[LLD][COFF] Add more --time-trace tags for ThinLTO linking (llvm#156471)

In order to better see what's going on during ThinLTO linking, this PR
adds more profile tags when using `--time-trace` on a `lld-link.exe`
invocation.

After PR, linking `clang.exe`:

<img width="3839" height="2026" alt="Capture d’écran 2025-09-02 082021"
src="https://github.com/user-attachments/assets/bf0c85ba-2f85-4bbf-a5c1-800039b56910"
/>

Linking a custom (Unreal Engine game) binary gives a completly
different picture, probably because of using Unity files, and the sheer
amount of input files (here, providing over 60 GB of .OBJs/.LIBs).

<img width="1940" height="1008" alt="Capture d’écran 2025-09-02 102048"
src="https://github.com/user-attachments/assets/60b28630-7995-45ce-9e8c-13f3cb5312e0"
/>

Author: aganea

lld/COFF/LTO.cpp

@@ -26,6 +26,7 @@
 #include "llvm/Support/Caching.h"
 #include "llvm/Support/CodeGen.h"
 #include "llvm/Support/MemoryBuffer.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/raw_ostream.h"
 #include <cstddef>
 #include <memory>
@@ -176,6 +177,7 @@ void BitcodeCompiler::add(BitcodeFile &f) {
 // Merge all the bitcode files we have seen, codegen the result
 // and return the resulting objects.
 std::vector<InputFile *> BitcodeCompiler::compile() {
+  llvm::TimeTraceScope timeScope("Bitcode compile");
   unsigned maxTasks = ltoObj->getMaxTasks();
   buf.resize(maxTasks);
   files.resize(maxTasks);

lld/COFF/SymbolTable.cpp

@@ -1437,11 +1437,13 @@ void SymbolTable::compileBitcodeFiles() {
   if (bitcodeFileInstances.empty())
     return;
 
-  llvm::TimeTraceScope timeScope("Compile bitcode");
   ScopedTimer t(ctx.ltoTimer);
   lto.reset(new BitcodeCompiler(ctx));
-  for (BitcodeFile *f : bitcodeFileInstances)
-    lto->add(*f);
+  {
+    llvm::TimeTraceScope addScope("Add bitcode file instances");
+    for (BitcodeFile *f : bitcodeFileInstances)
+      lto->add(*f);
+  }
   for (InputFile *newObj : lto->compile()) {
     ObjFile *obj = cast<ObjFile>(newObj);
     obj->parse();

llvm/lib/Bitcode/Reader/MetadataLoader.cpp

@@ -43,6 +43,7 @@
 #include "llvm/Support/CommandLine.h"
 #include "llvm/Support/Compiler.h"
 #include "llvm/Support/ErrorHandling.h"
+#include "llvm/Support/TimeProfiler.h"
 
 #include <algorithm>
 #include <cassert>
@@ -1052,6 +1053,7 @@ void MetadataLoader::MetadataLoaderImpl::callMDTypeCallback(Metadata **Val,
 /// Parse a METADATA_BLOCK. If ModuleLevel is true then we are parsing
 /// module level metadata.
 Error MetadataLoader::MetadataLoaderImpl::parseMetadata(bool ModuleLevel) {
+  llvm::TimeTraceScope timeScope("Parse metadata");
   if (!ModuleLevel && MetadataList.hasFwdRefs())
     return error("Invalid metadata: fwd refs into function blocks");
 

llvm/lib/IR/AutoUpgrade.cpp

@@ -48,6 +48,7 @@
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/NVPTXAddrSpace.h"
 #include "llvm/Support/Regex.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/TargetParser/Triple.h"
 #include <cstdint>
 #include <cstring>
@@ -5256,6 +5257,7 @@ bool llvm::UpgradeDebugInfo(Module &M) {
   if (DisableAutoUpgradeDebugInfo)
     return false;
 
+  llvm::TimeTraceScope timeScope("Upgrade debug info");
   // We need to get metadata before the module is verified (i.e., getModuleFlag
   // makes assumptions that we haven't verified yet). Carefully extract the flag
   // from the metadata.

llvm/lib/IR/DebugInfo.cpp

@@ -36,6 +36,7 @@
 #include "llvm/IR/Module.h"
 #include "llvm/IR/PassManager.h"
 #include "llvm/Support/Casting.h"
+#include "llvm/Support/TimeProfiler.h"
 #include <algorithm>
 #include <cassert>
 #include <optional>
@@ -563,6 +564,7 @@ bool llvm::stripDebugInfo(Function &F) {
 }
 
 bool llvm::StripDebugInfo(Module &M) {
+  llvm::TimeTraceScope timeScope("Strip debug info");
   bool Changed = false;
 
   for (NamedMDNode &NMD : llvm::make_early_inc_range(M.named_metadata())) {

llvm/lib/IR/Module.cpp

@@ -44,6 +44,7 @@
 #include "llvm/Support/MemoryBuffer.h"
 #include "llvm/Support/Path.h"
 #include "llvm/Support/RandomNumberGenerator.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/VersionTuple.h"
 #include <cassert>
 #include <cstdint>
@@ -478,6 +479,7 @@ Error Module::materializeAll() {
 }
 
 Error Module::materializeMetadata() {
+  llvm::TimeTraceScope timeScope("Materialize metadata");
   if (!Materializer)
     return Error::success();
   return Materializer->materializeMetadata();

llvm/lib/IR/Verifier.cpp

@@ -119,6 +119,7 @@
 #include "llvm/Support/ErrorHandling.h"
 #include "llvm/Support/MathExtras.h"
 #include "llvm/Support/ModRef.h"
+#include "llvm/Support/TimeProfiler.h"
 #include "llvm/Support/raw_ostream.h"
 #include <algorithm>
 #include <cassert>
@@ -399,6 +400,7 @@ class Verifier : public InstVisitor<Verifier>, VerifierSupport {
   bool hasBrokenDebugInfo() const { return BrokenDebugInfo; }
 
   bool verify(const Function &F) {
+    llvm::TimeTraceScope timeScope("Verifier");
     assert(F.getParent() == &M &&
            "An instance of this class only works with a specific module!");
 
@@ -2822,6 +2824,7 @@ static Instruction *getSuccPad(Instruction *Terminator) {
 }
 
 void Verifier::verifySiblingFuncletUnwinds() {
+  llvm::TimeTraceScope timeScope("Verifier verify sibling funclet unwinds");
   SmallPtrSet<Instruction *, 8> Visited;
   SmallPtrSet<Instruction *, 8> Active;
   for (const auto &Pair : SiblingFuncletInfo) {

llvm/lib/LTO/LTO.cpp

@@ -631,6 +631,7 @@ LTO::~LTO() = default;
 void LTO::addModuleToGlobalRes(ArrayRef<InputFile::Symbol> Syms,
                                ArrayRef<SymbolResolution> Res,
                                unsigned Partition, bool InSummary) {
+  llvm::TimeTraceScope timeScope("LTO add module to global resolution");
   auto *ResI = Res.begin();
   auto *ResE = Res.end();
   (void)ResE;
@@ -731,6 +732,7 @@ static void writeToResolutionFile(raw_ostream &OS, InputFile *Input,
 
 Error LTO::add(std::unique_ptr<InputFile> Input,
                ArrayRef<SymbolResolution> Res) {
+  llvm::TimeTraceScope timeScope("LTO add input", Input->getName());
   assert(!CalledGetMaxTasks);
 
   if (Conf.ResolutionFile)
@@ -756,6 +758,7 @@ Error LTO::add(std::unique_ptr<InputFile> Input,
 Expected<ArrayRef<SymbolResolution>>
 LTO::addModule(InputFile &Input, ArrayRef<SymbolResolution> InputRes,
                unsigned ModI, ArrayRef<SymbolResolution> Res) {
+  llvm::TimeTraceScope timeScope("LTO add module", Input.getName());
   Expected<BitcodeLTOInfo> LTOInfo = Input.Mods[ModI].getLTOInfo();
   if (!LTOInfo)
     return LTOInfo.takeError();
@@ -850,6 +853,7 @@ Expected<
 LTO::addRegularLTO(InputFile &Input, ArrayRef<SymbolResolution> InputRes,
                    BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
                    ArrayRef<SymbolResolution> Res) {
+  llvm::TimeTraceScope timeScope("LTO add regular LTO");
   RegularLTOState::AddedModule Mod;
   Expected<std::unique_ptr<Module>> MOrErr =
       BM.getLazyModule(RegularLTO.Ctx, /*ShouldLazyLoadMetadata*/ true,
@@ -1024,6 +1028,7 @@ LTO::addRegularLTO(InputFile &Input, ArrayRef<SymbolResolution> InputRes,
 
 Error LTO::linkRegularLTO(RegularLTOState::AddedModule Mod,
                           bool LivenessFromIndex) {
+  llvm::TimeTraceScope timeScope("LTO link regular LTO");
   std::vector<GlobalValue *> Keep;
   for (GlobalValue *GV : Mod.Keep) {
     if (LivenessFromIndex && !ThinLTO.CombinedIndex.isGUIDLive(GV->getGUID())) {
@@ -1063,6 +1068,7 @@ Error LTO::linkRegularLTO(RegularLTOState::AddedModule Mod,
 Expected<ArrayRef<SymbolResolution>>
 LTO::addThinLTO(BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
                 ArrayRef<SymbolResolution> Res) {
+  llvm::TimeTraceScope timeScope("LTO add thin LTO");
   ArrayRef<SymbolResolution> ResTmp = Res;
   for (const InputFile::Symbol &Sym : Syms) {
     assert(!ResTmp.empty());
@@ -1252,6 +1258,7 @@ Error LTO::run(AddStreamFn AddStream, FileCache Cache) {
 
 void lto::updateMemProfAttributes(Module &Mod,
                                   const ModuleSummaryIndex &Index) {
+  llvm::TimeTraceScope timeScope("LTO update memprof attributes");
   if (Index.withSupportsHotColdNew())
     return;
 
