diff options
Diffstat (limited to 'llvm/lib/Transforms/Scalar')
-rw-r--r-- | llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp | 35 | ||||
-rw-r--r-- | llvm/lib/Transforms/Scalar/SROA.cpp | 80 |
2 files changed, 81 insertions, 34 deletions
diff --git a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp index 11a91bfbe5ba..380d65836553 100644 --- a/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp +++ b/llvm/lib/Transforms/Scalar/DeadStoreElimination.cpp @@ -857,6 +857,9 @@ struct DSEState { // no longer be captured. bool ShouldIterateEndOfFunctionDSE; + /// Dead instructions to be removed at the end of DSE. + SmallVector<Instruction *> ToRemove; + // Class contains self-reference, make sure it's not copied/moved. DSEState(const DSEState &) = delete; DSEState &operator=(const DSEState &) = delete; @@ -1692,7 +1695,8 @@ struct DSEState { return {MaybeDeadAccess}; } - // Delete dead memory defs + /// Delete dead memory defs and recursively add their operands to ToRemove if + /// they became dead. void deleteDeadInstruction(Instruction *SI) { MemorySSAUpdater Updater(&MSSA); SmallVector<Instruction *, 32> NowDeadInsts; @@ -1708,8 +1712,11 @@ struct DSEState { salvageKnowledge(DeadInst); // Remove the Instruction from MSSA. - if (MemoryAccess *MA = MSSA.getMemoryAccess(DeadInst)) { - if (MemoryDef *MD = dyn_cast<MemoryDef>(MA)) { + MemoryAccess *MA = MSSA.getMemoryAccess(DeadInst); + bool IsMemDef = MA && isa<MemoryDef>(MA); + if (MA) { + if (IsMemDef) { + auto *MD = cast<MemoryDef>(MA); SkipStores.insert(MD); if (auto *SI = dyn_cast<StoreInst>(MD->getMemoryInst())) { if (SI->getValueOperand()->getType()->isPointerTy()) { @@ -1730,13 +1737,21 @@ struct DSEState { // Remove its operands for (Use &O : DeadInst->operands()) if (Instruction *OpI = dyn_cast<Instruction>(O)) { - O = nullptr; + O.set(PoisonValue::get(O->getType())); if (isInstructionTriviallyDead(OpI, &TLI)) NowDeadInsts.push_back(OpI); } EI.removeInstruction(DeadInst); - DeadInst->eraseFromParent(); + // Remove memory defs directly if they don't produce results, but only + // queue other dead instructions for later removal. They may have been + // used as memory locations that have been cached by BatchAA. Removing + // them here may lead to newly created instructions to be allocated at the + // same address, yielding stale cache entries. + if (IsMemDef && DeadInst->getType()->isVoidTy()) + DeadInst->eraseFromParent(); + else + ToRemove.push_back(DeadInst); } } @@ -1892,15 +1907,15 @@ struct DSEState { Malloc->getArgOperand(0), IRB, TLI); if (!Calloc) return false; + MemorySSAUpdater Updater(&MSSA); auto *NewAccess = Updater.createMemoryAccessAfter(cast<Instruction>(Calloc), nullptr, MallocDef); auto *NewAccessMD = cast<MemoryDef>(NewAccess); Updater.insertDef(NewAccessMD, /*RenameUses=*/true); - Updater.removeMemoryAccess(Malloc); Malloc->replaceAllUsesWith(Calloc); - Malloc->eraseFromParent(); + deleteDeadInstruction(Malloc); return true; } @@ -2233,6 +2248,12 @@ static bool eliminateDeadStores(Function &F, AliasAnalysis &AA, MemorySSA &MSSA, MadeChange |= State.eliminateRedundantStoresOfExistingValues(); MadeChange |= State.eliminateDeadWritesAtEndOfFunction(); + + while (!State.ToRemove.empty()) { + Instruction *DeadInst = State.ToRemove.pop_back_val(); + DeadInst->eraseFromParent(); + } + return MadeChange; } } // end anonymous namespace diff --git a/llvm/lib/Transforms/Scalar/SROA.cpp b/llvm/lib/Transforms/Scalar/SROA.cpp index bdbaf4f55c96..17a94f9381bf 100644 --- a/llvm/lib/Transforms/Scalar/SROA.cpp +++ b/llvm/lib/Transforms/Scalar/SROA.cpp @@ -2257,6 +2257,41 @@ checkVectorTypesForPromotion(Partition &P, const DataLayout &DL, return nullptr; } +static VectorType *createAndCheckVectorTypesForPromotion( + SetVector<Type *> &OtherTys, ArrayRef<VectorType *> CandidateTysCopy, + function_ref<void(Type *)> CheckCandidateType, Partition &P, + const DataLayout &DL, SmallVectorImpl<VectorType *> &CandidateTys, + bool &HaveCommonEltTy, Type *&CommonEltTy, bool &HaveVecPtrTy, + bool &HaveCommonVecPtrTy, VectorType *&CommonVecPtrTy) { + [[maybe_unused]] VectorType *OriginalElt = + CandidateTysCopy.size() ? CandidateTysCopy[0] : nullptr; + // Consider additional vector types where the element type size is a + // multiple of load/store element size. + for (Type *Ty : OtherTys) { + if (!VectorType::isValidElementType(Ty)) + continue; + unsigned TypeSize = DL.getTypeSizeInBits(Ty).getFixedValue(); + // Make a copy of CandidateTys and iterate through it, because we + // might append to CandidateTys in the loop. + for (VectorType *const VTy : CandidateTysCopy) { + // The elements in the copy should remain invariant throughout the loop + assert(CandidateTysCopy[0] == OriginalElt && "Different Element"); + unsigned VectorSize = DL.getTypeSizeInBits(VTy).getFixedValue(); + unsigned ElementSize = + DL.getTypeSizeInBits(VTy->getElementType()).getFixedValue(); + if (TypeSize != VectorSize && TypeSize != ElementSize && + VectorSize % TypeSize == 0) { + VectorType *NewVTy = VectorType::get(Ty, VectorSize / TypeSize, false); + CheckCandidateType(NewVTy); + } + } + } + + return checkVectorTypesForPromotion(P, DL, CandidateTys, HaveCommonEltTy, + CommonEltTy, HaveVecPtrTy, + HaveCommonVecPtrTy, CommonVecPtrTy); +} + /// Test whether the given alloca partitioning and range of slices can be /// promoted to a vector. /// @@ -2271,6 +2306,7 @@ static VectorType *isVectorPromotionViable(Partition &P, const DataLayout &DL) { // we have different element types. SmallVector<VectorType *, 4> CandidateTys; SetVector<Type *> LoadStoreTys; + SetVector<Type *> DeferredTys; Type *CommonEltTy = nullptr; VectorType *CommonVecPtrTy = nullptr; bool HaveVecPtrTy = false; @@ -2314,42 +2350,32 @@ static VectorType *isVectorPromotionViable(Partition &P, const DataLayout &DL) { Ty = SI->getValueOperand()->getType(); else continue; + + auto CandTy = Ty->getScalarType(); + if (CandTy->isPointerTy() && (S.beginOffset() != P.beginOffset() || + S.endOffset() != P.endOffset())) { + DeferredTys.insert(Ty); + continue; + } + LoadStoreTys.insert(Ty); // Consider any loads or stores that are the exact size of the slice. if (S.beginOffset() == P.beginOffset() && S.endOffset() == P.endOffset()) CheckCandidateType(Ty); } - if (auto *VTy = checkVectorTypesForPromotion( - P, DL, CandidateTys, HaveCommonEltTy, CommonEltTy, HaveVecPtrTy, + SmallVector<VectorType *, 4> CandidateTysCopy = CandidateTys; + if (auto *VTy = createAndCheckVectorTypesForPromotion( + LoadStoreTys, CandidateTysCopy, CheckCandidateType, P, DL, + CandidateTys, HaveCommonEltTy, CommonEltTy, HaveVecPtrTy, HaveCommonVecPtrTy, CommonVecPtrTy)) return VTy; - // Consider additional vector types where the element type size is a - // multiple of load/store element size. - for (Type *Ty : LoadStoreTys) { - if (!VectorType::isValidElementType(Ty)) - continue; - unsigned TypeSize = DL.getTypeSizeInBits(Ty).getFixedValue(); - // Make a copy of CandidateTys and iterate through it, because we might - // append to CandidateTys in the loop. - SmallVector<VectorType *, 4> CandidateTysCopy = CandidateTys; - CandidateTys.clear(); - for (VectorType *&VTy : CandidateTysCopy) { - unsigned VectorSize = DL.getTypeSizeInBits(VTy).getFixedValue(); - unsigned ElementSize = - DL.getTypeSizeInBits(VTy->getElementType()).getFixedValue(); - if (TypeSize != VectorSize && TypeSize != ElementSize && - VectorSize % TypeSize == 0) { - VectorType *NewVTy = VectorType::get(Ty, VectorSize / TypeSize, false); - CheckCandidateType(NewVTy); - } - } - } - - return checkVectorTypesForPromotion(P, DL, CandidateTys, HaveCommonEltTy, - CommonEltTy, HaveVecPtrTy, - HaveCommonVecPtrTy, CommonVecPtrTy); + CandidateTys.clear(); + return createAndCheckVectorTypesForPromotion( + DeferredTys, CandidateTysCopy, CheckCandidateType, P, DL, CandidateTys, + HaveCommonEltTy, CommonEltTy, HaveVecPtrTy, HaveCommonVecPtrTy, + CommonVecPtrTy); } /// Test whether a slice of an alloca is valid for integer widening. |