Index: clang/include/clang/Basic/CodeGenOptions.def =================================================================== --- clang/include/clang/Basic/CodeGenOptions.def +++ clang/include/clang/Basic/CodeGenOptions.def @@ -224,6 +224,7 @@ CODEGENOPT(StrictEnums , 1, 0) ///< Optimize based on strict enum definition. CODEGENOPT(StrictVTablePointers, 1, 0) ///< Optimize based on the strict vtable pointers CODEGENOPT(TimePasses , 1, 0) ///< Set when -ftime-report is enabled. +CODEGENOPT(TimeTrace , 1, 0) ///< Set when -ftime-trace is enabled. CODEGENOPT(UnrollLoops , 1, 0) ///< Control whether loops are unrolled. CODEGENOPT(RerollLoops , 1, 0) ///< Control whether loops are rerolled. CODEGENOPT(NoUseJumpTables , 1, 0) ///< Set when -fno-jump-tables is enabled. Index: clang/include/clang/Driver/Options.td =================================================================== --- clang/include/clang/Driver/Options.td +++ clang/include/clang/Driver/Options.td @@ -1732,6 +1732,7 @@ def : Flag<["-"], "fterminated-vtables">, Alias; def fthreadsafe_statics : Flag<["-"], "fthreadsafe-statics">, Group; def ftime_report : Flag<["-"], "ftime-report">, Group, Flags<[CC1Option]>; +def ftime_trace : Flag<["-"], "ftime-trace">, Group, Flags<[CC1Option]>; def ftlsmodel_EQ : Joined<["-"], "ftls-model=">, Group, Flags<[CC1Option]>; def ftrapv : Flag<["-"], "ftrapv">, Group, Flags<[CC1Option]>, HelpText<"Trap on integer overflow">; Index: clang/include/clang/Frontend/FrontendOptions.h =================================================================== --- clang/include/clang/Frontend/FrontendOptions.h +++ clang/include/clang/Frontend/FrontendOptions.h @@ -256,6 +256,9 @@ /// Show timers for individual actions. unsigned ShowTimers : 1; + /// Output time trace profile. + unsigned TimeTrace : 1; + /// Show the -version text. unsigned ShowVersion : 1; @@ -437,13 +440,14 @@ public: FrontendOptions() : DisableFree(false), RelocatablePCH(false), ShowHelp(false), - ShowStats(false), ShowTimers(false), ShowVersion(false), - FixWhatYouCan(false), FixOnlyWarnings(false), FixAndRecompile(false), - FixToTemporaries(false), ARCMTMigrateEmitARCErrors(false), - SkipFunctionBodies(false), UseGlobalModuleIndex(true), - GenerateGlobalModuleIndex(true), ASTDumpDecls(false), - ASTDumpLookups(false), BuildingImplicitModule(false), - ModulesEmbedAllFiles(false), IncludeTimestamps(true) {} + ShowStats(false), ShowTimers(false), TimeTrace(false), + ShowVersion(false), FixWhatYouCan(false), FixOnlyWarnings(false), + FixAndRecompile(false), FixToTemporaries(false), + ARCMTMigrateEmitARCErrors(false), SkipFunctionBodies(false), + UseGlobalModuleIndex(true), GenerateGlobalModuleIndex(true), + ASTDumpDecls(false), ASTDumpLookups(false), + BuildingImplicitModule(false), ModulesEmbedAllFiles(false), + IncludeTimestamps(true) {} /// getInputKindForExtension - Return the appropriate input kind for a file /// extension. For example, "c" would return InputKind::C. Index: clang/lib/CodeGen/CodeGenModule.cpp =================================================================== --- clang/lib/CodeGen/CodeGenModule.cpp +++ clang/lib/CodeGen/CodeGenModule.cpp @@ -57,6 +57,7 @@ #include "llvm/Support/ConvertUTF.