@@ -1282,6 +1289,7 @@ void lto::updateMemProfAttributes(Module &Mod,
 }
 
 Error LTO::runRegularLTO(AddStreamFn AddStream) {
+  llvm::TimeTraceScope timeScope("Run regular LTO");
   // Setup optimization remarks.
   auto DiagFileOrErr = lto::setupLLVMOptimizationRemarks(
       RegularLTO.CombinedModule->getContext(), Conf.RemarksFilename,
@@ -1294,10 +1302,12 @@ Error LTO::runRegularLTO(AddStreamFn AddStream) {
 
   // Finalize linking of regular LTO modules containing summaries now that
   // we have computed liveness information.
-  for (auto &M : RegularLTO.ModsWithSummaries)
-    if (Error Err = linkRegularLTO(std::move(M),
-                                   /*LivenessFromIndex=*/true))
-      return Err;
+  {
+    llvm::TimeTraceScope timeScope("Link regular LTO");
+    for (auto &M : RegularLTO.ModsWithSummaries)
+      if (Error Err = linkRegularLTO(std::move(M), /*LivenessFromIndex=*/true))
+        return Err;
+  }
 
   // Ensure we don't have inconsistently split LTO units with type tests.
   // FIXME: this checks both LTO and ThinLTO. It happens to work as we take
@@ -1526,6 +1536,9 @@ class InProcessThinBackend : public CGThinBackend {
       const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
       const GVSummaryMapTy &DefinedGlobals,
       MapVector<StringRef, BitcodeModule> &ModuleMap) {
+    auto ModuleID = BM.getModuleIdentifier();
+    llvm::TimeTraceScope timeScope("Run ThinLTO backend thread (in-process)",
+                                   ModuleID);
     auto RunThinBackend = [&](AddStreamFn AddStream) {
       LTOLLVMContext BackendContext(Conf);
       Expected<std::unique_ptr<Module>> MOrErr = BM.parseModule(BackendContext);
@@ -1536,9 +1549,6 @@ class InProcessThinBackend : public CGThinBackend {
                          ImportList, DefinedGlobals, &ModuleMap,
                          Conf.CodeGenOnly);
     };
-
-    auto ModuleID = BM.getModuleIdentifier();
-
     if (ShouldEmitIndexFiles) {
       if (auto E = emitFiles(ImportList, ModuleID, ModuleID.str()))
         return E;
@@ -1639,6 +1649,9 @@ class FirstRoundThinBackend : public InProcessThinBackend {
       const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
       const GVSummaryMapTy &DefinedGlobals,
       MapVector<StringRef, BitcodeModule> &ModuleMap) override {
+    auto ModuleID = BM.getModuleIdentifier();
+    llvm::TimeTraceScope timeScope("Run ThinLTO backend thread (first round)",
+                                   ModuleID);
     auto RunThinBackend = [&](AddStreamFn CGAddStream,
                               AddStreamFn IRAddStream) {
       LTOLLVMContext BackendContext(Conf);
@@ -1650,8 +1663,6 @@ class FirstRoundThinBackend : public InProcessThinBackend {
                          ImportList, DefinedGlobals, &ModuleMap,
                          Conf.CodeGenOnly, IRAddStream);
     };
-
-    auto ModuleID = BM.getModuleIdentifier();
     // Like InProcessThinBackend, we produce index files as needed for
     // FirstRoundThinBackend. However, these files are not generated for
     // SecondRoundThinBackend.
@@ -1735,6 +1746,9 @@ class SecondRoundThinBackend : public InProcessThinBackend {
       const std::map<GlobalValue::GUID, GlobalValue::LinkageTypes> &ResolvedODR,
       const GVSummaryMapTy &DefinedGlobals,
       MapVector<StringRef, BitcodeModule> &ModuleMap) override {
+    auto ModuleID = BM.getModuleIdentifier();
+    llvm::TimeTraceScope timeScope("Run ThinLTO backend thread (second round)",
+                                   ModuleID);
     auto RunThinBackend = [&](AddStreamFn AddStream) {
       LTOLLVMContext BackendContext(Conf);
       std::unique_ptr<Module> LoadedModule =
@@ -1744,8 +1758,6 @@ class SecondRoundThinBackend : public InProcessThinBackend {
                          ImportList, DefinedGlobals, &ModuleMap,
                          /*CodeGenOnly=*/true);
     };
-
-    auto ModuleID = BM.getModuleIdentifier();
     if (!Cache.isValid() || !CombinedIndex.modulePaths().count(ModuleID) ||
         all_of(CombinedIndex.getModuleHash(ModuleID),
                [](uint32_t V) { return V == 0; }))
@@ -1915,6 +1927,7 @@ ThinBackend lto::createWriteIndexesThinBackend(
 
