[SLP][REVEC] Make GetMinMaxCost support FixedVectorType when REVEC is enabled. #115417
Conversation
This file contains bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
|
@llvm/pr-subscribers-vectorizers Author: Han-Kuan Chen (HanKuanChen) Changesreference: #114946 Full diff: https://github.com/llvm/llvm-project/pull/115417.diff 2 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index b2f677fb84f983..bd8680d4c16638 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -10986,7 +10986,8 @@ BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
// If the selects are the only uses of the compares, they will be
// dead and we can adjust the cost by removing their cost.
if (VI && SelectOnly) {
- assert(!Ty->isVectorTy() && "Expected only for scalar type.");
+ assert((!Ty->isVectorTy() || SLPReVec) &&
+ "Expected only for scalar type.");
auto *CI = cast<CmpInst>(VI->getOperand(0));
IntrinsicCost -= TTI->getCmpSelInstrCost(
CI->getOpcode(), Ty, Builder.getInt1Ty(), CI->getPredicate(),
diff --git a/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll b/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
index 3d00ddf89aaa3b..b312688b7932dc 100644
--- a/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
+++ b/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
@@ -94,3 +94,43 @@ entry:
%23 = fcmp ogt <8 x float> zeroinitializer, %19
ret void
}
+
+define void @test3(float %0) {
+; CHECK-LABEL: @test3(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[FOR_BODY_LR_PH:%.*]]
+; CHECK: for.body.lr.ph:
+; CHECK-NEXT: [[TMP1:%.*]] = call <4 x float> @llvm.vector.insert.v4f32.v2f32(<4 x float> poison, <2 x float> zeroinitializer, i64 0)
+; CHECK-NEXT: [[TMP2:%.*]] = call <4 x float> @llvm.vector.insert.v4f32.v2f32(<4 x float> [[TMP1]], <2 x float> zeroinitializer, i64 2)
+; CHECK-NEXT: br i1 false, label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY:%.*]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: [[TMP3:%.*]] = phi <4 x float> [ [[TMP2]], [[FOR_BODY_LR_PH]] ], [ [[TMP10:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT: ret void
+; CHECK: for.body:
+; CHECK-NEXT: [[TMP4:%.*]] = load <2 x float>, ptr null, align 4
+; CHECK-NEXT: [[TMP5:%.*]] = fcmp olt <2 x float> zeroinitializer, [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = call <4 x i1> @llvm.vector.insert.v4i1.v2i1(<4 x i1> poison, <2 x i1> splat (i1 true), i64 0)
+; CHECK-NEXT: [[TMP7:%.*]] = call <4 x i1> @llvm.vector.insert.v4i1.v2i1(<4 x i1> [[TMP6]], <2 x i1> [[TMP5]], i64 2)
+; CHECK-NEXT: [[TMP8:%.*]] = call <4 x float> @llvm.vector.insert.v4f32.v2f32(<4 x float> poison, <2 x float> [[TMP4]], i64 0)
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x float> [[TMP8]], <4 x float> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
+; CHECK-NEXT: [[TMP10]] = select <4 x i1> [[TMP7]], <4 x float> [[TMP9]], <4 x float> [[TMP2]]
+; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
+;
+entry:
+ br label %for.body.lr.ph
+
+for.body.lr.ph:
+ br i1 false, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup: ; preds = %for.body, %for.body.lr.ph
+ %1 = phi <2 x float> [ zeroinitializer, %for.body.lr.ph ], [ %5, %for.body ]
+ %2 = phi <2 x float> [ zeroinitializer, %for.body.lr.ph ], [ %6, %for.body ]
+ ret void
+
+for.body:
+ %3 = load <2 x float>, ptr null, align 4
+ %4 = fcmp olt <2 x float> zeroinitializer, %3
+ %5 = select <2 x i1> <i1 true, i1 true>, <2 x float> %3, <2 x float> zeroinitializer
+ %6 = select <2 x i1> %4, <2 x float> %3, <2 x float> zeroinitializer
+ br label %for.cond.cleanup
+}
|
|
@llvm/pr-subscribers-llvm-transforms Author: Han-Kuan Chen (HanKuanChen) Changesreference: #114946 Full diff: https://github.com/llvm/llvm-project/pull/115417.diff 2 Files Affected:
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
index b2f677fb84f983..bd8680d4c16638 100644
--- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
+++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp
@@ -10986,7 +10986,8 @@ BoUpSLP::getEntryCost(const TreeEntry *E, ArrayRef<Value *> VectorizedVals,
// If the selects are the only uses of the compares, they will be
// dead and we can adjust the cost by removing their cost.
