[llvm] r354360 - [X86][SSE] Add pblendw commuted load test case

[Simon Pilgrim via llvm-commits]

Author: rksimon
Date: Tue Feb 19 09:56:14 2019
New Revision: 354360

URL: http://llvm.org/viewvc/llvm-project?rev=354360&view=rev
Log:
[X86][SSE] Add pblendw commuted load test case

Reduced test case for the regression caused in D57888/rL353610

Modified:
    llvm/trunk/test/CodeGen/X86/commute-blend-sse41.ll

Modified: llvm/trunk/test/CodeGen/X86/commute-blend-sse41.ll
URL: http://llvm.org/viewvc/llvm-project/llvm/trunk/test/CodeGen/X86/commute-blend-sse41.ll?rev=354360&r1=354359&r2=354360&view=diff
==============================================================================
--- llvm/trunk/test/CodeGen/X86/commute-blend-sse41.ll (original)
+++ llvm/trunk/test/CodeGen/X86/commute-blend-sse41.ll Tue Feb 19 09:56:14 2019
@@ -1,7 +1,7 @@
 ; NOTE: Assertions have been autogenerated by utils/update_llc_test_checks.py
 ; RUN: llc < %s -mtriple=x86_64-unknown -mattr=+sse4.1 | FileCheck %s
 
-define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) #0 {
+define <8 x i16> @commute_fold_pblendw(<8 x i16> %a, <8 x i16>* %b) {
 ; CHECK-LABEL: commute_fold_pblendw:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    pblendw {{.*#+}} xmm0 = xmm0[0],mem[1,2,3],xmm0[4],mem[5,6,7]
@@ -12,7 +12,7 @@ define <8 x i16> @commute_fold_pblendw(<
 }
 declare <8 x i16> @llvm.x86.sse41.pblendw(<8 x i16>, <8 x i16>, i8) nounwind readnone
 
-define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) #0 {
+define <4 x float> @commute_fold_blendps(<4 x float> %a, <4 x float>* %b) {
 ; CHECK-LABEL: commute_fold_blendps:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0],mem[1],xmm0[2],mem[3]
@@ -23,7 +23,7 @@ define <4 x float> @commute_fold_blendps
 }
 declare <4 x float> @llvm.x86.sse41.blendps(<4 x float>, <4 x float>, i8) nounwind readnone
 
-define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) #0 {
+define <2 x double> @commute_fold_blendpd(<2 x double> %a, <2 x double>* %b) {
 ; CHECK-LABEL: commute_fold_blendpd:
 ; CHECK:       # %bb.0:
 ; CHECK-NEXT:    blendps {{.*#+}} xmm0 = xmm0[0,1],mem[2,3]
@@ -33,3 +33,15 @@ define <2 x double> @commute_fold_blendp
   ret <2 x double> %2
 }
 declare <2 x double> @llvm.x86.sse41.blendpd(<2 x double>, <2 x double>, i8) nounwind readnone
+
+define <4 x i32> @commute_fold_blend_v4i32(<4 x i32>* %a, <4 x i32> %b) {
+; CHECK-LABEL: commute_fold_blend_v4i32:
+; CHECK:       # %bb.0:
+; CHECK-NEXT:    paddd %xmm0, %xmm0 ; force integer domain
+; CHECK-NEXT:    pblendw {{.*#+}} xmm0 = mem[0,1,2,3,4,5],xmm0[6,7]
+; CHECK-NEXT:    retq
+  %1 = load <4 x i32>, <4 x i32>* %a
+  %2 = add <4 x i32> %b, %b
+  %3 = shufflevector <4 x i32> %1, <4 x i32> %2, <4 x i32> <i32 0, i32 1, i32 2, i32 7>
+  ret <4 x i32> %3
+}