//===- LoopVectorize.cpp - A Loop Vectorizer ------------------------------===// // // Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions. // See https://llvm.org/LICENSE.txt for license information. // SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception // //===----------------------------------------------------------------------===// // // This is the LLVM loop vectorizer. This pass modifies 'vectorizable' loops // and generates target-independent LLVM-IR. // The vectorizer uses the TargetTransformInfo analysis to estimate the costs // of instructions in order to estimate the profitability of vectorization. // // The loop vectorizer combines consecutive loop iterations into a single // 'wide' iteration. After this transformation the index is incremented // by the SIMD vector width, and not by one. // // This pass has three parts: // 1. The main loop pass that drives the different parts. // 2. LoopVectorizationLegality - A unit that checks for the legality // of the vectorization. // 3. InnerLoopVectorizer - A unit that performs the actual // widening of instructions. // 4. LoopVectorizationCostModel - A unit that checks for the profitability // of vectorization. It decides on the optimal vector width, which // can be one, if vectorization is not profitable. // // There is a development effort going on to migrate loop vectorizer to the // VPlan infrastructure and to introduce outer loop vectorization support (see // docs/VectorizationPlan.rst and // http://lists.llvm.org/pipermail/llvm-dev/2017-December/119523.html). For this // purpose, we temporarily introduced the VPlan-native vectorization path: an // alternative vectorization path that is natively implemented on top of the // VPlan infrastructure. See EnableVPlanNativePath for enabling. // //===----------------------------------------------------------------------===// // // The reduction-variable vectorization is based on the paper: // D. Nuzman and R. Henderson. Multi-platform Auto-vectorization. // // Variable uniformity checks are inspired by: // Karrenberg, R. and Hack, S. Whole Function Vectorization. // // The interleaved access vectorization is based on the paper: // Dorit Nuzman, Ira Rosen and Ayal Zaks. Auto-Vectorization of Interleaved // Data for SIMD // // Other ideas/concepts are from: // A. Zaks and D. Nuzman. Autovectorization in GCC-two years later. // // S. Maleki, Y. Gao, M. Garzaran, T. Wong and D. Padua. An Evaluation of // Vectorizing Compilers. // //===----------------------------------------------------------------------===// #include "llvm/Transforms/Vectorize/LoopVectorize.h" #include "LoopVectorizationPlanner.h" #include "VPRecipeBuilder.h" #include "VPlan.h" #include "VPlanAnalysis.h" #include "VPlanHCFGBuilder.h" #include "VPlanPatternMatch.h" #include "VPlanTransforms.h" #include "VPlanUtils.h" #include "VPlanVerifier.h" #include "llvm/ADT/APInt.h" #include "llvm/ADT/ArrayRef.h" #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/DenseMapInfo.h" #include "llvm/ADT/Hashing.h" #include "llvm/ADT/MapVector.h" #include "llvm/ADT/STLExtras.h" #include "llvm/ADT/SmallPtrSet.h" #include "llvm/ADT/SmallVector.h" #include "llvm/ADT/Statistic.h" #include "llvm/ADT/StringRef.h" #include "llvm/ADT/Twine.h" #include "llvm/ADT/TypeSwitch.h" #include "llvm/ADT/iterator_range.h" #include "llvm/Analysis/AssumptionCache.h" #include "llvm/Analysis/BasicAliasAnalysis.h" #include "llvm/Analysis/BlockFrequencyInfo.h" #include "llvm/Analysis/CFG.h" #include "llvm/Analysis/CodeMetrics.h" #include "llvm/Analysis/DemandedBits.h" #include "llvm/Analysis/GlobalsModRef.h" #include "llvm/Analysis/LoopAccessAnalysis.h" #include "llvm/Analysis/LoopAnalysisManager.h" #include "llvm/Analysis/LoopInfo.h" #include "llvm/Analysis/LoopIterator.h" #include "llvm/Analysis/OptimizationRemarkEmitter.h" #include "llvm/Analysis/ProfileSummaryInfo.h" #include "llvm/Analysis/ScalarEvolution.h" #include "llvm/Analysis/ScalarEvolutionExpressions.h" #include "llvm/Analysis/TargetLibraryInfo.h" #include "llvm/Analysis/TargetTransformInfo.h" #include "llvm/Analysis/ValueTracking.h" #include "llvm/Analysis/VectorUtils.h" #include "llvm/IR/Attributes.h" #include "llvm/IR/BasicBlock.h" #include "llvm/IR/CFG.h" #include "llvm/IR/Constant.h" #include "llvm/IR/Constants.h" #include "llvm/IR/DataLayout.h" #include "llvm/IR/DebugInfo.h" #include "llvm/IR/DebugLoc.h" #include "llvm/IR/DerivedTypes.h" #include "llvm/IR/DiagnosticInfo.h" #include "llvm/IR/Dominators.h" #include "llvm/IR/Function.h" #include "llvm/IR/IRBuilder.h" #include "llvm/IR/InstrTypes.h" #include "llvm/IR/Instruction.h" #include "llvm/IR/Instructions.h" #include "llvm/IR/IntrinsicInst.h" #include "llvm/IR/Intrinsics.h" #include "llvm/IR/MDBuilder.h" #include "llvm/IR/Metadata.h" #include "llvm/IR/Module.h" #include "llvm/IR/Operator.h" #include "llvm/IR/PatternMatch.h" #include "llvm/IR/ProfDataUtils.h" #include "llvm/IR/Type.h" #include "llvm/IR/Use.h" #include "llvm/IR/User.h" #include "llvm/IR/Value.h" #include "llvm/IR/Verifier.h" #include "llvm/Support/Casting.h" #include "llvm/Support/CommandLine.h" #include "llvm/Support/Debug.