From 0fdca3bdc5e64cd320a3d0040f7c96b5ec3c09ee Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Sat, 18 Jun 2016 22:59:08 +0000
Subject: [PATCH] [X86][AVX] Added test case for PR28136

llvm-svn: 273098
---
 test/CodeGen/X86/vector-shuffle-256-v32.ll | 38 ++++++++++++++++++++++
 1 file changed, 38 insertions(+)

diff --git a/test/CodeGen/X86/vector-shuffle-256-v32.ll b/test/CodeGen/X86/vector-shuffle-256-v32.ll
index 80cbaab164c..6451663c0a9 100644
--- a/test/CodeGen/X86/vector-shuffle-256-v32.ll
+++ b/test/CodeGen/X86/vector-shuffle-256-v32.ll
@@ -2060,6 +2060,44 @@ define <32 x i8> @shuffle_v32i8_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_22_
   ret <32 x i8> %shuffle
 }
 
+define <4 x i64> @PR28136(<32 x i8> %a0, <32 x i8> %a1) {
+; AVX1-LABEL: PR28136:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vextractf128 $1, %ymm0, %xmm2
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm0 = xmm0[0],xmm2[0],xmm0[1],xmm2[1],xmm0[2],xmm2[2],xmm0[3],xmm2[3],xmm0[4],xmm2[4],xmm0[5],xmm2[5],xmm0[6],xmm2[6],xmm0[7],xmm2[7]
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm2 = [8,8,10,10,12,12,14,14,9,9,11,11,13,13,15,15]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm0, %xmm3
+; AVX1-NEXT:    vextractf128 $1, %ymm1, %xmm4
+; AVX1-NEXT:    vpunpcklbw {{.*#+}} xmm1 = xmm1[0],xmm4[0],xmm1[1],xmm4[1],xmm1[2],xmm4[2],xmm1[3],xmm4[3],xmm1[4],xmm4[4],xmm1[5],xmm4[5],xmm1[6],xmm4[6],xmm1[7],xmm4[7]
+; AVX1-NEXT:    vpshufb %xmm2, %xmm1, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm4 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX1-NEXT:    vpblendvb %xmm4, %xmm3, %xmm2, %xmm2
+; AVX1-NEXT:    vmovdqa {{.*#+}} xmm3 = [0,0,2,2,4,4,6,6,1,1,3,3,5,5,7,7]
+; AVX1-NEXT:    vpshufb %xmm3, %xmm0, %xmm0
+; AVX1-NEXT:    vpshufb %xmm3, %xmm1, %xmm1
+; AVX1-NEXT:    vpblendvb %xmm4, %xmm0, %xmm1, %xmm0
+; AVX1-NEXT:    vinsertf128 $1, %xmm2, %ymm0, %ymm0
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: PR28136:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpunpcklbw {{.*#+}} ymm2 = ymm0[0,0,1,1,2,2,3,3,4,4,5,5,6,6,7,7,16,16,17,17,18,18,19,19,20,20,21,21,22,22,23,23]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm0 = ymm0[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[u,u,u,u,u,u,u,u,0,u,1,u,2,u,3,u,20,u,21,u,22,u,23,u,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm0 = ymm2[0,1],ymm0[2,3,4,5],ymm2[6,7]
+; AVX2-NEXT:    vpunpcklbw {{.*#+}} ymm2 = ymm0[0],ymm1[0],ymm0[1],ymm1[1],ymm0[2],ymm1[2],ymm0[3],ymm1[3],ymm0[4],ymm1[4],ymm0[5],ymm1[5],ymm0[6],ymm1[6],ymm0[7],ymm1[7],ymm0[16],ymm1[16],ymm0[17],ymm1[17],ymm0[18],ymm1[18],ymm0[19],ymm1[19],ymm0[20],ymm1[20],ymm0[21],ymm1[21],ymm0[22],ymm1[22],ymm0[23],ymm1[23]
+; AVX2-NEXT:    vperm2i128 {{.*#+}} ymm1 = ymm1[2,3,0,1]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm1 = ymm1[u,u,u,u,u,u,u,u,u,0,u,1,u,2,u,3,u,20,u,21,u,22,u,23,u,u,u,u,u,u,u,u]
+; AVX2-NEXT:    vpblendd {{.*#+}} ymm1 = ymm2[0,1],ymm1[2,3,4,5],ymm2[6,7]
+; AVX2-NEXT:    vmovdqa {{.*#+}} ymm2 = [255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0,255,0]
+; AVX2-NEXT:    vpblendvb %ymm2, %ymm0, %ymm1, %ymm0
+; AVX2-NEXT:    retq
+  %1 = shufflevector <32 x i8> %a0, <32 x i8> %a1, <32 x i32> <i32 0, i32 32, i32 1, i32 33, i32 2, i32 34, i32 3, i32 35, i32 4, i32 36, i32 5, i32 37, i32 6, i32 38, i32 7, i32 39, i32 16, i32 48, i32 17, i32 49, i32 18, i32 50,i32 19, i32 51, i32 20, i32 52, i32 21, i32 53, i32 22, i32 54, i32 23, i32 55>
+  %2 = bitcast <32 x i8> %1 to <4 x i64>
+  %3 = shufflevector <4 x i64> %2, <4 x i64> undef, <4 x i32> <i32 0, i32 2, i32 1, i32 3>
+  ret <4 x i64> %3
+}
+
 define <32 x i8> @insert_dup_mem_v32i8_i32(i32* %ptr) {
 ; AVX1-LABEL: insert_dup_mem_v32i8_i32:
 ; AVX1:       # BB#0: