-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE2
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+ssse3 | 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 | FileCheck %s --check-prefix=ALL --check-prefix=SSE --check-prefix=SSE41
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX1
-; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -mattr=+avx2 | FileCheck %s --check-prefix=ALL --check-prefix=AVX --check-prefix=AVX2
+; RUN: llc < %s -mtriple=x86_64-unknown-unknown -mcpu=x86-64 -x86-experimental-vector-shuffle-legality | 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-legality | 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-legality | 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-legality | 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-legality | 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"
ret <16 x i8> %shuffle
}
-define <16 x i8> @shuffle_v16i8_16_17_18_19_04_05_06_07_24_25_10_11_28_13_30_15(<16 x i8> %a, <16 x i8> %b) {
-; SSE2-LABEL: shuffle_v16i8_16_17_18_19_04_05_06_07_24_25_10_11_28_13_30_15:
+define <16 x i8> @shuffle_v16i8_00_01_02_19_04_05_06_23_08_09_10_27_12_13_14_31(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: shuffle_v16i8_00_01_02_19_04_05_06_23_08_09_10_27_12_13_14_31:
; SSE2: # BB#0:
; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: movdqa %xmm0, %xmm3
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1],xmm3[2],xmm2[2],xmm3[3],xmm2[3],xmm3[4],xmm2[4],xmm3[5],xmm2[5],xmm3[6],xmm2[6],xmm3[7],xmm2[7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,3,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm3[0,1,1,3,4,5,6,7]
-; SSE2-NEXT: movdqa %xmm0, %xmm3
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm2[8],xmm3[9],xmm2[9],xmm3[10],xmm2[10],xmm3[11],xmm2[11],xmm3[12],xmm2[12],xmm3[13],xmm2[13],xmm3[14],xmm2[14],xmm3[15],xmm2[15]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,7,5,6,7]
-; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[2,1,2,3]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[0,3,1,0,4,5,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[3,1,2,3,4,5,6,7]
+; SSE2-NEXT: movdqa %xmm0, %xmm4
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[3,1,2,3,4,5,6,7]
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm4 = xmm4[0],xmm3[0],xmm4[1],xmm3[1],xmm4[2],xmm3[2],xmm4[3],xmm3[3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm4[2,0,3,1,4,5,6,7]
+; SSE2-NEXT: packuswb %xmm0, %xmm3
+; SSE2-NEXT: movdqa %xmm1, %xmm4
+; SSE2-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8],xmm2[8],xmm4[9],xmm2[9],xmm4[10],xmm2[10],xmm4[11],xmm2[11],xmm4[12],xmm2[12],xmm4[13],xmm2[13],xmm4[14],xmm2[14],xmm4[15],xmm2[15]
+; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[3,1,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[1,1,2,3,4,5,6,7]
+; SSE2-NEXT: punpcklbw {{.*#+}} 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]
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[3,1,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[1,1,2,3,4,5,6,7]
+; SSE2-NEXT: punpcklwd {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3]
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,3,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[2,0,3,1,4,5,6,7]
