-NEXT:    pshuflw {{.*#+}} xmm1 = xmm0[2,0,3,1,4,5,6,7]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
-; ALL-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[2,0,3,1,4,5,6,7]
-; ALL-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
-; ALL-NEXT:    movdqa %xmm1, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_109832ba:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm0[2,0,3,1,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[2,0,3,1,4,5,6,7]
+; SSE-NEXT:    punpcklqdq {{.*#+}} xmm1 = xmm1[0],xmm0[0]
+; SSE-NEXT:    movdqa %xmm1, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_109832ba:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm0[2,0,3,1,4,5,6,7]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[2,0,3,1,4,5,6,7]
+; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm1[0],xmm0[0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 1, i32 0, i32 9, i32 8, i32 3, i32 2, i32 11, i32 10>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_8091a2b3(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_8091a2b3:
-; ALL:       # BB#0:
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
-; ALL-NEXT:    movdqa %xmm1, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_8091a2b3:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; SSE-NEXT:    movdqa %xmm1, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_8091a2b3:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 8, i32 0, i32 9, i32 1, i32 10, i32 2, i32 11, i32 3>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_c4d5e6f7(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_c4d5e6f7:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
-; ALL-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_c4d5e6f7:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm2 = xmm0[2,3,0,1]
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,3,0,1]
+; SSE-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_c4d5e6f7:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 12, i32 4, i32 13, i32 5, i32 14, i32 6, i32 15, i32 7>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_0213cedf(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_0213cedf:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,1,3,4,5,6,7]
-; ALL-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
-; ALL-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,1,3,4,5,6,7]
-; ALL-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_0213cedf:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshuflw {{.*#+}} xmm0 = xmm0[0,2,1,3,4,5,6,7]
+; SSE-NEXT:    pshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
+; SSE-NEXT:    pshuflw {{.*#+}} xmm1 = xmm1[0,2,1,3,4,5,6,7]
+; SSE-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0213cedf:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,2,1,3,4,5,6,7]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,2,3]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,2,1,3,4,5,6,7]
+; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 2, i32 1, i32 3, i32 12, i32 14, i32 13, i32 15>
   ret <8 x i16> %shuffle
 }
@@ -789,6 +1048,14 @@ define <8 x i16> @shuffle_v8i16_443aXXXX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,12,13,10,11,12,13,10,11,12,13,14,15]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_443aXXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,1,2,3]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm0 = xmm0[0,0,2,3,4,5,6,7]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,12,13,10,11,12,13,10,11,12,13,14,15]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 4, i32 4, i32 3, i32 10, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -817,14 +1084,26 @@ define <8 x i16> @shuffle_v8i16_032dXXXX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,8,9,6,7,8,9,12,13,12,13,14,15]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_032dXXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,12,13,8,9,6,7,8,9,12,13,12,13,14,15]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 3, i32 2, i32 13, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
 define <8 x i16> @shuffle_v8i16_XXXdXXXX(<8 x i16> %a, <8 x i16> %b) {
-; ALL-LABEL: shuffle_v8i16_XXXdXXXX:
-; ALL:       # BB#0:
-; ALL-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,2,3,3]
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_XXXdXXXX:
+; SSE:       # BB#0:
+; SSE-NEXT:    pshufd {{.*#+}} xmm0 = xmm1[2,2,3,3]
