From b4b90fb8d64300add9d1bad696b27275453eb40b Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Fri, 4 Mar 2016 11:15:23 +0000
Subject: [PATCH] [X86][SSSE3] Added combine test for unary shuffle (pshufb)
 only referencing elements from the second input of a binary shuffle
 (punpcklbw)

llvm-svn: 262710
---
 .../X86/vector-shuffle-combining-ssse3.ll     | 23 ++++++++++++++++---
 1 file changed, 20 insertions(+), 3 deletions(-)

diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll
index 1af2fcb73c66..aecd45ac3f51 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-ssse3.ll
@@ -60,14 +60,14 @@ define <4 x float> @combine_pshufb_movsldup(<4 x float> %a0) {
   ret <4 x float> %4
 }
 
-define <16 x i8> @combine_unpckl_pshufb(<16 x i8> %a0, <16 x i8> %a1) {
-; SSE-LABEL: combine_unpckl_pshufb:
+define <16 x i8> @combine_unpckl_arg0_pshufb(<16 x i8> %a0, <16 x i8> %a1) {
+; SSE-LABEL: combine_unpckl_arg0_pshufb:
 ; SSE:       # BB#0:
 ; SSE-NEXT:    punpcklbw {{.*#+}} 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]
 ; SSE-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero
 ; SSE-NEXT:    retq
 ;
-; AVX-LABEL: combine_unpckl_pshufb:
+; AVX-LABEL: combine_unpckl_arg0_pshufb:
 ; AVX:       # BB#0:
 ; 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:    vpshufb {{.*#+}} xmm0 = xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero,xmm0[0],zero,zero,zero
@@ -76,3 +76,20 @@ define <16 x i8> @combine_unpckl_pshufb(<16 x i8> %a0, <16 x i8> %a1) {
   %2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1, i8 0, i8 -1, i8 -1, i8 -1>)
   ret <16 x i8> %2
 }
+
+define <16 x i8> @combine_unpckl_arg1_pshufb(<16 x i8> %a0, <16 x i8> %a1) {
+; SSE-LABEL: combine_unpckl_arg1_pshufb:
+; SSE:       # BB#0:
+; SSE-NEXT:    punpcklbw {{.*#+}} 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]
+; SSE-NEXT:    pshufb {{.*#+}} xmm0 = xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero
+; SSE-NEXT:    retq
+;
+; AVX-LABEL: combine_unpckl_arg1_pshufb:
+; AVX:       # BB#0:
+; 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:    vpshufb {{.*#+}} xmm0 = xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero,xmm0[1],zero,zero,zero
+; AVX-NEXT:    retq
+  %1 = shufflevector <16 x i8> %a0, <16 x i8> %a1, <16 x i32> <i32 0, i32 16, i32 1, i32 17, i32 2, i32 18, i32 3, i32 19, i32 4, i32 20, i32 5, i32 21, i32 6, i32 22, i32 7, i32 23>
+  %2 = tail call <16 x i8> @llvm.x86.ssse3.pshuf.b.128(<16 x i8> %1, <16 x i8> <i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1, i8 1, i8 -1, i8 -1, i8 -1>)
+  ret <16 x i8> %2
+}