diff options
| -rw-r--r-- | llvm/docs/ReleaseNotes.rst | 4 | ||||
| -rw-r--r-- | llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp | 877 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopIdiom/bcmp-basic.ll | 855 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopIdiom/bcmp-debugify-remarks.ll | 119 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopIdiom/bcmp-negative-tests.ll | 2 | ||||
| -rw-r--r-- | llvm/test/Transforms/LoopIdiom/bcmp-widening.ll | 2 |
6 files changed, 588 insertions, 1271 deletions
diff --git a/llvm/docs/ReleaseNotes.rst b/llvm/docs/ReleaseNotes.rst index 10f76e527f0..c498b96cdde 100644 --- a/llvm/docs/ReleaseNotes.rst +++ b/llvm/docs/ReleaseNotes.rst @@ -50,10 +50,6 @@ Non-comprehensive list of changes in this release Makes programs 10x faster by doing Special New Thing. -* The Loop Idiom Recognition (``-loop-idiom``) pass has learned to recognize - ``bcmp`` pattern, and convert it into a call to ``bcmp`` (or ``memcmp``) - function. - Changes to the LLVM IR ---------------------- diff --git a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp index 17d83c4d6fc..e561494f19c 100644 --- a/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp +++ b/llvm/lib/Transforms/Scalar/LoopIdiomRecognize.cpp @@ -41,7 +41,6 @@ #include "llvm/ADT/ArrayRef.h" #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/MapVector.h" -#include "llvm/ADT/STLExtras.h" #include "llvm/ADT/SetVector.h" #include "llvm/ADT/SmallPtrSet.h" #include "llvm/ADT/SmallVector.h" @@ -78,20 +77,16 @@ #include "llvm/IR/LLVMContext.h" #include "llvm/IR/Module.h" #include "llvm/IR/PassManager.h" -#include "llvm/IR/PatternMatch.h" #include "llvm/IR/Type.h" #include "llvm/IR/User.h" #include "llvm/IR/Value.h" #include "llvm/IR/ValueHandle.h" -#include "llvm/IR/Verifier.h" #include "llvm/Pass.h" #include "llvm/Support/Casting.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Debug.h" #include "llvm/Support/raw_ostream.h" #include "llvm/Transforms/Scalar.h" -#include "llvm/Transforms/Scalar/LoopPassManager.h" -#include "llvm/Transforms/Utils/BasicBlockUtils.h" #include "llvm/Transforms/Utils/BuildLibCalls.h" #include "llvm/Transforms/Utils/Local.h" #include "llvm/Transforms/Utils/LoopUtils.h" @@ -107,7 +102,6 @@ using namespace llvm; STATISTIC(NumMemSet, "Number of memset's formed from loop stores"); STATISTIC(NumMemCpy, "Number of memcpy's formed from loop load+stores"); -STATISTIC(NumBCmp, "Number of memcmp's formed from loop 2xload+eq-compare"); static cl::opt<bool> UseLIRCodeSizeHeurs( "use-lir-code-size-heurs", @@ -117,26 +111,6 @@ static cl::opt<bool> UseLIRCodeSizeHeurs( namespace { -// FIXME: reinventing the wheel much? Is there a cleaner solution? -struct PMAbstraction { - virtual void markLoopAsDeleted(Loop *L) = 0; - virtual ~PMAbstraction() = default; -}; -struct LegacyPMAbstraction : PMAbstraction { - LPPassManager &LPM; - LegacyPMAbstraction(LPPassManager &LPM) : LPM(LPM) {} - virtual ~LegacyPMAbstraction() = default; - void markLoopAsDeleted(Loop *L) override { LPM.markLoopAsDeleted(*L); } -}; -struct NewPMAbstraction : PMAbstraction { - LPMUpdater &Updater; - NewPMAbstraction(LPMUpdater &Updater) : Updater(Updater) {} - virtual ~NewPMAbstraction() = default; - void markLoopAsDeleted(Loop *L) override { - Updater.markLoopAsDeleted(*L, L->getName()); - } -}; - class LoopIdiomRecognize { Loop *CurLoop = nullptr; AliasAnalysis *AA; @@ -146,7 +120,6 @@ class LoopIdiomRecognize { TargetLibraryInfo *TLI; const TargetTransformInfo *TTI; const DataLayout *DL; - PMAbstraction &LoopDeleter; OptimizationRemarkEmitter &ORE; bool ApplyCodeSizeHeuristics; @@ -155,10 +128,9 @@ public: LoopInfo *LI, ScalarEvolution *SE, TargetLibraryInfo *TLI, const TargetTransformInfo *TTI, - const DataLayout *DL, PMAbstraction &LoopDeleter, + const DataLayout *DL, OptimizationRemarkEmitter &ORE) - : AA(AA), DT(DT), LI(LI), SE(SE), TLI(TLI), TTI(TTI), DL(DL), - LoopDeleter(LoopDeleter), ORE(ORE) {} + : AA(AA), DT(DT), LI(LI), SE(SE), TLI(TLI), TTI(TTI), DL(DL), ORE(ORE) {} bool runOnLoop(Loop *L); @@ -172,8 +144,6 @@ private: bool HasMemset; bool HasMemsetPattern; bool HasMemcpy; - bool HasMemCmp; - bool HasBCmp; /// Return code for isLegalStore() enum LegalStoreKind { @@ -216,32 +186,6 @@ private: bool runOnNoncountableLoop(); - struct CmpLoopStructure { - Value *BCmpValue, *LatchCmpValue; - BasicBlock *HeaderBrEqualBB, *HeaderBrUnequalBB; - BasicBlock *LatchBrFinishBB, *LatchBrContinueBB; - }; - bool matchBCmpLoopStructure(CmpLoopStructure &CmpLoop) const; - struct CmpOfLoads { - ICmpInst::Predicate BCmpPred; - Value *LoadSrcA, *LoadSrcB; - Value *LoadA, *LoadB; - }; - bool matchBCmpOfLoads(Value *BCmpValue, CmpOfLoads &CmpOfLoads) const; - bool recognizeBCmpLoopControlFlow(const CmpOfLoads &CmpOfLoads, - CmpLoopStructure &CmpLoop) const; - bool recognizeBCmpLoopSCEV(uint64_t BCmpTyBytes, CmpOfLoads &CmpOfLoads, - const SCEV *&SrcA, const SCEV *&SrcB, - const SCEV *&Iterations) const; - bool detectBCmpIdiom(ICmpInst *&BCmpInst, CmpInst *&LatchCmpInst, - LoadInst *&LoadA, LoadInst *&LoadB, const SCEV *&SrcA, - const SCEV *&SrcB, const SCEV *&NBytes) const; - BasicBlock *transformBCmpControlFlow(ICmpInst *ComparedEqual); - void transformLoopToBCmp(ICmpInst *BCmpInst, CmpInst *LatchCmpInst, - LoadInst *LoadA, LoadInst *LoadB, const SCEV *SrcA, - const SCEV *SrcB, const SCEV *NBytes); - bool recognizeBCmp(); - bool recognizePopcount(); void transformLoopToPopcount(BasicBlock *PreCondBB, Instruction *CntInst, PHINode *CntPhi, Value *Var); @@ -278,14 +222,13 @@ public: &getAnalysis<TargetTransformInfoWrapperPass>().getTTI( *L->getHeader()->getParent()); const DataLayout *DL = &L->getHeader()->getModule()->getDataLayout(); - LegacyPMAbstraction LoopDeleter(LPM); // For the old PM, we can't use OptimizationRemarkEmitter as an analysis // pass. Function analyses need to be preserved across loop transformations // but ORE cannot be preserved (see comment before the pass definition). OptimizationRemarkEmitter ORE(L->getHeader()->getParent()); - LoopIdiomRecognize LIR(AA, DT, LI, SE, TLI, TTI, DL, LoopDeleter, ORE); + LoopIdiomRecognize LIR(AA, DT, LI, SE, TLI, TTI, DL, ORE); return LIR.runOnLoop(L); } @@ -304,7 +247,7 @@ char LoopIdiomRecognizeLegacyPass::ID = 0; PreservedAnalyses LoopIdiomRecognizePass::run(Loop &L, LoopAnalysisManager &AM, LoopStandardAnalysisResults &AR, - LPMUpdater &Updater) { + LPMUpdater &) { const auto *DL = &L.getHeader()->getModule()->getDataLayout(); const auto &FAM = @@ -318,9 +261,8 @@ PreservedAnalyses LoopIdiomRecognizePass::run(Loop &L, LoopAnalysisManager &AM, "LoopIdiomRecognizePass: OptimizationRemarkEmitterAnalysis not cached " "at a higher level"); - NewPMAbstraction LoopDeleter(Updater); LoopIdiomRecognize LIR(&AR.AA, &AR.DT, &AR.LI, &AR.SE, &AR.TLI, &AR.TTI, DL, - LoopDeleter, *ORE); + *ORE); if (!LIR.runOnLoop(&L)) return PreservedAnalyses::all(); @@ -357,8 +299,7 @@ bool LoopIdiomRecognize::runOnLoop(Loop *L) { // Disable loop idiom recognition if the function's name is a common idiom. StringRef Name = L->getHeader()->getParent()->getName(); - if (Name == "memset" || Name == "memcpy" || Name == "memcmp" || - Name == "bcmp") + if (Name == "memset" || Name == "memcpy") return false; // Determine if code size heuristics need to be applied. @@ -368,10 +309,8 @@ bool LoopIdiomRecognize::runOnLoop(Loop *L) { HasMemset = TLI->has(LibFunc_memset); HasMemsetPattern = TLI->has(LibFunc_memset_pattern16); HasMemcpy = TLI->has(LibFunc_memcpy); - HasMemCmp = TLI->has(LibFunc_memcmp); - HasBCmp = TLI->has(LibFunc_bcmp); - if (HasMemset || HasMemsetPattern || HasMemcpy || HasMemCmp || HasBCmp) + if (HasMemset || HasMemsetPattern || HasMemcpy) if (SE->hasLoopInvariantBackedgeTakenCount(L)) return runOnCountableLoop(); @@ -1210,7 +1149,7 @@ bool LoopIdiomRecognize::runOnNoncountableLoop() { << "] Noncountable Loop %" << CurLoop->getHeader()->getName() << "\n"); - return recognizeBCmp() || recognizePopcount() || recognizeAndInsertFFS(); + return recognizePopcount() || recognizeAndInsertFFS(); } /// Check if the given conditional branch is based on the comparison between @@ -1884,803 +1823,3 @@ void LoopIdiomRecognize::transformLoopToPopcount(BasicBlock *PreCondBB, // loop. The loop would otherwise not be deleted even if it becomes empty. SE->forgetLoop(CurLoop); } - -bool LoopIdiomRecognize::matchBCmpLoopStructure( - CmpLoopStructure &CmpLoop) const { - ICmpInst::Predicate BCmpPred; - - // We are looking for the following basic layout: - // PreheaderBB: <preheader> ; preds = ??? - // <...> - // br label %LoopHeaderBB - // LoopHeaderBB: <header,exiting> ; preds = %PreheaderBB,%LoopLatchBB - // <...> - // %BCmpValue = icmp <...> - // br i1 %BCmpValue, label %LoopLatchBB, label %Successor0 - // LoopLatchBB: <latch,exiting> ; preds = %LoopHeaderBB - // <...> - // %LatchCmpValue = <are we done, or do next iteration?> - // br i1 %LatchCmpValue, label %Successor1, label %LoopHeaderBB - // Successor0: <exit> ; preds = %LoopHeaderBB - // <...> - // Successor1: <exit> ; preds = %LoopLatchBB - // <...> - // - // Successor0 and Successor1 may or may not be the same basic block. - - // Match basic frame-work of this supposedly-comparison loop. - using namespace PatternMatch; - if (!match(CurLoop->getHeader()->getTerminator(), - m_Br(m_CombineAnd(m_ICmp(BCmpPred, m_Value(), m_Value()), - m_Value(CmpLoop.BCmpValue)), - CmpLoop.HeaderBrEqualBB, CmpLoop.HeaderBrUnequalBB)) || - !match(CurLoop->getLoopLatch()->getTerminator(), - m_Br(m_CombineAnd(m_Cmp(), m_Value(CmpLoop.LatchCmpValue)), - CmpLoop.LatchBrFinishBB, CmpLoop.LatchBrContinueBB))) { - LLVM_DEBUG(dbgs() << "Basic control-flow layout unrecognized.\n"); - return false; - } - LLVM_DEBUG(dbgs() << "Recognized basic control-flow layout.\n"); - return true; -} - -bool LoopIdiomRecognize::matchBCmpOfLoads(Value *BCmpValue, - CmpOfLoads &CmpOfLoads) const { - using namespace PatternMatch; - LLVM_DEBUG(dbgs() << "Analyzing header icmp " << *BCmpValue - << " as bcmp pattern.\n"); - - // Match bcmp-style loop header cmp. It must be an eq-icmp of loads. Example: - // %v0 = load <...>, <...>* %LoadSrcA - // %v1 = load <...>, <...>* %LoadSrcB - // %CmpLoop.BCmpValue = icmp eq <...> %v0, %v1 - // There won't be any no-op bitcasts between load and icmp, - // they would have been transformed into a load of bitcast. - // FIXME: {b,mem}cmp() calls have the same semantics as icmp. Match them too. - if (!match(BCmpValue, - m_ICmp(CmpOfLoads.BCmpPred, - m_CombineAnd(m_Load(m_Value(CmpOfLoads.LoadSrcA)), - m_Value(CmpOfLoads.LoadA)), - m_CombineAnd(m_Load(m_Value(CmpOfLoads.LoadSrcB)), - m_Value(CmpOfLoads.LoadB)))) || - !ICmpInst::isEquality(CmpOfLoads.BCmpPred)) { - LLVM_DEBUG(dbgs() << "Loop header icmp did not match bcmp pattern.\n"); - return false; - } - LLVM_DEBUG(dbgs() << "Recognized header icmp as bcmp pattern with loads:\n\t" - << *CmpOfLoads.LoadA << "\n\t" << *CmpOfLoads.LoadB - << "\n"); - // FIXME: handle memcmp pattern? - return true; -} - -bool LoopIdiomRecognize::recognizeBCmpLoopControlFlow( - const CmpOfLoads &CmpOfLoads, CmpLoopStructure &CmpLoop) const { - BasicBlock *LoopHeaderBB = CurLoop->getHeader(); - BasicBlock *LoopLatchBB = CurLoop->getLoopLatch(); - - // Be wary, comparisons can be inverted, canonicalize order. - // If this 'element' comparison passed, we expect to proceed to the next elt. - if (CmpOfLoads.BCmpPred != ICmpInst::Predicate::ICMP_EQ) - std::swap(CmpLoop.HeaderBrEqualBB, CmpLoop.HeaderBrUnequalBB); - // The predicate on loop latch does not matter, just canonicalize some order. - if (CmpLoop.LatchBrContinueBB != LoopHeaderBB) - std::swap(CmpLoop.LatchBrFinishBB, CmpLoop.LatchBrContinueBB); - - // Check that control-flow between blocks is as expected. - if (CmpLoop.HeaderBrEqualBB != LoopLatchBB || - CmpLoop.LatchBrContinueBB != LoopHeaderBB) { - LLVM_DEBUG(dbgs() << "Loop control-flow not recognized.