 Error LTO::runThinLTO(AddStreamFn AddStream, FileCache Cache,
                       const DenseSet<GlobalValue::GUID> &GUIDPreservedSymbols) {
+  llvm::TimeTraceScope timeScope("Run ThinLTO");
   LLVM_DEBUG(dbgs() << "Running ThinLTO\n");
   ThinLTO.CombinedIndex.releaseTemporaryMemory();
   timeTraceProfilerBegin("ThinLink", StringRef(""));

llvm/lib/LTO/LTOBackend.cpp

@@ -366,6 +366,7 @@ bool lto::opt(const Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
               bool IsThinLTO, ModuleSummaryIndex *ExportSummary,
               const ModuleSummaryIndex *ImportSummary,
               const std::vector<uint8_t> &CmdArgs) {
+  llvm::TimeTraceScope timeScope("opt");
   if (EmbedBitcode == LTOBitcodeEmbedding::EmbedPostMergePreOptimized) {
     // FIXME: the motivation for capturing post-merge bitcode and command line
     // is replicating the compilation environment from bitcode, without needing
@@ -399,6 +400,7 @@ bool lto::opt(const Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
 static void codegen(const Config &Conf, TargetMachine *TM,
                     AddStreamFn AddStream, unsigned Task, Module &Mod,
                     const ModuleSummaryIndex &CombinedIndex) {
+  llvm::TimeTraceScope timeScope("codegen");
   if (Conf.PreCodeGenModuleHook && !Conf.PreCodeGenModuleHook(Task, Mod))
     return;
 
@@ -552,6 +554,7 @@ Error lto::finalizeOptimizationRemarks(
 Error lto::backend(const Config &C, AddStreamFn AddStream,
                    unsigned ParallelCodeGenParallelismLevel, Module &Mod,
                    ModuleSummaryIndex &CombinedIndex) {
+  llvm::TimeTraceScope timeScope("LTO backend");
   Expected<const Target *> TOrErr = initAndLookupTarget(C, Mod);
   if (!TOrErr)
     return TOrErr.takeError();
@@ -577,6 +580,7 @@ Error lto::backend(const Config &C, AddStreamFn AddStream,
 
 static void dropDeadSymbols(Module &Mod, const GVSummaryMapTy &DefinedGlobals,
                             const ModuleSummaryIndex &Index) {
+  llvm::TimeTraceScope timeScope("Drop dead symbols");
   std::vector<GlobalValue*> DeadGVs;
   for (auto &GV : Mod.global_values())
     if (GlobalValueSummary *GVS = DefinedGlobals.lookup(GV.getGUID()))
@@ -603,6 +607,7 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
                        MapVector<StringRef, BitcodeModule> *ModuleMap,
                        bool CodeGenOnly, AddStreamFn IRAddStream,
                        const std::vector<uint8_t> &CmdArgs) {
+  llvm::TimeTraceScope timeScope("Thin backend", Mod.getModuleIdentifier());
   Expected<const Target *> TOrErr = initAndLookupTarget(Conf, Mod);
   if (!TOrErr)
     return TOrErr.takeError();
@@ -679,6 +684,7 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
     return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
 
   auto ModuleLoader = [&](StringRef Identifier) {
+    llvm::TimeTraceScope moduleLoaderScope("Module loader", Identifier);
     assert(Mod.getContext().isODRUniquingDebugTypes() &&
            "ODR Type uniquing should be enabled on the context");
     if (ModuleMap) {
@@ -712,10 +718,13 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
     return MOrErr;
   };
 
-  FunctionImporter Importer(CombinedIndex, ModuleLoader,
-                            ClearDSOLocalOnDeclarations);
-  if (Error Err = Importer.importFunctions(Mod, ImportList).takeError())
-    return Err;
+  {
+    llvm::TimeTraceScope importScope("Import functions");
+    FunctionImporter Importer(CombinedIndex, ModuleLoader,
+                              ClearDSOLocalOnDeclarations);
+    if (Error Err = Importer.importFunctions(Mod, ImportList).takeError())
+      return Err;
+  }
 
   // Do this after any importing so that imported code is updated.
   updateMemProfAttributes(Mod, CombinedIndex);