Skip to content

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

New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

Sign up for GitHub

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

Merged
merged 4 commits into from
Sep 5, 2025
Merged

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

Show file tree
Hide file tree
Changes from 1 commit
Commits
Show all changes
4 commits
Select commit Hold shift + click to select a range
bfb0de6
[LLD][COFF] Add more `--time-trace` tags for ThinLTO linking
aganea Sep 1, 2025
076d475
Remove some unneeded tags
aganea Sep 3, 2025
a4cf7ef
Fix tags + clang-format
aganea Sep 3, 2025
13bf437
Adjust some tags following review
aganea Sep 3, 2025
File filter

Filter by extension

Filter by extension
Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
8 changes: 6 additions & 2 deletions lld/COFF/SymbolTable.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -1440,8 +1440,12 @@ void SymbolTable::compileBitcodeFiles() {
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);
}
llvm::TimeTraceScope compileScope("LTO compile");
Copy link
Contributor

@teresajohnson teresajohnson Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

There's already a "Compile bitcode" TimeTraceScope just above in the same scope. Is this needed too?

Copy link
Member Author

@aganea aganea Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

I moved this scope at the begining of BitcodeCompiler::compile() and removed the one at the top of this function.

for (InputFile *newObj : lto->compile()) {
ObjFile *obj = cast<ObjFile>(newObj);
obj->parse();
Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/Bitcode/Reader/MetadataLoader.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down Expand Up @@ -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");

Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/IR/AutoUpgrade.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down Expand Up @@ -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.
Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/IR/DebugInfo.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down Expand Up @@ -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())) {
Expand Down
2 changes: 2 additions & 0 deletions llvm/lib/IR/Module.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down Expand Up @@ -478,6 +479,7 @@ Error Module::materializeAll() {
}

Error Module::materializeMetadata() {
llvm::TimeTraceScope timeScope("Materialize metadata");
if (!Materializer)
return Error::success();
return Materializer->materializeMetadata();
Expand Down
12 changes: 10 additions & 2 deletions llvm/lib/IR/Verifier.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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>
Expand Down Expand Up @@ -399,6 +400,7 @@ class Verifier : public InstVisitor<Verifier>, VerifierSupport {
bool hasBrokenDebugInfo() const { return BrokenDebugInfo; }

bool verify(const Function &F) {
llvm::TimeTraceScope timeScope("Verifier");
Copy link
Collaborator

@zmodem zmodem Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Maybe this is enough; do you really need the "Dominator Tree Builder" and "Verifier visit' timers as well?

Copy link
Member Author

@aganea aganea Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Removed!

assert(F.getParent() == &M &&
"An instance of this class only works with a specific module!");

Expand All @@ -408,8 +410,10 @@ class Verifier : public InstVisitor<Verifier>, VerifierSupport {
// out-of-date dominator tree and makes it significantly more complex to run
// this code outside of a pass manager.
// FIXME: It's really gross that we have to cast away constness here.
if (!F.empty())
if (!F.empty()) {
llvm::TimeTraceScope domScope("Dominator Tree Builder");
DT.recalculate(const_cast<Function &>(F));
}

for (const BasicBlock &BB : F) {
if (!BB.empty() && BB.back().isTerminator())
Expand All @@ -431,7 +435,10 @@ class Verifier : public InstVisitor<Verifier>, VerifierSupport {

Broken = false;
// FIXME: We strip const here because the inst visitor strips const.
visit(const_cast<Function &>(F));
{
llvm::TimeTraceScope domScope("Verifier visit");
Copy link
Collaborator

@zmodem zmodem Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

scope name copy-past-o?

Copy link
Member Author

@aganea aganea Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Changed, thanks for noting. There was another one below.

visit(const_cast<Function &>(F));
}
verifySiblingFuncletUnwinds();

if (ConvergenceVerifyHelper.sawTokens())
Expand Down Expand Up @@ -2832,6 +2839,7 @@ static Instruction *getSuccPad(Instruction *Terminator) {
}

void Verifier::verifySiblingFuncletUnwinds() {
llvm::TimeTraceScope domScope("Verifier verify sibling funclet unwinds");
SmallPtrSet<Instruction *, 8> Visited;
SmallPtrSet<Instruction *, 8> Active;
for (const auto &Pair : SiblingFuncletInfo) {
Expand Down
45 changes: 24 additions & 21 deletions llvm/lib/LTO/LTO.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -631,6 +631,7 @@ LTO::~LTO() = default;
void LTO::addModuleToGlobalRes(ArrayRef<InputFile::Symbol> Syms,
ArrayRef<SymbolResolution> Res,
unsigned Partition, bool InSummary) {
llvm::TimeTraceScope importScope("LTO add module to global resolution");
auto *ResI = Res.begin();
auto *ResE = Res.end();
(void)ResE;
Expand Down Expand Up @@ -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 importScope("LTO add input", Input->getName());
assert(!CalledGetMaxTasks);

if (Conf.ResolutionFile)
Expand All @@ -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 importScope("LTO add module", Input.getName());
Expected<BitcodeLTOInfo> LTOInfo = Input.Mods[ModI].getLTOInfo();
if (!LTOInfo)
return LTOInfo.takeError();
Expand Down Expand Up @@ -850,6 +853,7 @@ Expected<
LTO::addRegularLTO(InputFile &Input, ArrayRef<SymbolResolution> InputRes,
BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
ArrayRef<SymbolResolution> Res) {
llvm::TimeTraceScope importScope("LTO add regular LTO");
RegularLTOState::AddedModule Mod;
Expected<std::unique_ptr<Module>> MOrErr =
BM.getLazyModule(RegularLTO.Ctx, /*ShouldLazyLoadMetadata*/ true,
Expand Down Expand Up @@ -1024,6 +1028,7 @@ LTO::addRegularLTO(InputFile &Input, ArrayRef<SymbolResolution> InputRes,

Error LTO::linkRegularLTO(RegularLTOState::AddedModule Mod,
bool LivenessFromIndex) {
llvm::TimeTraceScope importScope("LTO link regular LTO");
std::vector<GlobalValue *> Keep;
for (GlobalValue *GV : Mod.Keep) {
if (LivenessFromIndex && !ThinLTO.CombinedIndex.isGUIDLive(GV->getGUID())) {
Expand Down Expand Up @@ -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 importScope("LTO add thin LTO");
ArrayRef<SymbolResolution> ResTmp = Res;
for (const InputFile::Symbol &Sym : Syms) {
assert(!ResTmp.empty());
Expand Down Expand Up @@ -1252,6 +1258,7 @@ Error LTO::run(AddStreamFn AddStream, FileCache Cache) {

void lto::updateMemProfAttributes(Module &Mod,
const ModuleSummaryIndex &Index) {
llvm::TimeTraceScope importScope("LTO update memprof attributes");
if (Index.withSupportsHotColdNew())
return;

Expand Down Expand Up @@ -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,
Expand All @@ -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
Expand Down Expand Up @@ -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);
Expand All @@ -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;
Expand Down Expand Up @@ -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);
Expand All @@ -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.
Expand Down Expand Up @@ -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 =
Expand All @@ -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; }))
Expand Down Expand Up @@ -1915,13 +1927,9 @@ 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(""));
Copy link
Contributor

@teresajohnson teresajohnson Sep 3, 2025

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

With this removed, we've lost the timer of just the index-based thin link. Why remove it?

Copy link
Member Author

@aganea aganea Sep 3, 2025 •
edited
Loading

Choose a reason for hiding this comment

The reason will be displayed to describe this comment to others. Learn more.

Reverted this change, the ThinLink tag is now back.

auto TimeTraceScopeExit = llvm::make_scope_exit([]() {
if (llvm::timeTraceProfilerEnabled())
llvm::timeTraceProfilerEnd();
});
if (ThinLTO.ModuleMap.empty())
return Error::success();

Expand Down Expand Up @@ -2069,11 +2077,6 @@ Error LTO::runThinLTO(AddStreamFn AddStream, FileCache Cache,

generateParamAccessSummary(ThinLTO.CombinedIndex);

if (llvm::timeTraceProfilerEnabled())
llvm::timeTraceProfilerEnd();

TimeTraceScopeExit.release();

auto &ModuleMap =
ThinLTO.ModulesToCompile ? *ThinLTO.ModulesToCompile : ThinLTO.ModuleMap;

Expand Down
17 changes: 13 additions & 4 deletions llvm/lib/LTO/LTOBackend.cpp
View file
Open in desktop
Original file line number Diff line number Diff line change
Expand Up @@ -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
Expand Down Expand Up @@ -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;

Expand Down Expand Up @@ -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();
Expand All @@ -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()))
Expand All @@ -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();
Expand Down Expand Up @@ -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 importScope("Module loader", Identifier);
assert(Mod.getContext().isODRUniquingDebugTypes() &&
"ODR Type uniquing should be enabled on the context");
if (ModuleMap) {
Expand Down Expand Up @@ -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);
Expand Down
Loading
Loading