Index: include/llvm/InitializePasses.h =================================================================== --- include/llvm/InitializePasses.h +++ include/llvm/InitializePasses.h @@ -273,6 +273,7 @@ void initializePGOIndirectCallPromotionLegacyPassPass(PassRegistry&); void initializePGOInstrumentationGenLegacyPassPass(PassRegistry&); void initializePGOInstrumentationUseLegacyPassPass(PassRegistry&); +void initializePGOMemOPSizeOptLegacyPassPass(PassRegistry&); void initializePHIEliminationPass(PassRegistry&); void initializePartialInlinerLegacyPassPass(PassRegistry&); void initializePartiallyInlineLibCallsLegacyPassPass(PassRegistry&); Index: include/llvm/LinkAllPasses.h =================================================================== --- include/llvm/LinkAllPasses.h +++ include/llvm/LinkAllPasses.h @@ -97,6 +97,7 @@ (void) llvm::createPGOInstrumentationGenLegacyPass(); (void) llvm::createPGOInstrumentationUseLegacyPass(); (void) llvm::createPGOIndirectCallPromotionLegacyPass(); + (void) llvm::createPGOMemOPSizeOptLegacyPass(); (void) llvm::createInstrProfilingLegacyPass(); (void) llvm::createFunctionImportPass(); (void) llvm::createFunctionInliningPass(); Index: include/llvm/ProfileData/InstrProf.h =================================================================== --- include/llvm/ProfileData/InstrProf.h +++ include/llvm/ProfileData/InstrProf.h @@ -993,6 +993,10 @@ } // end namespace RawInstrProf +// Parse MemOP Size range option. +void getMemOPSizeRangeFromOption(std::string Str, int64_t &RangeStart, + int64_t &RangeLast); + } // end namespace llvm #endif // LLVM_PROFILEDATA_INSTRPROF_H Index: include/llvm/Transforms/InstrProfiling.h =================================================================== --- include/llvm/Transforms/InstrProfiling.h +++ include/llvm/Transforms/InstrProfiling.h @@ -60,12 +60,9 @@ size_t NamesSize; // The start value of precise value profile range for memory intrinsic sizes. - const int64_t DefaultMemOPSizeRangeStart = 0; int64_t MemOPSizeRangeStart; // The end value of precise value profile range for memory intrinsic sizes. - const int64_t DefaultMemOPSizeRangeLast = 8; int64_t MemOPSizeRangeLast; - int64_t MemOPSizeLargeVal; bool isMachO() const; @@ -117,9 +114,6 @@ /// Create a static initializer for our data, on platforms that need it, /// and for any profile output file that was specified. void emitInitialization(); - - /// Helper funtion that parsing the MemOPSize value profile options - void getMemOPSizeOptions(); }; } // end namespace llvm Index: include/llvm/Transforms/Instrumentation.h =================================================================== --- include/llvm/Transforms/Instrumentation.h +++ include/llvm/Transforms/Instrumentation.h @@ -88,6 +88,7 @@ createPGOInstrumentationUseLegacyPass(StringRef Filename = StringRef("")); ModulePass *createPGOIndirectCallPromotionLegacyPass(bool InLTO = false, bool SamplePGO = false); +FunctionPass *createPGOMemOPSizeOptLegacyPass(); // Helper function to check if it is legal to promote indirect call \p Inst // to a direct call of function \p F. Stores the reason in \p Reason. Index: include/llvm/Transforms/PGOInstrumentation.h =================================================================== --- include/llvm/Transforms/PGOInstrumentation.h +++ include/llvm/Transforms/PGOInstrumentation.h @@ -47,5 +47,15 @@ bool SamplePGO; }; +/// The profile size