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_XXXdXXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm1[2,2,3,3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 13, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -853,6 +1132,13 @@ define <8 x i16> @shuffle_v8i16_012dXXXX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,6,7,8,9,0,1,0,1,2,3]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_012dXXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,6,7,8,9,0,1,0,1,2,3]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 13, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -882,6 +1168,13 @@ define <8 x i16> @shuffle_v8i16_XXXXcde3(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[0,1,4,5,4,5,6,7,0,1,4,5,8,9,14,15]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_XXXXcde3:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
+; AVX-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,4,5,6,7,0,1,4,5,8,9,14,15]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 12, i32 13, i32 14, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -911,6 +1204,13 @@ define <8 x i16> @shuffle_v8i16_cde3XXXX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm1 = xmm1[0,1,4,5,8,9,14,15,8,9,14,15,12,13,14,15]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_cde3XXXX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[0,1,0,1]
+; AVX-NEXT:    vpunpckhwd {{.*#+}} xmm0 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,14,15,8,9,14,15,12,13,14,15]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 12, i32 13, i32 14, i32 3, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -953,6 +1253,17 @@ define <8 x i16> @shuffle_v8i16_012dcde3(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,6,7,8,9,0,1,0,1,2,3]
 ; SSE41-NEXT:    punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_012dcde3:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm2 = xmm0[0,1,0,1]
+; AVX-NEXT:    vpunpckhwd {{.*#+}} xmm2 = xmm1[4],xmm2[4],xmm1[5],xmm2[5],xmm1[6],xmm2[6],xmm1[7],xmm2[7]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm2 = xmm2[0,1,4,5,8,9,14,15,8,9,14,15,12,13,14,15]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[2,3,0,1]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,4,5,8,9,6,7,8,9,0,1,0,1,2,3]
+; AVX-NEXT:    vpunpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm2[0]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 0, i32 1, i32 2, i32 13, i32 12, i32 13, i32 14, i32 3>
   ret <8 x i16> %shuffle
 }
@@ -983,6 +1294,13 @@ define <8 x i16> @shuffle_v8i16_XXX1X579(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,4,5,8,9,8,9,12,13,6,7]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_XXX1X579:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,10,11,14,15,14,15,10,11,12,13,14,15]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1],xmm0[2],xmm1[2],xmm0[3],xmm1[3]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,4,5,4,5,8,9,8,9,12,13,6,7]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 1, i32 undef, i32 5, i32 7, i32 9>
   ret <8 x i16> %shuffle
 }
@@ -1017,64 +1335,107 @@ define <8 x i16> @shuffle_v8i16_XX4X8acX(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    punpcklwd {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3]
 ; SSE41-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,2,3,0,1,0,1,4,5,8,9,0,1]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_XX4X8acX:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,0,1]
+; AVX-NEXT:    vpshuflw {{.*#+}} xmm1 = xmm1[0,2,2,3,4,5,6,7]
+; AVX-NEXT:    vpshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; AVX-NEXT:    vpunpcklwd {{.*#+}} xmm0 = xmm1[0],xmm0[0],xmm1[1],xmm0[1],xmm1[2],xmm0[2],xmm1[3],xmm0[3]
+; AVX-NEXT:    vpshufb {{.*#+}} xmm0 = xmm0[0,1,2,3,2,3,0,1,0,1,4,5,8,9,0,1]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 undef, i32 4, i32 undef, i32 8, i32 10, i32 12, i32 undef>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_8zzzzzzz(i16 %i) {
-; ALL-LABEL: shuffle_v8i16_8zzzzzzz:
-; ALL:       # BB#0:
-; ALL-NEXT:    movzwl %di, %eax
-; ALL-NEXT:    movd %eax, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_8zzzzzzz:
+; SSE:       # BB#0:
+; SSE-NEXT:    movzwl %di, %eax
+; SSE-NEXT:    movd %eax, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_8zzzzzzz:
+; AVX:       # BB#0:
+; AVX-NEXT:    movzwl %di, %eax
+; AVX-NEXT:    vmovd %eax, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <8 x i16> undef, i16 %i, i32 0
   %shuffle = shufflevector <8 x i16> zeroinitializer, <8 x i16> %a, <8 x i32> <i32 8, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_z8zzzzzz(i16 %i) {
-; ALL-LABEL: shuffle_v8i16_z8zzzzzz:
-; ALL:       # BB#0:
-; ALL-NEXT:    movzwl %di, %eax
-; ALL-NEXT:    movd %eax, %xmm0
-; ALL-NEXT:    pslldq $2, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_z8zzzzzz:
+; SSE:       # BB#0:
+; SSE-NEXT:    movzwl %di, %eax
+; SSE-NEXT:    movd %eax, %xmm0
+; SSE-NEXT:    pslldq $2, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_z8zzzzzz:
+; AVX:       # BB#0:
+; AVX-NEXT:    movzwl %di, %eax
+; AVX-NEXT:    vmovd %eax, %xmm0
+; AVX-NEXT:    vpslldq $2, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <8 x i16> undef, i16 %i, i32 0
   %shuffle = shufflevector <8 x i16> zeroinitializer, <8 x i16> %a, <8 x i32> <i32 2, i32 8, i32 3, i32 7, i32 6, i32 5, i32 4, i32 3>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_zzzzz8zz(i16 %i) {
-; ALL-LABEL: shuffle_v8i16_zzzzz8zz:
-; ALL:       # BB#0:
-; ALL-NEXT:    movzwl %di, %eax
-; ALL-NEXT:    movd %eax, %xmm0
-; ALL-NEXT:    pslldq $10, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_zzzzz8zz:
+; SSE:       # BB#0:
+; SSE-NEXT:    movzwl %di, %eax
+; SSE-NEXT:    movd %eax, %xmm0
+; SSE-NEXT:    pslldq $10, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_zzzzz8zz:
+; AVX:       # BB#0:
+; AVX-NEXT:    movzwl %di, %eax
+; AVX-NEXT:    vmovd %eax, %xmm0
+; AVX-NEXT:    vpslldq $10, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <8 x i16> undef, i16 %i, i32 0
   %shuffle = shufflevector <8 x i16> zeroinitializer, <8 x i16> %a, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 8, i32 0, i32 0>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_zuuzuuz8(i16 %i) {
-; ALL-LABEL: shuffle_v8i16_zuuzuuz8:
-; ALL:       # BB#0:
-; ALL-NEXT:    movzwl %di, %eax
-; ALL-NEXT:    movd %eax, %xmm0
-; ALL-NEXT:    pslldq $14, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_zuuzuuz8:
+; SSE:       # BB#0:
+; SSE-NEXT:    movzwl %di, %eax
+; SSE-NEXT:    movd %eax, %xmm0
+; SSE-NEXT:    pslldq $14, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_zuuzuuz8:
+; AVX:       # BB#0:
+; AVX-NEXT:    movzwl %di, %eax
+; AVX-NEXT:    vmovd %eax, %xmm0
+; AVX-NEXT:    vpslldq $14, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <8 x i16> undef, i16 %i, i32 0
   %shuffle = shufflevector <8 x i16> zeroinitializer, <8 x i16> %a, <8 x i32> <i32 0, i32 undef, i32 undef, i32 3, i32 undef, i32 undef, i32 6, i32 8>
   ret <8 x i16> %shuffle
 }
 
 define <8 x i16> @shuffle_v8i16_zzBzzzzz(i16 %i) {
-; ALL-LABEL: shuffle_v8i16_zzBzzzzz:
-; ALL:       # BB#0:
-; ALL-NEXT:    movzwl %di, %eax
-; ALL-NEXT:    movd %eax, %xmm0
-; ALL-NEXT:    pslldq $4, %xmm0
-; ALL-NEXT:    retq
+; SSE-LABEL: shuffle_v8i16_zzBzzzzz:
+; SSE:       # BB#0:
+; SSE-NEXT:    movzwl %di, %eax
+; SSE-NEXT:    movd %eax, %xmm0
+; SSE-NEXT:    pslldq $4, %xmm0
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_zzBzzzzz:
+; AVX:       # BB#0:
+; AVX-NEXT:    movzwl %di, %eax
+; AVX-NEXT:    vmovd %eax, %xmm0
+; AVX-NEXT:    vpslldq $4, %xmm0, %xmm0
+; AVX-NEXT:    retq
   %a = insertelement <8 x i16> undef, i16 %i, i32 3
   %shuffle = shufflevector <8 x i16> zeroinitializer, <8 x i16> %a, <8 x i32> <i32 0, i32 1, i32 11, i32 3, i32 4, i32 5, i32 6, i32 7>
   ret <8 x i16> %shuffle
@@ -1106,6 +1467,11 @@ define <8 x i16> @shuffle_v8i16_def01234(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm1[10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_def01234:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 13, i32 14, i32 15, i32 0, i32 1, i32 2, i32 3, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -1130,6 +1496,11 @@ define <8 x i16> @shuffle_v8i16_ueuu123u(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm1[10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_ueuu123u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[10,11,12,13,14,15],xmm0[0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 14, i32 undef, i32 undef, i32 1, i32 2, i32 3, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1153,6 +1524,11 @@ define <8 x i16> @shuffle_v8i16_56701234(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_56701234:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 5, i32 6, i32 7, i32 0, i32 1, i32 2, i32 3, i32 4>
   ret <8 x i16> %shuffle
 }
@@ -1174,6 +1550,11 @@ define <8 x i16> @shuffle_v8i16_u6uu123u(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u6uu123u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 6, i32 undef, i32 undef, i32 1, i32 2, i32 3, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1194,6 +1575,11 @@ define <8 x i16> @shuffle_v8i16_uuuu123u(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_uuuu123u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15,0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 undef, i32 undef, i32 undef, i32 1, i32 2, i32 3, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1223,6 +1609,11 @@ define <8 x i16> @shuffle_v8i16_bcdef012(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm1[6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_bcdef012:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 11, i32 12, i32 13, i32 14, i32 15, i32 0, i32 1, i32 2>