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/InstructionCost.h" #include "llvm/Support/MathExtras.h" #include "llvm/Support/raw_ostream.h" #include "llvm/Transforms/Utils/BasicBlockUtils.h" #include "llvm/Transforms/Utils/InjectTLIMappings.h" #include "llvm/Transforms/Utils/Local.h" #include "llvm/Transforms/Utils/LoopSimplify.h" #include "llvm/Transforms/Utils/LoopUtils.h" #include "llvm/Transforms/Utils/LoopVersioning.h" #include "llvm/Transforms/Utils/ScalarEvolutionExpander.h" #include "llvm/Transforms/Utils/SizeOpts.h" #include "llvm/Transforms/Vectorize/LoopVectorizationLegality.h" #include <algorithm> #include <cassert> #include <cstdint> #include <functional> #include <iterator> #include <limits> #include <memory> #include <string> #include <tuple> #include <utility> usingnamespacellvm; #define LV_NAME … #define DEBUG_TYPE … #ifndef NDEBUG const char VerboseDebug[] = DEBUG_TYPE "-verbose"; #endif /// @{ /// Metadata attribute names const char LLVMLoopVectorizeFollowupAll[] = …; const char LLVMLoopVectorizeFollowupVectorized[] = …; const char LLVMLoopVectorizeFollowupEpilogue[] = …; /// @} STATISTIC(LoopsVectorized, "Number of loops vectorized"); STATISTIC(LoopsAnalyzed, "Number of loops analyzed for vectorization"); STATISTIC(LoopsEpilogueVectorized, "Number of epilogues vectorized"); static cl::opt<bool> EnableEpilogueVectorization( "enable-epilogue-vectorization", cl::init(true), cl::Hidden, cl::desc("Enable vectorization of epilogue loops.")); static cl::opt<unsigned> EpilogueVectorizationForceVF( "epilogue-vectorization-force-VF", cl::init(1), cl::Hidden, cl::desc("When epilogue vectorization is enabled, and a value greater than " "1 is specified, forces the given VF for all applicable epilogue " "loops.")); static cl::opt<unsigned> EpilogueVectorizationMinVF( "epilogue-vectorization-minimum-VF", cl::init(16), cl::Hidden, cl::desc("Only loops with vectorization factor equal to or larger than " "the specified value are considered for epilogue vectorization.")); /// Loops with a known constant trip count below this number are vectorized only /// if no scalar iteration overheads are incurred. static cl::opt<unsigned> TinyTripCountVectorThreshold( "vectorizer-min-trip-count", cl::init(16), cl::Hidden, cl::desc("Loops with a constant trip count that is smaller than this " "value are vectorized only if no scalar iteration overheads " "are incurred.")); static cl::opt<unsigned> VectorizeMemoryCheckThreshold( "vectorize-memory-check-threshold", cl::init(128), cl::Hidden, cl::desc("The maximum allowed number of runtime memory checks")); // Option prefer-predicate-over-epilogue indicates that an epilogue is undesired, // that predication is preferred, and this lists all options. I.e., the // vectorizer will try to fold the tail-loop (epilogue) into the vector body // and predicate the instructions accordingly. If tail-folding fails, there are // different fallback strategies depending on these values: namespace PreferPredicateTy { enum Option { … }; } // namespace PreferPredicateTy static cl::opt<PreferPredicateTy::Option> PreferPredicateOverEpilogue( "prefer-predicate-over-epilogue", cl::init(PreferPredicateTy::ScalarEpilogue), cl::Hidden, cl::desc("Tail-folding and predication preferences over creating a scalar " "epilogue loop."), cl::values(clEnumValN(PreferPredicateTy::ScalarEpilogue, "scalar-epilogue", "Don't tail-predicate loops, create scalar epilogue"), clEnumValN(PreferPredicateTy::PredicateElseScalarEpilogue, "predicate-else-scalar-epilogue", "prefer tail-folding, create scalar epilogue if tail " "folding fails."), clEnumValN(PreferPredicateTy::PredicateOrDontVectorize, "predicate-dont-vectorize", "prefers tail-folding, don't attempt vectorization if " "tail-folding fails."))); static cl::opt<TailFoldingStyle> ForceTailFoldingStyle( "force-tail-folding-style", cl::desc("Force the tail folding style"), cl::init(TailFoldingStyle::None), cl::values( clEnumValN(TailFoldingStyle::None, "none", "Disable tail folding"), clEnumValN( TailFoldingStyle::Data, "data", "Create lane mask for data only, using active.lane.mask intrinsic"), clEnumValN(TailFoldingStyle::DataWithoutLaneMask, "data-without-lane-mask", "Create lane mask with compare/stepvector"), clEnumValN(TailFoldingStyle::DataAndControlFlow, "data-and-control", "Create lane mask using active.lane.mask intrinsic, and use " "it for both data and control flow"), clEnumValN(TailFoldingStyle::DataAndControlFlowWithoutRuntimeCheck, "data-and-control-without-rt-check", "Similar to data-and-control, but remove the runtime check"), clEnumValN(TailFoldingStyle::DataWithEVL, "data-with-evl", "Use predicated EVL instructions for tail folding. If EVL " "is unsupported, fallback to data-without-lane-mask."))); static cl::opt<bool> MaximizeBandwidth( "vectorizer-maximize-bandwidth", cl::init(false), cl::Hidden, cl::desc("Maximize bandwidth when selecting vectorization factor which " "will be determined by the smallest type in loop.")); static cl::opt<bool> EnableInterleavedMemAccesses( "enable-interleaved-mem-accesses", cl::init(false), cl::Hidden, cl::desc("Enable vectorization on interleaved memory accesses in a loop")); /// An interleave-group may need masking if it resides in a block that needs /// predication, or in order to mask away gaps. static cl::opt<bool> EnableMaskedInterleavedMemAccesses( "enable-masked-interleaved-mem-accesses", cl::init(false), cl::Hidden, cl::desc("Enable vectorization on masked interleaved memory accesses in a loop")); static cl::opt<unsigned> ForceTargetNumScalarRegs( "force-target-num-scalar-regs", cl::init(0), cl::Hidden, cl::desc("A flag that overrides the target's number of scalar registers.")); static cl::opt<unsigned> ForceTargetNumVectorRegs( "force-target-num-vector-regs", cl::init(0), cl::Hidden, cl::desc("A flag that overrides the target's number of vector registers.")); static cl::opt<unsigned> ForceTargetMaxScalarInterleaveFactor( "force-target-max-scalar-interleave", cl::init(0), cl::Hidden, cl::desc("A flag that overrides the target's max interleave factor for " "scalar loops.")); static cl::opt<unsigned> ForceTargetMaxVectorInterleaveFactor( "force-target-max-vector-interleave", cl::init(0), cl::Hidden, cl::desc("A flag that overrides the target's max interleave factor for " "vectorized loops.")); cl::opt<unsigned> ForceTargetInstructionCost( "force-target-instruction-cost", cl::init(0), cl::Hidden, cl::desc("A flag that overrides the target's expected cost for " "an instruction to a single constant value. Mostly " "useful for getting consistent testing.")); static cl::opt<bool> ForceTargetSupportsScalableVectors( "force-target-supports-scalable-vectors", cl::init(false), cl::Hidden, cl::desc( "Pretend that scalable vectors are supported, even