based optimization pass for memory intrinsics. +class PGOMemOPSizeOpt : public PassInfoMixin { +public: + PGOMemOPSizeOpt() {} + PreservedAnalyses run(Function &F, FunctionAnalysisManager &AM); +}; + +void setProfMetadata(Module *M, Instruction *TI, ArrayRef EdgeCounts, + uint64_t MaxCount); + } // End llvm namespace #endif Index: lib/Passes/PassRegistry.def =================================================================== --- lib/Passes/PassRegistry.def +++ lib/Passes/PassRegistry.def @@ -174,6 +174,7 @@ FUNCTION_PASS("loop-load-elim", LoopLoadEliminationPass()) FUNCTION_PASS("loop-distribute", LoopDistributePass()) FUNCTION_PASS("loop-vectorize", LoopVectorizePass()) +FUNCTION_PASS("pgo-memop-opt", PGOMemOPSizeOpt()) FUNCTION_PASS("print", PrintFunctionPass(dbgs())) FUNCTION_PASS("print", AssumptionPrinterPass(dbgs())) FUNCTION_PASS("print", BlockFrequencyPrinterPass(dbgs())) Index: lib/ProfileData/InstrProf.cpp =================================================================== --- lib/ProfileData/InstrProf.cpp +++ lib/ProfileData/InstrProf.cpp @@ -936,4 +936,25 @@ return true; } +// Parse the value profile options. +void getMemOPSizeRangeFromOption(std::string MemOPSizeRange, + int64_t &RangeStart, int64_t &RangeLast) { + static const int64_t DefaultMemOPSizeRangeStart = 0; + static const int64_t DefaultMemOPSizeRangeLast = 8; + RangeStart = DefaultMemOPSizeRangeStart; + RangeLast = DefaultMemOPSizeRangeLast; + + if (!MemOPSizeRange.empty()) { + auto Pos = MemOPSizeRange.find(":"); + if (Pos != std::string::npos) { + if (Pos > 0) + RangeStart = atoi(MemOPSizeRange.substr(0, Pos).c_str()); + if (Pos < MemOPSizeRange.size() - 1) + RangeLast = atoi(MemOPSizeRange.substr(Pos + 1).c_str()); + } else + RangeLast = atoi(MemOPSizeRange.c_str()); + } + assert(RangeLast >= RangeStart); +} + } // end namespace llvm Index: lib/Transforms/IPO/PassManagerBuilder.cpp =================================================================== --- lib/Transforms/IPO/PassManagerBuilder.cpp +++ lib/Transforms/IPO/PassManagerBuilder.cpp @@ -302,6 +302,10 @@ MPM.add(createLibCallsShrinkWrapPass()); addExtensionsToPM(EP_Peephole, MPM); + // Optimize memory intrinsic calls based on the profiled size information. + if (SizeLevel == 0) + MPM.add(createPGOMemOPSizeOptLegacyPass()); + MPM.add(createTailCallEliminationPass()); // Eliminate tail calls MPM.add(createCFGSimplificationPass()); // Merge & remove BBs MPM.add(createReassociatePass()); // Reassociate expressions Index: lib/Transforms/Instrumentation/IndirectCallPromotion.cpp =================================================================== --- lib/Transforms/Instrumentation/IndirectCallPromotion.cpp +++ lib/Transforms/Instrumentation/IndirectCallPromotion.cpp @@ -1,4 +1,4 @@ -//===-- IndirectCallPromotion.cpp - Promote indirect calls to direct calls ===// +//===-- IndirectCallPromotion.cpp - Optimizations based on value profiling ===// // // The LLVM Compiler Infrastructure // @@ -17,6 +17,7 @@ #include "llvm/ADT/Statistic.h" #include "llvm/ADT/StringRef.h" #include "llvm/ADT/Twine.h" +#include "llvm/Analysis/BlockFrequencyInfo.h" #include "llvm/Analysis/IndirectCallPromotionAnalysis.h" #include "llvm/Analysis/IndirectCallSiteVisitor.h" #include "llvm/IR/BasicBlock.h" @@ -40,6 +41,7 @@ #include "llvm/Support/CommandLine.h" #include "llvm/Support/Debug.h" #include "llvm/Support/ErrorHandling.h" +#include "llvm/Support/MathExtras.h" #include "llvm/Transforms/Instrumentation.h" #include "llvm/Transforms/PGOInstrumentation.h" #include "llvm/Transforms/Utils/BasicBlockUtils.h" @@ -53,6 +55,8 @@ STATISTIC(NumOfPGOICallPromotion, "Number of indirect call promotions."); STATISTIC(NumOfPGOICallsites, "Number of indirect call candidate sites."); +STATISTIC(NumOfPGOMemOPOpt, "Number of memop intrinsics optimized."); +STATISTIC(NumOfPGOMemOPAnnotate, "Number of memop intrinsics annotated."); // Command line option to disable indirect-call promotion with the default as // false. This is for debug purpose. @@ -106,6 +110,44 @@ ICPDUMPAFTER("icp-dumpafter", cl::init(false), cl::Hidden, cl::desc("Dump IR after transformation happens")); +// The minimum call count to optimize memory intrinsic calls. +static cl::opt + MemOPCountThreshold("pgo-memop-count-threshold", cl::Hidden, cl::ZeroOrMore, + cl::init(1000), + cl::desc("The minimum count to optimize memory " + "intrinsic calls")); + +// Command line option to disable memory intrinsic optimization. The default is +// false. This is for debug purpose. +static cl::opt DisableMemOPOPT("disable-memop-opt", cl::init(false), + cl::Hidden, cl::desc("Disable optimize")); + +// The percent threshold to optimize memory intrinsic calls. +static cl::opt + MemOPPercentThreshold("pgo-memop-percent-threshold", cl::init(40), + cl::Hidden, cl::ZeroOrMore, + cl::desc("The percentage threshold for the " + "memory intrinsic calls optimization")); + +// Maximum number of versions for optimizing memory intrinsic call. +static cl::opt + MemOPMaxVersion("pgo-memop-max-version", cl::init(3), cl::Hidden, + cl::ZeroOrMore, + cl::desc("The max version for the optimized memory " + " intrinsic calls")); + +// Scale the counts from the annotation using the BB count value. +static cl::opt + MemOPScaleCount("pgo-memop-scale-count", cl::init(true), cl::Hidden, + cl::desc("Scale the memop size counts using the basic " + " block count value")); + +// This option set the rangge of precise profile memop sizes. +extern cl::opt MemOPSizeRange; + +// This option set the value that groups large memop sizes +extern cl::opt MemOPSizeLarge; + namespace { class PGOIndirectCallPromotionLegacyPass : public ModulePass { public: @@ -130,6 +172,23 @@ // the promoted direct call. bool SamplePGO; }; + +class PGOMemOPSizeOptLegacyPass : public FunctionPass { +public: + static char ID; + + PGOMemOPSizeOptLegacyPass() : FunctionPass(ID) { + initializePGOMemOPSizeOptLegacyPassPass(*PassRegistry::getPassRegistry()); + } + + StringRef getPassName() const override { return "PGOMemOPSize"; } + +private: + bool runOnFunction(Function &F) override; + void getAnalysisUsage(AnalysisUsage &AU) const override { + AU.addRequired(); + } +}; } // end anonymous namespace char PGOIndirectCallPromotionLegacyPass::ID = 0; @@ -143,6 +202,19 @@ return new PGOIndirectCallPromotionLegacyPass(InLTO, SamplePGO); } +char PGOMemOPSizeOptLegacyPass::ID = 0; +INITIALIZE_PASS_BEGIN(PGOMemOPSizeOptLegacyPass, "pgo-memop-opt", + "Optimize memory intrinsic using its size value profile", + false, false) +INITIALIZE_PASS_DEPENDENCY(BlockFrequencyInfoWrapperPass) +INITIALIZE_PASS_END(PGOMemOPSizeOptLegacyPass, "pgo-memop-opt", + "Optimize memory intrinsic using its size value profile", + false, false) + +FunctionPass *llvm::createPGOMemOPSizeOptLegacyPass() { + return new PGOMemOPSizeOptLegacyPass(); +} + namespace { // The class for main data structure to promote indirect calls to conditional // direct calls. @@ -675,3 +747,275 @@ return PreservedAnalyses::none(); } + +namespace { +class MemOPSizeOpt : public InstVisitor { +public: + MemOPSizeOpt(Function &Func, BlockFrequencyInfo &BFI) + : Func(Func), BFI(BFI), Changed(false) { + ValueDataArray = + llvm::make_unique(MemOPMaxVersion + 2); + // Get the MemOPSize range information from option MemOPSizeRange, + getMemOPSizeRangeFromOption(MemOPSizeRange, PreciseRangeStart, + PreciseRangeLast); + } + bool isChanged() const { return Changed; } + void perform() { + WorkList.clear(); + visit(Func); + + for (auto &MI : WorkList) { + ++NumOfPGOMemOPAnnotate; + if (perform(MI)) { + Changed = true; + ++NumOfPGOMemOPOpt; + DEBUG(dbgs() << "MemOP calls: " << MI->getCalledFunction()->getName() + << "is Transformed.\n"); + } + } + } + + void visitMemIntrinsic(MemIntrinsic &MI) { + Value *Length = MI.getLength(); + // Not perform on constant length calls. + if (dyn_cast(Length)) + return; + WorkList.push_back(&MI); + } + +private: + Function &Func; + BlockFrequencyInfo &BFI; + bool Changed; + std::vector WorkList; + // Start of the previse range. + int64_t PreciseRangeStart; + // Last value of the previse range. + int64_t PreciseRangeLast; + // The space to read the profile annotation. + std::unique_ptr ValueDataArray; + bool perform(MemIntrinsic *MI); + + // This kind shows which group the value falls in. For PreciseValue, we have + // the profile count for that value. LargeGroup groups the values that are in + // range [LargeValue, +inf). NonLargeGroup groups the rest of values. + enum MemOPSizeKind { PreciseValue, NonLargeGroup, LargeGroup }; + + MemOPSizeKind getMemOPSizeKind(int64_t Value) const { + if (Value == MemOPSizeLarge && MemOPSizeLarge != 0) + return LargeGroup; + if (Value == PreciseRangeLast + 1) + return NonLargeGroup; + return PreciseValue; + } +}; + +static const char *getMIName(const MemIntrinsic *MI) { + switch (MI->getIntrinsicID()) { + case Intrinsic::memcpy: + return "memcpy"; + case Intrinsic::memmove: + return "memmove"; + case Intrinsic::memset: + return "memset"; + default: + return "unknown"; + } +} + +static bool isProfitable(uint64_t Count, uint64_t TotalCount) { + assert(Count <= TotalCount); + if (Count < MemOPCountThreshold) + return false; + if (Count < TotalCount * MemOPPercentThreshold / 100) + return false; + return true; +} + +static inline uint64_t getScaledCount(uint64_t Count, uint64_t Num, + uint64_t Denom) { + if (!MemOPScaleCount) + return Count; + bool Overflowed; + uint64_t ScaleCount = SaturatingMultiply(Count, Num, &Overflowed); + return ScaleCount / Denom; +} + +bool MemOPSizeOpt::perform(MemIntrinsic *MI) { + assert(MI); + if (MI->getIntrinsicID() == Intrinsic::memmove) + return false; + + uint32_t NumVals, MaxNumPromotions = MemOPMaxVersion + 2; + uint64_t TotalCount; + if (!getValueProfDataFromInst(*MI, IPVK_MemOPSize, MaxNumPromotions, + ValueDataArray.get(), NumVals, TotalCount)) + return false; + + uint64_t ActualCount = TotalCount; + uint64_t SavedTotalCount = TotalCount; + if (MemOPScaleCount) { + auto BBEdgeCount = BFI.getBlockProfileCount(MI->getParent()); + if (!BBEdgeCount) + return false; + ActualCount = *BBEdgeCount; + } + + if (ActualCount < MemOPCountThreshold) + return false; + + ArrayRef VDs(ValueDataArray.get(), NumVals); + TotalCount = ActualCount; + if (MemOPScaleCount) + DEBUG(dbgs() << "Scale counts: numberator = " << ActualCount + << " denominator = " << SavedTotalCount << "\n"); + + // Keeping track of the count of the default case: + uint64_t RemainCount = TotalCount; + SmallVector SizeIds; + SmallVector CaseCounts; + uint64_t MaxCount = 0; + unsigned Version = 0; + // Default case is in the front -- save the slot here. + CaseCounts.push_back(0); + for (auto &VD : VDs) { + int64_t V = VD.Value; + uint64_t C = VD.Count; + if (MemOPScaleCount) + C = getScaledCount(C, ActualCount, SavedTotalCount); + + // Only care precise value here. + if (getMemOPSizeKind(V) != PreciseValue) + continue; + + // ValueCount are sorted on the count. Break at the first un-profitable + // value. + if (!isProfitable(C, RemainCount)) + break; + + SizeIds.push_back(V); + CaseCounts.push_back(C); + if (C > MaxCount) + MaxCount = C; + + assert(RemainCount >= C); + RemainCount -= C; + + if (++Version > MemOPMaxVersion && MemOPMaxVersion != 0) + break; + } + + if (Version == 0) + return false; + + CaseCounts[0] = RemainCount; + if (RemainCount > MaxCount) + MaxCount = RemainCount; + + uint64_t SumForOpt = TotalCount - RemainCount; + DEBUG(dbgs() << "Read one memory intrinsic profile: " << SumForOpt << " vs " + << TotalCount << "\n"); + DEBUG( + for (auto &VD + : VDs) { dbgs() << " (" << VD.Value << "," << VD.Count << ")\n"; }); + + DEBUG(dbgs() << "Optimize one memory intrinsic call to " << Version + << " Versions\n"); + + // mem_op(..., size) + // ==> + // switch (size) { + // case s1: + // mem_op(..., s1); + // goto merge_bb; + // case s2: + // mem_op(..., s2); + // goto merge_bb; + // ... + // default: + // mem_op(..., size); + // goto merge_bb; + // } + // merge_bb: + + BasicBlock *BB = MI->getParent(); + DEBUG(dbgs() << "\n\n== Basic Block Before ==\n"); + DEBUG(dbgs() << *BB << "\n"); + + BasicBlock *DefaultBB = SplitBlock(BB, MI); + BasicBlock::iterator It(*MI); + ++It; + assert(It != DefaultBB->end()); + BasicBlock *MergeBB = SplitBlock(DefaultBB, &(*It)); + DefaultBB->setName("MemOP.Default"); + MergeBB->setName("MemOP.Merge"); + + auto &Ctx = Func.getContext(); + IRBuilder<> IRB(BB); + BB->getTerminator()->eraseFromParent(); + Value *SizeVar = MI->getLength(); + SwitchInst *SI = IRB.CreateSwitch(SizeVar, DefaultBB, SizeIds.size()); + + // Clear the value profile data. + MI->setMetadata(LLVMContext::MD_prof, nullptr); + + DEBUG(dbgs() << "\n\n== Basic Block After==\n"); + + for (uint64_t SizeId : SizeIds) { + ConstantInt *CaseSizeId = ConstantInt::get(Type::getInt64Ty(Ctx), SizeId); + BasicBlock *CaseBB = BasicBlock::Create( + Ctx, Twine("MemOP.Case.") + Twine(SizeId), &Func, DefaultBB); + Instruction *NewInst = MI->clone(); + // Fix the argument. + dyn_cast(NewInst)->setLength(CaseSizeId); + CaseBB->getInstList().push_back(NewInst); + IRBuilder<> IRBCase(CaseBB); + IRBCase.CreateBr(MergeBB); + SI->addCase(CaseSizeId, CaseBB); + DEBUG(dbgs() << *CaseBB << "\n"); + } + setProfMetadata(Func.getParent(), SI, CaseCounts, MaxCount); + + DEBUG(dbgs() << *BB << "\n"); + DEBUG(dbgs() << *DefaultBB << "\n"); + DEBUG(dbgs() << *MergeBB << "\n"); + + emitOptimizationRemark(Func.getContext(), "memop-opt", Func, + MI->getDebugLoc(), + Twine("optimize ") + getMIName(MI) + " with count " + + Twine(SumForOpt) + " out of " + Twine(TotalCount) + + " for " + Twine(Version) + " versions"); + + return