\n"); - return false; - } - - SmallVector<BasicBlock *, 2> ExitBlocks; - CurLoop->getUniqueExitBlocks(ExitBlocks); - assert(ExitBlocks.size() <= 2U && "Can't have more than two exit blocks."); - - assert(!is_contained(ExitBlocks, CmpLoop.HeaderBrEqualBB) && - is_contained(ExitBlocks, CmpLoop.HeaderBrUnequalBB) && - !is_contained(ExitBlocks, CmpLoop.LatchBrContinueBB) && - is_contained(ExitBlocks, CmpLoop.LatchBrFinishBB) && - "Unexpected exit edges."); - - LLVM_DEBUG(dbgs() << "Recognized loop control-flow.\n"); - - LLVM_DEBUG(dbgs() << "Performing side-effect analysis on the loop.\n"); - assert(CurLoop->isLCSSAForm(*DT) && "Should only get LCSSA-form loops here."); - // No loop instructions must be used outside of the loop. Since we are in - // LCSSA form, we only need to check successor block's PHI nodes's incoming - // values for incoming blocks that are the loop basic blocks. - for (const BasicBlock *ExitBB : ExitBlocks) { - for (const PHINode &PHI : ExitBB->phis()) { - for (const BasicBlock *LoopBB : - make_filter_range(PHI.blocks(), [this](BasicBlock *PredecessorBB) { - return CurLoop->contains(PredecessorBB); - })) { - const auto *I = - dyn_cast<Instruction>(PHI.getIncomingValueForBlock(LoopBB)); - if (I && CurLoop->contains(I)) { - LLVM_DEBUG(dbgs() - << "Loop contains instruction " << *I - << " which is used outside of the loop in basic block " - << ExitBB->getName() << " in phi node " << PHI << "\n"); - return false; - } - } - } - } - // Similarly, the loop should not have any other observable side-effects - // other than the final comparison result. - for (BasicBlock *LoopBB : CurLoop->blocks()) { - for (Instruction &I : *LoopBB) { - if (isa<DbgInfoIntrinsic>(I)) // Ignore dbginfo. - continue; // FIXME: anything else? lifetime info? - if ((I.mayHaveSideEffects() || I.isAtomic() || I.isFenceLike()) && - &I != CmpOfLoads.LoadA && &I != CmpOfLoads.LoadB) { - LLVM_DEBUG( - dbgs() << "Loop contains instruction with potential side-effects: " - << I << "\n"); - return false; - } - } - } - LLVM_DEBUG(dbgs() << "No loop instructions deemed to have side-effects.\n"); - return true; -} - -bool LoopIdiomRecognize::recognizeBCmpLoopSCEV(uint64_t BCmpTyBytes, - CmpOfLoads &CmpOfLoads, - const SCEV *&SrcA, - const SCEV *&SrcB, - const SCEV *&Iterations) const { - // Try to compute SCEV of the loads, for this loop's scope. - const auto *ScevForSrcA = dyn_cast<SCEVAddRecExpr>( - SE->getSCEVAtScope(CmpOfLoads.LoadSrcA, CurLoop)); - const auto *ScevForSrcB = dyn_cast<SCEVAddRecExpr>( - SE->getSCEVAtScope(CmpOfLoads.LoadSrcB, CurLoop)); - if (!ScevForSrcA || !ScevForSrcB) { - LLVM_DEBUG(dbgs() << "Failed to get SCEV expressions for load sources.\n"); - return false; - } - - LLVM_DEBUG(dbgs() << "Got SCEV expressions (at loop scope) for loads:\n\t" - << *ScevForSrcA << "\n\t" << *ScevForSrcB << "\n"); - - // Loads must have folloving SCEV exprs: {%ptr,+,BCmpTyBytes}<%LoopHeaderBB> - const SCEV *RecStepForA = ScevForSrcA->getStepRecurrence(*SE); - const SCEV *RecStepForB = ScevForSrcB->getStepRecurrence(*SE); - if (!ScevForSrcA->isAffine() || !ScevForSrcB->isAffine() || - RecStepForA != RecStepForB || !isa<SCEVConstant>(RecStepForA) || - cast<SCEVConstant>(RecStepForA)->getAPInt() != BCmpTyBytes) { - LLVM_DEBUG( - dbgs() << "Unsupported SCEV expressions for loads. Only support affine " - "SCEV expressions with identical constant positive step, " - "equal to the count of bytes compared. Got:\n\t" - << *RecStepForA << "\n\t" << *RecStepForB << "\n"); - return false; - // FIXME: can support BCmpTyBytes > Step. - // But will need to account for the extra bytes compared at the end. - } - - SrcA = ScevForSrcA->getStart(); - SrcB = ScevForSrcB->getStart(); - LLVM_DEBUG(dbgs() << "Got SCEV expressions for load sources:\n\t" << *SrcA - << "\n\t" << *SrcB << "\n"); - - // The load sources must be loop-invants that dominate the loop header. - if (SrcA == SE->getCouldNotCompute() || SrcB == SE->getCouldNotCompute() || - !SE->isAvailableAtLoopEntry(SrcA, CurLoop) || - !SE->isAvailableAtLoopEntry(SrcB, CurLoop)) { - LLVM_DEBUG(dbgs() << "Unsupported SCEV expressions for loads, unavaliable " - "prior to loop header.\n"); - return false; - } - - LLVM_DEBUG(dbgs() << "SCEV expressions for loads are acceptable.\n"); - - // For how many iterations is loop guaranteed not to exit via LoopLatch? - // This is one less than the maximal number of comparisons,and is: n + -1 - const SCEV *LoopExitCount = - SE->getExitCount(CurLoop, CurLoop->getLoopLatch()); - LLVM_DEBUG(dbgs() << "Got SCEV expression for loop latch exit count: " - << *LoopExitCount << "\n"); - // Exit count, similarly, must be loop-invant that dominates the loop header. - if (LoopExitCount == SE->getCouldNotCompute() || - !LoopExitCount->getType()->isIntOrPtrTy() || - !SE->isAvailableAtLoopEntry(LoopExitCount, CurLoop)) { - LLVM_DEBUG(dbgs() << "Unsupported SCEV expression for loop latch exit.\n"); - return false; - } - - // LoopExitCount is always one less than the actual count of iterations. - // Do this before cast, else we will be stuck with 1 + zext(-1 + n) - Iterations = SE->getAddExpr( - LoopExitCount, SE->getOne(LoopExitCount->getType()), SCEV::FlagNUW); - assert(Iterations != SE->getCouldNotCompute() && - "Shouldn't fail to increment by one."); - - LLVM_DEBUG(dbgs() << "Computed iteration count: " << *Iterations << "\n"); - return true; -} - -/// Return true iff the bcmp idiom is detected in the loop. -/// -/// Additionally: -/// 1) \p BCmpInst is set to the root byte-comparison instruction. -/// 2) \p LatchCmpInst is set to the comparison that controls the latch. -/// 3) \p LoadA is set to the first LoadInst. -/// 4) \p LoadB is set to the second LoadInst. -/// 5) \p SrcA is set to the first source location that is being compared. -/// 6) \p SrcB is set to the second source location that is being compared. -/// 7) \p NBytes is set to the number of bytes to compare. -bool LoopIdiomRecognize::detectBCmpIdiom(ICmpInst *&BCmpInst, - CmpInst *&LatchCmpInst, - LoadInst *&LoadA, LoadInst *&LoadB, - const SCEV *&SrcA, const SCEV *&SrcB, - const SCEV *&NBytes) const { - LLVM_DEBUG(dbgs() << "Recognizing bcmp idiom\n"); - - // Give up if the loop is not in normal form, or has more than 2 blocks. - if (!CurLoop->isLoopSimplifyForm() || CurLoop->getNumBlocks() > 2) { - LLVM_DEBUG(dbgs() << "Basic loop structure unrecognized.\n"); - return false; - } - LLVM_DEBUG(dbgs() << "Recognized basic loop structure.\n"); - - CmpLoopStructure CmpLoop; - if (!matchBCmpLoopStructure(CmpLoop)) - return false; - - CmpOfLoads CmpOfLoads; - if (!matchBCmpOfLoads(CmpLoop.BCmpValue, CmpOfLoads)) - return false; - - if (!recognizeBCmpLoopControlFlow(CmpOfLoads, CmpLoop)) - return false; - - BCmpInst = cast<ICmpInst>(CmpLoop.BCmpValue); // FIXME: is there no - LatchCmpInst = cast<CmpInst>(CmpLoop.LatchCmpValue); // way to combine - LoadA = cast<LoadInst>(CmpOfLoads.LoadA); // these cast with - LoadB = cast<LoadInst>(CmpOfLoads.LoadB); // m_Value() matcher? - - Type *BCmpValTy = BCmpInst->getOperand(0)->getType(); - LLVMContext &Context = BCmpValTy->getContext(); - uint64_t BCmpTyBits = DL->getTypeSizeInBits(BCmpValTy); - static constexpr uint64_t ByteTyBits = 8; - - LLVM_DEBUG(dbgs() << "Got comparison between values of type " << *BCmpValTy - << " of size " << BCmpTyBits - << " bits (while byte = " << ByteTyBits << " bits).\n"); - // bcmp()/memcmp() minimal unit of work is a byte. Therefore we must check - // that we are dealing with a multiple of a byte here. - if (BCmpTyBits % ByteTyBits != 0) { - LLVM_DEBUG(dbgs() << "Value size is not a multiple of byte.\n"); - return false; - // FIXME: could still be done under a run-time check that the total bit - // count is a multiple of a byte i guess? Or handle remainder separately? - } - - // Each comparison is done on this many bytes. - uint64_t BCmpTyBytes = BCmpTyBits / ByteTyBits; - LLVM_DEBUG(dbgs() << "Size is exactly " << BCmpTyBytes - << " bytes, eligible for bcmp conversion.\n"); - - const SCEV *Iterations; - if (!recognizeBCmpLoopSCEV(BCmpTyBytes, CmpOfLoads, SrcA, SrcB, Iterations)) - return false; - - // bcmp / memcmp take length argument as size_t, do promotion now. - Type *CmpFuncSizeTy = DL->getIntPtrType(Context); - Iterations = SE->getNoopOrZeroExtend(Iterations, CmpFuncSizeTy); - assert(Iterations != SE->getCouldNotCompute() && "Promotion failed."); - // Note that it didn't do ptrtoint cast, we will need to do it manually. - - // We will be comparing *bytes*, not BCmpTy, we need to recalculate size. - // It's a multiplication, and it *could* overflow. But for it to overflow - // we'd want to compare more bytes than could be represented by size_t, But - // allocation functions also take size_t. So how'd you produce such buffer? - // FIXME: we likely need to actually check that we know this won't overflow, - // via llvm::computeOverflowForUnsignedMul(). - NBytes = SE->getMulExpr( - Iterations, SE->getConstant(CmpFuncSizeTy, BCmpTyBytes), SCEV::FlagNUW); - assert(NBytes != SE->getCouldNotCompute() && - "Shouldn't fail to increment by one."); - - LLVM_DEBUG(dbgs() << "Computed total byte count: " << *NBytes << "\n"); - - if (LoadA->getPointerAddressSpace() != LoadB->getPointerAddressSpace() || - LoadA->getPointerAddressSpace() != 0 || !LoadA->isSimple() || - !LoadB->isSimple()) { - StringLiteral L("Unsupported loads in idiom - only support identical, " - "simple loads from address space 0.\n"); - LLVM_DEBUG(dbgs() << L); - ORE.emit([&]() { - return OptimizationRemarkMissed(DEBUG_TYPE, "BCmpIdiomUnsupportedLoads", - BCmpInst->getDebugLoc(), - CurLoop->getHeader()) - << L; - }); - return false; // FIXME - } - - LLVM_DEBUG(dbgs() << "Recognized bcmp idiom\n"); - ORE.emit([&]() { - return OptimizationRemarkAnalysis(DEBUG_TYPE, "RecognizedBCmpIdiom", - CurLoop->getStartLoc(), - CurLoop->getHeader()) - << "Loop recognized as a bcmp idiom"; - }); - - return true; -} - -BasicBlock * -LoopIdiomRecognize::transformBCmpControlFlow(ICmpInst *ComparedEqual) { - LLVM_DEBUG(dbgs() << "Transforming control-flow.\n"); - SmallVector<DominatorTree::UpdateType, 8> DTUpdates; - - BasicBlock *PreheaderBB = CurLoop->getLoopPreheader(); - BasicBlock *HeaderBB = CurLoop->getHeader(); - BasicBlock *LoopLatchBB = CurLoop->getLoopLatch(); - SmallString<32> LoopName = CurLoop->getName(); - Function *Func = PreheaderBB->getParent(); - LLVMContext &Context = Func->getContext(); - - // Before doing anything, drop SCEV info. - SE->forgetLoop(CurLoop); - - // Here we start with: (0/6) - // PreheaderBB: <preheader> ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // br label %LoopHeaderBB - // LoopHeaderBB: <header,exiting> ; preds = %PreheaderBB,%LoopLatchBB - // <...> - // br i1 %<...>, label %LoopLatchBB, label %Successor0BB - // LoopLatchBB: <latch,exiting> ; preds = %LoopHeaderBB - // <...> - // br i1 %<...>, label %Successor1BB, label %LoopHeaderBB - // Successor0BB: <exit> ; preds = %LoopHeaderBB - // %S0PHI = phi <...> [ <...>, %LoopHeaderBB ] - // <...> - // Successor1BB: <exit> ; preds = %LoopLatchBB - // %S1PHI = phi <...> [ <...>, %LoopLatchBB ] - // <...