diff options
| author | Anton Afanasyev <anton.a.afanasyev@gmail.com> | 2019-11-11 11:29:10 +0300 |
|---|---|---|
| committer | Anton Afanasyev <anton.a.afanasyev@gmail.com> | 2019-11-22 20:01:59 +0300 |
| commit | 80cd6b6e043f04ff7cb525bc1f09ab1f6400e9db (patch) | |
| tree | e1417bdb3463edb14c883c49b67d69acbd703475 /llvm/lib/Transforms/Vectorize | |
| parent | 70a3c9f55f8494829d06caae0ab988da518d0e15 (diff) | |
| download | bcm5719-llvm-80cd6b6e043f04ff7cb525bc1f09ab1f6400e9db.tar.gz bcm5719-llvm-80cd6b6e043f04ff7cb525bc1f09ab1f6400e9db.zip | |
[SLP] Enhance SLPVectorizer to vectorize vector aggregate
Summary:
Vector aggregate is homogeneous aggregate of vectors like `{ <2 x float>, <2 x float> }`.
This patch allows `findBuildAggregate()` to consider vector aggregates as
well as scalar ones. For instance, `{ <2 x float>, <2 x float> }` maps to `<4 x float>`.
Fixes vector part of llvm.org/PR42022
Reviewers: RKSimon
Subscribers: hiraditya, llvm-commits
Tags: #llvm
Differential Revision: https://reviews.llvm.org/D70068
Diffstat (limited to 'llvm/lib/Transforms/Vectorize')
| -rw-r--r-- | llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp | 33 |
1 files changed, 27 insertions, 6 deletions
diff --git a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp index 57a17e03583..e4f50a8787d 100644 --- a/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp +++ b/llvm/lib/Transforms/Vectorize/SLPVectorizer.cpp @@ -630,6 +630,8 @@ public: } /// Check if ArrayType or StructType is isomorphic to some VectorType. + /// Accepts homogeneous aggregate of vectors like + /// { <2 x float>, <2 x float> } /// /// \returns number of elements in vector if isomorphism exists, 0 otherwise. unsigned canMapToVector(Type *T, const DataLayout &DL) const; @@ -3096,6 +3098,12 @@ unsigned BoUpSLP::canMapToVector(Type *T, const DataLayout &DL) const { N = cast<ArrayType>(T)->getNumElements(); EltTy = cast<ArrayType>(T)->getElementType(); } + + if (auto *VT = dyn_cast<VectorType>(EltTy)) { + EltTy = VT->getElementType(); + N *= VT->getNumElements(); + } + if (!isValidElementType(EltTy)) return 0; uint64_t VTSize = DL.getTypeStoreSizeInBits(VectorType::get(EltTy, N)); @@ -3104,7 +3112,7 @@ unsigned BoUpSLP::canMapToVector(Type *T, const DataLayout &DL) const { if (ST) { // Check that struct is homogeneous. for (const auto *Ty : ST->elements()) - if (Ty != EltTy) + if (Ty != *ST->element_begin()) return 0; } return N; @@ -6960,12 +6968,24 @@ static bool findBuildVector(InsertElementInst *LastInsertElem, } /// Like findBuildVector, but looks for construction of aggregate. +/// Accepts homegeneous aggregate of vectors like { <2 x float>, <2 x float> }. /// /// \return true if it matches. -static bool findBuildAggregate(InsertValueInst *IV, - SmallVectorImpl<Value *> &BuildVectorOpds) { +static bool findBuildAggregate(InsertValueInst *IV, TargetTransformInfo *TTI, + SmallVectorImpl<Value *> &BuildVectorOpds, + int &UserCost) { + UserCost = 0; do { - BuildVectorOpds.push_back(IV->getInsertedValueOperand()); + if (auto *IE = dyn_cast<InsertElementInst>(IV->getInsertedValueOperand())) { + int TmpUserCost; + SmallVector<Value *, 4> TmpBuildVectorOpds; + if (!findBuildVector(IE, TTI, TmpBuildVectorOpds, TmpUserCost)) + return false; + BuildVectorOpds.append(TmpBuildVectorOpds.rbegin(), TmpBuildVectorOpds.rend()); + UserCost += TmpUserCost; + } else { + BuildVectorOpds.push_back(IV->getInsertedValueOperand()); + } Value *V = IV->getAggregateOperand(); if (isa<UndefValue>(V)) break; @@ -7138,18 +7158,19 @@ bool SLPVectorizerPass::vectorizeRootInstruction(PHINode *P, Value *V, bool SLPVectorizerPass::vectorizeInsertValueInst(InsertValueInst *IVI, BasicBlock *BB, BoUpSLP &R) { + int UserCost = 0; const DataLayout &DL = BB->getModule()->getDataLayout(); if (!R.canMapToVector(IVI->getType(), DL)) return false; SmallVector<Value *, 16> BuildVectorOpds; - if (!findBuildAggregate(IVI, BuildVectorOpds)) + if (!findBuildAggregate(IVI, TTI, BuildVectorOpds, UserCost)) return false; LLVM_DEBUG(dbgs() << "SLP: array mappable to vector: " << *IVI << "\n"); // 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); + return tryToVectorizeList(BuildVectorOpds, R, UserCost); } bool SLPVectorizerPass::vectorizeInsertElementInst(InsertElementInst *IEI, |

