[X86][SSE] Generalised unpckl/unpckh shuffle matching

Added commuted unpckl/unpckh shuffle matching patterns as many cases containing undefined lanes fail to commute by themselves.

Differential Revision: http://reviews.llvm.org/D7564

llvm-svn: 229571

1 files changed, 15 insertions, 9 deletions

diff --git a/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll b/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
index 2914ab16eb1..f095a3e45c2 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-256-v8.ll
@@ -815,13 +815,21 @@ define <8 x float> @shuffle_v8f32_ba983210(<8 x float> %a, <8 x float> %b) {
   ret <8 x float> %shuffle
 }
 
-define <8 x float> @shuffle_v8f32_80u1b4uu(<8 x float> %a, <8 x float> %b) {
-; ALL-LABEL: shuffle_v8f32_80u1b4uu:
+define <8 x float> @shuffle_v8f32_80u1c4u5(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_80u1c4u5:
 ; ALL:       # BB#0:
-; ALL-NEXT:    vshufps {{.*#+}} ymm1 = ymm1[0,0],ymm0[0,0],ymm1[4,4],ymm0[4,4]
-; ALL-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[2,1],ymm1[4,6],ymm0[6,5]
+; ALL-NEXT:    vunpcklps {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[4],ymm0[4],ymm1[5],ymm0[5]
 ; ALL-NEXT:    retq
-  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 8, i32 0, i32 undef, i32 1, i32 12, i32 4, i32 undef, i32 undef>
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 8, i32 0, i32 undef, i32 1, i32 12, i32 4, i32 undef, i32 5>
+  ret <8 x float> %shuffle
+}
+
+define <8 x float> @shuffle_v8f32_a2u3e6f7(<8 x float> %a, <8 x float> %b) {
+; ALL-LABEL: shuffle_v8f32_a2u3e6f7:
+; ALL:       # BB#0:
+; ALL-NEXT:    vunpckhps {{.*#+}} ymm0 = ymm1[2],ymm0[2],ymm1[3],ymm0[3],ymm1[6],ymm0[6],ymm1[7],ymm0[7]
+; ALL-NEXT:    retq
+  %shuffle = shufflevector <8 x float> %a, <8 x float> %b, <8 x i32> <i32 10, i32 2, i32 undef, i32 3, i32 14, i32 6, i32 15, i32 7>
   ret <8 x float> %shuffle
 }
 
@@ -1882,14 +1890,12 @@ define <8 x i32> @shuffle_v8i32_9ubzdefz(<8 x i32> %a) {
 define <8 x i32> @shuffle_v8i32_80u1b4uu(<8 x i32> %a, <8 x i32> %b) {
 ; AVX1-LABEL: shuffle_v8i32_80u1b4uu:
 ; AVX1:       # BB#0:
-; AVX1-NEXT:    vshufps {{.*#+}} ymm1 = ymm1[0,0],ymm0[0,0],ymm1[4,4],ymm0[4,4]
-; AVX1-NEXT:    vshufps {{.*#+}} ymm0 = ymm1[0,2],ymm0[2,1],ymm1[4,6],ymm0[6,5]
+; AVX1-NEXT:    vunpcklps {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[4],ymm0[4],ymm1[5],ymm0[5]
 ; AVX1-NEXT:    retq
 ;
 ; AVX2-LABEL: shuffle_v8i32_80u1b4uu:
 ; AVX2:       # BB#0:
-; AVX2-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[0,0,2,1,4,4,6,5]
-; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm1[0],ymm0[1,2,3],ymm1[4],ymm0[5,6,7]
+; AVX2-NEXT:    vpunpckldq {{.*#+}} ymm0 = ymm1[0],ymm0[0],ymm1[1],ymm0[1],ymm1[4],ymm0[4],ymm1[5],ymm0[5]
 ; AVX2-NEXT:    retq
   %shuffle = shufflevector <8 x i32> %a, <8 x i32> %b, <8 x i32> <i32 8, i32 0, i32 undef, i32 1, i32 12, i32 4, i32 undef, i32 undef>
   ret <8 x i32> %shuffle