if (VI && SelectOnly) {
- assert(!Ty->isVectorTy() && "Expected only for scalar type.");
+ assert((!Ty->isVectorTy() || SLPReVec) &&
+ "Expected only for scalar type.");
auto *CI = cast<CmpInst>(VI->getOperand(0));
IntrinsicCost -= TTI->getCmpSelInstrCost(
CI->getOpcode(), Ty, Builder.getInt1Ty(), CI->getPredicate(),
diff --git a/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll b/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
index 3d00ddf89aaa3b..b312688b7932dc 100644
--- a/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
+++ b/llvm/test/Transforms/SLPVectorizer/RISCV/revec.ll
@@ -94,3 +94,43 @@ entry:
%23 = fcmp ogt <8 x float> zeroinitializer, %19
ret void
}
+
+define void @test3(float %0) {
+; CHECK-LABEL: @test3(
+; CHECK-NEXT: entry:
+; CHECK-NEXT: br label [[FOR_BODY_LR_PH:%.*]]
+; CHECK: for.body.lr.ph:
+; CHECK-NEXT: [[TMP1:%.*]] = call <4 x float> @llvm.vector.insert.v4f32.v2f32(<4 x float> poison, <2 x float> zeroinitializer, i64 0)
+; CHECK-NEXT: [[TMP2:%.*]] = call <4 x float> @llvm.vector.insert.v4f32.v2f32(<4 x float> [[TMP1]], <2 x float> zeroinitializer, i64 2)
+; CHECK-NEXT: br i1 false, label [[FOR_COND_CLEANUP:%.*]], label [[FOR_BODY:%.*]]
+; CHECK: for.cond.cleanup:
+; CHECK-NEXT: [[TMP3:%.*]] = phi <4 x float> [ [[TMP2]], [[FOR_BODY_LR_PH]] ], [ [[TMP10:%.*]], [[FOR_BODY]] ]
+; CHECK-NEXT: ret void
+; CHECK: for.body:
+; CHECK-NEXT: [[TMP4:%.*]] = load <2 x float>, ptr null, align 4
+; CHECK-NEXT: [[TMP5:%.*]] = fcmp olt <2 x float> zeroinitializer, [[TMP4]]
+; CHECK-NEXT: [[TMP6:%.*]] = call <4 x i1> @llvm.vector.insert.v4i1.v2i1(<4 x i1> poison, <2 x i1> splat (i1 true), i64 0)
+; CHECK-NEXT: [[TMP7:%.*]] = call <4 x i1> @llvm.vector.insert.v4i1.v2i1(<4 x i1> [[TMP6]], <2 x i1> [[TMP5]], i64 2)
+; CHECK-NEXT: [[TMP8:%.*]] = call <4 x float> @llvm.vector.insert.v4f32.v2f32(<4 x float> poison, <2 x float> [[TMP4]], i64 0)
+; CHECK-NEXT: [[TMP9:%.*]] = shufflevector <4 x float> [[TMP8]], <4 x float> poison, <4 x i32> <i32 0, i32 1, i32 0, i32 1>
+; CHECK-NEXT: [[TMP10]] = select <4 x i1> [[TMP7]], <4 x float> [[TMP9]], <4 x float> [[TMP2]]
+; CHECK-NEXT: br label [[FOR_COND_CLEANUP]]
+;
+entry:
+ br label %for.body.lr.ph
+
+for.body.lr.ph:
+ br i1 false, label %for.cond.cleanup, label %for.body
+
+for.cond.cleanup: ; preds = %for.body, %for.body.lr.ph
+ %1 = phi <2 x float> [ zeroinitializer, %for.body.lr.ph ], [ %5, %for.body ]
+ %2 = phi <2 x float> [ zeroinitializer, %for.body.lr.ph ], [ %6, %for.body ]
+ ret void
+
+for.body:
+ %3 = load <2 x float>, ptr null, align 4
+ %4 = fcmp olt <2 x float> zeroinitializer, %3
+ %5 = select <2 x i1> <i1 true, i1 true>, <2 x float> %3, <2 x float> zeroinitializer
+ %6 = select <2 x i1> %4, <2 x float> %3, <2 x float> zeroinitializer
+ br label %for.cond.cleanup
+}
|
|
Thank you for updating the patch! I don't know about its correctness, but it does pass |
|
Here is the diff |
alexey-bataev
approved these changes
Nov 8, 2024
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
Add this suggestion to a batch that can be applied as a single commit.
This suggestion is invalid because no changes were made to the code.
Suggestions cannot be applied while the pull request is closed.
Suggestions cannot be applied while viewing a subset of changes.
Only one suggestion per line can be applied in a batch.
Add this suggestion to a batch that can be applied as a single commit.
Applying suggestions on deleted lines is not supported.
You must change the existing code in this line in order to create a valid suggestion.
Outdated suggestions cannot be applied.
This suggestion has been applied or marked resolved.
Suggestions cannot be applied from pending reviews.
Suggestions cannot be applied on multi-line comments.
Suggestions cannot be applied while the pull request is queued to merge.
Suggestion cannot be applied right now. Please check back later.
reference: #114946