Adds -ftime-trace option to clang that produces Chrome chrome://tracing compatible JSON profiling output dumps.

This change adds hierarchical "time trace" profiling blocks that can be visualized in Chrome, in a "flame chart" style. Each profiling block can have a "detail" string that for example indicates the file being processed, template name being instantiated, function being optimized etc.

This is taken from GitHub PR: https://github.com/aras-p/llvm-project-20170507/pull/2

Patch by Aras Pranckevičius.

Differential Revision: https://reviews.llvm.org/D58675

llvm-svn: 357340

clang/include/clang/Basic/CodeGenOptions.def

@@ -224,6 +224,7 @@ CODEGENOPT(FineGrainedBitfieldAccesses, 1, 0) ///< Enable fine-grained bitfield
 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.

clang/include/clang/Driver/Options.td

@@ -1745,6 +1745,7 @@ def Wframe_larger_than_EQ : Joined<["-"], "Wframe-larger-than=">, Group<f_Group>
 def : Flag<["-"], "fterminated-vtables">, Alias<fapple_kext>;
 def fthreadsafe_statics : Flag<["-"], "fthreadsafe-statics">, Group<f_Group>;
 def ftime_report : Flag<["-"], "ftime-report">, Group<f_Group>, Flags<[CC1Option]>;
+def ftime_trace : Flag<["-"], "ftime-trace">, Group<f_Group>, Flags<[CC1Option]>;
 def ftlsmodel_EQ : Joined<["-"], "ftls-model=">, Group<f_Group>, Flags<[CC1Option]>;
 def ftrapv : Flag<["-"], "ftrapv">, Group<f_Group>, Flags<[CC1Option]>,
   HelpText<"Trap on integer overflow">;

clang/include/clang/Frontend/FrontendOptions.h

@@ -256,6 +256,9 @@ public:
   /// 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:
 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.

clang/lib/CodeGen/BackendUtil.cpp

@@ -42,6 +42,7 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/PrettyStackTrace.h"
 #include "llvm/Support/TargetRegistry.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/Timer.h"
 #include "llvm/Support/raw_ostream.h"
 #include "llvm/Target/TargetMachine.h"
@@ -1382,6 +1383,9 @@ void clang::EmitBackendOutput(DiagnosticsEngine &Diags,
                               const llvm::DataLayout &TDesc, Module *M,
                               BackendAction Action,
                               std::unique_ptr<raw_pwrite_stream> OS) {
+
+  llvm::TimeTraceScope TimeScope("Backend", StringRef(""));
+
   std::unique_ptr<llvm::Module> EmptyModule;
   if (!CGOpts.ThinLTOIndexFile.empty()) {
     // If we are performing a ThinLTO importing compile, load the function index

clang/lib/CodeGen/CodeGenModule.cpp

@@ -58,6 +58,7 @@
 #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;
@@ -2482,6 +2483,9 @@ void CodeGenModule::EmitGlobalDefinition(GlobalDecl GD, llvm::GlobalValue *GV) {
     if (!shouldEmitFunction(GD))
       return;
 
+    llvm::TimeTraceScope TimeScope(
+        "CodeGen Function", [&]() { return FD->getQualifiedNameAsString(); });
+
     if (const auto *Method = dyn_cast<CXXMethodDecl>(D)) {
       // Make sure to emit the definition(s) before we emit the thunks.
       // This is necessary for the generation of certain thunks.

clang/lib/Driver/ToolChains/Clang.cpp

@@ -4548,6 +4548,7 @@ void Clang::ConstructJob(Compilation &C, const JobAction &JA,
   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);
   Args.AddLastArg(CmdArgs, options::OPT_malign_double);
 

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 <sys/stat.h>
@@ -1025,6 +1026,8 @@ compileModuleImpl(CompilerInstance &ImportingInstance, SourceLocation ImportLoc,
                       [](CompilerInstance &) {},
                   llvm::function_ref<void(CompilerInstance &)> PostBuildStep =
                       [](CompilerInstance &) {}) {
+  llvm::TimeTraceScope TimeScope("Module Compile", ModuleName);
+
   // Construct a compiler invocation for creating this module.
   auto Invocation =
       std::make_shared<CompilerInvocation>(ImportingInstance.getInvocation());
@@ -1701,6 +1704,7 @@ CompilerInstance::loadModule(SourceLocation ImportLoc,
       Timer.init("loading." + ModuleFileName, "Loading " + ModuleFileName,
                  *FrontendTimerGroup);
     llvm::TimeRegion TimeLoading(FrontendTimerGroup ? &Timer : nullptr);
+    llvm::TimeTraceScope TimeScope("Module Load", ModuleName);
 
     // 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.

clang/lib/Frontend/CompilerInvocation.cpp

@@ -1717,6 +1717,7 @@ static InputKind ParseFrontendArgs(FrontendOptions &Opts, ArgList &Args,
   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);

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 <cstdio>
 #include <memory>
 
@@ -150,6 +151,7 @@ void clang::ParseAST(Sema &S, bool PrintStats, bool SkipFunctionBodies) {
   bool HaveLexer = S.getPreprocessor().getCurrentLexer();
 
   if (HaveLexer) {
+    llvm::TimeTraceScope TimeScope("Frontend", StringRef(""));
     P.Initialize();
     Parser::DeclGroupPtrTy ADecl;
     for (bool AtEOF = P.ParseFirstTopLevelDecl(ADecl); !AtEOF;

clang/lib/Parse/ParseDeclCXX.cpp

@@ -24,6 +24,7 @@
 #include "clang/Sema/ParsedTemplate.h"
 #include "clang/Sema/Scope.h"
 #include "llvm/ADT/SmallString.h"
+#include "llvm/Support/TimeProfiler.h"
 
 using namespace clang;
 
@@ -3114,6 +3115,12 @@ void Parser::ParseCXXMemberSpecification(SourceLocation RecordLoc,
          TagType == DeclSpec::TST_union  ||
          TagType == DeclSpec::TST_class) && "Invalid TagType!");
 
+  llvm::TimeTraceScope TimeScope("ParseClass", [&]() {
+    if (auto *TD = dyn_cast_or_null<NamedDecl>(TagDecl))
+      return TD->getQualifiedNameAsString();
+    return std::string("<anonymous>");
+  });
+
   PrettyDeclStackTraceEntry CrashInfo(Actions.Context, TagDecl, RecordLoc,
                                       "parsing struct/union/class body");
 

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 @@ Decl *Parser::ParseSingleDeclarationAfterTemplate(
     return nullptr;
   }
 
+  llvm::TimeTraceScope TimeScope("ParseTemplate", [&]() {
+    return DeclaratorInfo.getIdentifier() != nullptr
+               ? DeclaratorInfo.getIdentifier()->getName()
+               : "<unknown>";
+  });
+
   LateParsedAttrList LateParsedAttrs(true);
   if (DeclaratorInfo.isFunctionDeclarator())
     MaybeParseGNUAttributes(DeclaratorInfo, &LateParsedAttrs);

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 @@ public:
       SourceManager &SM = S->getSourceManager();
       SourceLocation IncludeLoc = SM.getIncludeLoc(SM.getFileID(Loc));
       if (IncludeLoc.isValid()) {
+        if (llvm::timeTraceProfilerEnabled()) {
+          const FileEntry *FE = SM.getFileEntryForID(SM.getFileID(Loc));
+          llvm::timeTraceProfilerBegin(
+              "Source", FE != nullptr ? FE->getName() : StringRef("<unknown>"));
+        }
+
         IncludeStack.push_back(IncludeLoc);
         S->DiagnoseNonDefaultPragmaPack(
             Sema::PragmaPackDiagnoseKind::NonDefaultStateAtInclude, IncludeLoc);
@@ -99,10 +107,14 @@ public:
       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 +926,11 @@ void Sema::ActOnEndOfTranslationUnit() {
                                    Pending.begin(), Pending.end());
     }
 
-    PerformPendingInstantiations();
+    {
+      llvm::TimeTraceScope TimeScope("PerformPendingInstantiations",
+                                     StringRef(""));
+      PerformPendingInstantiations();
+    }
 
     assert(LateParsedInstantiations.empty() &&
            "end of TU template instantiation should not create more "

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 @@ Sema::InstantiateClass(SourceLocation PointOfInstantiation,
                                 Instantiation->getInstantiatedFromMemberClass(),
                                      Pattern, PatternDef, TSK, Complain))
     return true;
+
+  llvm::TimeTraceScope TimeScope("InstantiateClass", [&]() {
+    return Instantiation->getQualifiedNameAsString();
+  });
+
   Pattern = PatternDef;
 
   // Record the point of instantiation.

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;
 
@@ -4124,6 +4125,10 @@ void Sema::InstantiateFunctionDefinition(SourceLocation PointOfInstantiation,
     return;
   }
 
+  llvm::TimeTraceScope TimeScope("InstantiateFunction", [&]() {
+    return Function->getQualifiedNameAsString();
+  });
+
   // 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.

clang/lib/Serialization/GlobalModuleIndex.cpp

@@ -10,6 +10,7 @@
 //
 //===----------------------------------------------------------------------===//
 
+
 #include "ASTReaderInternals.h"
 #include "clang/Basic/FileManager.h"
 #include "clang/Lex/HeaderSearch.h"
@@ -28,6 +29,7 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/OnDiskHashTable.h"
 #include "llvm/Support/Path.h"
+#include "llvm/Support/TimeProfiler.h"
 #include <cstdio>
 using namespace clang;
 using namespace serialization;
@@ -126,6 +128,7 @@ GlobalModuleIndex::GlobalModuleIndex(std::unique_ptr<llvm::MemoryBuffer> Buffer,
                                      llvm::BitstreamCursor Cursor)
     : Buffer(std::move(Buffer)), IdentifierIndex(), NumIdentifierLookups(),
       NumIdentifierLookupHits() {
+  llvm::TimeTraceScope TimeScope("Module LoadIndex", StringRef(""));
   // Read the global index.
   bool InGlobalIndexBlock = false;
   bool Done = false;
@@ -739,6 +742,7 @@ bool GlobalModuleIndexBuilder::writeIndex(llvm::BitstreamWriter &Stream) {
   }
 
   using namespace llvm;
+  llvm::TimeTraceScope TimeScope("Module WriteIndex", StringRef(""));
 
   // Emit the file header.
   Stream.Emit((unsigned)'B', 8);

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 <cstdio>
@@ -194,6 +196,9 @@ int cc1_main(ArrayRef<const char *> Argv, const char *Argv0, void *MainAddr) {
   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 @@ int cc1_main(ArrayRef<const char *> Argv, const char *Argv0, void *MainAddr) {
     return 1;
 
   // Execute the frontend actions.
-  Success = ExecuteCompilerInvocation(Clang.get());
+  {
+    llvm::TimeTraceScope TimeScope("ExecuteCompiler", StringRef(""));
+    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.

llvm/include/llvm/Support/TimeProfiler.h

@@ -0,0 +1,70 @@
+//===- 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<raw_pwrite_stream> &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(StringRef Name, StringRef Detail);
+void timeTraceProfilerBegin(StringRef Name,
+                            llvm::function_ref<std::string()> 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 when it is destroyed, it stops it. If the time profiler
+/// is not initialized, the overhead is a single branch.
+struct TimeTraceScope {
+  TimeTraceScope(StringRef Name, StringRef Detail) {
+    if (TimeTraceProfilerInstance != nullptr)
+      timeTraceProfilerBegin(Name, Detail);
+  }
+  TimeTraceScope(StringRef Name, llvm::function_ref<std::string()> Detail) {
+    if (TimeTraceProfilerInstance != nullptr)
+      timeTraceProfilerBegin(Name, Detail);
+  }
+  ~TimeTraceScope() {
+    if (TimeTraceProfilerInstance != nullptr)
+      timeTraceProfilerEnd();
+  }
+};
+
+} // end namespace llvm
+
+#endif

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 <algorithm>
@@ -1628,6 +1629,10 @@ bool FPPassManager::runOnFunction(Function &F) {
     FunctionSize = F.getInstructionCount();
   }
 
+  bool ProfileTime = llvm::timeTraceProfilerEnabled();
+  if (ProfileTime)
+    llvm::timeTraceProfilerBegin("OptFunction", F.getName());
+
   for (unsigned Index = 0; Index < getNumContainedPasses(); ++Index) {
     FunctionPass *FP = getContainedPass(Index);
     bool LocalChanged = false;
@@ -1668,12 +1673,17 @@ bool FPPassManager::runOnFunction(Function &F) {
     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());
   for (Function &F : M)
     Changed |= runOnFunction(F);
 