   ret <8 x i16> %shuffle
 }
@@ -1247,6 +1638,11 @@ define <8 x i16> @shuffle_v8i16_ucdeuu1u(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm1[6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_ucdeuu1u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm1[6,7,8,9,10,11,12,13,14,15],xmm0[0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 12, i32 13, i32 14, i32 undef, i32 undef, i32 1, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1270,6 +1666,11 @@ define <8 x i16> @shuffle_v8i16_34567012(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_34567012:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 0, i32 1, i32 2>
   ret <8 x i16> %shuffle
 }
@@ -1291,6 +1692,11 @@ define <8 x i16> @shuffle_v8i16_u456uu1u(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u456uu1u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 4, i32 5, i32 6, i32 undef, i32 undef, i32 1, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1311,6 +1717,11 @@ define <8 x i16> @shuffle_v8i16_u456uuuu(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    palignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5]
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u456uuuu:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15,0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 4, i32 5, i32 6, i32 undef, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1342,6 +1753,11 @@ define <8 x i16> @shuffle_v8i16_3456789a(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_3456789a:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10>
   ret <8 x i16> %shuffle
 }
@@ -1368,6 +1784,11 @@ define <8 x i16> @shuffle_v8i16_u456uu9u(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u456uu9u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[6,7,8,9,10,11,12,13,14,15],xmm1[0,1,2,3,4,5]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 4, i32 5, i32 6, i32 undef, i32 undef, i32 9, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1399,6 +1820,11 @@ define <8 x i16> @shuffle_v8i16_56789abc(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_56789abc:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12>
   ret <8 x i16> %shuffle
 }
@@ -1425,6 +1851,11 @@ define <8 x i16> @shuffle_v8i16_u6uu9abu(<8 x i16> %a, <8 x i16> %b) {
 ; SSE41-NEXT:    palignr {{.*#+}} xmm1 = xmm0[10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7,8,9]
 ; SSE41-NEXT:    movdqa %xmm1, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_u6uu9abu:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpalignr {{.*#+}} xmm0 = xmm0[10,11,12,13,14,15],xmm1[0,1,2,3,4,5,6,7,8,9]
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> %b, <8 x i32> <i32 undef, i32 6, i32 undef, i32 undef, i32 9, i32 10, i32 11, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1446,6 +1877,11 @@ define <8 x i16> @shuffle_v8i16_0uuu1uuu(<8 x i16> %a) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxwq %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0uuu1uuu:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxwq %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 undef, i32 undef, i32 undef, i32 1, i32 undef, i32 undef, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1469,6 +1905,11 @@ define <8 x i16> @shuffle_v8i16_0zzz1zzz(<8 x i16> %a) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxwq %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0zzz1zzz:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxwq %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
   ret <8 x i16> %shuffle
 }
@@ -1488,6 +1929,11 @@ define <8 x i16> @shuffle_v8i16_0u1u2u3u(<8 x i16> %a) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxwd %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0u1u2u3u:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxwd %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 undef, i32 1, i32 undef, i32 2, i32 undef, i32 3, i32 undef>
   ret <8 x i16> %shuffle
 }
@@ -1509,6 +1955,11 @@ define <8 x i16> @shuffle_v8i16_0z1z2z3z(<8 x i16> %a) {
 ; SSE41:       # BB#0:
 ; SSE41-NEXT:    pmovzxwd %xmm0, %xmm0
 ; SSE41-NEXT:    retq
+;
+; AVX-LABEL: shuffle_v8i16_0z1z2z3z:
+; AVX:       # BB#0:
+; AVX-NEXT:    vpmovzxwd %xmm0, %xmm0
+; AVX-NEXT:    retq
   %shuffle = shufflevector <8 x i16> %a, <8 x i16> zeroinitializer, <8 x i32> <i32 0, i32 9, i32 1, i32 11, i32 2, i32 13, i32 3, i32 15>
   ret <8 x i16> %shuffle
 }