+; SSE2-NEXT: packuswb %xmm0, %xmm1
+; SSE2-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]
+; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
+; SSE2-NEXT: packuswb %xmm0, %xmm0
+; SSE2-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]
+; SSE2-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v16i8_00_01_02_19_04_05_06_23_08_09_10_27_12_13_14_31:
+; SSSE3: # BB#0:
+; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = xmm1[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
+; SSSE3-NEXT: movdqa %xmm0, %xmm2
+; SSSE3-NEXT: pshufb {{.*#+}} xmm2 = xmm2[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
+; SSSE3-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]
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; SSSE3-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]
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v16i8_00_01_02_19_04_05_06_23_08_09_10_27_12_13_14_31:
+; SSE41: # BB#0:
+; SSE41-NEXT: pshufb {{.*#+}} xmm1 = xmm1[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
+; SSE41-NEXT: movdqa %xmm0, %xmm2
+; SSE41-NEXT: pshufb {{.*#+}} xmm2 = xmm2[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
+; SSE41-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]
+; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; SSE41-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]
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v16i8_00_01_02_19_04_05_06_23_08_09_10_27_12_13_14_31:
+; AVX: # BB#0:
+; AVX-NEXT: vpshufb {{.*#+}} xmm1 = xmm1[3,7,11,15,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX-NEXT: vpshufb {{.*#+}} xmm2 = xmm0[1,5,9,13,u,u,u,u,u,u,u,u,u,u,u,u]
+; AVX-NEXT: vpunpcklbw {{.*#+}} xmm1 = 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]
+; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
+; 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 1, i32 2, i32 19, i32 4, i32 5, i32 6, i32 23, i32 8, i32 9, i32 10, i32 27, i32 12, i32 13, i32 14, i32 31>
+ ret <16 x i8> %shuffle
+}
+
+define <16 x i8> @shuffle_v16i8_00_01_02_03_20_05_06_23_08_09_10_11_28_13_14_31(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: shuffle_v16i8_00_01_02_03_20_05_06_23_08_09_10_11_28_13_14_31:
+; SSE2: # BB#0:
+; SSE2-NEXT: pxor %xmm2, %xmm2
+; SSE2-NEXT: movdqa %xmm1, %xmm3
+; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm2[8],xmm3[9],xmm2[9],xmm3[10],xmm2[10],xmm3[11],xmm2[11],xmm3[12],xmm2[12],xmm3[13],xmm2[13],xmm3[14],xmm2[14],xmm3[15],xmm2[15]
+; SSE2-NEXT: movdqa %xmm0, %xmm4
+; SSE2-NEXT: punpckhbw {{.*#+}} xmm4 = xmm4[8],xmm2[8],xmm4[9],xmm2[9],xmm4[10],xmm2[10],xmm4[11],xmm2[11],xmm4[12],xmm2[12],xmm4[13],xmm2[13],xmm4[14],xmm2[14],xmm4[15],xmm2[15]
+; SSE2-NEXT: movdqa %xmm4, %xmm5
+; SSE2-NEXT: punpckhwd {{.*#+}} xmm5 = xmm5[4],xmm3[4],xmm5[5],xmm3[5],xmm5[6],xmm3[6],xmm5[7],xmm3[7]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm5[2,1,2,3,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,4,7,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm3 = xmm3[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[1,0,2,3,4,5,6,7]
; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm3[0]
+; SSE2-NEXT: punpcklbw {{.*#+}} 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]
