[llvm] [SLP] Update test against const-folding (PR #202532)

[via llvm-commits]

llvmorg-github-actions[bot] wrote:


<!--LLVM PR SUMMARY COMMENT-->

@llvm/pr-subscribers-llvm-transforms

Author: Ramkumar Ramachandra (artagnon)

<details>
<summary>Changes</summary>

223ef1f3 ([IRBuilder] ConstFold unary intrinsics, #<!-- -->200496) made a lot of test updates to SLPVectorizer. The tests were written a long time ago, and it is unclear what their intent was, but at least update the one test to replace constants with arguments, where the intent is clear.

---
Full diff: https://github.com/llvm/llvm-project/pull/202532.diff


1 Files Affected:

- (modified) llvm/test/Transforms/SLPVectorizer/X86/revec-reduced-value-vectorized-later.ll (+40-4) 


``````````diff
diff --git a/llvm/test/Transforms/SLPVectorizer/X86/revec-reduced-value-vectorized-later.ll b/llvm/test/Transforms/SLPVectorizer/X86/revec-reduced-value-vectorized-later.ll
index 4305ad171c4b9..0e50b135afe7f 100644
--- a/llvm/test/Transforms/SLPVectorizer/X86/revec-reduced-value-vectorized-later.ll
+++ b/llvm/test/Transforms/SLPVectorizer/X86/revec-reduced-value-vectorized-later.ll
@@ -1,13 +1,49 @@
 ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py UTC_ARGS: --version 5
 ; RUN: opt -S -passes=slp-vectorizer -mtriple=x86_64-unknown-linux-gnu -slp-revec -slp-max-reg-size=1024 -slp-threshold=-100 < %s | FileCheck %s
 
-define <4 x i16> @test() {
-; CHECK-LABEL: define <4 x i16> @test() {
+define <4 x i16> @test(<4 x i16> %a) {
+; CHECK-LABEL: define <4 x i16> @test(
+; CHECK-SAME: <4 x i16> [[A:%.*]]) {
 ; CHECK-NEXT:  [[ENTRY:.*:]]
-; CHECK-NEXT:    ret <4 x i16> zeroinitializer
+; CHECK-NEXT:    [[TMP0:%.*]] = shufflevector <4 x i16> [[A]], <4 x i16> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison, i32 poison>
+; CHECK-NEXT:    [[TMP1:%.*]] = shufflevector <16 x i16> <i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 0, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef, i16 undef>, <16 x i16> [[TMP0]], <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 4, i32 5, i32 6, i32 7, i32 16, i32 17, i32 18, i32 19, i32 12, i32 13, i32 14, i32 15>
+; CHECK-NEXT:    [[TMP2:%.*]] = shufflevector <16 x i16> [[TMP1]], <16 x i16> poison, <16 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 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:    [[TMP3:%.*]] = add <16 x i16> [[TMP2]], [[TMP2]]
+; CHECK-NEXT:    [[TMP4:%.*]] = shufflevector <16 x i16> [[TMP3]], <16 x i16> poison, <4 x i32> <i32 8, i32 9, i32 10, i32 11>
+; CHECK-NEXT:    [[TMP5:%.*]] = shufflevector <4 x i16> [[TMP4]], <4 x i16> poison, <16 x i32> <i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3, i32 0, i32 1, i32 2, i32 3>
+; CHECK-NEXT:    [[TMP6:%.*]] = add <16 x i16> [[TMP5]], zeroinitializer
+; CHECK-NEXT:    [[TMP7:%.*]] = add <16 x i16> [[TMP3]], zeroinitializer