true; +} +} // namespace + +static bool PGOMemOPSizeOptImpl(Function &F, BlockFrequencyInfo &BFI) { + if (DisableMemOPOPT) + return false; + + if (F.hasFnAttribute(Attribute::OptimizeForSize)) + return false; + MemOPSizeOpt MemOPSizeOpt(F, BFI); + MemOPSizeOpt.perform(); + return MemOPSizeOpt.isChanged(); +} + +bool PGOMemOPSizeOptLegacyPass::runOnFunction(Function &F) { + BlockFrequencyInfo &BFI = + getAnalysis().getBFI(); + return PGOMemOPSizeOptImpl(F, BFI); +} + +namespace llvm { +char &PGOMemOPSizeOptID = PGOMemOPSizeOptLegacyPass::ID; + +PreservedAnalyses PGOMemOPSizeOpt::run(Function &F, + FunctionAnalysisManager &FAM) { + auto &BFI = FAM.getResult(F); + bool Changed = PGOMemOPSizeOptImpl(F, BFI); + if (!Changed) + return PreservedAnalyses::all(); + return PreservedAnalyses::none(); +} +} // namespace llvm Index: lib/Transforms/Instrumentation/InstrProfiling.cpp =================================================================== --- lib/Transforms/Instrumentation/InstrProfiling.cpp +++ lib/Transforms/Instrumentation/InstrProfiling.cpp @@ -51,6 +51,21 @@ #define DEBUG_TYPE "instrprof" +// The start and end values of precise value profile range for memory +// intrinsic sizes +cl::opt MemOPSizeRange( + "memop-size-range", + cl::desc("Set the range of size in memory intrinsic calls to be profiled " + "precisely, in a format of :"), + cl::init("")); + +// The value that considered to be large value in memory intrinsic. +cl::opt MemOPSizeLarge( + "memop-size-large", + cl::desc("Set large value thresthold in memory intrinsic size profiling. " + "Value of 0 disables the large value profiling."), + cl::init(8192)); + namespace { cl::opt DoNameCompression("enable-name-compression", @@ -77,17 +92,6 @@ // is usually smaller than 2. cl::init(1.0)); -cl::opt MemOPSizeRange( - "memop-size-range", - cl::desc("Set the range of size in memory intrinsic calls to be profiled " - "precisely, in a format of :"), - cl::init("")); -cl::opt MemOPSizeLarge( - "memop-size-large", - cl::desc("Set large value thresthold in memory intrinsic size profiling. " - "Value of 0 disables the large value profiling."), - cl::init(8192)); - class InstrProfilingLegacyPass : public ModulePass { InstrProfiling InstrProf; @@ -176,7 +180,8 @@ NamesSize = 0; ProfileDataMap.clear(); UsedVars.clear(); - getMemOPSizeOptions(); + getMemOPSizeRangeFromOption(MemOPSizeRange, MemOPSizeRangeStart, + MemOPSizeRangeLast); // We did not know how many value sites there would be inside // the instrumented function. This is counting the number of instrumented @@ -299,12 +304,13 @@ Builder.getInt32(Index)}; Call = Builder.CreateCall(getOrInsertValueProfilingCall(*M, *TLI), Args); } else { - Value *Args[6] = {Ind->getTargetValue(), - Builder.CreateBitCast(DataVar, Builder.getInt8PtrTy()), - Builder.getInt32(Index), - Builder.getInt64(MemOPSizeRangeStart), - Builder.getInt64(MemOPSizeRangeLast), - Builder.getInt64(MemOPSizeLargeVal)}; + Value *Args[6] = { + Ind->getTargetValue(), + Builder.CreateBitCast(DataVar, Builder.getInt8PtrTy()), + Builder.getInt32(Index), + Builder.getInt64(MemOPSizeRangeStart), + Builder.getInt64(MemOPSizeRangeLast), + Builder.getInt64(MemOPSizeLarge == 0 ? INT64_MIN : MemOPSizeLarge)}; Call = Builder.CreateCall(getOrInsertValueProfilingCall(*M, *TLI, true), Args); } @@ -700,24 +706,3 @@ appendToGlobalCtors(*M, F, 0); } - -void InstrProfiling::getMemOPSizeOptions() { - // Parse