aboutsummaryrefslogtreecommitdiff
path: root/test/CodeGen/X86/vector-shuffle-256-v8.ll
diff options
context:
space:
mode:
Diffstat (limited to 'test/CodeGen/X86/vector-shuffle-256-v8.ll')
-rw-r--r--test/CodeGen/X86/vector-shuffle-256-v8.ll250
1 files changed, 109 insertions, 141 deletions
diff --git a/test/CodeGen/X86/vector-shuffle-256-v8.ll b/test/CodeGen/X86/vector-shuffle-256-v8.ll
index e8b886afd1ae..4aab5cd17009 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v8.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v8.ll
@@ -29,8 +29,8 @@ define <8 x float> @shuffle_v8f32_00000010(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_00000010:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [0,0,0,0,0,0,1,0]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,0]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
ret <8 x float> %shuffle
@@ -46,8 +46,8 @@ define <8 x float> @shuffle_v8f32_00000200(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_00000200:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [0,0,0,0,0,2,0,0]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,2]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,1,0]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
ret <8 x float> %shuffle
@@ -63,8 +63,8 @@ define <8 x float> @shuffle_v8f32_00003000(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_00003000:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [0,0,0,0,3,0,0,0]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,3,0]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,1,0]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
ret <8 x float> %shuffle
@@ -152,8 +152,8 @@ define <8 x float> @shuffle_v8f32_01014545(<8 x float> %a, <8 x float> %b) {
define <8 x float> @shuffle_v8f32_00112233(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_00112233:
; AVX1: # BB#0:
-; AVX1-NEXT: vunpcklps {{.*#+}} xmm1 = xmm0[0,0,1,1]
-; AVX1-NEXT: vunpckhps {{.*#+}} xmm0 = xmm0[2,2,3,3]
+; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,1,1]
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
@@ -176,8 +176,8 @@ define <8 x float> @shuffle_v8f32_00001111(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_00001111:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [0,0,0,0,1,1,1,1]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,0,1,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
ret <8 x float> %shuffle
@@ -195,18 +195,15 @@ define <8 x float> @shuffle_v8f32_81a3c5e7(<8 x float> %a, <8 x float> %b) {
define <8 x float> @shuffle_v8f32_08080808(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_08080808:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
-; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_08080808:
; AVX2: # BB#0:
-; AVX2-NEXT: vbroadcastss %xmm1, %ymm1
+; AVX2-NEXT: vinsertps {{.*#+}} xmm0 = xmm0[0],xmm1[0],zero,zero
; AVX2-NEXT: vbroadcastsd %xmm0, %ymm0
-; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8>
ret <8 x float> %shuffle
@@ -216,7 +213,7 @@ define <8 x float> @shuffle_v8f32_08084c4c(<8 x float> %a, <8 x float> %b) {
; ALL-LABEL: shuffle_v8f32_08084c4c:
; ALL: # BB#0:
; ALL-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
-; ALL-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; ALL-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 4, i32 12, i32 4, i32 12>
ret <8 x float> %shuffle
@@ -299,10 +296,10 @@ define <8 x float> @shuffle_v8f32_08991abb(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_08991abb:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
-; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,0,1,1,u,2,3,3>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 9, i32 1, i32 10, i32 11, i32 11>
@@ -338,8 +335,8 @@ define <8 x float> @shuffle_v8f32_09ab1def(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_09ab1def:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
-; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,1,1,3]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,1,1,3]
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
@@ -647,10 +644,10 @@ define <8 x float> @shuffle_v8f32_c348cda0(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_c348cda0:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,3,4,u,u,u,u,0>
-; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <4,u,u,0,4,5,2,u>
; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,3,2,0,4,7,6,4]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,2,1]
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2],ymm1[3,4,5,6],ymm0[7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 12, i32 3, i32 4, i32 8, i32 12, i32 13, i32 10, i32 0>