+; CHECK-NEXT:    [[TMP8:%.*]] = shufflevector <16 x i16> [[TMP6]], <16 x i16> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CHECK-NEXT:    [[TMP9:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP8]])
+; CHECK-NEXT:    [[TMP10:%.*]] = insertelement <4 x i16> poison, i16 [[TMP9]], i64 0
+; CHECK-NEXT:    [[TMP11:%.*]] = shufflevector <16 x i16> [[TMP6]], <16 x i16> poison, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
+; CHECK-NEXT:    [[TMP12:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP11]])
+; CHECK-NEXT:    [[TMP13:%.*]] = insertelement <4 x i16> [[TMP10]], i16 [[TMP12]], i64 1
+; CHECK-NEXT:    [[TMP14:%.*]] = shufflevector <16 x i16> [[TMP6]], <16 x i16> poison, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
+; CHECK-NEXT:    [[TMP15:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP14]])
+; CHECK-NEXT:    [[TMP16:%.*]] = insertelement <4 x i16> [[TMP13]], i16 [[TMP15]], i64 2
+; CHECK-NEXT:    [[TMP17:%.*]] = shufflevector <16 x i16> [[TMP6]], <16 x i16> poison, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
+; CHECK-NEXT:    [[TMP18:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP17]])
+; CHECK-NEXT:    [[TMP19:%.*]] = insertelement <4 x i16> [[TMP16]], i16 [[TMP18]], i64 3
+; CHECK-NEXT:    [[TMP20:%.*]] = shufflevector <16 x i16> [[TMP7]], <16 x i16> poison, <4 x i32> <i32 0, i32 4, i32 8, i32 12>
+; CHECK-NEXT:    [[TMP21:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP20]])
+; CHECK-NEXT:    [[TMP22:%.*]] = insertelement <4 x i16> poison, i16 [[TMP21]], i64 0
+; CHECK-NEXT:    [[TMP23:%.*]] = shufflevector <16 x i16> [[TMP7]], <16 x i16> poison, <4 x i32> <i32 1, i32 5, i32 9, i32 13>
+; CHECK-NEXT:    [[TMP24:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP23]])
+; CHECK-NEXT:    [[TMP25:%.*]] = insertelement <4 x i16> [[TMP22]], i16 [[TMP24]], i64 1
+; CHECK-NEXT:    [[TMP26:%.*]] = shufflevector <16 x i16> [[TMP7]], <16 x i16> poison, <4 x i32> <i32 2, i32 6, i32 10, i32 14>
+; CHECK-NEXT:    [[TMP27:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP26]])
+; CHECK-NEXT:    [[TMP28:%.*]] = insertelement <4 x i16> [[TMP25]], i16 [[TMP27]], i64 2
+; CHECK-NEXT:    [[TMP29:%.*]] = shufflevector <16 x i16> [[TMP7]], <16 x i16> poison, <4 x i32> <i32 3, i32 7, i32 11, i32 15>
+; CHECK-NEXT:    [[TMP30:%.*]] = call i16 @llvm.vector.reduce.or.v4i16(<4 x i16> [[TMP29]])
+; CHECK-NEXT:    [[TMP31:%.*]] = insertelement <4 x i16> [[TMP28]], i16 [[TMP30]], i64 3
+; CHECK-NEXT:    [[OP_RDX:%.*]] = or <4 x i16> [[TMP31]], [[TMP4]]
+; CHECK-NEXT:    [[OP_RDX15:%.*]] = or <4 x i16> zeroinitializer, [[TMP19]]
+; CHECK-NEXT:    [[OP_RDX16:%.*]] = or <4 x i16> [[OP_RDX]], [[OP_RDX15]]
+; CHECK-NEXT:    ret <4 x i16> [[OP_RDX16]]
 ;
 entry:
-  %subi = add <4 x i16> zeroinitializer, zeroinitializer
+  %subi = add <4 x i16> %a, %a
   %sub40.i = add <4 x i16> %subi, zeroinitializer
   %sub41.i = add <4 x i16> %subi, zeroinitializer
   %sub42.i = add <4 x i16> %subi, zeroinitializer

``````````

</details>


https://github.com/llvm/llvm-project/pull/202532