[AVX512] add PSLLW and PSLLV Intrinsic

[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 8c6d5105d8203775c529252cfec86c04e251a4ad..7e33f5f3aa861c80a1bd4d5e429b061d726866a7 100644 (file)
--- a/test/CodeGen/X86/vector-shuffle-256-v4.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v4.ll
@@ -236,23 +236,11 @@ define <4 x double> @shuffle_v4f64_1022(<4 x double> %a, <4 x double> %b) {
 }
 
 define <4 x double> @shuffle_v4f64_0423(<4 x double> %a, <4 x double> %b) {
-; AVX1-LABEL: shuffle_v4f64_0423:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovddup {{.*#+}} ymm1 = ymm1[0,0,2,2]
-; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: shuffle_v4f64_0423:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vbroadcastsd %xmm1, %ymm1
-; AVX2-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
-; AVX2-NEXT:    retq
-;
-; AVX512VL-LABEL: shuffle_v4f64_0423:
-; AVX512VL:       # BB#0:
-; AVX512VL-NEXT:    vbroadcastsd %xmm1, %ymm1
-; AVX512VL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
-; AVX512VL-NEXT:    retq
+; ALL-LABEL: shuffle_v4f64_0423:
+; ALL:       # BB#0:
+; ALL-NEXT:    vmovddup {{.*#+}} xmm1 = xmm1[0,0]
+; ALL-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
+; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 0, i32 4, i32 2, i32 3>
   ret <4 x double> %shuffle
 }
@@ -488,10 +476,19 @@ define <4 x double> @shuffle_v4f64_u062(<4 x double> %a, <4 x double> %b) {
   ret <4 x double> %shuffle
 }
 
+define <4 x double> @shuffle_v4f64_15uu(<4 x double> %a, <4 x double> %b) {
+; ALL-LABEL: shuffle_v4f64_15uu:
+; ALL:       # BB#0:
+; ALL-NEXT:    vunpckhpd {{.*#+}} xmm0 = xmm0[1],xmm1[1]
+; ALL-NEXT:    retq
+  %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 5, i32 undef, i32 undef>
+  ret <4 x double> %shuffle
+}
+
 define <4 x double> @shuffle_v4f64_11uu(<4 x double> %a, <4 x double> %b) {
 ; ALL-LABEL: shuffle_v4f64_11uu:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
+; ALL-NEXT:    vmovhlps {{.*#+}} xmm0 = xmm0[1,1]
 ; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x double> %a, <4 x double> %b, <4 x i32> <i32 1, i32 1, i32 undef, i32 undef>
   ret <4 x double> %shuffle
@@ -750,21 +747,21 @@ 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:    vinsertf128 $1, %xmm1, %ymm1, %ymm1
+; 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:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm1, %ymm1
+; AVX2-NEXT:    vinserti128 $1, %xmm1, %ymm0, %ymm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,2,2]
 ; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
 ; AVX2-NEXT:    retq
 ;
 ; AVX512VL-LABEL: shuffle_v4i64_0142:
 ; AVX512VL:       # BB#0:
-; AVX512VL-NEXT:    vinserti32x4 $1, %xmm1, %ymm1, %ymm1
+; AVX512VL-NEXT:    vinserti32x4 $1, %xmm1, %ymm0, %ymm1
 ; AVX512VL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,2,2]
 ; AVX512VL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1,2,3],ymm1[4,5],ymm0[6,7]
 ; AVX512VL-NEXT:    retq
@@ -778,21 +775,21 @@ define <4 x i64> @shuffle_v4i64_0412(<4 x i64> %a, <4 x i64> %b) {
 ; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
 ; AVX1-NEXT:    vshufpd {{.*#+}} xmm2 = xmm0[1],xmm2[0]
 ; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
-; AVX1-NEXT:    vmovddup {{.*#+}} ymm1 = ymm1[0,0,2,2]
+; AVX1-NEXT:    vmovddup {{.*#+}} xmm1 = xmm1[0,0]
 ; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0],ymm1[1],ymm0[2,3]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v4i64_0412:
 ; AVX2:       # BB#0:
+; AVX2-NEXT:    vpbroadcastq %xmm1, %xmm1
 ; AVX2-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,2]
-; AVX2-NEXT:    vpbroadcastq %xmm1, %ymm1
 ; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
 ; AVX2-NEXT:    retq
 ;
 ; AVX512VL-LABEL: shuffle_v4i64_0412:
 ; AVX512VL:       # BB#0:
+; AVX512VL-NEXT:    vpbroadcastq %xmm1, %xmm1
 ; AVX512VL-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[0,1,1,2]
-; AVX512VL-NEXT:    vpbroadcastq %xmm1, %ymm1
 ; AVX512VL-NEXT:    vpblendd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3],ymm0[4,5,6,7]
 ; AVX512VL-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 0, i32 4, i32 1, i32 2>
@@ -1134,21 +1131,20 @@ define <4 x i64> @shuffle_v4i64_40u2(<4 x i64> %a, <4 x i64> %b) {
   ret <4 x i64> %shuffle
 }
 