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/MD5.h" +#include "llvm/Support/TimeProfiler.h" using namespace clang; using namespace CodeGen; @@ -2479,6 +2480,10 @@ if (!shouldEmitFunction(GD)) return; + llvm::TimeTraceScope timeScope( + "CodeGen Function", + TIME_TRACE_OR_NULL(FD->getQualifiedNameAsString().c_str())); + if (const auto *Method = dyn_cast(D)) { // Make sure to emit the definition(s) before we emit the thunks. // This is necessary for the generation of certain thunks. Index: clang/lib/Driver/ToolChains/Clang.cpp =================================================================== --- clang/lib/Driver/ToolChains/Clang.cpp +++ clang/lib/Driver/ToolChains/Clang.cpp @@ -4524,6 +4524,7 @@ Args.AddLastArg(CmdArgs, options::OPT_fdiagnostics_print_source_range_info); Args.AddLastArg(CmdArgs, options::OPT_fdiagnostics_parseable_fixits); Args.AddLastArg(CmdArgs, options::OPT_ftime_report); + Args.AddLastArg(CmdArgs, options::OPT_ftime_trace); Args.AddLastArg(CmdArgs, options::OPT_ftrapv); if (Arg *A = Args.getLastArg(options::OPT_ftrapv_handler_EQ)) { Index: clang/lib/Frontend/CompilerInstance.cpp =================================================================== --- clang/lib/Frontend/CompilerInstance.cpp +++ clang/lib/Frontend/CompilerInstance.cpp @@ -46,6 +46,7 @@ #include "llvm/Support/Path.h" #include "llvm/Support/Program.h" #include "llvm/Support/Signals.h" +#include "llvm/Support/TimeProfiler.h" #include "llvm/Support/Timer.h" #include "llvm/Support/raw_ostream.h" #include @@ -1033,6 +1034,8 @@ [](CompilerInstance &) {}, llvm::function_ref PostBuildStep = [](CompilerInstance &) {}) { + llvm::TimeTraceScope timeScope("Module Compile", ModuleName.data()); + // Construct a compiler invocation for creating this module. auto Invocation = std::make_shared(ImportingInstance.getInvocation()); @@ -1712,6 +1715,7 @@ Timer.init("loading." + ModuleFileName, "Loading " + ModuleFileName, *FrontendTimerGroup); llvm::TimeRegion TimeLoading(FrontendTimerGroup ? &Timer : nullptr); + llvm::TimeTraceScope timeScope("Module Load", ModuleName.data()); // Try to load the module file. If we are not trying to load from the // module cache, we don't know how to rebuild modules. Index: clang/lib/Frontend/CompilerInvocation.cpp =================================================================== --- clang/lib/Frontend/CompilerInvocation.cpp +++ clang/lib/Frontend/CompilerInvocation.cpp @@ -1708,6 +1708,7 @@ Opts.ShowHelp = Args.hasArg(OPT_help); Opts.ShowStats = Args.hasArg(OPT_print_stats); Opts.ShowTimers = Args.hasArg(OPT_ftime_report); + Opts.TimeTrace = Args.hasArg(OPT_ftime_trace); Opts.ShowVersion = Args.hasArg(OPT_version); Opts.ASTMergeFiles = Args.getAllArgValues(OPT_ast_merge); Opts.LLVMArgs = Args.getAllArgValues(OPT_mllvm); Index: clang/lib/Parse/ParseAST.cpp =================================================================== --- clang/lib/Parse/ParseAST.cpp +++ clang/lib/Parse/ParseAST.cpp @@ -22,6 +22,7 @@ #include "clang/Sema/SemaConsumer.h" #include "clang/Sema/TemplateInstCallback.h" #include "llvm/Support/CrashRecoveryContext.h" +#include "llvm/Support/TimeProfiler.h" #include #include @@ -150,6 +151,7 @@ bool HaveLexer = S.getPreprocessor().getCurrentLexer(); if (HaveLexer) { + llvm::TimeTraceScope scope("Frontend", ""); P.Initialize(); Parser::DeclGroupPtrTy ADecl; for (bool AtEOF = P.ParseFirstTopLevelDecl(ADecl); !AtEOF; @@ -166,7 +168,10 @@ for (Decl *D : S.WeakTopLevelDecls()) Consumer->HandleTopLevelDecl(DeclGroupRef(D)); - Consumer->HandleTranslationUnit(S.getASTContext()); + { + llvm::TimeTraceScope scope("Backend", ""); + Consumer->HandleTranslationUnit(S.getASTContext()); + } // Finalize the template instantiation observer chain. // FIXME: This (and init.) should be done in the Sema class, but because Index: clang/lib/Parse/ParseDeclCXX.cpp =================================================================== --- clang/lib/Parse/ParseDeclCXX.cpp +++ clang/lib/Parse/ParseDeclCXX.cpp @@ -10,7 +10,6 @@ // //===----------------------------------------------------------------------===// -#include "clang/Parse/Parser.h" #include "clang/AST/ASTContext.h" #include "clang/AST/DeclTemplate.h" #include "clang/AST/PrettyDeclStackTrace.h" @@ -19,11 +18,13 @@ #include "clang/Basic/OperatorKinds.h" #include "clang/Basic/TargetInfo.h" #include "clang/Parse/ParseDiagnostic.h" +#include "clang/Parse/Parser.h" #include "clang/Parse/RAIIObjectsForParser.h" #include "clang/Sema/DeclSpec.h" #include "clang/Sema/ParsedTemplate.h" #include "clang/Sema/Scope.h" #include "llvm/ADT/SmallString.h" +#include "llvm/Support/TimeProfiler.h" using namespace clang; @@ -3109,6 +3110,12 @@ TagType == DeclSpec::TST_union || TagType == DeclSpec::TST_class) && "Invalid TagType!"); + llvm::TimeTraceScope timeScope( + "ParseClass", + TIME_TRACE_OR_NULL( + TagDecl != nullptr && isa(TagDecl) + ? cast(TagDecl)->getQualifiedNameAsString().data() + : "")); PrettyDeclStackTraceEntry CrashInfo(Actions.Context, TagDecl, RecordLoc, "parsing struct/union/class body"); Index: clang/lib/Parse/ParseTemplate.cpp =================================================================== --- clang/lib/Parse/ParseTemplate.cpp +++ clang/lib/Parse/ParseTemplate.cpp @@ -18,6 +18,7 @@ #include "clang/Sema/DeclSpec.h" #include "clang/Sema/ParsedTemplate.h" #include "clang/Sema/Scope.h" +#include "llvm/Support/TimeProfiler.h" using namespace clang; /// Parse a template declaration, explicit instantiation, or @@ -231,6 +232,12 @@ return nullptr; } + llvm::TimeTraceScope timeScope( + "ParseTemplate", + TIME_TRACE_OR_NULL(DeclaratorInfo.getIdentifier() != nullptr + ? DeclaratorInfo.getIdentifier()->getName().data() + : "")); + LateParsedAttrList LateParsedAttrs(true); if (DeclaratorInfo.isFunctionDeclarator()) MaybeParseGNUAttributes(DeclaratorInfo, &LateParsedAttrs); Index: clang/lib/Sema/Sema.cpp =================================================================== --- clang/lib/Sema/Sema.cpp +++ clang/lib/Sema/Sema.cpp @@ -39,6 +39,8 @@ #include "clang/Sema/TemplateInstCallback.h" #include "llvm/ADT/DenseMap.h" #include "llvm/ADT/SmallSet.h" +#include "llvm/Support/TimeProfiler.h" + using namespace clang; using namespace sema; @@ -92,6 +94,12 @@ SourceManager &SM = S->getSourceManager(); SourceLocation IncludeLoc = SM.getIncludeLoc(SM.getFileID(Loc)); if (IncludeLoc.isValid()) { + if (llvm::TimeTraceProfilerEnabled()) { + auto fe = SM.getFileEntryForID(SM.getFileID(Loc)); + llvm::TimeTraceProfilerBegin( + "Source", fe != nullptr ? fe->getName().data() : ""); + } + IncludeStack.push_back(IncludeLoc); S->DiagnoseNonDefaultPragmaPack( Sema::PragmaPackDiagnoseKind::NonDefaultStateAtInclude, IncludeLoc); @@ -99,10 +107,14 @@ break; } case ExitFile: - if (!IncludeStack.empty()) + if (!IncludeStack.empty()) { + if (llvm::TimeTraceProfilerEnabled()) + llvm::TimeTraceProfilerEnd(); + S->DiagnoseNonDefaultPragmaPack( Sema::PragmaPackDiagnoseKind::ChangedStateAtExit, IncludeStack.pop_back_val()); + } break; default: break; @@ -914,7 +926,10 @@ Pending.begin(), Pending.end()); } - PerformPendingInstantiations(); + { + llvm::TimeTraceScope timeScope("PerformPendingInstantiations", ""); + PerformPendingInstantiations(); + } assert(LateParsedInstantiations.empty() && "end of TU template instantiation should not create more " Index: clang/lib/Sema/SemaTemplateInstantiate.cpp =================================================================== --- clang/lib/Sema/SemaTemplateInstantiate.cpp +++ clang/lib/Sema/SemaTemplateInstantiate.cpp @@ -25,6 +25,7 @@ #include "clang/Sema/Template.h" #include "clang/Sema/TemplateDeduction.h" #include "clang/Sema/TemplateInstCallback.h" +#include "llvm/Support/TimeProfiler.h" using namespace clang; using namespace sema; @@ -2008,6 +2009,11 @@ Instantiation->getInstantiatedFromMemberClass(), Pattern, PatternDef, TSK, Complain)) return true; + + llvm::TimeTraceScope timeScope( + "InstantiateClass", + TIME_TRACE_OR_NULL(Instantiation->getQualifiedNameAsString().c_str())); + Pattern = PatternDef; // Record the point of instantiation. Index: clang/lib/Sema/SemaTemplateInstantiateDecl.cpp =================================================================== --- clang/lib/Sema/SemaTemplateInstantiateDecl.cpp +++ clang/lib/Sema/SemaTemplateInstantiateDecl.cpp @@ -23,6 +23,7 @@ #include "clang/Sema/Lookup.h" #include "clang/Sema/Template.h" #include "clang/Sema/TemplateInstCallback.h" +#include "llvm/Support/TimeProfiler.h" using namespace clang; @@ -4084,6 +4085,10 @@ return; } + llvm::TimeTraceScope timeScope( + "InstantiateFunction", + TIME_TRACE_OR_NULL(Function->getQualifiedNameAsString().c_str())); + // If we're performing recursive template instantiation, create our own // queue of pending implicit instantiations that we will instantiate later, // while we're still within our own instantiation context. Index: clang/lib/Serialization/GlobalModuleIndex.cpp =================================================================== --- clang/lib/Serialization/GlobalModuleIndex.cpp +++ clang/lib/Serialization/GlobalModuleIndex.cpp @@ -10,11 +10,11 @@ // //===----------------------------------------------------------------------===// +#include "clang/Serialization/GlobalModuleIndex.h" #include "ASTReaderInternals.h" #include "clang/Basic/FileManager.h" #include "clang/Lex/HeaderSearch.h" #include "clang/Serialization/ASTBitCodes.h" -#include "clang/Serialization/GlobalModuleIndex.h" #include "clang/Serialization/Module.h" #include "clang/Serialization/PCHContainerOperations.h" #include "llvm/ADT/DenseMap.h" @@ -28,6 +28,7 @@ #include "llvm/Support/MemoryBuffer.h" #include "llvm/Support/OnDiskHashTable.h" #include "llvm/Support/Path.h" +#include "llvm/Support/TimeProfiler.h" #include using namespace clang; using namespace serialization; @@ -126,6 +127,7 @@ llvm::BitstreamCursor Cursor) : Buffer(std::move(Buffer)), IdentifierIndex(), NumIdentifierLookups(), NumIdentifierLookupHits() { + llvm::TimeTraceScope timeScope("Module LoadIndex", ""); // Read the global index. bool InGlobalIndexBlock = false; bool Done = false; @@ -739,6 +741,7 @@ } using namespace llvm; + llvm::TimeTraceScope timeScope("Module WriteIndex", ""); // Emit the file header. Stream.Emit((unsigned)'B', 8); Index: clang/tools/driver/cc1_main.cpp =================================================================== --- clang/tools/driver/cc1_main.cpp +++ clang/tools/driver/cc1_main.cpp @@ -34,8 +34,10 @@ #include "llvm/Support/Compiler.h" #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/ManagedStatic.h" +#include "llvm/Support/Path.h" #include "llvm/Support/Signals.h" #include "llvm/Support/TargetSelect.h" +#include "llvm/Support/TimeProfiler.h" #include "llvm/Support/Timer.h" #include "llvm/Support/raw_ostream.h" #include @@ -194,6 +196,9 @@ bool Success = CompilerInvocation::CreateFromArgs( Clang->getInvocation(), Argv.begin(), Argv.end(), Diags); + if (Clang->getFrontendOpts().TimeTrace) + llvm::TimeTraceProfilerInitialize(); + // Infer the builtin include path if unspecified. if (Clang->getHeaderSearchOpts().UseBuiltinIncludes && Clang->getHeaderSearchOpts().ResourceDir.empty()) @@ -215,12 +220,29 @@ return 1; // Execute the frontend actions. - Success = ExecuteCompilerInvocation(Clang.get()); + { + llvm::TimeTraceScope scope("ExecuteCompiler", ""); + Success = ExecuteCompilerInvocation(Clang.get()); + } // If any timers were active but haven't been destroyed yet, print their // results now. This happens in -disable-free mode. llvm::TimerGroup::printAll(llvm::errs()); + if (llvm::TimeTraceProfilerEnabled()) { + SmallString<128> Path(Clang->getFrontendOpts().OutputFile); + llvm::sys::path::replace_extension(Path, "json"); + auto profilerOutput = + Clang->createOutputFile(Path.str(), + /*Binary=*/false, + /*RemoveFileOnSignal=*/false, "", + /*Extension=*/"json", + /*useTemporary=*/false); + + llvm::TimeTraceProfilerWrite(profilerOutput); + llvm::TimeTraceProfilerCleanup(); + } + // Our error handler depends on the Diagnostics object, which we're // potentially about to delete. Uninstall the handler now so that any // later errors use the default handling behavior instead. Index: llvm/lib/IR/LegacyPassManager.cpp =================================================================== --- llvm/lib/IR/LegacyPassManager.cpp +++ llvm/lib/IR/LegacyPassManager.cpp @@ -27,6 +27,7 @@ #include "llvm/Support/ErrorHandling.h" #include "llvm/Support/ManagedStatic.h" #include "llvm/Support/Mutex.h" +#include "llvm/Support/TimeProfiler.h" #include "llvm/Support/Timer.h" #include "llvm/Support/raw_ostream.h" #include @@ -1628,6 +1629,10 @@ FunctionSize = F.getInstructionCount(); } + bool profileTime = llvm::TimeTraceProfilerEnabled(); + if (profileTime) + llvm::TimeTraceProfilerBegin("OptFunction", F.getName().data()); + for (unsigned Index = 0; Index < getNumContainedPasses(); ++Index) { FunctionPass *FP = getContainedPass(Index); bool LocalChanged = false; @@ -1668,12 +1673,17 @@ recordAvailableAnalysis(FP); removeDeadPasses(FP, F.getName(), ON_FUNCTION_MSG); } + + if (profileTime) + llvm::TimeTraceProfilerEnd(); + return Changed; } bool FPPassManager::runOnModule(Module &M) { bool Changed = false; + llvm::TimeTraceScope timeScope("OptModule", M.getName().data()); for (Function &F : M) Changed |= runOnFunction(F); @@ -1706,6 +1716,8 @@ /// the module, and if so, return true. bool MPPassManager::runOnModule(Module &M) { + llvm::TimeTraceScope timeScope("OptModule", M.getName().data()); + bool Changed = false; // Initialize on-the-fly passes Index: llvm/lib/Support/CMakeLists.txt =================================================================== --- llvm/lib/Support/CMakeLists.txt +++ llvm/lib/Support/CMakeLists.txt @@ -132,6 +132,7 @@ TarWriter.cpp TargetParser.cpp ThreadPool.cpp + TimeProfiler.cpp Timer.cpp ToolOutputFile.cpp TrigramIndex.cpp Index: llvm/lib/Support/TimeProfiler.h =================================================================== --- /dev/null +++ llvm/lib/Support/TimeProfiler.h @@ -0,0 +1,71 @@ +//===- llvm/Support/TimeProfiler.h - Hierarchical Time Profiler -*- C++ -*-===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// + +#ifndef LLVM_SUPPORT_TIME_PROFILER_H +#define LLVM_SUPPORT_TIME_PROFILER_H + +#include "llvm/Support/raw_ostream.h" + +namespace llvm { + +struct TimeTraceProfiler; +extern TimeTraceProfiler *TimeTraceProfilerInstance; + +/// Initialize the