@@ -1706,6 +1716,8 @@ bool FPPassManager::doFinalization(Module &M) {
 /// the module, and if so, return true.
 bool
 MPPassManager::runOnModule(Module &M) {
+  llvm::TimeTraceScope TimeScope("OptModule", M.getName());
+
   bool Changed = false;
 
   // Initialize on-the-fly passes

llvm/lib/Support/CMakeLists.txt

@@ -139,6 +139,7 @@ add_llvm_library(LLVMSupport
   TarWriter.cpp
   TargetParser.cpp
   ThreadPool.cpp
+  TimeProfiler.cpp
   Timer.cpp
   ToolOutputFile.cpp
   TrigramIndex.cpp

llvm/lib/Support/TimeProfiler.cpp

@@ -0,0 +1,184 @@
+//===-- 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/ADT/StringExtras.h"
+#include "llvm/Support/FileSystem.h"
+#include <cassert>
+#include <chrono>
+#include <string>
+#include <unordered_map>
+#include <vector>
+
+using namespace std::chrono;
+
+namespace llvm {
+
+TimeTraceProfiler *TimeTraceProfilerInstance = nullptr;
+
+static std::string escapeString(StringRef Src) {
+  std::string OS;
+  for (const unsigned char &C : Src) {
+    switch (C) {
+    case '"':
+    case '/':
+    case '\\':
+    case '\b':
+    case '\f':
+    case '\n':
+    case '\r':
+    case '\t':
+      OS += '\\';
+      OS += C;
+      break;
+    default:
+      if (isPrint(C)) {
+        OS += C;
+      }
+    }
+  }
+  return OS;
+}
+
+typedef duration<steady_clock::rep, steady_clock::period> DurationType;
+typedef std::pair<std::string, DurationType> NameAndDuration;
+
+struct Entry {
+  time_point<steady_clock> Start;
+  DurationType Duration;
+  std::string Name;
+  std::string Detail;
+};
+
+struct TimeTraceProfiler {
+  TimeTraceProfiler() {
+    Stack.reserve(8);
+    Entries.reserve(128);
+    StartTime = steady_clock::now();
+  }
+
+  void begin(std::string Name, llvm::function_ref<std::string()> Detail) {
+    Entry E = {steady_clock::now(), {}, Name, Detail()};
+    Stack.push_back(std::move(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<microseconds>(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<raw_pwrite_stream> &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<microseconds>(E.Start - StartTime).count();
+      auto DurUs = duration_cast<microseconds>(E.Duration).count();
+      *OS << "{ \"pid\":1, \"tid\":0, \"ph\":\"X\", \"ts\":" << StartUs
+          << ", \"dur\":" << DurUs << ", \"name\":\"" << escapeString(E.Name)
+          << "\", \"args\":{ \"detail\":\"" << escapeString(E.Detail)
+          << "\"} },\n";
+    }
+
+    // Emit totals by section name as additional "thread" events, sorted from
+    // longest one.
+    int Tid = 1;
+    std::vector<NameAndDuration> 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<microseconds>(E.second).count();
+      *OS << "{ \"pid\":1, \"tid\":" << Tid << ", \"ph\":\"X\", \"ts\":" << 0
+          << ", \"dur\":" << DurUs << ", \"name\":\"Total "
+          << escapeString(E.first)
+          << "\", \"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<Entry> Stack;
+  std::vector<Entry> Entries;
+  std::unordered_map<std::string, DurationType> TotalPerName;
+  std::unordered_map<std::string, size_t> CountPerName;
+  time_point<steady_clock> 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<raw_pwrite_stream> &OS) {
+  assert(TimeTraceProfilerInstance != nullptr &&
+         "Profiler object can't be null");
+  TimeTraceProfilerInstance->Write(OS);
+}
+
+void timeTraceProfilerBegin(StringRef Name, StringRef Detail) {
+  if (TimeTraceProfilerInstance != nullptr)
+    TimeTraceProfilerInstance->begin(Name, [&]() { return Detail; });
+}
+
+void timeTraceProfilerBegin(StringRef Name,
+                            llvm::function_ref<std::string()> Detail) {
+  if (TimeTraceProfilerInstance != nullptr)
+    TimeTraceProfilerInstance->begin(Name, Detail);
+}
+
+void timeTraceProfilerEnd() {
+  if (TimeTraceProfilerInstance != nullptr)
+    TimeTraceProfilerInstance->end();
+}
+
+} // namespace llvm