> - // - // Successor0 and Successor1 may or may not be the same basic block. - - // Decouple the edge between loop preheader basic block and loop header basic - // block. Thus the loop has become unreachable. - assert(cast<BranchInst>(PreheaderBB->getTerminator())->isUnconditional() && - PreheaderBB->getTerminator()->getSuccessor(0) == HeaderBB && - "Preheader bb must end with an unconditional branch to header bb."); - PreheaderBB->getTerminator()->eraseFromParent(); - DTUpdates.push_back({DominatorTree::Delete, PreheaderBB, HeaderBB}); - - // Create a new preheader basic block before loop header basic block. - auto *PhonyPreheaderBB = BasicBlock::Create( - Context, LoopName + ".phonypreheaderbb", Func, HeaderBB); - // And insert an unconditional branch from phony preheader basic block to - // loop header basic block. - IRBuilder<>(PhonyPreheaderBB).CreateBr(HeaderBB); - DTUpdates.push_back({DominatorTree::Insert, PhonyPreheaderBB, HeaderBB}); - - // Create a *single* new empty block that we will substitute as a - // successor basic block for the loop's exits. This one is temporary. - // Much like phony preheader basic block, it is not connected. - auto *PhonySuccessorBB = - BasicBlock::Create(Context, LoopName + ".phonysuccessorbb", Func, - LoopLatchBB->getNextNode()); - // That block must have *some* non-PHI instruction, or else deleteDeadLoop() - // will mess up cleanup of dbginfo, and verifier will complain. - IRBuilder<>(PhonySuccessorBB).CreateUnreachable(); - - // Create two new empty blocks that we will use to preserve the original - // loop exit control-flow, and preserve the incoming values in the PHI nodes - // in loop's successor exit blocks. These will live one. - auto *ComparedUnequalBB = - BasicBlock::Create(Context, ComparedEqual->getName() + ".unequalbb", Func, - PhonySuccessorBB->getNextNode()); - auto *ComparedEqualBB = - BasicBlock::Create(Context, ComparedEqual->getName() + ".equalbb", Func, - PhonySuccessorBB->getNextNode()); - - // By now we have: (1/6) - // PreheaderBB: ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // [no terminator instruction!] - // PhonyPreheaderBB: <preheader> ; No preds, UNREACHABLE! - // br label %LoopHeaderBB - // LoopHeaderBB: <header,exiting> ; preds = %PhonyPreheaderBB, %LoopLatchBB - // <...> - // br i1 %<...>, label %LoopLatchBB, label %Successor0BB - // LoopLatchBB: <latch,exiting> ; preds = %LoopHeaderBB - // <...> - // br i1 %<...>, label %Successor1BB, label %LoopHeaderBB - // PhonySuccessorBB: ; No preds, UNREACHABLE! - // unreachable - // EqualBB: ; No preds, UNREACHABLE! - // [no terminator instruction!] - // UnequalBB: ; No preds, UNREACHABLE! - // [no terminator instruction!] - // Successor0BB: <exit> ; preds = %LoopHeaderBB - // %S0PHI = phi <...> [ <...>, %LoopHeaderBB ] - // <...> - // Successor1BB: <exit> ; preds = %LoopLatchBB - // %S1PHI = phi <...> [ <...>, %LoopLatchBB ] - // <...> - - // What is the mapping/replacement basic block for exiting out of the loop - // from either of old's loop basic blocks? - auto GetReplacementBB = [this, ComparedEqualBB, - ComparedUnequalBB](const BasicBlock *OldBB) { - assert(CurLoop->contains(OldBB) && "Only for loop's basic blocks."); - if (OldBB == CurLoop->getLoopLatch()) // "all elements compared equal". - return ComparedEqualBB; - if (OldBB == CurLoop->getHeader()) // "element compared unequal". - return ComparedUnequalBB; - llvm_unreachable("Only had two basic blocks in loop."); - }; - - // What are the exits out of this loop? - SmallVector<Loop::Edge, 2> LoopExitEdges; - CurLoop->getExitEdges(LoopExitEdges); - assert(LoopExitEdges.size() == 2 && "Should have only to two exit edges."); - - // Populate new basic blocks, update the exiting control-flow, PHI nodes. - for (const Loop::Edge &Edge : LoopExitEdges) { - auto *OldLoopBB = const_cast<BasicBlock *>(Edge.first); - auto *SuccessorBB = const_cast<BasicBlock *>(Edge.second); - assert(CurLoop->contains(OldLoopBB) && !CurLoop->contains(SuccessorBB) && - "Unexpected edge."); - - // If we would exit the loop from this loop's basic block, - // what semantically would that mean? Did comparison succeed or fail? - BasicBlock *NewBB = GetReplacementBB(OldLoopBB); - assert(NewBB->empty() && "Should not get same new basic block here twice."); - IRBuilder<> Builder(NewBB); - Builder.SetCurrentDebugLocation(OldLoopBB->getTerminator()->getDebugLoc()); - Builder.CreateBr(SuccessorBB); - DTUpdates.push_back({DominatorTree::Insert, NewBB, SuccessorBB}); - // Also, be *REALLY* careful with PHI nodes in successor basic block, - // update them to recieve the same input value, but not from current loop's - // basic block, but from new basic block instead. - SuccessorBB->replacePhiUsesWith(OldLoopBB, NewBB); - // Also, change loop control-flow. This loop's basic block shall no longer - // exit from the loop to it's original successor basic block, but to our new - // phony successor basic block. Note that new successor will be unique exit. - OldLoopBB->getTerminator()->replaceSuccessorWith(SuccessorBB, - PhonySuccessorBB); - DTUpdates.push_back({DominatorTree::Delete, OldLoopBB, SuccessorBB}); - DTUpdates.push_back({DominatorTree::Insert, OldLoopBB, PhonySuccessorBB}); - } - - // Inform DomTree about edge changes. Note that LoopInfo is still out-of-date. - assert(DTUpdates.size() == 8 && "Update count prediction failed."); - DomTreeUpdater DTU(DT, DomTreeUpdater::UpdateStrategy::Eager); - DTU.applyUpdates(DTUpdates); - DTUpdates.clear(); - - // By now we have: (2/6) - // PreheaderBB: ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // [no terminator instruction!] - // PhonyPreheaderBB: <preheader> ; No preds, UNREACHABLE! - // br label %LoopHeaderBB - // LoopHeaderBB: <header,exiting> ; preds = %PhonyPreheaderBB, %LoopLatchBB - // <...> - // br i1 %<...>, label %LoopLatchBB, label %PhonySuccessorBB - // LoopLatchBB: <latch,exiting> ; preds = %LoopHeaderBB - // <...> - // br i1 %<...>, label %PhonySuccessorBB, label %LoopHeaderBB - // PhonySuccessorBB: <uniq. exit> ; preds = %LoopHeaderBB, %LoopLatchBB - // unreachable - // EqualBB: ; No preds, UNREACHABLE! - // br label %Successor1BB - // UnequalBB: ; No preds, UNREACHABLE! - // br label %Successor0BB - // Successor0BB: ; preds = %UnequalBB - // %S0PHI = phi <...> [ <...>, %UnequalBB ] - // <...> - // Successor1BB: ; preds = %EqualBB - // %S0PHI = phi <...> [ <...>, %EqualBB ] - // <...> - - // *Finally*, zap the original loop. Record it's parent loop though. - Loop *ParentLoop = CurLoop->getParentLoop(); - LLVM_DEBUG(dbgs() << "Deleting old loop.\n"); - LoopDeleter.markLoopAsDeleted(CurLoop); // Mark as deleted *BEFORE* deleting! - deleteDeadLoop(CurLoop, DT, SE, LI); // And actually delete the loop. - CurLoop = nullptr; - - // By now we have: (3/6) - // PreheaderBB: ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // [no terminator instruction!] - // PhonyPreheaderBB: ; No preds, UNREACHABLE! - // br label %PhonySuccessorBB - // PhonySuccessorBB: ; preds = %PhonyPreheaderBB - // unreachable - // EqualBB: ; No preds, UNREACHABLE! - // br label %Successor1BB - // UnequalBB: ; No preds, UNREACHABLE! - // br label %Successor0BB - // Successor0BB: ; preds = %UnequalBB - // %S0PHI = phi <...> [ <...>, %UnequalBB ] - // <...> - // Successor1BB: ; preds = %EqualBB - // %S0PHI = phi <...> [ <...>, %EqualBB ] - // <...> - - // Now, actually restore the CFG. - - // Insert an unconditional branch from an actual preheader basic block to - // phony preheader basic block. - IRBuilder<>(PreheaderBB).CreateBr(PhonyPreheaderBB); - DTUpdates.push_back({DominatorTree::Insert, PhonyPreheaderBB, HeaderBB}); - // Insert proper conditional branch from phony successor basic block to the - // "dispatch" basic blocks, which were used to preserve incoming values in - // original loop's successor basic blocks. - assert(isa<UnreachableInst>(PhonySuccessorBB->getTerminator()) && - "Yep, that's the one we created to keep deleteDeadLoop() happy."); - PhonySuccessorBB->getTerminator()->eraseFromParent(); - { - IRBuilder<> Builder(PhonySuccessorBB); - Builder.SetCurrentDebugLocation(ComparedEqual->getDebugLoc()); - Builder.CreateCondBr(ComparedEqual, ComparedEqualBB, ComparedUnequalBB); - } - DTUpdates.push_back( - {DominatorTree::Insert, PhonySuccessorBB, ComparedEqualBB}); - DTUpdates.push_back( - {DominatorTree::Insert, PhonySuccessorBB, ComparedUnequalBB}); - - BasicBlock *DispatchBB = PhonySuccessorBB; - DispatchBB->setName(LoopName + ".bcmpdispatchbb"); - - assert(DTUpdates.size() == 3 && "Update count prediction failed."); - DTU.applyUpdates(DTUpdates); - DTUpdates.clear(); - - // By now we have: (4/6) - // PreheaderBB: ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // br label %PhonyPreheaderBB - // PhonyPreheaderBB: ; preds = %PreheaderBB - // br label %DispatchBB - // DispatchBB: ; preds = %PhonyPreheaderBB - // br i1 %ComparedEqual, label %EqualBB, label %UnequalBB - // EqualBB: ; preds = %DispatchBB - // br label %Successor1BB - // UnequalBB: ; preds = %DispatchBB - // br label %Successor0BB - // Successor0BB: ; preds = %UnequalBB - // %S0PHI = phi <...> [ <...>, %UnequalBB ] - // <...> - // Successor1BB: ; preds = %EqualBB - // %S0PHI = phi <...> [ <...>, %EqualBB ] - // <...> - - // The basic CFG has been restored! Now let's merge redundant basic blocks. - - // Merge phony successor basic block into it's only predecessor, - // phony preheader basic block. It is fully pointlessly redundant. - MergeBasicBlockIntoOnlyPred(DispatchBB, &DTU); - - // By now we have: (5/6) - // PreheaderBB: ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // br label %DispatchBB - // DispatchBB: ; preds = %PreheaderBB - // br i1 %ComparedEqual, label %EqualBB, label %UnequalBB - // EqualBB: ; preds = %DispatchBB - // br label %Successor1BB - // UnequalBB: ; preds = %DispatchBB - // br label %Successor0BB - // Successor0BB: ; preds = %UnequalBB - // %S0PHI = phi <...> [ <...>, %UnequalBB ] - // <...> - // Successor1BB: ; preds = %EqualBB - // %S0PHI = phi <...> [ <...>, %EqualBB ] - // <...> - - // Was this loop nested? - if (!ParentLoop) { - // If the loop was *NOT* nested, then let's also merge phony successor - // basic block into it's only predecessor, preheader basic block. - // Also, here we need to update LoopInfo. - LI->removeBlock(PreheaderBB); - MergeBasicBlockIntoOnlyPred(DispatchBB, &DTU); - - // By now we have: (6/6) - // DispatchBB: ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // br i1 %ComparedEqual, label %EqualBB, label %UnequalBB - // EqualBB: ; preds = %DispatchBB - // br label %Successor1BB - // UnequalBB: ; preds = %DispatchBB - // br label %Successor0BB - // Successor0BB: ; preds = %UnequalBB - // %S0PHI = phi <...> [ <...>, %UnequalBB ] - // <...> - // Successor1BB: ; preds = %EqualBB - // %S0PHI = phi <...> [ <...>, %EqualBB ] - // <...