the value profile options. - MemOPSizeRangeStart = DefaultMemOPSizeRangeStart; - MemOPSizeRangeLast = DefaultMemOPSizeRangeLast; - if (!MemOPSizeRange.empty()) { - auto Pos = MemOPSizeRange.find(":"); - if (Pos != std::string::npos) { - if (Pos > 0) - MemOPSizeRangeStart = atoi(MemOPSizeRange.substr(0, Pos).c_str()); - if (Pos < MemOPSizeRange.size() - 1) - MemOPSizeRangeLast = atoi(MemOPSizeRange.substr(Pos + 1).c_str()); - } else - MemOPSizeRangeLast = atoi(MemOPSizeRange.c_str()); - } - assert(MemOPSizeRangeLast >= MemOPSizeRangeStart); - - MemOPSizeLargeVal = MemOPSizeLarge; - if (MemOPSizeLargeVal == 0) - MemOPSizeLargeVal = INT64_MIN; -} Index: lib/Transforms/Instrumentation/Instrumentation.cpp =================================================================== --- lib/Transforms/Instrumentation/Instrumentation.cpp +++ lib/Transforms/Instrumentation/Instrumentation.cpp @@ -63,6 +63,7 @@ initializePGOInstrumentationGenLegacyPassPass(Registry); initializePGOInstrumentationUseLegacyPassPass(Registry); initializePGOIndirectCallPromotionLegacyPassPass(Registry); + initializePGOMemOPSizeOptLegacyPassPass(Registry); initializeInstrProfilingLegacyPassPass(Registry); initializeMemorySanitizerPass(Registry); initializeThreadSanitizerPass(Registry); Index: lib/Transforms/Instrumentation/PGOInstrumentation.cpp =================================================================== --- lib/Transforms/Instrumentation/PGOInstrumentation.cpp +++ lib/Transforms/Instrumentation/PGOInstrumentation.cpp @@ -1038,21 +1038,6 @@ DEBUG(FuncInfo.dumpInfo("after reading profile.")); } -static void setProfMetadata(Module *M, Instruction *TI, - ArrayRef EdgeCounts, uint64_t MaxCount) { - MDBuilder MDB(M->getContext()); - assert(MaxCount > 0 && "Bad max count"); - uint64_t Scale = calculateCountScale(MaxCount); - SmallVector Weights; - for (const auto &ECI : EdgeCounts) - Weights.push_back(scaleBranchCount(ECI, Scale)); - - DEBUG(dbgs() << "Weight is: "; - for (const auto &W : Weights) { dbgs() << W << " "; } - dbgs() << "\n";); - TI->setMetadata(llvm::LLVMContext::MD_prof, MDB.createBranchWeights(Weights)); -} - // Assign the scaled count values to the BB with multiple out edges. void PGOUseFunc::setBranchWeights() { // Generate MD_prof metadata for every branch instruction. @@ -1426,6 +1411,21 @@ } namespace llvm { +void setProfMetadata(Module *M, Instruction *TI, + ArrayRef EdgeCounts, uint64_t MaxCount) { + MDBuilder MDB(M->getContext()); + assert(MaxCount > 0 && "Bad max count"); + uint64_t Scale = calculateCountScale(MaxCount); + SmallVector Weights; + for (const auto &ECI : EdgeCounts) + Weights.push_back(scaleBranchCount(ECI, Scale)); + + DEBUG(dbgs() << "Weight is: "; + for (const auto &W : Weights) { dbgs() << W << " "; } + dbgs() << "\n";); + TI->setMetadata(llvm::LLVMContext::MD_prof, MDB.createBranchWeights(Weights)); +} + template <> struct GraphTraits { typedef const BasicBlock *NodeRef; typedef succ_const_iterator ChildIteratorType; Index: test/Transforms/PGOProfile/memop_size_opt.ll =================================================================== --- test/Transforms/PGOProfile/memop_size_opt.ll +++ test/Transforms/PGOProfile/memop_size_opt.ll @@ -0,0 +1,100 @@ +; RUN: opt < %s -passes=pgo-memop-opt -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -S | FileCheck %s --check-prefix=MEMOP_OPT +; RUN: opt < %s -pgo-memop-opt -pgo-memop-count-threshold=90 -pgo-memop-percent-threshold=15 -S | FileCheck %s --check-prefix=MEMOP_OPT + +target datalayout = "e-m:e-i64:64-f80:128-n8:16:32:64-S128" +target triple = "x86_64-unknown-linux-gnu" + +define void @foo(i8* %dst, i8* %src, i32* %a, i32 %n) !prof !27 { +entry: + br label %for.cond + +for.cond: + %i.0 = phi i32 [ 0, %entry ], [ %inc5, %for.inc4 ] + %cmp = icmp slt i32 %i.0, %n + br i1 %cmp, label %for.body, label %for.end6, !prof !28 + +for.body: + br label %for.cond1 + +for.cond1: + %j.0 = phi i32 [ 0, %for.body ], [ %inc, %for.inc ] + %idx.ext = sext i32 %i.0 to i64 + %add.ptr = getelementptr inbounds i32, i32* %a, i64 %idx.ext + %0 = load i32, i32* %add.ptr, align 4 + %cmp2 = icmp slt i32 %j.0, %0 + br i1 %cmp2, label %for.body3, label %for.end, !prof !29 + +for.body3: + %add = add nsw i32 %i.0, 1 + %conv = sext i32 %add to i64 + call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof !30 + br label %for.inc + +; MEMOP_OPT: switch i64 %conv, label %[[Default_LABEL:.*]] [ +; MEMOP_OPT: i64 1, label %[[CASE_1_LABEL:.*]] +; MEMOP_OPT: ], !prof [[SWITCH_BW:![0-9]+]] +; MEMOP_OPT: [[CASE_1_LABEL]]: +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 1, i32 1, i1 false) +; MEMOP_OPT: br label %[[MERGE_LABEL:.*]] +; MEMOP_OPT: [[Default_LABEL]]: +; MEMOP_OPT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false) +; MEMOP_OPT-NOT: call void @llvm.memcpy.p0i8.p0i8.i64(i8* %dst, i8* %src, i64 %conv, i32 1, i1 false), !prof +; MEMOP_OPT: br label %[[MERGE_LABEL]] +; MEMOP_OPT: [[MERGE_LABEL]]: +; MEMOP_OPT: br label %for.inc +; MEMOP_OPT: [[SWITCH_BW]] = !{!"branch_weights", i32 457, i32 99} + +for.inc: + %inc = add nsw i32 %j.0, 1 + br label %for.cond1 + +for.end: + br label %for.inc4 + +for.inc4: + %inc5 = add nsw i32 %i.0, 1 + br label %for.cond + +for.end6: + ret void +} + +!llvm.module.flags = !{!0} + +!0 = !{i32 1, !"ProfileSummary", !1} +!1 = !{!2, !3, !4, !5, !6, !7, !8, !9} +!2 = !{!"ProfileFormat", !"InstrProf"} +!3 = !{!"TotalCount", i64 579} +!4 = !{!"MaxCount", i64 556} +!5 = !{!"MaxInternalCount", i64 20} +!6 = !{!"MaxFunctionCount", i64 556} +!7 = !{!"NumCounts", i64 6} +!8 = !{!"NumFunctions", i64 3} +!9 = !{!"DetailedSummary", !10} +!10 = !{!11, !12, !13, !14, !15, !16, !16, !17, !17, !18, !19, !20, !21, !22, !23, !24, !25, !26} +!11 = !{i32 10000, i64 556, i32 1} +!12 = !{i32 100000, i64 556, i32 1} +!13 = !{i32 200000, i64 556, i32 1} +!14 = !{i32 300000, i64 556, i32 1} +!15 = !{i32 400000, i64 556, i32 1} +!16 = !{i32 500000, i64 556, i32 1} +!17 = !{i32 600000, i64 556, i32 1} +!18 = !{i32 700000, i64 556, i32 1} +!19 = !{i32 800000, i64 556, i32 1} +!20 = !{i32 900000, i64 556, i32 1} +!21 = !{i32 950000, i64 556, i32 1} +!22 = !{i32 990000, i64 20, i32 2} +!23 = !{i32 999000, i64 1, i32 5} +!24 = !{i32 999900, i64 1, i32 5} +!25 = !{i32 999990, i64 1, i32 5} +!26 = !{i32 999999, i64 1, i32 5} +!27 = !{!"function_entry_count", i64 1} +!28 = !{!"branch_weights", i32 20, i32 1} +!29 = !{!"branch_weights", i32 556, i32 20} +!30 = !{!"VP", i32 1, i64 556, i64 1, i64 99, i64 2, i64 88, i64 3, i64 77, i64 9, i64 72, i64 4, i64 66, i64 5, i64 55, i64 6, i64 44, i64 7, i64 33, i64 8, i64 22} + +declare void @llvm.lifetime.start(i64, i8* nocapture) + +declare void @llvm.memcpy.p0i8.p0i8.i64(i8* nocapture writeonly, i8* nocapture readonly, i64, i32, i1) + +declare void @llvm.lifetime.end(i64, i8* nocapture)