if the target does " "not support them. This flag should only be used for testing.")); static cl::opt<unsigned> SmallLoopCost( "small-loop-cost", cl::init(20), cl::Hidden, cl::desc( "The cost of a loop that is considered 'small' by the interleaver.")); static cl::opt<bool> LoopVectorizeWithBlockFrequency( "loop-vectorize-with-block-frequency", cl::init(true), cl::Hidden, cl::desc("Enable the use of the block frequency analysis to access PGO " "heuristics minimizing code growth in cold regions and being more " "aggressive in hot regions.")); // Runtime interleave loops for load/store throughput. static cl::opt<bool> EnableLoadStoreRuntimeInterleave( "enable-loadstore-runtime-interleave", cl::init(true), cl::Hidden, cl::desc( "Enable runtime interleaving until load/store ports are saturated")); /// The number of stores in a loop that are allowed to need predication. static cl::opt<unsigned> NumberOfStoresToPredicate( "vectorize-num-stores-pred", cl::init(1), cl::Hidden, cl::desc("Max number of stores to be predicated behind an if.")); static cl::opt<bool> EnableIndVarRegisterHeur( "enable-ind-var-reg-heur", cl::init(true), cl::Hidden, cl::desc("Count the induction variable only once when interleaving")); static cl::opt<bool> EnableCondStoresVectorization( "enable-cond-stores-vec", cl::init(true), cl::Hidden, cl::desc("Enable if predication of stores during vectorization.")); static cl::opt<unsigned> MaxNestedScalarReductionIC( "max-nested-scalar-reduction-interleave", cl::init(2), cl::Hidden, cl::desc("The maximum interleave count to use when interleaving a scalar " "reduction in a nested loop.")); static cl::opt<bool> PreferInLoopReductions("prefer-inloop-reductions", cl::init(false), cl::Hidden, cl::desc("Prefer in-loop vector reductions, " "overriding the targets preference.")); static cl::opt<bool> ForceOrderedReductions( "force-ordered-reductions", cl::init(false), cl::Hidden, cl::desc("Enable the vectorisation of loops with in-order (strict) " "FP reductions")); static cl::opt<bool> PreferPredicatedReductionSelect( "prefer-predicated-reduction-select", cl::init(false), cl::Hidden, cl::desc( "Prefer predicating a reduction operation over an after loop select.")); namespace llvm { cl::opt<bool> EnableVPlanNativePath( "enable-vplan-native-path", cl::Hidden, cl::desc("Enable VPlan-native vectorization path with " "support for outer loop vectorization.")); } // namespace llvm // This flag enables the stress testing of the VPlan H-CFG construction in the // VPlan-native vectorization path. It must be used in conjuction with // -enable-vplan-native-path. -vplan-verify-hcfg can also be used to enable the // verification of the H-CFGs built. static cl::opt<bool> VPlanBuildStressTest( "vplan-build-stress-test", cl::init(false), cl::Hidden, cl::desc( "Build VPlan for every supported loop nest in the function and bail " "out right after the build (stress test the VPlan H-CFG construction " "in the VPlan-native vectorization path).")); cl::opt<bool> llvm::EnableLoopInterleaving( "interleave-loops", cl::init(true), cl::Hidden, cl::desc("Enable loop interleaving in Loop vectorization passes")); cl::opt<bool> llvm::EnableLoopVectorization( "vectorize-loops", cl::init(true), cl::Hidden, cl::desc("Run the Loop vectorization passes")); static cl::opt<cl::boolOrDefault> ForceSafeDivisor( "force-widen-divrem-via-safe-divisor", cl::Hidden, cl::desc( "Override cost based safe divisor widening for div/rem instructions")); static cl::opt<bool> UseWiderVFIfCallVariantsPresent( "vectorizer-maximize-bandwidth-for-vector-calls", cl::init(true), cl::Hidden, cl::desc("Try wider VFs if they enable the use of vector variants")); // Likelyhood of bypassing the vectorized loop because assumptions about SCEV // variables not overflowing do not hold. See `emitSCEVChecks`. static constexpr uint32_t SCEVCheckBypassWeights[] = …; // Likelyhood of bypassing the vectorized loop because pointers overlap. See // `emitMemRuntimeChecks`. static constexpr uint32_t MemCheckBypassWeights[] = …; // Likelyhood of bypassing the vectorized loop because there are zero trips left // after prolog. See `emitIterationCountCheck`. static constexpr uint32_t MinItersBypassWeights[] = …; /// A helper function that returns true if the given type is irregular. The /// type is irregular if its allocated size doesn't equal the store size of an /// element of the corresponding vector type. static bool hasIrregularType(Type *Ty, const DataLayout &DL) { … } /// Returns "best known" trip count for the specified loop \p L as defined by /// the following procedure: /// 1) Returns exact trip count if it is known. /// 2) Returns expected trip count according to profile data if any. /// 3) Returns upper bound estimate if known, and if \p CanUseConstantMax. /// 4) Returns std::nullopt if all of the above failed. static std::optional<unsigned> getSmallBestKnownTC(ScalarEvolution &SE, Loop *L, bool CanUseConstantMax = true) { … } namespace { // Forward declare GeneratedRTChecks. class GeneratedRTChecks; SCEV2ValueTy; } // namespace namespace llvm { AnalysisKey ShouldRunExtraVectorPasses::Key; /// InnerLoopVectorizer vectorizes loops which contain only one basic /// block to a specified vectorization factor (VF). /// This class performs the widening of scalars into vectors, or multiple /// scalars. This class also implements the following features: /// * It inserts an epilogue loop for handling loops that don't have iteration /// counts that are known to be a multiple of the vectorization factor. /// * It handles the code generation for reduction variables. /// * Scalarization (implementation using scalars) of un-vectorizable /// instructions. /// InnerLoopVectorizer does not perform any vectorization-legality /// checks, and relies on the caller to check for the different legality /// aspects. The InnerLoopVectorizer relies on the /// LoopVectorizationLegality class to provide information about the induction /// and reduction variables that were found to a given vectorization factor. class InnerLoopVectorizer { … }; /// Encapsulate information regarding vectorization of a loop and its epilogue. /// This information is meant to be updated and used across two stages of /// epilogue vectorization. struct EpilogueLoopVectorizationInfo { … }; /// An extension of the inner loop vectorizer that creates a skeleton for a /// vectorized loop that has its epilogue (residual) also vectorized. /// The idea is to run the vplan on a given loop twice, firstly to setup the /// skeleton and vectorize the main loop, and secondly to complete the skeleton /// from the first step and vectorize the epilogue. This is achieved by /// deriving two concrete strategy classes from this base class and invoking /// them in succession from the loop vectorizer planner. class InnerLoopAndEpilogueVectorizer : public InnerLoopVectorizer { … }; /// A specialized derived class of inner loop vectorizer that performs /// vectorization of *main* loops in the process of vectorizing loops and their /// epilogues. class EpilogueVectorizerMainLoop : public InnerLoopAndEpilogueVectorizer { … }; // A specialized derived class of inner loop vectorizer that performs // vectorization of *epilogue* loops in the process of vectorizing loops and // their epilogues. class EpilogueVectorizerEpilogueLoop : public InnerLoopAndEpilogueVectorizer { … }; } // end namespace llvm /// Look for a meaningful debug location on the instruction or it's /// operands. static DebugLoc getDebugLocFromInstOrOperands(Instruction *I) { … } /// Write a \p DebugMsg about vectorization to the debug output stream. If \p I /// is passed, the message relates to that particular instruction. #ifndef NDEBUG static void debugVectorizationMessage(const StringRef Prefix, const StringRef DebugMsg, Instruction *I) { dbgs() << "LV: " << Prefix << DebugMsg; if (I != nullptr) dbgs() << " " << *I; else dbgs() << '.'; dbgs() << '\n'; } #endif /// Create an analysis remark that explains why vectorization failed /// /// \p PassName is the name of the pass (e.g. can be AlwaysPrint). \p /// RemarkName is the identifier for the remark. If \p I is passed it is an /// instruction that prevents vectorization. Otherwise \p TheLoop is used for /// the location of the remark. If \p DL is passed, use it as debug location for /// the remark. \return the remark object that can be streamed to. static OptimizationRemarkAnalysis createLVAnalysis(const char *PassName, StringRef RemarkName, Loop *TheLoop, Instruction *I, DebugLoc DL = { … } namespace llvm { /// Return a value for Step multiplied by VF. Value *createStepForVF(IRBuilderBase &B, Type *Ty, ElementCount VF, int64_t Step) { … } /// Return the runtime value for VF. Value *getRuntimeVF(IRBuilderBase &B, Type *Ty, ElementCount VF) { … } void reportVectorizationFailure(const StringRef DebugMsg, const StringRef OREMsg, const StringRef ORETag, OptimizationRemarkEmitter *ORE, Loop *TheLoop, Instruction *I) { … } /// Reports an informative message: print \p Msg for debugging purposes as well /// as an optimization remark. Uses either \p I as location of the remark, or /// otherwise \p TheLoop. If \p DL is passed, use it as debug location for the /// remark. If \p DL is passed, use it as debug location for the remark. static void reportVectorizationInfo(const StringRef Msg, const StringRef ORETag, OptimizationRemarkEmitter *ORE, Loop *TheLoop, Instruction *I = nullptr, DebugLoc DL = { … } /// Report successful vectorization of the loop. In case an outer loop is /// vectorized, prepend "outer" to the vectorization remark. static void reportVectorization(OptimizationRemarkEmitter *ORE, Loop *TheLoop, VectorizationFactor VF, unsigned IC) { … } } // end namespace llvm namespace llvm { // Loop vectorization cost-model hints how the scalar epilogue loop should be // lowered. enum ScalarEpilogueLowering { … }; InstructionVFPair; /// LoopVectorizationCostModel - estimates the expected speedups due to /// vectorization. /// In many cases vectorization is not profitable. This can happen because of /// a number of reasons. In this class we mainly attempt to predict the /// expected speedup/slowdowns due to the supported instruction set. We use the /// TargetTransformInfo to query the different backends for the cost of /// different operations. class LoopVectorizationCostModel { … }; } // end namespace llvm namespace { /// Helper struct to manage generating runtime checks for vectorization. /// /// The runtime checks are created up-front in temporary blocks to allow better /// estimating the cost and un-linked from the existing IR. After deciding to /// vectorize, the checks are moved back. If deciding not to vectorize, the /// temporary blocks are completely removed. class GeneratedRTChecks { … }; } // namespace static bool useActiveLaneMask(TailFoldingStyle Style) { … } static bool useActiveLaneMaskForControlFlow(TailFoldingStyle Style) { … } // Return true if \p OuterLp is an outer loop annotated with hints for explicit // vectorization. The loop needs to be annotated with #pragma omp simd // simdlen(#) or #pragma clang vectorize(enable) vectorize_width(#). If the // vector length information is not provided, vectorization is not considered // explicit. Interleave hints are not allowed either. These limitations will be // relaxed in the future. // Please, note that we are currently forced to abuse the pragma 'clang // vectorize' semantics. This pragma provides *auto-vectorization hints* // (i.e., LV must check that vectorization is legal) whereas pragma 'omp simd' // provides *explicit vectorization hints* (LV can bypass legal checks and // assume that vectorization is legal). However, both hints are implemented // using the same metadata (llvm.loop.vectorize, processed by // LoopVectorizeHints). This will be fixed in the future when the native IR // representation for pragma 'omp simd' is introduced. static bool