+; 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: movdqa %xmm0, %xmm2
+; SSE2-NEXT: punpckhwd {{.*#+}} xmm2 = xmm2[4],xmm1[4],xmm2[5],xmm1[5],xmm2[6],xmm1[6],xmm2[7],xmm1[7]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm2[2,1,2,3,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,7,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,2,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[1,0,2,3,4,5,6,7]
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm0 = xmm0[0],xmm1[0]
+; SSE2-NEXT: packuswb %xmm4, %xmm0
+; SSE2-NEXT: retq
+;
+; SSSE3-LABEL: shuffle_v16i8_00_01_02_03_20_05_06_23_08_09_10_11_28_13_14_31:
+; SSSE3: # BB#0:
+; SSSE3-NEXT: pshufb {{.*#+}} xmm1 = zero,zero,zero,zero,xmm1[4],zero,zero,xmm1[7],zero,zero,zero,zero,xmm1[12],zero,zero,xmm1[15]
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,1,2,3],zero,xmm0[5,6],zero,xmm0[8,9,10,11],zero,xmm0[13,14],zero
+; SSSE3-NEXT: por %xmm1, %xmm0
+; SSSE3-NEXT: retq
+;
+; SSE41-LABEL: shuffle_v16i8_00_01_02_03_20_05_06_23_08_09_10_11_28_13_14_31:
+; SSE41: # BB#0:
+; SSE41-NEXT: movdqa %xmm0, %xmm2
+; SSE41-NEXT: movaps {{.*#+}} xmm0 = [255,255,255,255,0,255,255,0,255,255,255,255,0,255,255,0]
+; SSE41-NEXT: pblendvb %xmm2, %xmm1
+; SSE41-NEXT: movdqa %xmm1, %xmm0
+; SSE41-NEXT: retq
+;
+; AVX-LABEL: shuffle_v16i8_00_01_02_03_20_05_06_23_08_09_10_11_28_13_14_31:
+; AVX: # BB#0:
+; AVX-NEXT: vmovdqa {{.*#+}} xmm2 = [255,255,255,255,0,255,255,0,255,255,255,255,0,255,255,0]
+; AVX-NEXT: vpblendvb %xmm2, %xmm0, %xmm1, %xmm0
+; AVX-NEXT: retq
+ %shuffle = shufflevector <16 x i8> %a, <16 x i8> %b, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 20, i32 5, i32 6, i32 23, i32 8, i32 9, i32 10, i32 11, i32 28, i32 13, i32 14, i32 31>
+ ret <16 x i8> %shuffle
+}
+
+define <16 x i8> @shuffle_v16i8_16_17_18_19_04_05_06_07_24_25_10_11_28_13_30_15(<16 x i8> %a, <16 x i8> %b) {
+; SSE2-LABEL: shuffle_v16i8_16_17_18_19_04_05_06_07_24_25_10_11_28_13_30_15:
+; SSE2: # BB#0:
+; SSE2-NEXT: pxor %xmm2, %xmm2
; SSE2-NEXT: movdqa %xmm1, %xmm3
; SSE2-NEXT: punpckhbw {{.*#+}} xmm3 = xmm3[8],xmm2[8],xmm3[9],xmm2[9],xmm3[10],xmm2[10],xmm3[11],xmm2[11],xmm3[12],xmm2[12],xmm3[13],xmm2[13],xmm3[14],xmm2[14],xmm3[15],xmm2[15]
-; SSE2-NEXT: movdqa %xmm1, %xmm5
-; SSE2-NEXT: punpcklbw {{.*#+}} xmm5 = xmm5[0],xmm2[0],xmm5[1],xmm2[1],xmm5[2],xmm2[2],xmm5[3],xmm2[3],xmm5[4],xmm2[4],xmm5[5],xmm2[5],xmm5[6],xmm2[6],xmm5[7],xmm2[7]
-; SSE2-NEXT: punpcklwd {{.*#+}} xmm5 = xmm5[0],xmm3[0],xmm5[1],xmm3[1],xmm5[2],xmm3[2],xmm5[3],xmm3[3]
-; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm5[3,1,2,1]
-; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[2,0,2,3,4,5,6,7]
-; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,7,5,6,7]
-; SSE2-NEXT: movdqa %xmm4, %xmm3
-; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[1,0],xmm2[0,0]
-; SSE2-NEXT: shufps {{.*#+}} xmm3 = xmm3[2,0],xmm2[2,3]
-; SSE2-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; SSE2-NEXT: movdqa %xmm1, %xmm4
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; 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[3,1,2,1]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm3 = xmm3[2,0,2,3,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm3 = xmm3[0,1,2,3,7,5,6,7]
