Index: lib/Transforms/Scalar/LoopIdiomRecognize.cpp =================================================================== --- lib/Transforms/Scalar/LoopIdiomRecognize.cpp +++ lib/Transforms/Scalar/LoopIdiomRecognize.cpp @@ -108,7 +108,11 @@ private: typedef SmallVector StoreList; - StoreList StoreRefs; + StoreList StoreRefsForMemset; + StoreList StoreRefsForMemcpy; + bool HasMemset; + bool HasMemsetPattern; + bool HasMemcpy; /// \name Countable Loop Idiom Handling /// @{ @@ -118,17 +122,16 @@ SmallVectorImpl &ExitBlocks); void collectStores(BasicBlock *BB); - bool isLegalStore(StoreInst *SI); + bool isLegalStore(StoreInst *SI, bool &ForMemset, bool &ForMemcpy); bool processLoopStore(StoreInst *SI, const SCEV *BECount); bool processLoopMemSet(MemSetInst *MSI, const SCEV *BECount); bool processLoopStridedStore(Value *DestPtr, unsigned StoreSize, unsigned StoreAlignment, Value *SplatValue, - Instruction *TheStore, const SCEVAddRecExpr *Ev, - const SCEV *BECount, bool NegStride); - bool processLoopStoreOfLoopLoad(StoreInst *SI, unsigned StoreSize, - const SCEVAddRecExpr *StoreEv, - const SCEV *BECount, bool NegStride); + Constant *PatternValue, Instruction *TheStore, + const SCEVAddRecExpr *Ev, const SCEV *BECount, + bool NegStride); + bool processLoopStoreOfLoopLoad(StoreInst *SI, const SCEV *BECount); /// @} /// \name Noncountable Loop Idiom Handling @@ -207,8 +210,13 @@ *CurLoop->getHeader()->getParent()); DL = &CurLoop->getHeader()->getModule()->getDataLayout(); - if (SE->hasLoopInvariantBackedgeTakenCount(L)) - return runOnCountableLoop(); + HasMemset = TLI->has(LibFunc::memset); + HasMemsetPattern = TLI->has(LibFunc::memset_pattern16); + HasMemcpy = TLI->has(LibFunc::memcpy); + + if (HasMemset || HasMemsetPattern || HasMemcpy) + if (SE->hasLoopInvariantBackedgeTakenCount(L)) + return runOnCountableLoop(); return runOnNoncountableLoop(); } @@ -297,7 +305,8 @@ return ConstantArray::get(AT, std::vector(ArraySize, C)); } -bool LoopIdiomRecognize::isLegalStore(StoreInst *SI) { +bool LoopIdiomRecognize::isLegalStore(StoreInst *SI, bool &ForMemset, + bool &ForMemcpy) { // Don't touch volatile stores. if (!SI->isSimple()) return false; @@ -322,22 +331,96 @@ if (!isa(StoreEv->getOperand(1))) return false; + // turned into a memset of i8 -1, assuming that all the consecutive bytes + // are stored. A store of i32 0x01020304 can never be turned into a memset, + // but it can be turned into memset_pattern if the target supports it. + Value *SplatValue = isBytewiseValue(StoredVal); + Constant *PatternValue = nullptr; + unsigned DestAS = StorePtr->getType()->getPointerAddressSpace(); + + // If we're allowed to form a memset, and the stored value would be + // acceptable for memset, use it. + if (SplatValue && HasMemset && + // Verify that the stored value is loop invariant. If not, we can't + // promote the memset. + CurLoop->isLoopInvariant(SplatValue)) { + // Keep and use SplatValue. + PatternValue = nullptr; + ForMemset = true; + } else if (DestAS == 0 && HasMemsetPattern && + (PatternValue = getMemSetPatternValue(StoredVal, DL))) { + // Don't create memset_pattern16s with address spaces. + // It looks like we can use PatternValue! + SplatValue = nullptr; + ForMemset = true; + } else { + // Otherwise, this isn't an idiom we can transform. For example, we can't + // do anything with a 3-byte store. + ForMemset = false; + } + + if (ForMemset) + return true; + + // Looking for a store that can be turned into a memcpy. + if (HasMemcpy) { + ForMemcpy = true; + + // Check to see if the stride matches the size of the store. If so, then we + // know that every byte is touched in the loop. + unsigned Stride = getStoreStride(StoreEv); + unsigned StoreSize = getStoreSizeInBytes(SI, DL); + if (StoreSize != Stride && StoreSize != -Stride) { + ForMemcpy = false; + return false; + } + + // The store must be feeding a non-volatile load. + LoadInst *LI = dyn_cast(SI->getValueOperand()); + if (!LI || !LI->isSimple()) { + ForMemcpy = false; + return false; + } + + // See if the pointer expression is an AddRec like {base,+,1} on the current + // loop, which indicates a strided load. If we have something else, it's a + // random load we can't handle. + const SCEVAddRecExpr *LoadEv = + dyn_cast(SE->getSCEV(LI->getPointerOperand())); + if (!LoadEv || LoadEv->getLoop() != CurLoop || !LoadEv->isAffine()) { + ForMemcpy = false; + return false; + } + + // The store and load must share the same stride. + if (StoreEv->getOperand(1) != LoadEv->getOperand(1)) { + ForMemcpy = false; + return false; + } + } + return true; } void LoopIdiomRecognize::collectStores(BasicBlock *BB) { - StoreRefs.clear(); + StoreRefsForMemset.clear(); + StoreRefsForMemcpy.clear(); for (Instruction &I : *BB) { StoreInst *SI = dyn_cast(&I); if (!SI) continue; + bool ForMemset = false; + bool ForMemcpy = false; // Make sure this is a strided store with a constant stride. - if (!isLegalStore(SI)) + if (!isLegalStore(SI, ForMemset, ForMemcpy)) continue; // Save the store locations. - StoreRefs.push_back(SI); + if (ForMemset) + StoreRefsForMemset.push_back(SI); + else if (ForMemcpy) + StoreRefsForMemcpy.push_back(SI); } } @@ -357,9 +440,15 @@ bool MadeChange = false; // Look for store instructions, which may be optimized to memset/memcpy. collectStores(BB); - for (auto &SI : StoreRefs) + + // Look for a single store which can be optimized into a memset. + for (auto &SI : StoreRefsForMemset) MadeChange |= processLoopStore(SI, BECount); + // Optimize the store into a memcpy, if it feeds an similarly strided load. + for (auto &SI : StoreRefsForMemcpy) + MadeChange |= processLoopStoreOfLoopLoad(SI, BECount); + for (BasicBlock::iterator I = BB->begin(), E = BB->end(); I != E;) { Instruction *Inst = &*I++; // Look for memset instructions, which may be optimized to a larger memset. @@ -380,30 +469,35 @@ return MadeChange; } -/// processLoopStore - See if this store can be promoted to a memset or memcpy. +/// processLoopStore - See if this store can be promoted to a memset. bool LoopIdiomRecognize::processLoopStore(StoreInst *SI, const SCEV *BECount) { assert(SI->isSimple() && "Expected only non-volatile stores."); - Value *StoredVal = SI->getValueOperand(); - Value *StorePtr = SI->getPointerOperand(); - // Check to see if the stride matches the size of the store. If so, then we // know that every byte is touched in the loop. + Value *StorePtr = SI->getPointerOperand(); const SCEVAddRecExpr *StoreEv = cast(SE->getSCEV(StorePtr)); unsigned Stride = getStoreStride(StoreEv); unsigned StoreSize = getStoreSizeInBytes(SI, DL); - if (StoreSize != Stride && StoreSize != -Stride) + if (StoreSize != Stride && StoreSize != -Stride) return false; bool NegStride = StoreSize == -Stride; - // See if we can optimize just this store in isolation. - if (processLoopStridedStore(StorePtr, StoreSize, SI->getAlignment(), - StoredVal, SI, StoreEv, BECount, NegStride)) - return true; + Value *StoredVal = SI->getValueOperand(); + Value *SplatValue = isBytewiseValue(StoredVal); + Constant *PatternValue = nullptr; - // Optimize the store into a memcpy, if it feeds an similarly strided load. - return processLoopStoreOfLoopLoad(SI, StoreSize, StoreEv, BECount, NegStride); + if (!SplatValue && HasMemsetPattern) + PatternValue = getMemSetPatternValue(StoredVal, DL); + + assert((SplatValue || PatternValue) && + "Expected either splat value or pattern value."); + + // See if we can optimize just this store in isolation. + return processLoopStridedStore(StorePtr, StoreSize, SI->getAlignment(), + SplatValue, PatternValue, SI, StoreEv, BECount, + NegStride); } /// processLoopMemSet - See if this memset can be promoted to a large memset. @@ -441,8 +535,8 @@ return false; return processLoopStridedStore(Pointer, (unsigned)SizeInBytes, - MSI->getAlignment(), MSI->getValue(), MSI, Ev, - BECount, /*NegStride=*/false); + MSI->getAlignment(), MSI->getValue(), nullptr, + MSI, Ev, BECount, /*NegStride=*/false); } /// mayLoopAccessLocation - Return true if the specified loop might access the @@ -494,39 +588,12 @@ /// transform this into a memset or memset_pattern in the loop preheader, do so. bool LoopIdiomRecognize::processLoopStridedStore( Value *DestPtr, unsigned StoreSize, unsigned StoreAlignment, - Value *StoredVal, Instruction *TheStore, const SCEVAddRecExpr *Ev, - const SCEV *BECount, bool NegStride) { - - // If the stored value is a byte-wise value (like i32 -1), then it may be - // turned into a memset of i8 -1, assuming that all the consecutive bytes - // are stored. A store of i32 0x01020304 can never be turned into a memset, - // but it can be turned into memset_pattern if the target supports it. - Value *SplatValue = isBytewiseValue(StoredVal); - Constant *PatternValue = nullptr; - unsigned DestAS = DestPtr->getType()->getPointerAddressSpace(); - - // If we're allowed to form a memset, and the stored value would be acceptable - // for memset, use it. - if (SplatValue && TLI->has(LibFunc::memset) && - // Verify that the stored value is loop invariant. If not, we can't - // promote the memset. - CurLoop->isLoopInvariant(SplatValue)) { - // Keep and use SplatValue. - PatternValue = nullptr; - } else if (DestAS == 0 && TLI->has(LibFunc::memset_pattern16) && - (PatternValue = getMemSetPatternValue(StoredVal, DL))) { - // Don't create memset_pattern16s with address spaces. - // It looks like we can use PatternValue! - SplatValue = nullptr; - } else { - // Otherwise, this isn't an idiom we can transform. For example, we can't - // do anything with a 3-byte store. - return false; - } - + Value *SplatValue, Constant *PatternValue, Instruction *TheStore, + const SCEVAddRecExpr *Ev, const SCEV *BECount, bool NegStride) { // The trip count of the loop and the base pointer of the addrec SCEV is // guaranteed to be loop invariant, which means that it should dominate the // header. This allows us to insert code for it in the preheader. + unsigned DestAS = DestPtr->getType()->getPointerAddressSpace(); BasicBlock *Preheader = CurLoop->getLoopPreheader(); IRBuilder<> Builder(Preheader->getTerminator()); SCEVExpander Expander(*SE, *DL, "loop-idiom"); @@ -608,29 +675,25 @@ /// If the stored value is a strided load in the same loop with the same stride /// this may be transformable into a memcpy. This kicks in for stuff like /// for (i) A[i] = B[i]; -bool LoopIdiomRecognize::processLoopStoreOfLoopLoad( - StoreInst *SI, unsigned StoreSize, const SCEVAddRecExpr *StoreEv, - const SCEV *BECount, bool NegStride) { - // If we're not allowed to form memcpy, we fail. - if (!TLI->has(LibFunc::memcpy)) - return false; +bool LoopIdiomRecognize::processLoopStoreOfLoopLoad(StoreInst *SI, + const SCEV *BECount) { + assert(SI->isSimple() && "Expected only non-volatile stores."); + + Value *StorePtr = SI->getPointerOperand(); + const SCEVAddRecExpr *StoreEv = cast(SE->getSCEV(StorePtr)); + unsigned Stride = getStoreStride(StoreEv); + unsigned StoreSize = getStoreSizeInBytes(SI, DL); + bool NegStride = StoreSize == -Stride; // The store must be feeding a non-volatile load. - LoadInst *LI = dyn_cast(SI->getValueOperand()); - if (!LI || !LI->isSimple()) - return false; + LoadInst *LI = cast(SI->getValueOperand()); + assert(LI->isSimple() && "Expected only non-volatile stores."); // See if the pointer expression is an AddRec like {base,+,1} on the current // loop, which indicates a strided load. If we have something else, it's a // random load we can't handle. const SCEVAddRecExpr *LoadEv = - dyn_cast(SE->getSCEV(LI->getPointerOperand())); - if (!LoadEv || LoadEv->getLoop() != CurLoop || !LoadEv->isAffine()) - return false; - - // The store and load must share the same stride. - if (StoreEv->getOperand(1) != LoadEv->getOperand(1)) - return false; + cast(SE->getSCEV(LI->getPointerOperand())); // The trip count of the loop and the base pointer of the addrec SCEV is // guaranteed to be loop invariant, which means that it should dominate the