isExplicitVecOuterLoop(Loop *OuterLp, OptimizationRemarkEmitter *ORE) { … } static void collectSupportedLoops(Loop &L, LoopInfo *LI, OptimizationRemarkEmitter *ORE, SmallVectorImpl<Loop *> &V) { … } //===----------------------------------------------------------------------===// // Implementation of LoopVectorizationLegality, InnerLoopVectorizer and // LoopVectorizationCostModel and LoopVectorizationPlanner. //===----------------------------------------------------------------------===// /// Compute the transformed value of Index at offset StartValue using step /// StepValue. /// For integer induction, returns StartValue + Index * StepValue. /// For pointer induction, returns StartValue[Index * StepValue]. /// FIXME: The newly created binary instructions should contain nsw/nuw /// flags, which can be found from the original scalar operations. static Value * emitTransformedIndex(IRBuilderBase &B, Value *Index, Value *StartValue, Value *Step, InductionDescriptor::InductionKind InductionKind, const BinaryOperator *InductionBinOp) { … } std::optional<unsigned> getMaxVScale(const Function &F, const TargetTransformInfo &TTI) { … } /// For the given VF and UF and maximum trip count computed for the loop, return /// whether the induction variable might overflow in the vectorized loop. If not, /// then we know a runtime overflow check always evaluates to false and can be /// removed. static bool isIndvarOverflowCheckKnownFalse( const LoopVectorizationCostModel *Cost, ElementCount VF, std::optional<unsigned> UF = std::nullopt) { … } // Return whether we allow using masked interleave-groups (for dealing with // strided loads/stores that reside in predicated blocks, or for dealing // with gaps). static bool useMaskedInterleavedAccesses(const TargetTransformInfo &TTI) { … } void InnerLoopVectorizer::scalarizeInstruction(const Instruction *Instr, VPReplicateRecipe *RepRecipe, const VPLane &Lane, VPTransformState &State) { … } Value * InnerLoopVectorizer::getOrCreateVectorTripCount(BasicBlock *InsertBlock) { … } void InnerLoopVectorizer::emitIterationCountCheck(BasicBlock *Bypass) { … } BasicBlock *InnerLoopVectorizer::emitSCEVChecks(BasicBlock *Bypass) { … } BasicBlock *InnerLoopVectorizer::emitMemRuntimeChecks(BasicBlock *Bypass) { … } void InnerLoopVectorizer::createVectorLoopSkeleton(StringRef Prefix) { … } PHINode *InnerLoopVectorizer::createInductionResumeValue( PHINode *OrigPhi, const InductionDescriptor &II, Value *Step, ArrayRef<BasicBlock *> BypassBlocks, std::pair<BasicBlock *, Value *> AdditionalBypass) { … } /// Return the expanded step for \p ID using \p ExpandedSCEVs to look up SCEV /// expansion results. static Value *getExpandedStep(const InductionDescriptor &ID, const SCEV2ValueTy &ExpandedSCEVs) { … } void InnerLoopVectorizer::createInductionResumeValues( const SCEV2ValueTy &ExpandedSCEVs, std::pair<BasicBlock *, Value *> AdditionalBypass) { … } std::pair<BasicBlock *, Value *> InnerLoopVectorizer::createVectorizedLoopSkeleton( const SCEV2ValueTy &ExpandedSCEVs) { … } // Fix up external users of the induction variable. At this point, we are // in LCSSA form, with all external PHIs that use the IV having one input value, // coming from the remainder loop. We need those PHIs to also have a correct // value for the IV when arriving directly from the middle block. void InnerLoopVectorizer::fixupIVUsers(PHINode *OrigPhi, const InductionDescriptor &II, Value *VectorTripCount, Value *EndValue, BasicBlock *MiddleBlock, VPlan &Plan, VPTransformState &State) { … } namespace { struct CSEDenseMapInfo { … }; } // end anonymous namespace ///Perform cse of induction variable instructions. static void cse(BasicBlock *BB) { … } InstructionCost LoopVectorizationCostModel::getVectorCallCost(CallInst *CI, ElementCount VF) const { … } static Type *maybeVectorizeType(Type *Elt, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getVectorIntrinsicCost(CallInst *CI, ElementCount VF) const { … } void InnerLoopVectorizer::fixVectorizedLoop(VPTransformState &State, VPlan &Plan) { … } void InnerLoopVectorizer::sinkScalarOperands(Instruction *PredInst) { … } void InnerLoopVectorizer::fixNonInductionPHIs(VPlan &Plan, VPTransformState &State) { … } void LoopVectorizationCostModel::collectLoopScalars(ElementCount VF) { … } bool LoopVectorizationCostModel::isScalarWithPredication( Instruction *I, ElementCount VF) const { … } // TODO: Fold into LoopVectorizationLegality::isMaskRequired. bool LoopVectorizationCostModel::isPredicatedInst(Instruction *I) const { … } std::pair<InstructionCost, InstructionCost> LoopVectorizationCostModel::getDivRemSpeculationCost(Instruction *I, ElementCount VF) const { … } bool LoopVectorizationCostModel::interleavedAccessCanBeWidened( Instruction *I, ElementCount VF) const { … } bool LoopVectorizationCostModel::memoryInstructionCanBeWidened( Instruction *I, ElementCount VF) { … } void LoopVectorizationCostModel::collectLoopUniforms(ElementCount VF) { … } bool LoopVectorizationCostModel::runtimeChecksRequired() { … } bool LoopVectorizationCostModel::isScalableVectorizationAllowed() { … } ElementCount LoopVectorizationCostModel::getMaxLegalScalableVF(unsigned MaxSafeElements) { … } FixedScalableVFPair LoopVectorizationCostModel::computeFeasibleMaxVF( unsigned MaxTripCount, ElementCount UserVF, bool FoldTailByMasking) { … } FixedScalableVFPair LoopVectorizationCostModel::computeMaxVF(ElementCount UserVF, unsigned UserIC) { … } ElementCount LoopVectorizationCostModel::getMaximizedVFForTarget( unsigned MaxTripCount, unsigned SmallestType, unsigned WidestType, ElementCount MaxSafeVF, bool FoldTailByMasking) { … } /// Convenience function that returns the value of vscale_range iff /// vscale_range.min == vscale_range.max or otherwise returns the value /// returned by the corresponding TTI method. static std::optional<unsigned> getVScaleForTuning(const Loop *L, const TargetTransformInfo &TTI) { … } bool LoopVectorizationPlanner::isMoreProfitable( const VectorizationFactor &A, const VectorizationFactor &B) const { … } void LoopVectorizationPlanner::emitInvalidCostRemarks( OptimizationRemarkEmitter *ORE) { … } /// Check if any recipe of \p Plan will generate a vector value, which will be /// assigned a vector register. static bool willGenerateVectors(VPlan &Plan, ElementCount VF, const TargetTransformInfo &TTI) { … } #ifndef NDEBUG VectorizationFactor LoopVectorizationPlanner::selectVectorizationFactor() { InstructionCost ExpectedCost = CM.expectedCost(ElementCount::getFixed(1)); LLVM_DEBUG(dbgs() << "LV: Scalar loop costs: " << ExpectedCost << ".