+; SSE2-NEXT: movdqa %xmm0, %xmm4
+; SSE2-NEXT: punpcklbw {{.*#+}} xmm4 = xmm4[0],xmm2[0],xmm4[1],xmm2[1],xmm4[2],xmm2[2],xmm4[3],xmm2[3],xmm4[4],xmm2[4],xmm4[5],xmm2[5],xmm4[6],xmm2[6],xmm4[7],xmm2[7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm4[2,3,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm4 = xmm4[0,1,1,3,4,5,6,7]
+; SSE2-NEXT: movdqa %xmm0, %xmm5
+; SSE2-NEXT: punpckhbw {{.*#+}} xmm5 = xmm5[8],xmm2[8],xmm5[9],xmm2[9],xmm5[10],xmm2[10],xmm5[11],xmm2[11],xmm5[12],xmm2[12],xmm5[13],xmm2[13],xmm5[14],xmm2[14],xmm5[15],xmm2[15]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm5[0,1,2,3,7,5,6,7]
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[2,1,2,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm2[0,3,1,0,4,5,6,7]
+; SSE2-NEXT: punpcklqdq {{.*#+}} xmm4 = xmm4[0],xmm2[0]
+; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm4[1,1,2,3]
+; SSE2-NEXT: punpckhwd {{.*#+}} xmm4 = xmm4[4],xmm3[4],xmm4[5],xmm3[5],xmm4[6],xmm3[6],xmm4[7],xmm3[7]
+; SSE2-NEXT: punpckldq {{.*#+}} xmm3 = xmm3[0],xmm2[0],xmm3[1],xmm2[1]
; SSE2-NEXT: pshuflw {{.*#+}} xmm2 = xmm4[2,1,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm2 = xmm2[0,1,2,3,4,6,6,7]
; SSE2-NEXT: pshufd {{.*#+}} xmm2 = xmm2[0,2,2,3]
; SSE2-NEXT: movdqa {{.*#+}} xmm2 = [255,255,255,255,255,255,255,255]
; SSE2-NEXT: pand %xmm2, %xmm1
; SSE2-NEXT: pand %xmm2, %xmm0
-; SSE2-NEXT: movdqa %xmm0, %xmm2
-; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[1,0],xmm1[0,0]
-; SSE2-NEXT: shufps {{.*#+}} xmm2 = xmm2[2,0],xmm1[2,3]
+; SSE2-NEXT: pshufd {{.*#+}} xmm4 = xmm0[1,1,2,3]
+; SSE2-NEXT: movdqa %xmm1, %xmm2
+; SSE2-NEXT: punpckldq {{.*#+}} xmm2 = xmm2[0],xmm4[0],xmm2[1],xmm4[1]
; SSE2-NEXT: punpckhwd {{.*#+}} xmm1 = xmm1[4],xmm0[4],xmm1[5],xmm0[5],xmm1[6],xmm0[6],xmm1[7],xmm0[7]
; SSE2-NEXT: pshuflw {{.*#+}} xmm0 = xmm1[0,3,2,3,4,5,6,7]
; SSE2-NEXT: pshufhw {{.*#+}} xmm0 = xmm0[0,1,2,3,4,6,6,7]
; SSE2-LABEL: PR20540:
; SSE2: # BB#0:
; SSE2-NEXT: pand {{.*}}(%rip), %xmm0
-; SSE2-NEXT: packuswb %xmm0, %xmm0
-; SSE2-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
+; SSE2-NEXT: pxor %xmm1, %xmm1
+; SSE2-NEXT: pshufd {{.*#+}} xmm1 = xmm1[0,1,0,3]
+; SSE2-NEXT: pshuflw {{.*#+}} xmm1 = xmm1[0,0,0,0,4,5,6,7]
+; SSE2-NEXT: pshufhw {{.*#+}} xmm1 = xmm1[0,1,2,3,4,4,4,4]
+; SSE2-NEXT: packuswb %xmm1, %xmm0
; SSE2-NEXT: retq
;
; SSSE3-LABEL: PR20540:
; SSSE3: # BB#0:
-; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
-; SSSE3-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
+; SSSE3-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
; SSSE3-NEXT: retq
;
; SSE41-LABEL: PR20540:
; SSE41: # BB#0:
-; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
-; SSE41-NEXT: movq {{.*#+}} xmm0 = xmm0[0],zero
+; SSE41-NEXT: pshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
; SSE41-NEXT: retq
;
; AVX-LABEL: PR20540:
; AVX: # BB#0:
-; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14,u,u,u,u,u,u,u,u]
-; AVX-NEXT: vmovq {{.*#+}} xmm0 = xmm0[0],zero
+; AVX-NEXT: vpshufb {{.*#+}} xmm0 = xmm0[0,2,4,6,8,10,12,14],zero,zero,zero,zero,zero,zero,zero,zero
; 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