[x86] Teach the new vector shuffle lowering to use AVX2 instructions for

[oota-llvm.git] / test / CodeGen / X86 / vector-shuffle-256-v4.ll

diff --git a/test/CodeGen/X86/vector-shuffle-256-v4.ll b/test/CodeGen/X86/vector-shuffle-256-v4.ll
index cca593912fb0ad35be4d14122afb28b417a42766..423400c00a6c74d3b11f3e28c6a93a817d8559b5 100644 (file)
--- a/test/CodeGen/X86/vector-shuffle-256-v4.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v4.ll
@@ -4,77 +4,112 @@
 target triple = "x86_64-unknown-unknown"
 
 define <4 x double> @shuffle_v4f64_0001(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0001
-; ALL:       # BB#0:
-; ALL-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm0[0,0]
-; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_0001
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm0[0,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_0001
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,0,1]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 0, i32 1>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0020(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0020
-; ALL:       # BB#0:
-; ALL-NEXT:    vextractf128 $1, %ymm0, %xmm1
-; ALL-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0],xmm0[0]
-; ALL-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
-; ALL-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_0020
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm1
+; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0],xmm0[0]
+; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_0020
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,0,2,0]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 0, i32 2, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_0300(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0300
-; ALL:       # BB#0:
-; ALL-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,1,2,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_0300
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,1,2,2]
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_0300
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,3,0,0]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 3, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_1000(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_1000
-; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*}} # xmm1 = xmm0[1,0]
-; ALL-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
-; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_1000
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm0[1,0]
+; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_1000
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[1,0,0,0]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 0, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_2200(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_2200
-; ALL:       # BB#0:
-; ALL-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_2200
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,2,2]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_2200
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[2,2,0,0]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 2, i32 2, i32 0, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_3330(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_3330
-; ALL:       # BB#0:
-; ALL-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,1,2,2]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,3,2]
-; ALL-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2],ymm1[3]
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_3330
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vperm2f128 {{.*}} # ymm1 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[1,1,2,2]
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,0,3,2]
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2],ymm1[3]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_3330
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,3,3,0]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 3, i32 3, i32 3, i32 0>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_3210(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_3210
-; ALL:       # BB#0:
-; ALL-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
-; ALL-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,3,2]
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_3210
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vperm2f128 {{.*}} # ymm0 = ymm0[2,3,0,1]
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,3,2]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_3210
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[3,2,1,0]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
   ret <4 x double> %shuffle
 }
@@ -218,19 +253,33 @@ define <4 x double> @shuffle_v4f64_4163(<4 x double> %a, <4 x double> %b) {
 }
 
 define <4 x double> @shuffle_v4f64_0145(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_0145
-; ALL:       # BB#0:
-; ALL-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_0145
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_0145
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm1 = ymm1[0,1,0,1]
+; AVX2-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
   ret <4 x double> %shuffle
 }
 
 define <4 x double> @shuffle_v4f64_4501(<4 x double> %a, <4 x double> %b) {
-; ALL-LABEL: @shuffle_v4f64_4501
-; ALL:       # BB#0:
-; ALL-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
-; ALL-NEXT:    retq
+; AVX1-LABEL: @shuffle_v4f64_4501
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: @shuffle_v4f64_4501
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermpd {{.*}} # ymm0 = ymm0[0,1,0,1]
+; AVX2-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
+; AVX2-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 4, i32 5, i32 0, i32 1>
   ret <4 x double> %shuffle
 }
@@ -374,10 +423,9 @@ define <4 x i64> @shuffle_v4i64_3210(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_0124(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: @shuffle_v4i64_0124
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm1 = xmm2[0],xmm1[1]
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1,2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_0124
@@ -392,10 +440,9 @@ define <4 x i64> @shuffle_v4i64_0124(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_0142(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: @shuffle_v4i64_0142
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm2 = xmm2[0,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm1 = xmm1[0],xmm2[1]
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[0,1,2,2]
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2],ymm0[3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_0142
@@ -413,9 +460,9 @@ define <4 x i64> @shuffle_v4i64_0412(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1:       # BB#0:
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vshufpd {{.*}} # xmm2 = xmm0[1],xmm2[0]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm0 = xmm0[0],xmm1[1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm1 = ymm1[0,0,2,2]
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_0412
@@ -434,8 +481,8 @@ define <4 x i64> @shuffle_v4i64_4012(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vshufpd {{.*}} # xmm2 = xmm0[1],xmm2[0]
 ; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm0 = xmm1[0],xmm0[1]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1,2,3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_4012
@@ -450,7 +497,8 @@ define <4 x i64> @shuffle_v4i64_4012(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_0145(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: @shuffle_v4i64_0145
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm1
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0,1],ymm1[2,3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_0145
@@ -465,11 +513,11 @@ define <4 x i64> @shuffle_v4i64_0145(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_0451(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: @shuffle_v4i64_0451
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm2 = xmm1[1,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm2 = xmm2[0],xmm0[1]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm1 = xmm1[0,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm0 = xmm0[0],xmm1[1]
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT:    vunpcklpd {{.*}} # xmm2 = xmm1[0,0]
+; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm1[1,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm2, %ymm1
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2],ymm0[3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_0451
@@ -485,7 +533,8 @@ define <4 x i64> @shuffle_v4i64_0451(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_4501(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: @shuffle_v4i64_4501
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm1, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0,1],ymm0[2,3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_4501
@@ -500,11 +549,11 @@ define <4 x i64> @shuffle_v4i64_4501(<4 x i64> %a, <4 x i64> %b) {
 define <4 x i64> @shuffle_v4i64_4015(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-LABEL: @shuffle_v4i64_4015
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm2 = xmm0[1,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm2 = xmm2[0],xmm1[1]
-; AVX1-NEXT:    vunpcklpd {{.*}} # xmm0 = xmm0[0,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm0 = xmm1[0],xmm0[1]
-; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
+; AVX1-NEXT:    vunpcklpd {{.*}} # xmm2 = xmm0[0,0]
+; AVX1-NEXT:    vpermilpd {{.*}} # xmm0 = xmm0[1,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm2, %ymm0
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm1[0],ymm0[1,2],ymm1[3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @shuffle_v4i64_4015
@@ -526,10 +575,10 @@ define <4 x i64> @stress_test1(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm1
 ; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm1[1,0]
 ; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,1,3,2]
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm0 = xmm0[1,0]
-; AVX1-NEXT:    vblendpd {{.*}} # xmm0 = xmm0[0],xmm1[1]
-; AVX1-NEXT:    vpermilpd {{.*}} # xmm1 = xmm1[1,0]
-; AVX1-NEXT:    vinsertf128 $1, %xmm1, %ymm0, %ymm0
+; AVX1-NEXT:    vpermilpd {{.*}} # xmm2 = xmm1[1,0]
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm1, %ymm1
+; AVX1-NEXT:    vpermilpd {{.*}} # ymm0 = ymm0[1,0,2,2]
+; AVX1-NEXT:    vblendpd {{.*}} # ymm0 = ymm0[0],ymm1[1,2,3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: @stress_test1