@@ -660,21 +657,21 @@ define <8 x float> @shuffle_v8f32_c348cda0(<8 x float> %a, <8 x float> %b) {
define <8 x float> @shuffle_v8f32_f511235a(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_f511235a:
; AVX1: # BB#0:
+; AVX1-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,1,2,2,7,5,6,6]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm1[2,3,0,1]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilpd {{.*#+}} ymm2 = ymm2[0,0,3,2]
; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,1,1,1,4,5,5,5]
; AVX1-NEXT: vblendpd {{.*#+}} ymm0 = ymm2[0],ymm0[1],ymm2[2],ymm0[3]
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm1 = ymm1[2,3,0,1]
-; AVX1-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,1,2,2,7,5,6,6]
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_f511235a:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <7,u,u,u,u,u,u,2>
-; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,5,1,1,2,3,5,u>
-; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} ymm1 = ymm1[3,2,2,3,7,6,6,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm1 = ymm1[2,1,2,0]
+; AVX2-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[1,1,2,3,5,5,6,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[2,0,1,2]
; AVX2-NEXT: vblendps {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3,4,5,6],ymm1[7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 15, i32 5, i32 1, i32 1, i32 2, i32 3, i32 5, i32 10>
@@ -690,42 +687,29 @@ define <8 x float> @shuffle_v8f32_32103210(<8 x float> %a, <8 x float> %b) {
;
; AVX2-LABEL: shuffle_v8f32_32103210:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX2-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_76547654(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: shuffle_v8f32_76547654:
-; AVX1: # BB#0:
-; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v8f32_76547654:
-; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v8f32_76547654:
+; ALL: # BB#0:
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
+; ALL-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4>
ret <8 x float> %shuffle
}
define <8 x float> @shuffle_v8f32_76543210(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: shuffle_v8f32_76543210:
-; AVX1: # BB#0:
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
-; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v8f32_76543210:
-; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0]
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v8f32_76543210:
+; ALL: # BB#0:
+; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; ALL-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; ALL-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x float> %shuffle
}
@@ -783,11 +767,8 @@ define <8 x float> @PR21138(<8 x float> %truc, <8 x float> %tchose) {
;
; AVX2-LABEL: PR21138:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <u,u,u,u,1,3,5,7>
-; AVX2-NEXT: vpermps %ymm1, %ymm2, %ymm1
-; AVX2-NEXT: vmovaps {{.*#+}} ymm2 = <1,3,5,7,u,u,u,u>
-; AVX2-NEXT: vpermps %ymm0, %ymm2, %ymm0
-; AVX2-NEXT: vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX2-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
+; AVX2-NEXT: vpermpd {{.*#+}} ymm0 = ymm0[0,2,1,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %truc, <8 x float> %tchose, <8 x i32> <i32 1, i32 3, i32 5, i32 7, i32 9, i32 11, i32 13, i32 15>
ret <8 x float> %shuffle
@@ -806,10 +787,10 @@ define <8 x float> @shuffle_v8f32_ba987654(<8 x float> %a, <8 x float> %b) {
define <8 x float> @shuffle_v8f32_ba983210(<8 x float> %a, <8 x float> %b) {
; ALL-LABEL: shuffle_v8f32_ba983210:
; ALL: # BB#0:
-; ALL-NEXT: vblendpd {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,3]
+; ALL-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; ALL-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
; ALL-NEXT: retq
- %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 7, i32 6, i32 5, i32 4>
+ %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 11, i32 10, i32 9, i32 8, i32 3, i32 2, i32 1, i32 0>
ret <8 x float> %shuffle
}
@@ -844,15 +825,14 @@ define <8 x float> @shuffle_v8f32_uuuu1111(<8 x float> %a, <8 x float> %b) {
define <8 x float> @shuffle_v8f32_44444444(<8 x float> %a, <8 x float> %b) {
; AVX1-LABEL: shuffle_v8f32_44444444:
; AVX1: # BB#0:
-; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8f32_44444444:
; AVX2: # BB#0:
-; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vbroadcastss %xmm0, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