+define <4 x i64> @shuffle_v4i64_15uu(<4 x i64> %a, <4 x i64> %b) {
+; ALL-LABEL: shuffle_v4i64_15uu:
+; ALL:       # BB#0:
+; ALL-NEXT:    vpunpckhqdq {{.*#+}} xmm0 = xmm0[1],xmm1[1]
+; ALL-NEXT:    retq
+  %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 5, i32 undef, i32 undef>
+  ret <4 x i64> %shuffle
+}
+
 define <4 x i64> @shuffle_v4i64_11uu(<4 x i64> %a, <4 x i64> %b) {
-; AVX1-LABEL: shuffle_v4i64_11uu:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,1,2,2]
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: shuffle_v4i64_11uu:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7]
-; AVX2-NEXT:    retq
-;
-; AVX512VL-LABEL: shuffle_v4i64_11uu:
-; AVX512VL:       # BB#0:
-; AVX512VL-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,2,3,6,7,6,7]
-; AVX512VL-NEXT:    retq
+; ALL-LABEL: shuffle_v4i64_11uu:
+; ALL:       # BB#0:
+; ALL-NEXT:    vpshufd {{.*#+}} xmm0 = xmm0[2,3,2,3]
+; ALL-NEXT:    retq
   %shuffle = shufflevector <4 x i64> %a, <4 x i64> %b, <4 x i32> <i32 1, i32 1, i32 undef, i32 undef>
   ret <4 x i64> %shuffle
 }
@@ -1357,8 +1353,7 @@ define <4 x i64> @splat_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
 ;
 ; AVX512VL-LABEL: splat_mem_v4i64_from_v2i64:
 ; AVX512VL:       # BB#0:
-; AVX512VL-NEXT:    vmovdqa64 (%rdi), %xmm0
-; AVX512VL-NEXT:    vpbroadcastq %xmm0, %ymm0
+; AVX512VL-NEXT:    vpbroadcastq (%rdi), %ymm0
 ; AVX512VL-NEXT:    retq
   %v = load <2 x i64>, <2 x i64>* %ptr
   %shuffle = shufflevector <2 x i64> %v, <2 x i64> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
@@ -1366,21 +1361,10 @@ define <4 x i64> @splat_mem_v4i64_from_v2i64(<2 x i64>* %ptr) {
 }
 
 define <4 x double> @splat_mem_v4f64_from_v2f64(<2 x double>* %ptr) {
-; AVX1-LABEL: splat_mem_v4f64_from_v2f64:
-; AVX1:       # BB#0:
-; AVX1-NEXT:    vmovddup {{.*#+}} xmm0 = mem[0,0]
-; AVX1-NEXT:    vinsertf128 $1, %xmm0, %ymm0, %ymm0
-; AVX1-NEXT:    retq
-;
-; AVX2-LABEL: splat_mem_v4f64_from_v2f64:
-; AVX2:       # BB#0:
-; AVX2-NEXT:    vbroadcastsd (%rdi), %ymm0
-; AVX2-NEXT:    retq
-;
-; AVX512VL-LABEL: splat_mem_v4f64_from_v2f64:
-; AVX512VL:       # BB#0:
-; AVX512VL-NEXT:    vbroadcastsd (%rdi), %ymm0
-; AVX512VL-NEXT:    retq
+; ALL-LABEL: splat_mem_v4f64_from_v2f64:
+; ALL:       # BB#0:
+; ALL-NEXT:    vbroadcastsd (%rdi), %ymm0
+; ALL-NEXT:    retq
   %v = load <2 x double>, <2 x double>* %ptr
   %shuffle = shufflevector <2 x double> %v, <2 x double> undef, <4 x i32> <i32 0, i32 0, i32 0, i32 0>
   ret <4 x double> %shuffle