> - - return DispatchBB; - } - - // Otherwise, we need to "preserve" the LoopSimplify form of the deleted loop. - // To achieve that, we shall keep the preheader basic block (mainly so that - // the loop header block will be guaranteed to have a predecessor outside of - // the loop), and create a phony loop with all these new three basic blocks. - Loop *PhonyLoop = LI->AllocateLoop(); - ParentLoop->addChildLoop(PhonyLoop); - PhonyLoop->addBasicBlockToLoop(DispatchBB, *LI); - PhonyLoop->addBasicBlockToLoop(ComparedEqualBB, *LI); - PhonyLoop->addBasicBlockToLoop(ComparedUnequalBB, *LI); - - // But we only have a preheader basic block, a header basic block block and - // two exiting basic blocks. For a proper loop we also need a backedge from - // non-header basic block to header bb. - // Let's just add a never-taken branch from both of the exiting basic blocks. - for (BasicBlock *BB : {ComparedEqualBB, ComparedUnequalBB}) { - BranchInst *OldTerminator = cast<BranchInst>(BB->getTerminator()); - assert(OldTerminator->isUnconditional() && "That's the one we created."); - BasicBlock *SuccessorBB = OldTerminator->getSuccessor(0); - - IRBuilder<> Builder(OldTerminator); - Builder.SetCurrentDebugLocation(OldTerminator->getDebugLoc()); - Builder.CreateCondBr(ConstantInt::getTrue(Context), SuccessorBB, - DispatchBB); - OldTerminator->eraseFromParent(); - // Yes, the backedge will never be taken. The control-flow is redundant. - // If it can be simplified further, other passes will take care. - DTUpdates.push_back({DominatorTree::Delete, BB, SuccessorBB}); - DTUpdates.push_back({DominatorTree::Insert, BB, SuccessorBB}); - DTUpdates.push_back({DominatorTree::Insert, BB, DispatchBB}); - } - assert(DTUpdates.size() == 6 && "Update count prediction failed."); - DTU.applyUpdates(DTUpdates); - DTUpdates.clear(); - - // By now we have: (6/6) - // PreheaderBB: <preheader> ; preds = ??? - // <...> - // %memcmp = call i32 @memcmp(i8* %LoadSrcA, i8* %LoadSrcB, i64 %Nbytes) - // %ComparedEqual = icmp eq <...> %memcmp, 0 - // br label %BCmpDispatchBB - // BCmpDispatchBB: <header> ; preds = %PreheaderBB - // br i1 %ComparedEqual, label %EqualBB, label %UnequalBB - // EqualBB: <latch,exiting> ; preds = %BCmpDispatchBB - // br i1 %true, label %Successor1BB, label %BCmpDispatchBB - // UnequalBB: <latch,exiting> ; preds = %BCmpDispatchBB - // br i1 %true, label %Successor0BB, label %BCmpDispatchBB - // Successor0BB: ; preds = %UnequalBB - // %S0PHI = phi <...> [ <...>, %UnequalBB ] - // <...> - // Successor1BB: ; preds = %EqualBB - // %S0PHI = phi <...> [ <...>, %EqualBB ] - // <...> - - // Finally fully DONE! - return DispatchBB; -} - -void LoopIdiomRecognize::transformLoopToBCmp(ICmpInst *BCmpInst, - CmpInst *LatchCmpInst, - LoadInst *LoadA, LoadInst *LoadB, - const SCEV *SrcA, const SCEV *SrcB, - const SCEV *NBytes) { - // We will be inserting before the terminator instruction of preheader block. - IRBuilder<> Builder(CurLoop->getLoopPreheader()->getTerminator()); - - LLVM_DEBUG(dbgs() << "Transforming bcmp loop idiom into a call.\n"); - LLVM_DEBUG(dbgs() << "Emitting new instructions.\n"); - - // Expand the SCEV expressions for both sources to compare, and produce value - // for the byte len (beware of Iterations potentially being a pointer, and - // account for element size being BCmpTyBytes bytes, which may be not 1 byte) - Value *PtrA, *PtrB, *Len; - { - SCEVExpander SExp(*SE, *DL, "LoopToBCmp"); - SExp.setInsertPoint(&*Builder.GetInsertPoint()); - - auto HandlePtr = [&SExp](LoadInst *Load, const SCEV *Src) { - SExp.SetCurrentDebugLocation(DebugLoc()); - // If the pointer operand of original load had dbgloc - use it. - if (const auto *I = dyn_cast<Instruction>(Load->getPointerOperand())) - SExp.SetCurrentDebugLocation(I->getDebugLoc()); - return SExp.expandCodeFor(Src); - }; - PtrA = HandlePtr(LoadA, SrcA); - PtrB = HandlePtr(LoadB, SrcB); - - // For len calculation let's use dbgloc for the loop's latch condition. - Builder.SetCurrentDebugLocation(LatchCmpInst->getDebugLoc()); - SExp.SetCurrentDebugLocation(LatchCmpInst->getDebugLoc()); - Len = SExp.expandCodeFor(NBytes); - - Type *CmpFuncSizeTy = DL->getIntPtrType(Builder.getContext()); - assert(SE->getTypeSizeInBits(Len->getType()) == - DL->getTypeSizeInBits(CmpFuncSizeTy) && - "Len should already have the correct size."); - - // Make sure that iteration count is a number, insert ptrtoint cast if not. - if (Len->getType()->isPointerTy()) - Len = Builder.CreatePtrToInt(Len, CmpFuncSizeTy); - assert(Len->getType() == CmpFuncSizeTy && "Should have correct type now."); - - Len->setName(Len->getName() + ".bytecount"); - - // There is no legality check needed. We want to compare that the memory - // regions [PtrA, PtrA+Len) and [PtrB, PtrB+Len) are fully identical, equal. - // For them to be fully equal, they must match bit-by-bit. And likewise, - // for them to *NOT* be fully equal, they have to differ just by one bit. - // The step of comparison (bits compared at once) simply does not matter. - } - - // For the rest of new instructions, dbgloc should point at the value cmp. - Builder.SetCurrentDebugLocation(BCmpInst->getDebugLoc()); - - // Emit the comparison itself. - auto *CmpCall = - cast<CallInst>(HasBCmp ? emitBCmp(PtrA, PtrB, Len, Builder, *DL, TLI) - : emitMemCmp(PtrA, PtrB, Len, Builder, *DL, TLI)); - // FIXME: add {B,Mem}CmpInst with MemoryCompareInst - // (based on MemIntrinsicBase) as base? - // FIXME: propagate metadata from loads? (alignments, AS, TBAA, ...) - - // {b,mem}cmp returned 0 if they were equal, or non-zero if not equal. - auto *ComparedEqual = cast<ICmpInst>(Builder.CreateICmpEQ( - CmpCall, ConstantInt::get(CmpCall->getType(), 0), - PtrA->getName() + ".vs." + PtrB->getName() + ".eqcmp")); - - BasicBlock *BB = transformBCmpControlFlow(ComparedEqual); - Builder.ClearInsertionPoint(); - - // We're done. - LLVM_DEBUG(dbgs() << "Transformed loop bcmp idiom into a call.\n"); - ORE.emit([&]() { - return OptimizationRemark(DEBUG_TYPE, "TransformedBCmpIdiomToCall", - CmpCall->getDebugLoc(), BB) - << "Transformed bcmp idiom into a call to " - << ore::NV("NewFunction", CmpCall->getCalledFunction()) - << "() function"; - }); - ++NumBCmp; -} - -/// Recognizes a bcmp idiom in a non-countable loop. -/// -/// If detected, transforms the relevant code to issue the bcmp (or memcmp) -/// intrinsic function call, and returns true; otherwise, returns false. -bool LoopIdiomRecognize::recognizeBCmp() { - if (!HasMemCmp && !HasBCmp) - return false; - - ICmpInst *BCmpInst; - CmpInst *LatchCmpInst; - LoadInst *LoadA, *LoadB; - const SCEV *SrcA, *SrcB, *NBytes; - if (!detectBCmpIdiom(BCmpInst, LatchCmpInst, LoadA, LoadB, SrcA, SrcB, - NBytes)) { - LLVM_DEBUG(dbgs() << "bcmp idiom recognition failed.\n"); - return false; - } - - transformLoopToBCmp(BCmpInst, LatchCmpInst, LoadA, LoadB, SrcA, SrcB, NBytes); - return true; -} diff --git a/llvm/test/Transforms/LoopIdiom/bcmp-basic.ll b/llvm/test/Transforms/LoopIdiom/bcmp-basic.ll index d2c782029b2..25a80763023 100644 --- a/llvm/test/Transforms/LoopIdiom/bcmp-basic.ll +++ b/llvm/test/Transforms/LoopIdiom/bcmp-basic.ll @@ -1,5 +1,5 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py -; RUN: opt -loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info < %s -S | FileCheck %s +; RUN: opt -loop-idiom < %s -S | FileCheck %s target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64" @@ -239,17 +239,24 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3 define i1 @_Z39pointer_iteration_const_size_no_overlapPKc(i8* %ptr) { ; CHECK-LABEL: @_Z39pointer_iteration_const_size_no_overlapPKc( -; CHECK-NEXT: for.body.i.i.bcmpdispatchbb: +; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 8 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 8) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[ADD_PTR]], [[ENTRY:%.*]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_IDX:%.*]] = phi i64 [ [[__FIRST1_ADDR_06_I_I_ADD:%.*]], [[FOR_INC_I_I]] ], [ 0, [[ENTRY]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[__FIRST1_ADDR_06_I_I_IDX]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I_PTR]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_ADD]] = add nuw nsw i64 [[__FIRST1_ADDR_06_I_I_IDX]], 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i64 [[__FIRST1_ADDR_06_I_I_ADD]], 8 +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: -; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: ret i1 [[RETVAL_0_I_I]] ; entry: @@ -278,17 +285,24 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i1 @_Z44pointer_iteration_const_size_partial_overlapPKc(i8* %ptr) { ; CHECK-LABEL: @_Z44pointer_iteration_const_size_partial_overlapPKc( -; CHECK-NEXT: for.body.i.i.bcmpdispatchbb: +; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR1:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 8 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR1]], i64 16) -; CHECK-NEXT: [[PTR_VS_ADD_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR1_EQCMP]], label [[PTR_VS_ADD_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]] -; CHECK: ptr.vs.add.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[ADD_PTR1]], [[ENTRY:%.*]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_IDX:%.*]] = phi i64 [ [[__FIRST1_ADDR_06_I_I_ADD:%.*]], [[FOR_INC_I_I]] ], [ 0, [[ENTRY]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[__FIRST1_ADDR_06_I_I_IDX]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I_PTR]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_ADD]] = add nuw nsw i64 [[__FIRST1_ADDR_06_I_I_IDX]], 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i64 [[__FIRST1_ADDR_06_I_I_ADD]], 16 +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: -; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: ret i1 [[RETVAL_0_I_I]] ; entry: @@ -317,16 +331,23 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i1 @_Z44pointer_iteration_const_size_overlap_unknownPKcS0_(i8* %ptr0, i8* %ptr1) { ; CHECK-LABEL: @_Z44pointer_iteration_const_size_overlap_unknownPKcS0_( -; CHECK-NEXT: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[PTR1:%.*]], i64 8) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[ENTRY:%.*]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_IDX:%.*]] = phi i64 [ [[__FIRST1_ADDR_06_I_I_ADD:%.*]], [[FOR_INC_I_I]] ], [ 0, [[ENTRY]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[__FIRST1_ADDR_06_I_I_IDX]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I_PTR]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I_ADD]] = add nuw nsw i64 [[__FIRST1_ADDR_06_I_I_IDX]], 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i64 [[__FIRST1_ADDR_06_I_I_ADD]], 8 +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: -; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: ret i1 [[RETVAL_0_I_I]] ; entry: @@ -355,19 +376,25 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i1 @_Z42pointer_iteration_variable_size_no_overlapPKcm(i8* %ptr, i64 %count) { ; CHECK-LABEL: @_Z42pointer_iteration_variable_size_no_overlapPKcm( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[ADD_PTR]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -400,21 +427,27 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i1 @_Z47pointer_iteration_variable_size_partial_overlapPKcm(i8* %ptr, i64 %count) { ; CHECK-LABEL: @_Z47pointer_iteration_variable_size_partial_overlapPKcm( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[MUL_BYTECOUNT:%.*]] = shl i64 [[COUNT:%.*]], 1 -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[MUL_BYTECOUNT]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[MUL_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: +; CHECK-NEXT: [[MUL:%.*]] = shl i64 [[COUNT:%.*]], 1 +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[MUL]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[MUL]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: ; CHECK-NEXT: [[ADD_PTR1:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[COUNT]] -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR1]], i64 [[MUL_BYTECOUNT]]) -; CHECK-NEXT: [[PTR_VS_ADD_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR1_EQCMP]], label [[PTR_VS_ADD_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr.vs.add.