\n"); assert(ExpectedCost.isValid() && "Unexpected invalid cost for scalar loop"); assert(any_of(VPlans, [](std::unique_ptr<VPlan> &P) { return P->hasVF(ElementCount::getFixed(1)); }) && "Expected Scalar VF to be a candidate"); const VectorizationFactor ScalarCost(ElementCount::getFixed(1), ExpectedCost, ExpectedCost); VectorizationFactor ChosenFactor = ScalarCost; bool ForceVectorization = Hints.getForce() == LoopVectorizeHints::FK_Enabled; if (ForceVectorization && (VPlans.size() > 1 || !VPlans[0]->hasScalarVFOnly())) { // Ignore scalar width, because the user explicitly wants vectorization. // Initialize cost to max so that VF = 2 is, at least, chosen during cost // evaluation. ChosenFactor.Cost = InstructionCost::getMax(); } for (auto &P : VPlans) { for (ElementCount VF : P->vectorFactors()) { // The cost for scalar VF=1 is already calculated, so ignore it. if (VF.isScalar()) continue; InstructionCost C = CM.expectedCost(VF); VectorizationFactor Candidate(VF, C, ScalarCost.ScalarCost); unsigned AssumedMinimumVscale = getVScaleForTuning(OrigLoop, TTI).value_or(1); unsigned Width = Candidate.Width.isScalable() ? Candidate.Width.getKnownMinValue() * AssumedMinimumVscale : Candidate.Width.getFixedValue(); LLVM_DEBUG(dbgs() << "LV: Vector loop of width " << VF << " costs: " << (Candidate.Cost / Width)); if (VF.isScalable()) LLVM_DEBUG(dbgs() << " (assuming a minimum vscale of " << AssumedMinimumVscale << ")"); LLVM_DEBUG(dbgs() << ".\n"); if (!ForceVectorization && !willGenerateVectors(*P, VF, TTI)) { LLVM_DEBUG( dbgs() << "LV: Not considering vector loop of width " << VF << " because it will not generate any vector instructions.\n"); continue; } if (isMoreProfitable(Candidate, ChosenFactor)) ChosenFactor = Candidate; } } if (!EnableCondStoresVectorization && CM.hasPredStores()) { reportVectorizationFailure( "There are conditional stores.", "store that is conditionally executed prevents vectorization", "ConditionalStore", ORE, OrigLoop); ChosenFactor = ScalarCost; } LLVM_DEBUG(if (ForceVectorization && !ChosenFactor.Width.isScalar() && !isMoreProfitable(ChosenFactor, ScalarCost)) dbgs() << "LV: Vectorization seems to be not beneficial, " << "but was forced by a user.\n"); LLVM_DEBUG(dbgs() << "LV: Selecting VF: " << ChosenFactor.Width << ".\n"); return ChosenFactor; } #endif bool LoopVectorizationPlanner::isCandidateForEpilogueVectorization( ElementCount VF) const { … } bool LoopVectorizationCostModel::isEpilogueVectorizationProfitable( const ElementCount VF) const { … } VectorizationFactor LoopVectorizationPlanner::selectEpilogueVectorizationFactor( const ElementCount MainLoopVF, unsigned IC) { … } std::pair<unsigned, unsigned> LoopVectorizationCostModel::getSmallestAndWidestTypes() { … } void LoopVectorizationCostModel::collectElementTypesForWidening() { … } unsigned LoopVectorizationCostModel::selectInterleaveCount(ElementCount VF, InstructionCost LoopCost) { … } SmallVector<LoopVectorizationCostModel::RegisterUsage, 8> LoopVectorizationCostModel::calculateRegisterUsage(ArrayRef<ElementCount> VFs) { … } bool LoopVectorizationCostModel::useEmulatedMaskMemRefHack(Instruction *I, ElementCount VF) { … } void LoopVectorizationCostModel::collectInstsToScalarize(ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::computePredInstDiscount( Instruction *PredInst, ScalarCostsTy &ScalarCosts, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::expectedCost(ElementCount VF) { … } /// Gets Address Access SCEV after verifying that the access pattern /// is loop invariant except the induction variable dependence. /// /// This SCEV can be sent to the Target in order to estimate the address /// calculation cost. static const SCEV *getAddressAccessSCEV( Value *Ptr, LoopVectorizationLegality *Legal, PredicatedScalarEvolution &PSE, const Loop *TheLoop) { … } InstructionCost LoopVectorizationCostModel::getMemInstScalarizationCost(Instruction *I, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getConsecutiveMemOpCost(Instruction *I, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getUniformMemOpCost(Instruction *I, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getGatherScatterCost(Instruction *I, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getInterleaveGroupCost(Instruction *I, ElementCount VF) { … } std::optional<InstructionCost> LoopVectorizationCostModel::getReductionPatternCost( Instruction *I, ElementCount VF, Type *Ty, TTI::TargetCostKind CostKind) const { … } InstructionCost LoopVectorizationCostModel::getMemoryInstructionCost(Instruction *I, ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getScalarizationOverhead( Instruction *I, ElementCount VF, TTI::TargetCostKind CostKind) const { … } void LoopVectorizationCostModel::setCostBasedWideningDecision(ElementCount VF) { … } void LoopVectorizationCostModel::setVectorizedCallDecision(ElementCount VF) { … } InstructionCost LoopVectorizationCostModel::getInstructionCost(Instruction *I, ElementCount VF) { … } void LoopVectorizationCostModel::collectValuesToIgnore() { … } void LoopVectorizationCostModel::collectInLoopReductions() { … } // This function will select a scalable VF if the target supports scalable // vectors and a fixed one otherwise. // TODO: we could return a pair of values that specify the max VF and // min VF, to be used in `buildVPlans(MinVF, MaxVF)` instead of // `buildVPlans(VF, VF)`. We