ret <8 x float> %shuffle
@@ -897,17 +877,11 @@ define <8 x float> @shuffle_v8f32_1111uuuu(<8 x float> %a, <8 x float> %b) {
}
define <8 x float> @shuffle_v8f32_5555uuuu(<8 x float> %a, <8 x float> %b) {
-; AVX1-LABEL: shuffle_v8f32_5555uuuu:
-; AVX1: # BB#0:
-; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
-; AVX1-NEXT: retq
-;
-; AVX2-LABEL: shuffle_v8f32_5555uuuu:
-; AVX2: # BB#0:
-; AVX2-NEXT: vbroadcastss {{.*}}(%rip), %ymm1
-; AVX2-NEXT: vpermps %ymm0, %ymm1, %ymm0
-; AVX2-NEXT: retq
+; ALL-LABEL: shuffle_v8f32_5555uuuu:
+; ALL: # BB#0:
+; ALL-NEXT: vextractf128 $1, %ymm0, %xmm0
+; ALL-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; ALL-NEXT: retq
%shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x float> %shuffle
}
@@ -930,15 +904,15 @@ define <8 x i32> @shuffle_v8i32_00000000(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00000010:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,1,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_00000010:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,0,0,0,0,0,1,0]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,0]
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 0, i32 1, i32 0>
ret <8 x i32> %shuffle
@@ -947,15 +921,15 @@ define <8 x i32> @shuffle_v8i32_00000010(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00000200:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,0,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,2,0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_00000200:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,0,0,0,0,2,0,0]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,0,2]
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,1,0]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 0, i32 2, i32 0, i32 0>
ret <8 x i32> %shuffle
@@ -964,15 +938,15 @@ define <8 x i32> @shuffle_v8i32_00000200(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_00003000(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00003000:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,0,0,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,0,0,0]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_00003000:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,0,0,0,3,0,0,0]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,3,0]
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,1,0]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 3, i32 0, i32 0, i32 0>
ret <8 x i32> %shuffle
@@ -1065,8 +1039,8 @@ define <8 x i32> @shuffle_v8i32_01014545(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00112233:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,1,1]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,2,3,3]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,1,1]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,2,3,3]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
@@ -1082,15 +1056,15 @@ define <8 x i32> @shuffle_v8i32_00112233(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_00001111(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_00001111:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm0[0,0,0,0]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm1 = xmm0[0,0,0,0]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm1, %ymm0
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_00001111:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [0,0,0,0,1,1,1,1]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[0,0,1,1]
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,0,1,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 0, i32 0, i32 0, i32 1, i32 1, i32 1, i32 1>
ret <8 x i32> %shuffle
@@ -1113,18 +1087,15 @@ define <8 x i32> @shuffle_v8i32_81a3c5e7(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_08080808(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_08080808:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm1 = xmm1[0,0,2,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm1, %ymm1, %ymm1
-; AVX1-NEXT: vmovddup {{.*#+}} xmm0 = xmm0[0,0]
+; AVX1-NEXT: vshufps {{.*#+}} xmm0 = xmm0[0,0],xmm1[0,0]
+; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,2,1,3]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_08080808:
; AVX2: # BB#0:
-; AVX2-NEXT: vpbroadcastd %xmm1, %ymm1
+; AVX2-NEXT: vpunpckldq {{.*#+}} xmm0 = xmm0[0],xmm1[0],xmm0[1],xmm1[1]
; AVX2-NEXT: vpbroadcastq %xmm0, %ymm0
-; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 0, i32 8, i32 0, i32 8, i32 0, i32 8>
ret <8 x i32> %shuffle
@@ -1134,7 +1105,7 @@ define <8 x i32> @shuffle_v8i32_08084c4c(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_08084c4c:
; AVX1: # BB#0:
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,0],ymm1[0,0],ymm0[4,4],ymm1[4,4]
-; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_08084c4c:
@@ -1252,10 +1223,10 @@ define <8 x i32> @shuffle_v8i32_08991abb(<8 x i32> %a, <8 x i32> %b) {
;
; AVX2-LABEL: shuffle_v8i32_08991abb:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
-; AVX2-NEXT: vpermd %ymm0, %ymm2, %ymm0
; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <u,0,1,1,u,2,3,3>
; AVX2-NEXT: vpermd %ymm1, %ymm2, %ymm1
+; AVX2-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,1,3]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 8, i32 9, i32 9, i32 1, i32 10, i32 11, i32 11>
@@ -1265,8 +1236,8 @@ define <8 x i32> @shuffle_v8i32_08991abb(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_091b2d3f(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_091b2d3f:
; AVX1: # BB#0:
-; AVX1-NEXT: vpermilps {{.*#+}} xmm2 = xmm0[0,1,1,3]
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[2,1,3,3]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[0,1,1,3]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[2,1,3,3]
; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm2, %ymm0
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2],ymm1[3],ymm0[4],ymm1[5],ymm0[6],ymm1[7]
; AVX1-NEXT: retq
@@ -1283,15 +1254,15 @@ define <8 x i32> @shuffle_v8i32_091b2d3f(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_09ab1def(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_09ab1def:
; AVX1: # BB#0:
-; AVX1-NEXT: vmovshdup {{.*#+}} xmm2 = xmm0[1,1,3,3]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm2 = xmm0[1,1,3,3]
; AVX1-NEXT: vinsertf128 $1, %xmm2, %ymm0, %ymm0
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_09ab1def:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <0,u,u,u,1,u,u,u>
-; AVX2-NEXT: vpermd %ymm0, %ymm2, %ymm0
+; AVX2-NEXT: vpmovzxdq {{.*#+}} xmm0 = xmm0[0],zero,xmm0[1],zero
+; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[0,1,1,3]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3],ymm0[4],ymm1[5,6,7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 0, i32 9, i32 10, i32 11, i32 1, i32 13, i32 14, i32 15>
@@ -1768,19 +1739,18 @@ define <8 x i32> @shuffle_v8i32_uuu3uu66(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_6caa87e5(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_6caa87e5:
; AVX1: # BB#0:
+; AVX1-NEXT: vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: vperm2f128 {{.*#+}} ymm2 = ymm1[2,3,0,1]
; AVX1-NEXT: vshufps {{.*#+}} ymm1 = ymm2[0,0],ymm1[2,2],ymm2[4,4],ymm1[6,6]
-; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilpd {{.*#+}} xmm0 = xmm0[1,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
; AVX1-NEXT: vblendps {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_6caa87e5:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm2 = <u,4,2,2,0,u,6,u>
-; AVX2-NEXT: vpermd %ymm1, %ymm2, %ymm1
; AVX2-NEXT: vpermq {{.*#+}} ymm0 = ymm0[3,1,3,2]
+; AVX2-NEXT: vpshufd {{.*#+}} ymm1 = ymm1[0,0,2,2,4,4,6,6]
+; AVX2-NEXT: vpermq {{.*#+}} ymm1 = ymm1[2,1,0,3]
; AVX2-NEXT: vpblendd {{.*#+}} ymm0 = ymm0[0],ymm1[1,2,3,4],ymm0[5],ymm1[6],ymm0[7]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 6, i32 12, i32 10, i32 10, i32 8, i32 7, i32 14, i32 5>
@@ -1796,8 +1766,8 @@ define <8 x i32> @shuffle_v8i32_32103210(<8 x i32> %a, <8 x i32> %b) {
;
; AVX2-LABEL: shuffle_v8i32_32103210:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [3,2,1,0,3,2,1,0]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[3,2,1,0]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[0,1,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 3, i32 2, i32 1, i32 0, i32 3, i32 2, i32 1, i32 0>
ret <8 x i32> %shuffle
@@ -1806,15 +1776,14 @@ define <8 x i32> @shuffle_v8i32_32103210(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_76547654(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_76547654:
; AVX1: # BB#0:
-; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[3,2,1,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_76547654:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,7,6,5,4]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 7, i32 6, i32 5, i32 4>
ret <8 x i32> %shuffle
@@ -1823,14 +1792,14 @@ define <8 x i32> @shuffle_v8i32_76547654(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_76543210(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_76543210:
; AVX1: # BB#0:
-; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_76543210:
; AVX2: # BB#0:
-; AVX2-NEXT: vmovdqa {{.*#+}} ymm1 = [7,6,5,4,3,2,1,0]