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[ADD_PTR1]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -452,19 +485,25 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i1 @_Z47pointer_iteration_variable_size_overlap_unknownPKcS0_m(i8* %ptr0, i8* %ptr1, i64 %count) { ; CHECK-LABEL: @_Z47pointer_iteration_variable_size_overlap_unknownPKcS0_m( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -496,17 +535,23 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i1 @_Z40index_iteration_eq_const_size_no_overlapPKc(i8* %ptr) { ; CHECK-LABEL: @_Z40index_iteration_eq_const_size_no_overlapPKc( -; CHECK-NEXT: for.body.bcmpdispatchbb: +; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 8 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 8) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], 8 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_013:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC]], [[FOR_COND:%.*]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[I_013]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[ADD_PTR]], i64 [[I_013]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]] +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_013]], 1 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: ret i1 [[RES]] ; entry: @@ -534,17 +579,23 @@ cleanup: ; preds = %for.cond, %for.body define i1 @_Z45index_iteration_eq_const_size_partial_overlapPKc(i8* %ptr) { ; CHECK-LABEL: @_Z45index_iteration_eq_const_size_partial_overlapPKc( -; CHECK-NEXT: for.body.bcmpdispatchbb: +; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 8 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 16) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], 16 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_013:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC]], [[FOR_COND:%.*]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[I_013]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[ADD_PTR]], i64 [[I_013]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]] +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_013]], 1 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: ret i1 [[RES]] ; entry: @@ -572,16 +623,22 @@ cleanup: ; preds = %for.cond, %for.body define i1 @_Z45index_iteration_eq_const_size_overlap_unknownPKcS0_(i8* %ptr0, i8* %ptr1) { ; CHECK-LABEL: @_Z45index_iteration_eq_const_size_overlap_unknownPKcS0_( -; CHECK-NEXT: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[PTR1:%.*]], i64 8) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], 8 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_08:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC]], [[FOR_COND:%.*]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[I_08]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[PTR1:%.*]], i64 [[I_08]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]] +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_08]], 1 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: ret i1 [[RES]] ; entry: @@ -609,19 +666,25 @@ cleanup: ; preds = %for.cond, %for.body define i1 @_Z43index_iteration_eq_variable_size_no_overlapPKcm(i8* %ptr, i64 %count) { ; CHECK-LABEL: @_Z43index_iteration_eq_variable_size_no_overlapPKcm( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], [[COUNT]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_015:%.*]] = phi i64 [ [[INC]], [[FOR_COND:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[I_015]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[ADD_PTR]], i64 [[I_015]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]] +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_015]], 1 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -655,19 +718,25 @@ define i1 @_Z48index_iteration_eq_variable_size_partial_overlapPKcm(i8* %ptr, i6 ; CHECK-LABEL: @_Z48index_iteration_eq_variable_size_partial_overlapPKcm( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT:%.*]] -; CHECK-NEXT: [[MUL_BYTECOUNT:%.*]] = shl i64 [[COUNT]], 1 -; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[MUL_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 [[MUL_BYTECOUNT]]) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: [[MUL:%.*]] = shl i64 [[COUNT]], 1 +; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[MUL]], 0 +; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], [[MUL]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_015:%.*]] = phi i64 [ [[INC]], [[FOR_COND:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[I_015]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[ADD_PTR]], i64 [[I_015]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]] +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_015]], 1 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -701,18 +770,24 @@ cleanup: ; preds = %for.body, %for.cond define i1 @_Z48index_iteration_eq_variable_size_overlap_unknownPKcS0_m(i8* %ptr0, i8* %ptr1, i64 %count) { ; CHECK-LABEL: @_Z48index_iteration_eq_variable_size_overlap_unknownPKcS0_m( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[CMP8:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT:%.*]], 0 -; CHECK-NEXT: br i1 [[CMP8]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: [[CMP8:%.*]] = icmp eq i64 [[COUNT:%.*]], 0 +; CHECK-NEXT: br i1 [[CMP8]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], [[COUNT]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_09:%.*]] = phi i64 [ [[INC]], [[FOR_COND:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[I_09]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[PTR1:%.*]], i64 [[I_09]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]] +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_09]], 1 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -743,18 +818,22 @@ cleanup: ; preds = %for.body, %for.cond define i1 @_Z38index_iteration_starting_from_negativePKcS0_(i8* %ptr0, i8* %ptr1) { ; CHECK-LABEL: @_Z38index_iteration_starting_from_negativePKcS0_( -; CHECK-NEXT: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PTR0:%.*]], i64 -4 -; CHECK-NEXT: [[SCEVGEP1:%.*]] = getelementptr i8, i8* [[PTR1:%.*]], i64 -4 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[SCEVGEP]], i8* [[SCEVGEP1]], i64 8) -; CHECK-NEXT: [[SCEVGEP_VS_SCEVGEP1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[SCEVGEP_VS_SCEVGEP1_EQCMP]], label [[SCEVGEP_VS_SCEVGEP1_EQCMP_EQUALBB:%.*]], label [[SCEVGEP_VS_SCEVGEP1_EQCMP_UNEQUALBB:%.*]] -; CHECK: scevgep.vs.scevgep1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: scevgep.vs.scevgep1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp slt i64 [[INDVARS_IV_NEXT:%.*]], 4 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ -4, [[ENTRY:%.*]] ], [ [[INDVARS_IV_NEXT]], [[FOR_COND:%.*]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i8, i8* [[PTR1:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX2]] +; CHECK-NEXT: [[CMP4:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: br i1 [[CMP4]], label [[FOR_COND]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RET:%.*]] = phi i1 [ false, [[SCEVGEP_VS_SCEVGEP1_EQCMP_UNEQUALBB]] ], [ true, [[SCEVGEP_VS_SCEVGEP1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RET:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: ret i1 [[RET]] ; entry: @@ -781,17 +860,25 @@ cleanup: ; preds = %for.cond, %for.body define i1 @_Z43combined_iteration_eq_const_size_no_overlapPKc(i8* %ptr) { ; CHECK-LABEL: @_Z43combined_iteration_eq_const_size_no_overlapPKc( -; CHECK-NEXT: for.body.bcmpdispatchbb: +; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 8 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 8) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_015:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ] +; CHECK-NEXT: [[PTR1_014:%.*]] = phi i8* [ [[ADD_PTR]], [[ENTRY]] ], [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ] +; CHECK-NEXT: [[PTR0_013:%.*]] = phi i8* [ [[PTR]], [[ENTRY]] ], [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[PTR0_013]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[PTR1_014]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_015]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_013]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_014]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], 8 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: ret i1 [[RES]] ; entry: @@ -821,17 +908,25 @@ cleanup: ; preds = %for.inc, %for.body define i1 @_Z48combined_iteration_eq_const_size_partial_overlapPKc(i8* %ptr) { ; CHECK-LABEL: @_Z48combined_iteration_eq_const_size_partial_overlapPKc( -; CHECK-NEXT: for.body.bcmpdispatchbb: +; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 8 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 16) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_015:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ] +; CHECK-NEXT: [[PTR1_014:%.*]] = phi i8* [ [[ADD_PTR]], [[ENTRY]] ], [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ] +; CHECK-NEXT: [[PTR0_013:%.*]] = phi i8* [ [[PTR]], [[ENTRY]] ], [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[PTR0_013]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[PTR1_014]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_015]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_013]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_014]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], 16 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: ret i1 [[RES]] ; entry: @@ -861,16 +956,24 @@ cleanup: ; preds = %for.inc, %for.body define i1 @_Z48combined_iteration_eq_const_size_overlap_unknownPKcS0_(i8* %ptr0, i8* %ptr1) { ; CHECK-LABEL: @_Z48combined_iteration_eq_const_size_overlap_unknownPKcS0_( -; CHECK-NEXT: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[PTR1:%.*]], i64 8) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP]] +; CHECK-NEXT: entry: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_010:%.*]] = phi i64 [ 0, [[ENTRY:%.*]] ], [ [[INC:%.*]], [[FOR_INC:%.*]] ] +; CHECK-NEXT: [[PTR1_ADDR_09:%.*]] = phi i8* [ [[PTR1:%.*]], [[ENTRY]] ], [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ] +; CHECK-NEXT: [[PTR0_ADDR_08:%.*]] = phi i8* [ [[PTR0:%.*]], [[ENTRY]] ], [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[PTR0_ADDR_08]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[PTR1_ADDR_09]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw nsw i64 [[I_010]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_ADDR_08]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_ADDR_09]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], 8 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP]] ; CHECK: cleanup: -; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: ret i1 [[RES]] ; entry: @@ -900,19 +1003,27 @@ cleanup: ; preds = %for.inc, %for.body define i1 @_Z46combined_iteration_eq_variable_size_no_overlapPKcm(i8* %ptr, i64 %count) { ; CHECK-LABEL: @_Z46combined_iteration_eq_variable_size_no_overlapPKcm( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT:%.*]], 0 -; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT_BYTECOUNT]] -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[COUNT:%.*]], 0 +; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_017:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR1_016:%.*]] = phi i8* [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ], [ [[ADD_PTR]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR0_015:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ], [ [[PTR]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[PTR0_015]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[PTR1_016]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_017]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_015]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_016]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], [[COUNT]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -950,20 +1061,28 @@ cleanup: ; preds = %for.body, %for.inc, define i1 @_Z51combined_iteration_eq_variable_size_partial_overlapPKcm(i8* %ptr, i64 %count) { ; CHECK-LABEL: @_Z51combined_iteration_eq_variable_size_partial_overlapPKcm( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[MUL_BYTECOUNT:%.