diff options
4 files changed, 49 insertions, 5 deletions
diff --git a/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h b/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h index 06f6fa11a94..25f264c4722 100644 --- a/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h +++ b/llvm/include/llvm/Transforms/Vectorize/SLPVectorizer.h @@ -96,11 +96,13 @@ private: /// \brief Try to vectorize a list of operands. /// \@param BuildVector A list of users to ignore for the purpose of - /// scheduling and that don't need extracting. + /// scheduling and cost estimation when NeedExtraction + /// is false. /// \returns true if a value was vectorized. bool tryToVectorizeList(ArrayRef<Value *> VL, slpvectorizer::BoUpSLP &R, ArrayRef<Value *> BuildVector = None, - bool AllowReorder = false); + bool AllowReorder = false, + bool NeedExtraction = false); /// \brief Try to vectorize a chain that may start at the operands of \p I. bool tryToVectorize(Instruction *I, slpvectorizer::BoUpSLP &R); diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp index 9b35f35e870..76ba62f5d59 100644 --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -4533,7 +4533,8 @@ bool SLPVectorizerPass::tryToVectorizePair(Value *A, Value *B, BoUpSLP &R) { bool SLPVectorizerPass::tryToVectorizeList(ArrayRef<Value *> VL, BoUpSLP &R, ArrayRef<Value *> BuildVector, - bool AllowReorder) { + bool AllowReorder, + bool NeedExtraction) { if (VL.size() < 2) return false; @@ -4627,11 +4628,12 @@ bool SLPVectorizerPass::tryToVectorizeList(ArrayRef<Value *> VL, BoUpSLP &R, << "\n"); ArrayRef<Value *> Ops = VL.slice(I, OpsWidth); + ArrayRef<Value *> EmptyArray; ArrayRef<Value *> BuildVectorSlice; if (!BuildVector.empty()) BuildVectorSlice = BuildVector.slice(I, OpsWidth); - R.buildTree(Ops, BuildVectorSlice); + R.buildTree(Ops, NeedExtraction ? EmptyArray : BuildVectorSlice); // TODO: check if we can allow reordering for more cases. if (AllowReorder && R.shouldReorder()) { // Conceptually, there is nothing actually preventing us from trying to @@ -5821,7 +5823,9 @@ bool SLPVectorizerPass::vectorizeInsertValueInst(InsertValueInst *IVI, return false; DEBUG(dbgs() << "SLP: array mappable to vector: " << *IVI << "\n"); - return tryToVectorizeList(BuildVectorOpds, R, BuildVector, false); + // Aggregate value is unlikely to be processed in vector register, we need to + // extract scalars into scalar registers, so NeedExtraction is set true. + return tryToVectorizeList(BuildVectorOpds, R, BuildVector, false, true); } bool SLPVectorizerPass::vectorizeInsertElementInst(InsertElementInst *IEI, diff --git a/llvm/test/Transforms/SLPVectorizer/PowerPC/aggregate.ll b/llvm/test/Transforms/SLPVectorizer/PowerPC/aggregate.ll new file mode 100644 index 00000000000..015c1f1ed8f --- /dev/null +++ b/llvm/test/Transforms/SLPVectorizer/PowerPC/aggregate.ll @@ -0,0 +1,19 @@ +; RUN: opt -S -mtriple=powerpc64-linux-gnu -mcpu=pwr9 -mattr=+vsx -slp-vectorizer < %s | FileCheck %s + +%struct.S = type { i8*, i8* } + +@kS0 = common global %struct.S zeroinitializer, align 8 + +define { i64, i64 } @getS() { +entry: + %0 = load i64, i64* bitcast (%struct.S* @kS0 to i64*), align 8 + %1 = load i64, i64* bitcast (i8** getelementptr inbounds (%struct.S, %struct.S* @kS0, i64 0, i32 1) to i64*), align 8 + %2 = insertvalue { i64, i64 } undef, i64 %0, 0 + %3 = insertvalue { i64, i64 } %2, i64 %1, 1 + ret { i64, i64 } %3 +} + +; CHECK: load i64 +; CHECK-NOT: load <2 x i64> +; CHECK-NOT: extractelement + diff --git a/llvm/test/Transforms/SLPVectorizer/X86/aggregate.ll b/llvm/test/Transforms/SLPVectorizer/X86/aggregate.ll new file mode 100644 index 00000000000..350929dc539 --- /dev/null +++ b/llvm/test/Transforms/SLPVectorizer/X86/aggregate.ll @@ -0,0 +1,19 @@ +; RUN: opt -S -mtriple=x86_64-unknown-linux -mcpu=corei7 -slp-vectorizer < %s | FileCheck %s + +%struct.S = type { i8*, i8* } + +@kS0 = common global %struct.S zeroinitializer, align 8 + +define { i64, i64 } @getS() { +entry: + %0 = load i64, i64* bitcast (%struct.S* @kS0 to i64*), align 8 + %1 = load i64, i64* bitcast (i8** getelementptr inbounds (%struct.S, %struct.S* @kS0, i64 0, i32 1) to i64*), align 8 + %2 = insertvalue { i64, i64 } undef, i64 %0, 0 + %3 = insertvalue { i64, i64 } %2, i64 %1, 1 + ret { i64, i64 } %3 +} + +; CHECK: load i64 +; CHECK-NOT: load <2 x i64> +; CHECK-NOT: extractelement + |