cannot do it because VPLAN at the moment // doesn't have a cost model that can choose which plan to execute if // more than one is generated. static ElementCount determineVPlanVF(const TargetTransformInfo &TTI, LoopVectorizationCostModel &CM) { … } VectorizationFactor LoopVectorizationPlanner::planInVPlanNativePath(ElementCount UserVF) { … } void LoopVectorizationPlanner::plan(ElementCount UserVF, unsigned UserIC) { … } InstructionCost VPCostContext::getLegacyCost(Instruction *UI, ElementCount VF) const { … } bool VPCostContext::skipCostComputation(Instruction *UI, bool IsVector) const { … } InstructionCost LoopVectorizationPlanner::precomputeCosts(VPlan &Plan, ElementCount VF, VPCostContext &CostCtx) const { … } InstructionCost LoopVectorizationPlanner::cost(VPlan &Plan, ElementCount VF) const { … } #ifndef NDEBUG /// Return true if the original loop \ TheLoop contains any instructions that do /// not have corresponding recipes in \p Plan and are not marked to be ignored /// in \p CostCtx. This means the VPlan contains simplification that the legacy /// cost-model did not account for. static bool planContainsAdditionalSimplifications(VPlan &Plan, VPCostContext &CostCtx, Loop *TheLoop) { // First collect all instructions for the recipes in Plan. auto GetInstructionForCost = [](const VPRecipeBase *R) -> Instruction * { if (auto *S = dyn_cast<VPSingleDefRecipe>(R)) return dyn_cast_or_null<Instruction>(S->getUnderlyingValue()); if (auto *WidenMem = dyn_cast<VPWidenMemoryRecipe>(R)) return &WidenMem->getIngredient(); return nullptr; }; DenseSet<Instruction *> SeenInstrs; auto Iter = vp_depth_first_deep(Plan.getVectorLoopRegion()->getEntry()); for (VPBasicBlock *VPBB : VPBlockUtils::blocksOnly<VPBasicBlock>(Iter)) { for (VPRecipeBase &R : *VPBB) { if (auto *IR = dyn_cast<VPInterleaveRecipe>(&R)) { auto *IG = IR->getInterleaveGroup(); unsigned NumMembers = IG->getNumMembers(); for (unsigned I = 0; I != NumMembers; ++I) { if (Instruction *M = IG->getMember(I)) SeenInstrs.insert(M); } continue; } if (Instruction *UI = GetInstructionForCost(&R)) SeenInstrs.insert(UI); } } // Return true if the loop contains any instructions that are not also part of // the VPlan or are skipped for VPlan-based cost computations. This indicates // that the VPlan contains extra simplifications. return any_of(TheLoop->blocks(), [&SeenInstrs, &CostCtx, TheLoop](BasicBlock *BB) { return any_of(*BB, [&SeenInstrs, &CostCtx, TheLoop, BB](Instruction &I) { if (isa<PHINode>(&I) && BB == TheLoop->getHeader()) return false; return !SeenInstrs.contains(&I) && !CostCtx.skipCostComputation(&I, true); }); }); } #endif VectorizationFactor LoopVectorizationPlanner::computeBestVF() { … } static void addRuntimeUnrollDisableMetaData(Loop *L) { … } // Check if \p RedResult is a ComputeReductionResult instruction, and if it is // create a merge phi node for it. static void createAndCollectMergePhiForReduction( VPInstruction *RedResult, VPTransformState &State, Loop *OrigLoop, BasicBlock *LoopMiddleBlock, bool VectorizingEpilogue) { … } DenseMap<const SCEV *, Value *> LoopVectorizationPlanner::executePlan( ElementCount BestVF, unsigned BestUF, VPlan &BestVPlan, InnerLoopVectorizer &ILV, DominatorTree *DT, bool IsEpilogueVectorization, const DenseMap<const SCEV *, Value *> *ExpandedSCEVs) { … } //===--------------------------------------------------------------------===// // EpilogueVectorizerMainLoop //===--------------------------------------------------------------------===// /// This function is partially responsible for generating the control flow /// depicted in https://llvm.org/docs/Vectorizers.html#epilogue-vectorization. std::pair<BasicBlock *, Value *> EpilogueVectorizerMainLoop::createEpilogueVectorizedLoopSkeleton( const SCEV2ValueTy &ExpandedSCEVs) { … } void EpilogueVectorizerMainLoop::printDebugTracesAtStart() { … } void EpilogueVectorizerMainLoop::printDebugTracesAtEnd() { … } BasicBlock * EpilogueVectorizerMainLoop::emitIterationCountCheck(BasicBlock *Bypass, bool ForEpilogue) { … } //===--------------------------------------------------------------------===// // EpilogueVectorizerEpilogueLoop //===--------------------------------------------------------------------===// /// This function is partially responsible for generating the control flow /// depicted in https://llvm.org/docs/Vectorizers.html#epilogue-vectorization. std::pair<BasicBlock *, Value *> EpilogueVectorizerEpilogueLoop::createEpilogueVectorizedLoopSkeleton( const SCEV2ValueTy &ExpandedSCEVs) { … } BasicBlock * EpilogueVectorizerEpilogueLoop::emitMinimumVectorEpilogueIterCountCheck( BasicBlock *Bypass, BasicBlock *Insert) { … } void EpilogueVectorizerEpilogueLoop::printDebugTracesAtStart() { … } void EpilogueVectorizerEpilogueLoop::printDebugTracesAtEnd() { … } iterator_range<mapped_iterator<Use *, std::function<VPValue *(Value *)>>> VPRecipeBuilder::mapToVPValues(User::op_range Operands) { … } void VPRecipeBuilder::createSwitchEdgeMasks(SwitchInst *SI) { … } VPValue *VPRecipeBuilder::createEdgeMask(BasicBlock *Src, BasicBlock *Dst) { … } VPValue *VPRecipeBuilder::getEdgeMask(BasicBlock *Src, BasicBlock *Dst) const { … } void VPRecipeBuilder::createHeaderMask() { … } VPValue *VPRecipeBuilder::getBlockInMask(BasicBlock *BB) const { … } void VPRecipeBuilder::createBlockInMask(BasicBlock *BB) { … } VPWidenMemoryRecipe * VPRecipeBuilder::tryToWidenMemory(Instruction *I, ArrayRef<VPValue *> Operands, VFRange &Range) { … } /// Creates a VPWidenIntOrFpInductionRecpipe for \p Phi. If needed, it will also /// insert a recipe to expand the step for the induction recipe. static VPWidenIntOrFpInductionRecipe * createWidenInductionRecipes(PHINode *Phi, Instruction *PhiOrTrunc, VPValue *Start, const InductionDescriptor &IndDesc, VPlan &Plan, ScalarEvolution &SE, Loop &OrigLoop) { … } VPHeaderPHIRecipe *VPRecipeBuilder::tryToOptimizeInductionPHI( PHINode *Phi, ArrayRef<VPValue *> Operands, VFRange &Range) { … } VPWidenIntOrFpInductionRecipe *VPRecipeBuilder::tryToOptimizeInductionTruncate( TruncInst *I, ArrayRef<VPValue *> Operands, VFRange &Range) { … } VPBlendRecipe *VPRecipeBuilder::tryToBlend(PHINode *Phi, ArrayRef<VPValue *> Operands) { … } VPWidenCallRecipe *VPRecipeBuilder::tryToWidenCall(CallInst *CI, ArrayRef<VPValue *> Operands, VFRange &Range) { … } bool VPRecipeBuilder::shouldWiden(Instruction *I, VFRange &Range) const { … } VPWidenRecipe *VPRecipeBuilder::tryToWiden(Instruction *I, ArrayRef<VPValue *> Operands, VPBasicBlock *VPBB) { … } VPHistogramRecipe * VPRecipeBuilder::tryToWidenHistogram(const HistogramInfo *HI, ArrayRef<VPValue *> Operands) { … } void VPRecipeBuilder::fixHeaderPhis() { … } VPReplicateRecipe *VPRecipeBuilder::handleReplication(Instruction *I, VFRange &Range) { … } VPRecipeBase * VPRecipeBuilder::tryToCreateWidenRecipe(Instruction *Instr, ArrayRef<VPValue *> Operands, VFRange &Range, VPBasicBlock *VPBB) { … } void LoopVectorizationPlanner::buildVPlansWithVPRecipes(ElementCount MinVF, ElementCount MaxVF) { … } // Add the necessary canonical IV and branch recipes required to control the // loop. static void addCanonicalIVRecipes(VPlan &Plan, Type *IdxTy, bool HasNUW, DebugLoc DL) { … } // Collect VPIRInstructions for phis in the original exit block that are modeled // in VPlan and add the exiting VPValue as operand. Some exiting values are not // modeled explicitly yet and won't be included. Those are un-truncated // VPWidenIntOrFpInductionRecipe, VPWidenPointerInductionRecipe and induction // increments. static SetVector<VPIRInstruction *> collectUsersInExitBlock( Loop *OrigLoop, VPRecipeBuilder &Builder, VPlan &Plan, const MapVector<PHINode *, InductionDescriptor> &Inductions) { … } // Add exit values to \p Plan. Extracts are added for each entry in \p // ExitUsersToFix if needed and their operands are updated. static void addUsersInExitBlock(VPlan &Plan, const SetVector<VPIRInstruction *> &ExitUsersToFix) { … } /// Handle live-outs for first order reductions, both in the scalar preheader /// and the original exit block: /// 1. Feed a resume value for every FOR from the vector loop to the scalar /// loop, if middle block branches to scalar preheader, by introducing /// ExtractFromEnd and ResumePhi recipes in each, respectively, and a /// VPLiveOut which uses the latter and corresponds to the scalar header. /// 2. Feed the penultimate value of recurrences to their LCSSA phi users in /// the original exit block using a VPLiveOut. static void addLiveOutsForFirstOrderRecurrences( VPlan &Plan, SetVector<VPIRInstruction *> &ExitUsersToFix) { … } VPlanPtr LoopVectorizationPlanner::tryToBuildVPlanWithVPRecipes(VFRange &Range) { … } VPlanPtr LoopVectorizationPlanner::buildVPlan(VFRange &Range) { … } // Adjust the recipes for reductions. For in-loop reductions the chain of // instructions leading from the loop exit instr to the phi need to be converted // to reductions, with one operand being vector and the other being the scalar // reduction chain. For other reductions, a select is introduced between the phi // and live-out recipes when folding the tail. // // A ComputeReductionResult recipe is added to the middle block, also for // in-loop reductions which compute their result in-loop, because generating // the subsequent bc.merge.rdx phi is driven by ComputeReductionResult recipes. // // Adjust AnyOf reductions; replace the reduction phi for the selected value // with a boolean reduction phi node to check if the condition is true in any // iteration. The final value is selected by the final ComputeReductionResult. void LoopVectorizationPlanner::adjustRecipesForReductions( VPlanPtr &Plan, VPRecipeBuilder &RecipeBuilder, ElementCount MinVF) { … } void VPDerivedIVRecipe::execute(VPTransformState &State) { … } void VPReplicateRecipe::execute(VPTransformState &State) { … } // Determine how to lower the scalar epilogue, which depends on 1) optimising // for minimum code-size, 2) predicate compiler options, 3) loop hints forcing // predication, and 4) a TTI hook that analyses whether the loop is suitable // for predication. static ScalarEpilogueLowering getScalarEpilogueLowering( Function *F, Loop *L, LoopVectorizeHints &Hints, ProfileSummaryInfo *PSI, BlockFrequencyInfo *BFI, TargetTransformInfo *TTI, TargetLibraryInfo *TLI, LoopVectorizationLegality &LVL, InterleavedAccessInfo *IAI) { … } // Process the loop in the VPlan-native vectorization path. This path builds // VPlan upfront in the vectorization pipeline, which allows to apply // VPlan-to-VPlan transformations from the very beginning without modifying the // input LLVM IR. static bool processLoopInVPlanNativePath( Loop *L, PredicatedScalarEvolution &PSE, LoopInfo *LI, DominatorTree *DT, LoopVectorizationLegality *LVL, TargetTransformInfo *TTI, TargetLibraryInfo *TLI, DemandedBits *DB, AssumptionCache *AC, OptimizationRemarkEmitter *ORE, BlockFrequencyInfo *BFI, ProfileSummaryInfo *PSI, LoopVectorizeHints &Hints, LoopVectorizationRequirements &Requirements) { … } // Emit a remark if there are stores to floats that required a floating point // extension. If the vectorized loop was generated with floating point there // will be a performance penalty from the conversion overhead and the change in // the vector width. static void checkMixedPrecision(Loop *L, OptimizationRemarkEmitter *ORE) { … } static bool areRuntimeChecksProfitable(GeneratedRTChecks &Checks, VectorizationFactor &VF, std::optional<unsigned> VScale, Loop *L, ScalarEvolution &SE, ScalarEpilogueLowering SEL) { … } LoopVectorizePass::LoopVectorizePass(LoopVectorizeOptions Opts) : … { … } bool LoopVectorizePass::processLoop(Loop *L) { … } LoopVectorizeResult LoopVectorizePass::runImpl(Function &F) { … } PreservedAnalyses LoopVectorizePass::run(Function &F, FunctionAnalysisManager &AM) { … } void LoopVectorizePass::printPipeline( raw_ostream &OS, function_ref<StringRef(StringRef)> MapClassName2PassName) { … }
Codebase Browser
llvm