*]] = shl i64 [[COUNT:%.*]], 1 -; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[MUL_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: +; CHECK-NEXT: [[MUL:%.*]] = shl i64 [[COUNT:%.*]], 1 +; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[MUL]], 0 +; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT]] -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 [[MUL_BYTECOUNT]]) -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_017:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR1_016:%.*]] = phi i8* [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ], [ [[ADD_PTR]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR0_015:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ], [ [[PTR]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[PTR0_015]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[PTR1_016]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_017]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_015]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_016]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], [[MUL]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -1002,18 +1121,26 @@ cleanup: ; preds = %for.body, %for.inc, define i1 @_Z51combined_iteration_eq_variable_size_overlap_unknownPKcS0_m(i8* %ptr0, i8* %ptr1, i64 %count) { ; CHECK-LABEL: @_Z51combined_iteration_eq_variable_size_overlap_unknownPKcS0_m( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[CMP8:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT:%.*]], 0 -; CHECK-NEXT: br i1 [[CMP8]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: [[CMP8:%.*]] = icmp eq i64 [[COUNT:%.*]], 0 +; CHECK-NEXT: br i1 [[CMP8]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_011:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR1_ADDR_010:%.*]] = phi i8* [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ], [ [[PTR1:%.*]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR0_ADDR_09:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ], [ [[PTR0:%.*]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[PTR0_ADDR_09]] +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[PTR1_ADDR_010]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[V0]], [[V1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_011]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_ADDR_09]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_ADDR_010]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], [[COUNT]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -1047,19 +1174,25 @@ cleanup: ; preds = %for.body, %for.inc, define i1 @_Z55negated_pointer_iteration_variable_size_overlap_unknownPKcS0_m(i8* %ptr0, i8* %ptr1, i64 %count) { ; CHECK-LABEL: @_Z55negated_pointer_iteration_variable_size_overlap_unknownPKcS0_m( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ true, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ false, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ true, [[FOR_BODY_I_I]] ], [ false, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ false, [[ENTRY:%.*]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -1094,24 +1227,23 @@ define i1 @_Z55integer_pointer_iteration_variable_size_overlap_unknownPKiS0_m(i3 ; CHECK-NEXT: entry: ; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i32, i32* [[PTR0:%.*]], i64 [[COUNT:%.*]] ; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[TMP0:%.*]] = shl nsw i64 [[COUNT]], 2 -; CHECK-NEXT: [[TMP1:%.*]] = add i64 [[TMP0]], -4 -; CHECK-NEXT: [[TMP2:%.*]] = lshr i64 [[TMP1]], 2 -; CHECK-NEXT: [[TMP3:%.*]] = shl nuw i64 [[TMP2]], 2 -; CHECK-NEXT: [[DOTBYTECOUNT:%.*]] = add i64 [[TMP3]], 4 -; CHECK-NEXT: [[CSTR:%.*]] = bitcast i32* [[PTR0]] to i8* -; CHECK-NEXT: [[CSTR1:%.*]] = bitcast i32* [[PTR1:%.*]] to i8* -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[CSTR]], i8* [[CSTR1]], i64 [[DOTBYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i32* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i32* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i32, i32* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T1:%.*]] = load i32, i32* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i32 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i32, i32* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i32, i32* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i32* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKiS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKiS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKIS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -1145,18 +1277,25 @@ define i1 @_Z21small_index_iterationPKcS0_i(i8* %ptr0, i8* %ptr1, i32 %count) { ; CHECK-LABEL: @_Z21small_index_iterationPKcS0_i( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[CMP8:%.*]] = icmp sgt i32 [[COUNT:%.*]], 0 -; CHECK-NEXT: br i1 [[CMP8]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]], label [[CLEANUP:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[DOTBYTECOUNT:%.*]] = zext i32 [[COUNT]] to i64 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[PTR1:%.*]], i64 [[DOTBYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]] +; CHECK-NEXT: br i1 [[CMP8]], label [[FOR_BODY_PREHEADER:%.*]], label [[CLEANUP:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[I_011:%.*]] = phi i32 [ [[INC:%.*]], [[FOR_INC:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR1_ADDR_010:%.*]] = phi i8* [ [[INCDEC_PTR3:%.*]], [[FOR_INC]] ], [ [[PTR1:%.*]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR0_ADDR_09:%.*]] = phi i8* [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ], [ [[PTR0:%.*]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i8, i8* [[PTR0_ADDR_09]] +; CHECK-NEXT: [[T1:%.*]] = load i8, i8* [[PTR1_ADDR_010]] +; CHECK-NEXT: [[CMP2:%.*]] = icmp eq i8 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP2]], label [[FOR_INC]], label [[CLEANUP_LOOPEXIT:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw nsw i32 [[I_011]], 1 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds i8, i8* [[PTR0_ADDR_09]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR3]] = getelementptr inbounds i8, i8* [[PTR1_ADDR_010]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp slt i32 [[INC]], [[COUNT]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT]] ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[T2_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[T2_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: br label [[CLEANUP]] ; CHECK: cleanup: ; CHECK-NEXT: [[T2:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[T2_PH]], [[CLEANUP_LOOPEXIT]] ] @@ -1190,22 +1329,24 @@ cleanup: ; preds = %for.body, %for.inc, define i1 @_Z23three_pointer_iterationPKcS0_S0_(i8* %ptr0, i8* %ptr0_end, i8* %ptr1) { ; CHECK-LABEL: @_Z23three_pointer_iterationPKcS0_S0_( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[PTR01:%.*]] = ptrtoint i8* [[PTR0:%.*]] to i64 -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i8* [[PTR0]], [[PTR0_END:%.*]] -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[TMP0:%.*]] = sub i64 0, [[PTR01]] -; CHECK-NEXT: [[SCEVGEP:%.*]] = getelementptr i8, i8* [[PTR0_END]], i64 [[TMP0]] -; CHECK-NEXT: [[DOTBYTECOUNT:%.*]] = ptrtoint i8* [[SCEVGEP]] to i64 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0]], i8* [[PTR1:%.*]], i64 [[DOTBYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i8* [[PTR0:%.*]], [[PTR0_END:%.*]] +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[PTR0_END]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -1237,19 +1378,25 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.body.i.i, %for. define i32 @_Z17value_propagationPKcS0_mii(i8* %ptr0, i8* %ptr1, i64 %count, i32 %on_equal, i32 %on_unequal) { ; CHECK-LABEL: @_Z17value_propagationPKcS0_mii( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[T2_PH:%.*]] = phi i32 [ [[ON_UNEQUAL:%.*]], [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ [[ON_EQUAL:%.*]], [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[T2_PH:%.*]] = phi i32 [ [[ON_UNEQUAL:%.*]], [[FOR_BODY_I_I]] ], [ [[ON_EQUAL:%.*]], [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[T2:%.*]] = phi i32 [ [[ON_EQUAL]], [[ENTRY:%.*]] ], [ [[T2_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -1282,17 +1429,23 @@ _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; preds = %for.inc.i.i, %for.b define void @_Z20multiple_exit_blocksPKcS0_m(i8* %ptr0, i8* %ptr1, i64 %count) { ; CHECK-LABEL: @_Z20multiple_exit_blocksPKcS0_m( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[IF_END:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[IF_END_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[IF_THEN:%.*]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[IF_END:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[IF_THEN:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[IF_END_LOOPEXIT:%.*]], label [[FOR_BODY_I_I]] ; CHECK: if.then: ; CHECK-NEXT: tail call void @_Z17callee_on_unequalv() ; CHECK-NEXT: br label [[RETURN:%.*]] @@ -1340,20 +1493,26 @@ declare void @_Z17callee_on_successv() define void @_Z13multiple_phisPKcS0_mS0_S0_S0_S0_PS0_S1_(i8* %ptr0, i8* %ptr1, i64 %count, i8* %v0, i8* %v1, i8* %v2, i8* %v3, i8** %out0, i8** %out1) { ; CHECK-LABEL: @_Z13multiple_phisPKcS0_mS0_S0_S0_S0_PS0_S1_( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT_BYTECOUNT:%.*]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0 -; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0]], i8* [[PTR1:%.*]], i64 [[COUNT_BYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR0:%.*]], i64 [[COUNT:%.*]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[COUNT]], 0 +; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT:%.*]], label [[FOR_BODY_I_I_PREHEADER:%.*]] +; CHECK: for.body.i.i.preheader: +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[PTR1:%.*]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[PTR0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T0:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T1:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T0]], [[T1]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[T2_PH:%.*]] = phi i8* [ [[V2:%.*]], [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ [[V0:%.*]], [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] -; CHECK-NEXT: [[T3_PH:%.*]] = phi i8* [ [[V3:%.*]], [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ [[V1:%.*]], [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[T2_PH:%.*]] = phi i8* [ [[V2:%.*]], [[FOR_BODY_I_I]] ], [ [[V0:%.*]], [[FOR_INC_I_I]] ] +; CHECK-NEXT: [[T3_PH:%.*]] = phi i8* [ [[V3:%.*]], [[FOR_BODY_I_I]] ], [ [[V1:%.*]], [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[T2:%.*]] = phi i8* [ [[V0]], [[ENTRY:%.*]] ], [ [[T2_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -1405,24 +1564,28 @@ define void @_Z16loop_within_loopmPPKcS1_Pm(i64 %outer_count, i8** %ptr0, i8** % ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8*, i8** [[PTR0:%.*]], i64 [[I_012]] ; CHECK-NEXT: [[T0:%.*]] = load i8*, i8** [[ARRAYIDX]] ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[COUNT:%.*]], i64 [[I_012]] -; CHECK-NEXT: [[T1_BYTECOUNT:%.