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vpshufd {{.*#+}} ymm0 = ymm0[3,2,1,0,7,6,5,4]
+; AVX2-NEXT: vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 7, i32 6, i32 5, i32 4, i32 3, i32 2, i32 1, i32 0>
ret <8 x i32> %shuffle
@@ -1935,7 +1904,7 @@ define <8 x i32> @shuffle_v8i32_ba983210(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_zuu8zuuc(<8 x i32> %a) {
; AVX1-LABEL: shuffle_v8i32_zuu8zuuc:
; AVX1: # BB#0:
-; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm1[0,1],ymm0[2,0],ymm1[4,5],ymm0[6,4]
; AVX1-NEXT: retq
;
@@ -1950,7 +1919,7 @@ define <8 x i32> @shuffle_v8i32_zuu8zuuc(<8 x i32> %a) {
define <8 x i32> @shuffle_v8i32_9ubzdefz(<8 x i32> %a) {
; AVX1-LABEL: shuffle_v8i32_9ubzdefz:
; AVX1: # BB#0:
-; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vshufps {{.*#+}} ymm1 = ymm1[3,0],ymm0[3,0],ymm1[7,4],ymm0[7,4]
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,2],ymm1[2,0],ymm0[5,6],ymm1[6,4]
; AVX1-NEXT: retq
@@ -2014,15 +1983,14 @@ define <8 x i32> @shuffle_v8i32_2A3Buuuu(<8 x i32> %a, <8 x i32> %b) {
define <8 x i32> @shuffle_v8i32_44444444(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_44444444:
; AVX1: # BB#0:
-; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[0,0,0,0]
-; AVX1-NEXT: vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,0,0,0,4,4,4,4]
+; AVX1-NEXT: vperm2f128 {{.*#+}} ymm0 = ymm0[2,3,2,3]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_44444444:
; AVX2: # BB#0:
-; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vextractf128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vbroadcastss %xmm0, %ymm0
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4, i32 4>
ret <8 x i32> %shuffle
@@ -2032,13 +2000,13 @@ define <8 x i32> @shuffle_v8i32_5555uuuu(<8 x i32> %a, <8 x i32> %b) {
; AVX1-LABEL: shuffle_v8i32_5555uuuu:
; AVX1: # BB#0:
; AVX1-NEXT: vextractf128 $1, %ymm0, %xmm0
-; AVX1-NEXT: vpermilps {{.*#+}} xmm0 = xmm0[1,1,1,1]
+; AVX1-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_5555uuuu:
; AVX2: # BB#0:
-; AVX2-NEXT: vpbroadcastd {{.*}}(%rip), %ymm1
-; AVX2-NEXT: vpermd %ymm0, %ymm1, %ymm0
+; AVX2-NEXT: vextracti128 $1, %ymm0, %xmm0
+; AVX2-NEXT: vpshufd {{.*#+}} xmm0 = xmm0[1,1,1,1]
; AVX2-NEXT: retq
%shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 5, i32 5, i32 5, i32 5, i32 undef, i32 undef, i32 undef, i32 undef>
ret <8 x i32> %shuffle
@@ -2077,9 +2045,9 @@ define <8 x float> @splat_v8f32(<4 x float> %r) {
define <8 x i32> @shuffle_v8i32_z0U2zUz6(<8 x i32> %a) {
; AVX1-LABEL: shuffle_v8i32_z0U2zUz6:
; AVX1: # BB#0:
-; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2],ymm1[0,2],ymm0[4,6],ymm1[4,6]
-; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[2,0,3,1,6,4,7,5]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_z0U2zUz6:
@@ -2093,9 +2061,9 @@ define <8 x i32> @shuffle_v8i32_z0U2zUz6(<8 x i32> %a) {
define <8 x i32> @shuffle_v8i32_1U3z5zUU(<8 x i32> %a) {
; AVX1-LABEL: shuffle_v8i32_1U3z5zUU:
; AVX1: # BB#0:
-; AVX1-NEXT: vxorps %xmm1, %xmm1, %xmm1
+; AVX1-NEXT: vxorps %ymm1, %ymm1, %ymm1
; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[1,3],ymm1[1,3],ymm0[5,7],ymm1[5,7]
-; AVX1-NEXT: vshufps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
+; AVX1-NEXT: vpermilps {{.*#+}} ymm0 = ymm0[0,2,1,3,4,6,5,7]
; AVX1-NEXT: retq
;
; AVX2-LABEL: shuffle_v8i32_1U3z5zUU:
@@ -2198,7 +2166,7 @@ define <8x float> @concat_v2f32_1(<2 x float>* %tmp64, <2 x float>* %tmp65) {
; ALL-LABEL: concat_v2f32_1:
; ALL: # BB#0: # %entry
; ALL-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
-; ALL-NEXT: vmovhpd (%rsi), %xmm0, %xmm0
+; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: retq
entry:
%tmp74 = load <2 x float>, <2 x float>* %tmp65, align 8
@@ -2213,7 +2181,7 @@ define <8x float> @concat_v2f32_2(<2 x float>* %tmp64, <2 x float>* %tmp65) {
; ALL-LABEL: concat_v2f32_2:
; ALL: # BB#0: # %entry
; ALL-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
-; ALL-NEXT: vmovhpd (%rsi), %xmm0, %xmm0
+; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: retq
entry:
%tmp74 = load <2 x float>, <2 x float>* %tmp65, align 8
@@ -2226,7 +2194,7 @@ define <8x float> @concat_v2f32_3(<2 x float>* %tmp64, <2 x float>* %tmp65) {
; ALL-LABEL: concat_v2f32_3:
; ALL: # BB#0: # %entry
; ALL-NEXT: vmovq {{.*#+}} xmm0 = mem[0],zero
-; ALL-NEXT: vmovhpd (%rsi), %xmm0, %xmm0
+; ALL-NEXT: vmovhpd {{.*#+}} xmm0 = xmm0[0],mem[0]
; ALL-NEXT: retq
entry:
%tmp74 = load <2 x float>, <2 x float>* %tmp65, align 8
generated by cgit v1.2.3 (git 2.25.1) at 2025-10-31 08:29:02 +0000