time trace profiler. +/// This sets up the global \p TimeTraceProfilerInstance +/// variable to be the profiler instance. +void TimeTraceProfilerInitialize(); + +/// Cleanup the time trace profiler, if it was initialized. +void TimeTraceProfilerCleanup(); + +/// Is the time trace profiler enabled, i.e. initialized? +inline bool TimeTraceProfilerEnabled() { + return TimeTraceProfilerInstance != nullptr; +} + +/// Write profiling data to output file. +/// Data produced is JSON, in Chrome "Trace Event" format, see +/// https://docs.google.com/document/d/1CvAClvFfyA5R-PhYUmn5OOQtYMH4h6I0nSsKchNAySU/preview +void TimeTraceProfilerWrite(std::unique_ptr &OS); + +/// Manually begin a time section, with the given \p name and \p detail. +/// Profiler copies the string data, so the pointers can be given into +/// temporaries. Time sections can be hierarchical; every Begin must have a +/// matching End pair but they can nest. +void TimeTraceProfilerBegin(const char *name, const char *detail); + +/// Manually end the last time section. +void TimeTraceProfilerEnd(); + +/// The TimeTraceScope is a helper class to call the begin and end functions. +/// of the time trace profiler. When the object is constructed, it +/// begins the section; and wen it is destroyed, it stops +/// it. If the time profiler is not initialized, the overhead +/// is a single branch. +struct TimeTraceScope { + TimeTraceScope(const char *name, const char *detail) { + if (TimeTraceProfilerInstance != nullptr) + TimeTraceProfilerBegin(name, detail); + } + ~TimeTraceScope() { + if (TimeTraceProfilerInstance != nullptr) + TimeTraceProfilerEnd(); + } +}; + +/// Evaluates expression if time trace profiler is enabled, or passed null when +/// it is not. Useful to avoid possibly expensive work in creating a string for +/// profiling, when profiler is not enabled at all. +#define TIME_TRACE_OR_NULL(expr) \ + (llvm::TimeTraceProfilerInstance != nullptr ? (expr) : nullptr) + +} // end namespace llvm + +#endif Index: llvm/lib/Support/TimeProfiler.cpp =================================================================== --- /dev/null +++ llvm/lib/Support/TimeProfiler.cpp @@ -0,0 +1,178 @@ +//===-- TimeProfiler.cpp - Hierarchical Time Profiler ---------------------===// +// +// The LLVM Compiler Infrastructure +// +// This file is distributed under the University of Illinois Open Source +// License. See LICENSE.TXT for details. +// +//===----------------------------------------------------------------------===// +// +/// \file Hierarchical time profiler implementation. +// +//===----------------------------------------------------------------------===// + +#include "llvm/Support/TimeProfiler.h" +#include "llvm/Support/FileSystem.h" +#include +#include +#include +#include +#include + +using namespace std::chrono; + +namespace llvm { + +TimeTraceProfiler *TimeTraceProfilerInstance = nullptr; + +static std::string EscapeString(const char *src) { + std::string os; + while (*src) { + char c = *src; + switch (c) { + case '"': + case '\\': + case '\b': + case '\f': + case '\n': + case '\r': + case '\t': + os += '\\'; + os += c; + break; + default: + if (c >= 32 && c < 126) { + os += c; + } + } + ++src; + } + return os; +} + +typedef duration DurationType; +typedef std::pair NameAndDuration; + +struct Entry { + time_point Start; + DurationType Duration; + std::string Name; + std::string Detail; +}; + +struct TimeTraceProfiler { + TimeTraceProfiler() { + Stack.reserve(8); + Entries.reserve(128); + StartTime = steady_clock::now(); + } + + void Begin(const std::string &name, const std::string &detail) { + Entry e = {steady_clock::now(), {}, name, detail}; + Stack.emplace_back(e); + } + + void End() { + assert(!Stack.empty() && "Must call Begin first"); + auto &e = Stack.back(); + e.Duration = steady_clock::now() - e.Start; + + // only include sections longer than 500us + if (duration_cast(e.Duration).count() > 500) + Entries.emplace_back(e); + + // track total time taken by each "name", but only the topmost levels of + // them; e.g. if there's a template instantiation that instantiates other + // templates from within, we only want to add the topmost one. "topmost" + // happens to be the ones that don't have any currently open entries above + // itself. + if (std::find_if(++Stack.rbegin(), Stack.rend(), [&](const Entry &val) { + return val.Name == e.Name; + }) == Stack.rend()) { + TotalPerName[e.Name] += e.Duration; + CountPerName[e.Name]++; + } + + Stack.pop_back(); + } + + void Write(std::unique_ptr &os) { + assert(Stack.empty() && + "All profiler sections should be ended when calling Write"); + + *os << "{ \"traceEvents\": [\n"; + + // emit all events for the main flame graph + for (const auto &e : Entries) { + auto startUs = duration_cast(e.Start - StartTime).count(); + auto durUs = duration_cast(e.Duration).count(); + *os << "{ \"pid\":1, \"tid\":0, \"ph\":\"X\", \"ts\":" << startUs + << ", \"dur\":" << durUs << ", \"name\":\"" + << EscapeString(e.Name.c_str()) << "\", \"args\":{ \"detail\":\"" + << EscapeString(e.Detail.c_str()) << "\"} },\n"; + } + + // emit totals by section name as additional "thread" events, sorted from + // longest one + int tid = 1; + std::vector sortedTotals; + sortedTotals.reserve(TotalPerName.size()); + for (const auto &e : TotalPerName) { + sortedTotals.push_back(e); + } + std::sort(sortedTotals.begin(), sortedTotals.end(), + [](const NameAndDuration &a, const NameAndDuration &b) { + return a.second > b.second; + }); + for (const auto &e : sortedTotals) { + auto durUs = duration_cast(e.second).count(); + *os << "{ \"pid\":1, \"tid\":" << tid << ", \"ph\":\"X\", \"ts\":" << 0 + << ", \"dur\":" << durUs << ", \"name\":\"Total " + << EscapeString(e.first.c_str()) + << "\", \"args\":{ \"count\":" << CountPerName[e.first] + << ", \"avg ms\":" << (durUs / CountPerName[e.first] / 1000) + << "} },\n"; + ++tid; + } + + // emit metadata event with process name + *os << "{ \"cat\":\"\", \"pid\":1, \"tid\":0, \"ts\":0, \"ph\":\"M\", " + "\"name\":\"process_name\", \"args\":{ \"name\":\"clang\" } }\n"; + *os << "] }\n"; + } + + std::vector Stack; + std::vector Entries; + std::unordered_map TotalPerName; + std::unordered_map CountPerName; + time_point StartTime; +}; + +void TimeTraceProfilerInitialize() { + assert(TimeTraceProfilerInstance == nullptr && + "Profiler should not be initialized"); + TimeTraceProfilerInstance = new TimeTraceProfiler(); +} + +void TimeTraceProfilerCleanup() { + delete TimeTraceProfilerInstance; + TimeTraceProfilerInstance = nullptr; +} + +void TimeTraceProfilerWrite(std::unique_ptr &OS) { + assert(TimeTraceProfilerInstance != nullptr && + "Profiler object can't be null"); + TimeTraceProfilerInstance->Write(OS); +} + +void TimeTraceProfilerBegin(const char *name, const char *detail) { + if (TimeTraceProfilerInstance != nullptr) + TimeTraceProfilerInstance->Begin(name, detail); +} + +void TimeTraceProfilerEnd() { + if (TimeTraceProfilerInstance != nullptr) + TimeTraceProfilerInstance->End(); +} + +} // namespace llvm