*]] = load i64, i64* [[ARRAYIDX2]] -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[T0]], i64 [[T1_BYTECOUNT]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[T1_BYTECOUNT]], 0 +; CHECK-NEXT: [[T1:%.*]] = load i64, i64* [[ARRAYIDX2]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[T0]], i64 [[T1]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[T1]], 0 ; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], label [[FOR_BODY_I_I_PREHEADER:%.*]] ; CHECK: for.body.i.i.preheader: ; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i8*, i8** [[PTR1:%.*]], i64 [[I_012]] ; CHECK-NEXT: [[T2:%.*]] = load i8*, i8** [[ARRAYIDX3]] -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[T0]], i8* [[T2]], i64 [[T1_BYTECOUNT]]) -; CHECK-NEXT: [[T0_VS_T2_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: br i1 [[T0_VS_T2_EQCMP]], label [[T0_VS_T2_EQCMP_EQUALBB:%.*]], label [[T0_VS_T2_EQCMP_UNEQUALBB:%.*]] -; CHECK: t0.vs.t2.eqcmp.equalbb: -; CHECK-NEXT: br i1 true, label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB]] -; CHECK: t0.vs.t2.eqcmp.unequalbb: -; CHECK-NEXT: br i1 true, label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I_BCMPDISPATCHBB]] +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[T2]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[T0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T3:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T4:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T3]], [[T4]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[T0_VS_T2_EQCMP_UNEQUALBB]] ], [ true, [[T0_VS_T2_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] ; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]] ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: ; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[FOR_BODY]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ] @@ -1488,22 +1651,26 @@ define void @_Z42loop_within_loop_with_multiple_exit_blocksmPPKcS1_Pm(i64 %outer ; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8*, i8** [[PTR0:%.*]], i64 [[I_012]] ; CHECK-NEXT: [[T0:%.*]] = load i8*, i8** [[ARRAYIDX]] ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[COUNT:%.*]], i64 [[I_012]] -; CHECK-NEXT: [[T1_BYTECOUNT:%.*]] = load i64, i64* [[ARRAYIDX2]] -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[T0]], i64 [[T1_BYTECOUNT]] -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[T1_BYTECOUNT]], 0 +; CHECK-NEXT: [[T1:%.*]] = load i64, i64* [[ARRAYIDX2]] +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[T0]], i64 [[T1]] +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[T1]], 0 ; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[IF_END]], label [[FOR_BODY_I_I_PREHEADER:%.*]] ; CHECK: for.body.i.i.preheader: ; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i8*, i8** [[PTR1:%.*]], i64 [[I_012]] ; CHECK-NEXT: [[T2:%.*]] = load i8*, i8** [[ARRAYIDX3]] -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[T0]], i8* [[T2]], i64 [[T1_BYTECOUNT]]) -; CHECK-NEXT: [[T0_VS_T2_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: br i1 [[T0_VS_T2_EQCMP]], label [[T0_VS_T2_EQCMP_EQUALBB:%.*]], label [[T0_VS_T2_EQCMP_UNEQUALBB:%.*]] -; CHECK: t0.vs.t2.eqcmp.equalbb: -; CHECK-NEXT: br i1 true, label [[IF_END_LOOPEXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB]] -; CHECK: t0.vs.t2.eqcmp.unequalbb: -; CHECK-NEXT: br i1 true, label [[IF_THEN:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB]] +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]] +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[T2]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[T0]], [[FOR_BODY_I_I_PREHEADER]] ] +; CHECK-NEXT: [[T3:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]] +; CHECK-NEXT: [[T4:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]] +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T3]], [[T4]] +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[IF_THEN:%.*]] +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]] +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[IF_END_LOOPEXIT:%.*]], label [[FOR_BODY_I_I]] ; CHECK: if.then: ; CHECK-NEXT: tail call void @_Z17callee_on_unequalv() ; CHECK-NEXT: br label [[CLEANUP]] @@ -1573,17 +1740,19 @@ define void @_Z21endless_loop_if_equalPiS_(i32* %a, i32* %b) { ; CHECK: for.cond.loopexit: ; CHECK-NEXT: br label [[FOR_COND]] ; CHECK: for.cond: -; CHECK-NEXT: [[CSTR:%.*]] = bitcast i32* [[A:%.*]] to i8* -; CHECK-NEXT: [[CSTR1:%.*]] = bitcast i32* [[B:%.*]] to i8* -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[CSTR]], i8* [[CSTR1]], i64 16) -; CHECK-NEXT: [[A_VS_B_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: br i1 [[A_VS_B_EQCMP]], label [[A_VS_B_EQCMP_EQUALBB:%.*]], label [[A_VS_B_EQCMP_UNEQUALBB:%.*]] -; CHECK: a.vs.b.eqcmp.equalbb: -; CHECK-NEXT: br i1 true, label [[FOR_COND_LOOPEXIT:%.*]], label [[FOR_BODY_BCMPDISPATCHBB]] -; CHECK: a.vs.b.eqcmp.unequalbb: -; CHECK-NEXT: br i1 true, label [[RETURN:%.*]], label [[FOR_BODY_BCMPDISPATCHBB]] +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.cond1: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INDVARS_IV_NEXT:%.*]], 4 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[FOR_COND_LOOPEXIT:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[INDVARS_IV:%.*]] = phi i64 [ 0, [[FOR_COND]] ], [ [[INDVARS_IV_NEXT]], [[FOR_COND1:%.*]] ] +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i32, i32* [[A:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP0:%.*]] = load i32, i32* [[ARRAYIDX]] +; CHECK-NEXT: [[ARRAYIDX3:%.*]] = getelementptr inbounds i32, i32* [[B:%.*]], i64 [[INDVARS_IV]] +; CHECK-NEXT: [[TMP1:%.*]] = load i32, i32* [[ARRAYIDX3]] +; CHECK-NEXT: [[CMP4:%.*]] = icmp eq i32 [[TMP0]], [[TMP1]] +; CHECK-NEXT: [[INDVARS_IV_NEXT]] = add nuw nsw i64 [[INDVARS_IV]], 1 +; CHECK-NEXT: br i1 [[CMP4]], label [[FOR_COND1]], label [[RETURN:%.*]] ; CHECK: return: ; CHECK-NEXT: ret void ; @@ -1615,19 +1784,27 @@ define i1 @_Z21load_of_bitcastsPKcPKfm(i8* %ptr0, float* %ptr1, i64 %count) { ; CHECK-LABEL: @_Z21load_of_bitcastsPKcPKfm( ; CHECK-NEXT: entry: ; CHECK-NEXT: [[CMP13:%.*]] = icmp eq i64 [[COUNT:%.*]], 0 -; CHECK-NEXT: br i1 [[CMP13]], label [[CLEANUP3:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[DOTBYTECOUNT:%.*]] = shl nuw i64 [[COUNT]], 2 -; CHECK-NEXT: [[CSTR:%.*]] = bitcast float* [[PTR1:%.*]] to i8* -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR0:%.*]], i8* [[CSTR]], i64 [[DOTBYTECOUNT]]) -; CHECK-NEXT: [[PTR0_VS_PTR1_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0 -; CHECK-NEXT: br i1 [[PTR0_VS_PTR1_EQCMP]], label [[PTR0_VS_PTR1_EQCMP_EQUALBB:%.*]], label [[PTR0_VS_PTR1_EQCMP_UNEQUALBB:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP3_LOOPEXIT:%.*]] -; CHECK: ptr0.vs.ptr1.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP3_LOOPEXIT]] +; CHECK-NEXT: br i1 [[CMP13]], label [[CLEANUP3:%.*]], label [[FOR_BODY_PREHEADER:%.*]] +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]] +; CHECK: for.body: +; CHECK-NEXT: [[PTR0_ADDR_016:%.*]] = phi i8* [ [[ADD_PTR:%.*]], [[FOR_INC:%.*]] ], [ [[PTR0:%.*]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[I_015:%.*]] = phi i64 [ [[INC:%.*]], [[FOR_INC]] ], [ 0, [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[PTR1_ADDR_014:%.*]] = phi float* [ [[INCDEC_PTR:%.*]], [[FOR_INC]] ], [ [[PTR1:%.*]], [[FOR_BODY_PREHEADER]] ] +; CHECK-NEXT: [[V0_0__SROA_CAST:%.*]] = bitcast i8* [[PTR0_ADDR_016]] to i32* +; CHECK-NEXT: [[V0_0_COPYLOAD:%.*]] = load i32, i32* [[V0_0__SROA_CAST]] +; CHECK-NEXT: [[V1_0__SROA_CAST:%.*]] = bitcast float* [[PTR1_ADDR_014]] to i32* +; CHECK-NEXT: [[V1_0_COPYLOAD:%.*]] = load i32, i32* [[V1_0__SROA_CAST]] +; CHECK-NEXT: [[CMP1:%.*]] = icmp eq i32 [[V0_0_COPYLOAD]], [[V1_0_COPYLOAD]] +; CHECK-NEXT: br i1 [[CMP1]], label [[FOR_INC]], label [[CLEANUP3_LOOPEXIT:%.*]] +; CHECK: for.inc: +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_015]], 1 +; CHECK-NEXT: [[ADD_PTR]] = getelementptr inbounds i8, i8* [[PTR0_ADDR_016]], i64 4 +; CHECK-NEXT: [[INCDEC_PTR]] = getelementptr inbounds float, float* [[PTR1_ADDR_014]], i64 1 +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC]], [[COUNT]] +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP3_LOOPEXIT]] ; CHECK: cleanup3.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR0_VS_PTR1_EQCMP_UNEQUALBB]] ], [ true, [[PTR0_VS_PTR1_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_INC]] ] ; CHECK-NEXT: br label [[CLEANUP3]] ; CHECK: cleanup3: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP3_LOOPEXIT]] ] diff --git a/llvm/test/Transforms/LoopIdiom/bcmp-debugify-remarks.ll b/llvm/test/Transforms/LoopIdiom/bcmp-debugify-remarks.ll index d60ef2db000..f21def9ec0c 100644 --- a/llvm/test/Transforms/LoopIdiom/bcmp-debugify-remarks.ll +++ b/llvm/test/Transforms/LoopIdiom/bcmp-debugify-remarks.ll @@ -1,5 +1,5 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py -; RUN: opt -debugify -loop-idiom -pass-remarks=loop-idiom -pass-remarks-analysis=loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info < %s -S 2>&1 | FileCheck %s +; RUN: opt -debugify -loop-idiom < %s -S 2>&1 | FileCheck %s target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64" @@ -23,37 +23,38 @@ target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f3 ; sink(std::equal(ptr0[i], ptr0[i] + count[i], ptr1[i])); ; } -; CHECK: remark: <stdin>:13:1: Loop recognized as a bcmp idiom -; CHECK: remark: <stdin>:11:1: Transformed bcmp idiom into a call to memcmp() function -; CHECK: remark: <stdin>:29:1: Loop recognized as a bcmp idiom -; CHECK: remark: <stdin>:34:1: Transformed bcmp idiom into a call to memcmp() function - define i1 @_Z43index_iteration_eq_variable_size_no_overlapPKcm(i8* nocapture %ptr, i64 %count) { ; CHECK-LABEL: @_Z43index_iteration_eq_variable_size_no_overlapPKcm( ; CHECK-NEXT: entry: -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT_BYTECOUNT:%.*]], !dbg !22 +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[PTR:%.*]], i64 [[COUNT:%.*]], !dbg !22 ; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[ADD_PTR]], metadata !9, metadata !DIExpression()), !dbg !22 -; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[COUNT_BYTECOUNT]], 0, !dbg !23 +; CHECK-NEXT: [[CMP14:%.*]] = icmp eq i64 [[COUNT]], 0, !dbg !23 ; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP14]], metadata !11, metadata !DIExpression()), !dbg !23 -; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_BCMPDISPATCHBB:%.*]], !dbg !24 -; CHECK: for.body.bcmpdispatchbb: -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[PTR]], i8* [[ADD_PTR]], i64 [[COUNT_BYTECOUNT]]), !dbg !25 -; CHECK-NEXT: [[PTR_VS_ADD_PTR_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0, !dbg !25 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !14, metadata !DIExpression()), !dbg !26 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !15, metadata !DIExpression()), !dbg !27 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !16, metadata !DIExpression()), !dbg !28 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !17, metadata !DIExpression()), !dbg !29 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !18, metadata !DIExpression()), !dbg !30 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !19, metadata !DIExpression()), !dbg !25 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !20, metadata !DIExpression()), !dbg !31 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !13, metadata !DIExpression()), !dbg !32 -; CHECK-NEXT: br i1 [[PTR_VS_ADD_PTR_EQCMP]], label [[PTR_VS_ADD_PTR_EQCMP_EQUALBB:%.*]], label [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB:%.*]], !dbg !25 -; CHECK: ptr.vs.add.ptr.eqcmp.equalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT:%.*]], !dbg !33 -; CHECK: ptr.vs.add.ptr.eqcmp.unequalbb: -; CHECK-NEXT: br label [[CLEANUP_LOOPEXIT]], !dbg !34 +; CHECK-NEXT: br i1 [[CMP14]], label [[CLEANUP:%.*]], label [[FOR_BODY_PREHEADER:%.*]], !dbg !24 +; CHECK: for.body.preheader: +; CHECK-NEXT: br label [[FOR_BODY:%.*]], !dbg !25 +; CHECK: for.cond: +; CHECK-NEXT: [[CMP:%.*]] = icmp ult i64 [[INC:%.*]], [[COUNT]], !dbg !26 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP]], metadata !13, metadata !DIExpression()), !dbg !26 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_BODY]], label [[CLEANUP_LOOPEXIT:%.*]], !dbg !27 +; CHECK: for.body: +; CHECK-NEXT: [[I_015:%.*]] = phi i64 [ [[INC]], [[FOR_COND:%.*]] ], [ 0, [[FOR_BODY_PREHEADER]] ], !dbg !28 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 [[I_015]], metadata !14, metadata !DIExpression()), !dbg !28 +; CHECK-NEXT: [[ARRAYIDX:%.*]] = getelementptr inbounds i8, i8* [[PTR]], i64 [[I_015]], !dbg !29 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[ARRAYIDX]], metadata !15, metadata !DIExpression()), !dbg !29 +; CHECK-NEXT: [[V0:%.*]] = load i8, i8* [[ARRAYIDX]], !dbg !30 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[V0]], metadata !16, metadata !DIExpression()), !dbg !30 +; CHECK-NEXT: [[ARRAYIDX1:%.*]] = getelementptr inbounds i8, i8* [[ADD_PTR]], i64 [[I_015]], !dbg !31 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[ARRAYIDX1]], metadata !17, metadata !DIExpression()), !dbg !31 +; CHECK-NEXT: [[V1:%.*]] = load i8, i8* [[ARRAYIDX1]], !dbg !32 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[V1]], metadata !18, metadata !DIExpression()), !dbg !32 +; CHECK-NEXT: [[CMP3:%.*]] = icmp eq i8 [[V0]], [[V1]], !dbg !33 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP3]], metadata !19, metadata !DIExpression()), !dbg !33 +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_015]], 1, !dbg !34 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 [[INC]], metadata !20, metadata !DIExpression()), !dbg !34 +; CHECK-NEXT: br i1 [[CMP3]], label [[FOR_COND]], label [[CLEANUP_LOOPEXIT]], !dbg !25 ; CHECK: cleanup.loopexit: -; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[PTR_VS_ADD_PTR_EQCMP_UNEQUALBB]] ], [ true, [[PTR_VS_ADD_PTR_EQCMP_EQUALBB]] ] +; CHECK-NEXT: [[RES_PH:%.*]] = phi i1 [ false, [[FOR_BODY]] ], [ true, [[FOR_COND]] ] ; CHECK-NEXT: br label [[CLEANUP]], !dbg !35 ; CHECK: cleanup: ; CHECK-NEXT: [[RES:%.*]] = phi i1 [ true, [[ENTRY:%.*]] ], [ [[RES_PH]], [[CLEANUP_LOOPEXIT]] ], !dbg !36 @@ -105,11 +106,11 @@ define void @_Z16loop_within_loopmPPKcS1_Pm(i64 %outer_count, i8** %ptr0, i8** % ; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[T0]], metadata !42, metadata !DIExpression()), !dbg !66 ; CHECK-NEXT: [[ARRAYIDX2:%.*]] = getelementptr inbounds i64, i64* [[COUNT:%.*]], i64 [[I_012]], !dbg !67 ; CHECK-NEXT: call void @llvm.dbg.value(metadata i64* [[ARRAYIDX2]], metadata !43, metadata !DIExpression()), !dbg !67 -; CHECK-NEXT: [[T1_BYTECOUNT:%.*]] = load i64, i64* [[ARRAYIDX2]], !dbg !68 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 [[T1_BYTECOUNT]], metadata !44, metadata !DIExpression()), !dbg !68 -; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[T0]], i64 [[T1_BYTECOUNT]], !dbg !69 +; CHECK-NEXT: [[T1:%.*]] = load i64, i64* [[ARRAYIDX2]], !dbg !68 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 [[T1]], metadata !44, metadata !DIExpression()), !dbg !68 +; CHECK-NEXT: [[ADD_PTR:%.*]] = getelementptr inbounds i8, i8* [[T0]], i64 [[T1]], !dbg !69 ; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[ADD_PTR]], metadata !45, metadata !DIExpression()), !dbg !69 -; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[T1_BYTECOUNT]], 0, !dbg !70 +; CHECK-NEXT: [[CMP5_I_I:%.*]] = icmp eq i64 [[T1]], 0, !dbg !70 ; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP5_I_I]], metadata !46, metadata !DIExpression()), !dbg !70 ; CHECK-NEXT: br i1 [[CMP5_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], label [[FOR_BODY_I_I_PREHEADER:%.*]], !dbg !62 ; CHECK: for.body.i.i.preheader: @@ -117,35 +118,39 @@ define void @_Z16loop_within_loopmPPKcS1_Pm(i64 %outer_count, i8** %ptr0, i8** % ; CHECK-NEXT: call void @llvm.dbg.value(metadata i8** [[ARRAYIDX3]], metadata !47, metadata !DIExpression()), !dbg !71 ; CHECK-NEXT: [[T2:%.*]] = load i8*, i8** [[ARRAYIDX3]], !dbg !72 ; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[T2]], metadata !48, metadata !DIExpression()), !dbg !72 -; CHECK-NEXT: [[MEMCMP:%.*]] = call i32 @memcmp(i8* [[T0]], i8* [[T2]], i64 [[T1_BYTECOUNT]]), !dbg !73 -; CHECK-NEXT: [[T0_VS_T2_EQCMP:%.*]] = icmp eq i32 [[MEMCMP]], 0, !dbg !73 -; CHECK-NEXT: br label [[FOR_BODY_I_I_BCMPDISPATCHBB:%.*]] -; CHECK: for.body.i.i.bcmpdispatchbb: -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !49, metadata !DIExpression()), !dbg !74 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !50, metadata !DIExpression()), !dbg !75 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !51, metadata !DIExpression()), !dbg !76 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !52, metadata !DIExpression()), !dbg !77 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !53, metadata !DIExpression()), !dbg !73 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !54, metadata !DIExpression()), !dbg !78 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !55, metadata !DIExpression()), !dbg !79 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i32 undef, metadata !56, metadata !DIExpression()), !dbg !80 -; CHECK-NEXT: br i1 [[T0_VS_T2_EQCMP]], label [[T0_VS_T2_EQCMP_EQUALBB:%.*]], label [[T0_VS_T2_EQCMP_UNEQUALBB:%.*]], !dbg !73 -; CHECK: t0.vs.t2.eqcmp.equalbb: -; CHECK-NEXT: br i1 true, label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]], label [[FOR_BODY_I_I_BCMPDISPATCHBB]], !dbg !81 -; CHECK: t0.vs.t2.eqcmp.unequalbb: -; CHECK-NEXT: br i1 true, label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I_BCMPDISPATCHBB]], !dbg !82 +; CHECK-NEXT: br label [[FOR_BODY_I_I:%.*]], !dbg !73 +; CHECK: for.body.i.i: +; CHECK-NEXT: [[__FIRST2_ADDR_07_I_I:%.*]] = phi i8* [ [[INCDEC_PTR1_I_I:%.*]], [[FOR_INC_I_I:%.*]] ], [ [[T2]], [[FOR_BODY_I_I_PREHEADER]] ], !dbg !74 +; CHECK-NEXT: [[__FIRST1_ADDR_06_I_I:%.*]] = phi i8* [ [[INCDEC_PTR_I_I:%.*]], [[FOR_INC_I_I]] ], [ [[T0]], [[FOR_BODY_I_I_PREHEADER]] ], !dbg !75 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[__FIRST2_ADDR_07_I_I]], metadata !49, metadata !DIExpression()), !dbg !74 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[__FIRST1_ADDR_06_I_I]], metadata !50, metadata !DIExpression()), !dbg !75 +; CHECK-NEXT: [[T3:%.*]] = load i8, i8* [[__FIRST1_ADDR_06_I_I]], !dbg !76 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[T3]], metadata !51, metadata !DIExpression()), !dbg !76 +; CHECK-NEXT: [[T4:%.*]] = load i8, i8* [[__FIRST2_ADDR_07_I_I]], !dbg !77 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8 [[T4]], metadata !52, metadata !DIExpression()), !dbg !77 +; CHECK-NEXT: [[CMP_I_I_I:%.*]] = icmp eq i8 [[T3]], [[T4]], !dbg !78 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP_I_I_I]], metadata !53, metadata !DIExpression()), !dbg !78 +; CHECK-NEXT: br i1 [[CMP_I_I_I]], label [[FOR_INC_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT:%.*]], !dbg !79 +; CHECK: for.inc.i.i: +; CHECK-NEXT: [[INCDEC_PTR_I_I]] = getelementptr inbounds i8, i8* [[__FIRST1_ADDR_06_I_I]], i64 1, !dbg !80 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[INCDEC_PTR_I_I]], metadata !54, metadata !DIExpression()), !dbg !80 +; CHECK-NEXT: [[INCDEC_PTR1_I_I]] = getelementptr inbounds i8, i8* [[__FIRST2_ADDR_07_I_I]], i64 1, !dbg !81 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i8* [[INCDEC_PTR1_I_I]], metadata !55, metadata !DIExpression()), !dbg !81 +; CHECK-NEXT: [[CMP_I_I:%.*]] = icmp eq i8* [[INCDEC_PTR_I_I]], [[ADD_PTR]], !dbg !82 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP_I_I]], metadata !56, metadata !DIExpression()), !dbg !82 +; CHECK-NEXT: br i1 [[CMP_I_I]], label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]], label [[FOR_BODY_I_I]], !dbg !83 ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit.loopexit: -; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[T0_VS_T2_EQCMP_UNEQUALBB]] ], [ true, [[T0_VS_T2_EQCMP_EQUALBB]] ] -; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], !dbg !83 +; CHECK-NEXT: [[RETVAL_0_I_I_PH:%.*]] = phi i1 [ false, [[FOR_BODY_I_I]] ], [ true, [[FOR_INC_I_I]] ] +; CHECK-NEXT: br label [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT]], !dbg !84 ; CHECK: _ZNSt3__15equalIPKcS2_EEbT_S3_T0_.exit: -; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[FOR_BODY]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ], !dbg !84 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[RETVAL_0_I_I]], metadata !57, metadata !DIExpression()), !dbg !84 -; CHECK-NEXT: tail call void @_Z4sinkb(i1 [[RETVAL_0_I_I]]), !dbg !83 -; CHECK-NEXT: [[INC]] = add nuw i64 [[I_012]], 1, !dbg !85 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 [[INC]], metadata !58, metadata !DIExpression()), !dbg !85 -; CHECK-NEXT: [[CMP:%.*]] = icmp eq i64 [[INC]], [[OUTER_COUNT]], !dbg !86 -; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP]], metadata !59, metadata !DIExpression()), !dbg !86 -; CHECK-NEXT: br i1 [[CMP]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY]], !dbg !87 +; CHECK-NEXT: [[RETVAL_0_I_I:%.*]] = phi i1 [ true, [[FOR_BODY]] ], [ [[RETVAL_0_I_I_PH]], [[_ZNST3__15EQUALIPKCS2_EEBT_S3_T0__EXIT_LOOPEXIT]] ], !dbg !85 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[RETVAL_0_I_I]], metadata !57, metadata !DIExpression()), !dbg !85 +; CHECK-NEXT: tail call void @_Z4sinkb(i1 [[RETVAL_0_I_I]]), !dbg !84 +; CHECK-NEXT: [[INC]] = add nuw i64 [[I_012]], 1, !dbg !86 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i64 [[INC]], metadata !58, metadata !DIExpression()), !dbg !86 +; CHECK-NEXT: [[CMP:%.*]] = icmp eq i64 [[INC]], [[OUTER_COUNT]], !dbg !87 +; CHECK-NEXT: call void @llvm.dbg.value(metadata i1 [[CMP]], metadata !59, metadata !DIExpression()), !dbg !87 +; CHECK-NEXT: br i1 [[CMP]], label [[FOR_COND_CLEANUP_LOOPEXIT:%.*]], label [[FOR_BODY]], !dbg !88 ; entry: %cmp11 = icmp eq i64 %outer_count, 0 diff --git a/llvm/test/Transforms/LoopIdiom/bcmp-negative-tests.ll b/llvm/test/Transforms/LoopIdiom/bcmp-negative-tests.ll index 59f7cf45c65..3808cdd2fe1 100644 --- a/llvm/test/Transforms/LoopIdiom/bcmp-negative-tests.ll +++ b/llvm/test/Transforms/LoopIdiom/bcmp-negative-tests.ll @@ -1,5 +1,5 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py -; RUN: opt -loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info < %s -S | FileCheck %s +; RUN: opt -loop-idiom < %s -S | FileCheck %s ; CHECK: source_filename ; CHECK-NOT; bcmp diff --git a/llvm/test/Transforms/LoopIdiom/bcmp-widening.ll b/llvm/test/Transforms/LoopIdiom/bcmp-widening.ll index 4c8b7f3f030..d7af3875395 100644 --- a/llvm/test/Transforms/LoopIdiom/bcmp-widening.ll +++ b/llvm/test/Transforms/LoopIdiom/bcmp-widening.ll @@ -1,5 +1,5 @@ ; NOTE: Assertions have been autogenerated by utils/update_test_checks.py -; RUN: opt -loop-idiom -verify -verify-each -verify-dom-info -verify-loop-info < %s -S | FileCheck %s +; RUN: opt -loop-idiom < %s -S | FileCheck %s target datalayout = "e-p:64:64:64-i1:8:8-i8:8:8-i16:16:16-i32:32:32-i64:64:64-f32:32:32-f64:64:64-v64:64:64-v128:128:128-a0:0:64-s0:64:64-f80:128:128-n8:16:32:64" |
