From 700e4a1ab87f1a04cfe0733ac0b67149eaad0d30 Mon Sep 17 00:00:00 2001
From: Simon Pilgrim <llvm-dev@redking.me.uk>
Date: Thu, 14 Jul 2016 12:21:40 +0000
Subject: [PATCH] [X86][AVX] Add 128-bit wide shuffle tests that should combine
 to blend-with-zero

llvm-svn: 275402
---
 .../X86/vector-shuffle-combining-avx.ll       | 26 +++++++++++++++++++
 .../X86/vector-shuffle-combining-avx2.ll      | 12 +++++++++
 2 files changed, 38 insertions(+)

diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
index 351c91e7acf0..2dc50cfe4165 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx.ll
@@ -123,6 +123,32 @@ define <8 x float> @combine_vpermilvar_vperm2f128_zero_8f32(<8 x float> %a0) {
   ret <8 x float> %3
 }
 
+define <4 x double> @combine_vperm2f128_vpermilvar_as_vpblendpd(<4 x double> %a0) {
+; AVX1-LABEL: combine_vperm2f128_vpermilvar_as_vpblendpd:
+; AVX1:       # BB#0:
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
+; AVX1-NEXT:    vxorpd %ymm1, %ymm1, %ymm1
+; AVX1-NEXT:    vblendpd {{.*#+}} ymm0 = ymm0[0,1],ymm1[2,3]
+; AVX1-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
+; AVX1-NEXT:    retq
+;
+; AVX2-LABEL: combine_vperm2f128_vpermilvar_as_vpblendpd:
+; AVX2:       # BB#0:
+; AVX2-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
+; AVX2-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX2-NEXT:    retq
+;
+; AVX512F-LABEL: combine_vperm2f128_vpermilvar_as_vpblendpd:
+; AVX512F:       # BB#0:
+; AVX512F-NEXT:    vpermilpd {{.*#+}} ymm0 = ymm0[1,0,3,2]
+; AVX512F-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; AVX512F-NEXT:    retq
+  %1 = tail call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %a0, <4 x i64> <i64 2, i64 0, i64 2, i64 0>)
+  %2 = shufflevector <4 x double> %1, <4 x double> zeroinitializer, <4 x i32> <i32 0, i32 1, i32 4, i32 5>
+  %3 = tail call <4 x double> @llvm.x86.avx.vpermilvar.pd.256(<4 x double> %2, <4 x i64> <i64 2, i64 0, i64 2, i64 0>)
+  ret <4 x double> %3
+}
+
 define <8 x float> @combine_vpermilvar_8f32_movddup(<8 x float> %a0) {
 ; ALL-LABEL: combine_vpermilvar_8f32_movddup:
 ; ALL:       # BB#0:
diff --git a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
index b087fc43ae36..97492dddd3d2 100644
--- a/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
+++ b/llvm/test/CodeGen/X86/vector-shuffle-combining-avx2.ll
@@ -62,6 +62,18 @@ define <4 x i64> @combine_permq_pshufb_as_vperm2i128(<4 x i64> %a0) {
   ret <4 x i64> %5
 }
 
+define <32 x i8> @combine_permq_pshufb_as_vpblendd(<4 x i64> %a0) {
+; CHECK-LABEL: combine_permq_pshufb_as_vpblendd:
+; CHECK:       # BB#0:
+; CHECK-NEXT:    vpshufd {{.*#+}} ymm0 = ymm0[2,3,0,1,6,7,4,5]
+; CHECK-NEXT:    vpshufb {{.*#+}} ymm0 = ymm0[8,9,10,11,12,13,14,15,0,1,2,3,4,5,6,7],zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero,zero
+; CHECK-NEXT:    retq
+  %1 = shufflevector <4 x i64> %a0, <4 x i64> undef, <4 x i32> <i32 1, i32 0, i32 3, i32 2>
+  %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 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255, i8 255>)
+  ret <32 x i8> %3
+}
+
 define <16 x i8> @combine_pshufb_as_vpbroadcastb128(<16 x i8> %a) {
 ; CHECK-LABEL: combine_pshufb_as_vpbroadcastb128:
 ; CHECK:       # BB#0: