From 21b2c5660e3a741a516d382ee4230ba905b82784 Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Mon, 2 May 2016 19:46:58 +0000
Subject: [PATCH] [X86][AVX2] Added 128-bit wide shuffle test

Demonstrate missing 128-bit wide shuffle combine support

llvm-svn: 268290
---
 llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll | 14 ++++++++++++++
 1 file changed, 14 insertions(+)

diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
index 37c1f0b..fc8cce0 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
@@ -3,6 +3,7 @@
 
 declare <8 x i32> @llvm.x86.avx2.permd(<8 x i32>, <8 x i32>)
 declare <8 x float> @llvm.x86.avx2.permps(<8 x float>, <8 x i32>)
+declare <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8>, <32 x i8>)
 
 define <32 x i8> @combine_pshufb_vpermd(<8 x i32> %a) {
 ; CHECK-LABEL: combine_pshufb_vpermd:
@@ -25,3 +26,16 @@ define <32 x i8> @combine_pshufb_vpermps(<8 x float> %a) {
   %tmp2 = shufflevector <32 x i8> %tmp1, <32 x i8> undef, <32 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 8, i32 9, i32 10, i32 11, i32 12, i32 13, i32 14, i32 15, i32 16, i32 17, i32 18, i32 19, i32 20, i32 21, i32 22, i32 23, i32 24, i32 25, i32 26, i32 27, i32 28, i32 29, i32 30, i32 30>
   ret <32 x i8> %tmp2
 }
+
+define <4 x i64> @combine_permq_pshufb(<4 x i64> %a0) {
+; CHECK-LABEL: combine_permq_pshufb:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpermq {{.*#+}} ymm0 = ymm0[3,2,1,0]
+; CHECK-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7,24,25,26,27,28,29,30,31,16,17,18,19,20,21,22,23]
+; CHECK-NEXT:    retq
+  %1 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 3, i32 2, i32 1, i32 0>
+  %2 = bitcast <4 x i64> %1 to <32 x i8>
+  %3 = call <32 x i8> @llvm.x86.avx2.pshuf.b(<32 x i8> %2, <32 x i8> <i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7, i8 8, i8 9, i8 10, i8 11, i8 12, i8 13, i8 14, i8 15, i8 0, i8 1, i8 2, i8 3, i8 4, i8 5, i8 6, i8 7>)
+  %4 = bitcast <32 x i8> %3 to <4 x i64>
+  ret <4 x i64> %4
+}
-- 
2.7.4