aboutsummaryrefslogtreecommitdiff
path: root/llvm/lib/LTO
diff options
context:
space:
mode:
Diffstat (limited to 'llvm/lib/LTO')
-rw-r--r--llvm/lib/LTO/Caching.cpp2
-rw-r--r--llvm/lib/LTO/LTO.cpp185
-rw-r--r--llvm/lib/LTO/LTOBackend.cpp106
-rw-r--r--llvm/lib/LTO/LTOCodeGenerator.cpp20
-rw-r--r--llvm/lib/LTO/LTOModule.cpp14
-rw-r--r--llvm/lib/LTO/ThinLTOCodeGenerator.cpp63
-rw-r--r--llvm/lib/LTO/UpdateCompilerUsed.cpp1
7 files changed, 275 insertions, 116 deletions
diff --git a/llvm/lib/LTO/Caching.cpp b/llvm/lib/LTO/Caching.cpp
index 12dcd182de2d..46cac3fb1830 100644
--- a/llvm/lib/LTO/Caching.cpp
+++ b/llvm/lib/LTO/Caching.cpp
@@ -144,7 +144,7 @@ Expected<NativeObjectCache> lto::localCache(StringRef CacheDirectoryPath,
// This CacheStream will move the temporary file into the cache when done.
return std::make_unique<CacheStream>(
std::make_unique<raw_fd_ostream>(Temp->FD, /* ShouldClose */ false),
- AddBuffer, std::move(*Temp), EntryPath.str(), Task);
+ AddBuffer, std::move(*Temp), std::string(EntryPath.str()), Task);
};
};
}
diff --git a/llvm/lib/LTO/LTO.cpp b/llvm/lib/LTO/LTO.cpp
index 297b11de17a9..6e1e3998e490 100644
--- a/llvm/lib/LTO/LTO.cpp
+++ b/llvm/lib/LTO/LTO.cpp
@@ -12,6 +12,8 @@
#include "llvm/LTO/LTO.h"
#include "llvm/ADT/Statistic.h"
+#include "llvm/Analysis/OptimizationRemarkEmitter.h"
+#include "llvm/Analysis/StackSafetyAnalysis.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Bitcode/BitcodeReader.h"
@@ -21,10 +23,10 @@
#include "llvm/IR/AutoUpgrade.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/Intrinsics.h"
+#include "llvm/IR/LLVMRemarkStreamer.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/Metadata.h"
-#include "llvm/IR/RemarkStreamer.h"
#include "llvm/LTO/LTOBackend.h"
#include "llvm/LTO/SummaryBasedOptimizations.h"
#include "llvm/Linker/IRMover.h"
@@ -39,6 +41,7 @@
#include "llvm/Support/TargetRegistry.h"
#include "llvm/Support/ThreadPool.h"
#include "llvm/Support/Threading.h"
+#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/VCSRevision.h"
#include "llvm/Support/raw_ostream.h"
#include "llvm/Target/TargetMachine.h"
@@ -96,22 +99,12 @@ void llvm::computeLTOCacheKey(
};
auto AddUnsigned = [&](unsigned I) {
uint8_t Data[4];
- Data[0] = I;
- Data[1] = I >> 8;
- Data[2] = I >> 16;
- Data[3] = I >> 24;
+ support::endian::write32le(Data, I);
Hasher.update(ArrayRef<uint8_t>{Data, 4});
};
auto AddUint64 = [&](uint64_t I) {
uint8_t Data[8];
- Data[0] = I;
- Data[1] = I >> 8;
- Data[2] = I >> 16;
- Data[3] = I >> 24;
- Data[4] = I >> 32;
- Data[5] = I >> 40;
- Data[6] = I >> 48;
- Data[7] = I >> 56;
+ support::endian::write64le(Data, I);
Hasher.update(ArrayRef<uint8_t>{Data, 8});
};
AddString(Conf.CPU);
@@ -147,8 +140,17 @@ void llvm::computeLTOCacheKey(
// Include the hash for the current module
auto ModHash = Index.getModuleHash(ModuleID);
Hasher.update(ArrayRef<uint8_t>((uint8_t *)&ModHash[0], sizeof(ModHash)));
+
+ std::vector<uint64_t> ExportsGUID;
+ ExportsGUID.reserve(ExportList.size());
for (const auto &VI : ExportList) {
auto GUID = VI.getGUID();
+ ExportsGUID.push_back(GUID);
+ }
+
+ // Sort the export list elements GUIDs.
+ llvm::sort(ExportsGUID);
+ for (uint64_t GUID : ExportsGUID) {
// The export list can impact the internalization, be conservative here
Hasher.update(ArrayRef<uint8_t>((uint8_t *)&GUID, sizeof(GUID)));
}
@@ -156,12 +158,23 @@ void llvm::computeLTOCacheKey(
// Include the hash for every module we import functions from. The set of
// imported symbols for each module may affect code generation and is
// sensitive to link order, so include that as well.
- for (auto &Entry : ImportList) {
- auto ModHash = Index.getModuleHash(Entry.first());
+ using ImportMapIteratorTy = FunctionImporter::ImportMapTy::const_iterator;
+ std::vector<ImportMapIteratorTy> ImportModulesVector;
+ ImportModulesVector.reserve(ImportList.size());
+
+ for (ImportMapIteratorTy It = ImportList.begin(); It != ImportList.end();
+ ++It) {
+ ImportModulesVector.push_back(It);
+ }
+ llvm::sort(ImportModulesVector,
+ [](const ImportMapIteratorTy &Lhs, const ImportMapIteratorTy &Rhs)
+ -> bool { return Lhs->getKey() < Rhs->getKey(); });
+ for (const ImportMapIteratorTy &EntryIt : ImportModulesVector) {
+ auto ModHash = Index.getModuleHash(EntryIt->first());
Hasher.update(ArrayRef<uint8_t>((uint8_t *)&ModHash[0], sizeof(ModHash)));
- AddUint64(Entry.second.size());
- for (auto &Fn : Entry.second)
+ AddUint64(EntryIt->second.size());
+ for (auto &Fn : EntryIt->second)
AddUint64(Fn);
}
@@ -513,7 +526,7 @@ void LTO::addModuleToGlobalRes(ArrayRef<InputFile::Symbol> Syms,
assert(!GlobalRes.Prevailing &&
"Multiple prevailing defs are not allowed");
GlobalRes.Prevailing = true;
- GlobalRes.IRName = Sym.getIRName();
+ GlobalRes.IRName = std::string(Sym.getIRName());
} else if (!GlobalRes.Prevailing && GlobalRes.IRName.empty()) {
// Sometimes it can be two copies of symbol in a module and prevailing
// symbol can have no IR name. That might happen if symbol is defined in
@@ -521,7 +534,7 @@ void LTO::addModuleToGlobalRes(ArrayRef<InputFile::Symbol> Syms,
// the same symbol we want to use IR name of the prevailing symbol.
// Otherwise, if we haven't seen a prevailing symbol, set the name so that
// we can later use it to check if there is any prevailing copy in IR.
- GlobalRes.IRName = Sym.getIRName();
+ GlobalRes.IRName = std::string(Sym.getIRName());
}
// Set the partition to external if we know it is re-defined by the linker
@@ -611,6 +624,7 @@ Error LTO::addModule(InputFile &Input, unsigned ModI,
if (LTOInfo->IsThinLTO)
return addThinLTO(BM, ModSyms, ResI, ResE);
+ RegularLTO.EmptyCombinedModule = false;
Expected<RegularLTOState::AddedModule> ModOrErr =
addRegularLTO(BM, ModSyms, ResI, ResE);
if (!ModOrErr)
@@ -762,10 +776,11 @@ LTO::addRegularLTO(BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
if (Sym.isCommon()) {
// FIXME: We should figure out what to do about commons defined by asm.
// For now they aren't reported correctly by ModuleSymbolTable.
- auto &CommonRes = RegularLTO.Commons[Sym.getIRName()];
+ auto &CommonRes = RegularLTO.Commons[std::string(Sym.getIRName())];
CommonRes.Size = std::max(CommonRes.Size, Sym.getCommonSize());
- CommonRes.Align =
- std::max(CommonRes.Align, MaybeAlign(Sym.getCommonAlignment()));
+ MaybeAlign SymAlign(Sym.getCommonAlignment());
+ if (SymAlign)
+ CommonRes.Align = max(*SymAlign, CommonRes.Align);
CommonRes.Prevailing |= Res.Prevailing;
}
@@ -781,8 +796,15 @@ Error LTO::linkRegularLTO(RegularLTOState::AddedModule Mod,
bool LivenessFromIndex) {
std::vector<GlobalValue *> Keep;
for (GlobalValue *GV : Mod.Keep) {
- if (LivenessFromIndex && !ThinLTO.CombinedIndex.isGUIDLive(GV->getGUID()))
+ if (LivenessFromIndex && !ThinLTO.CombinedIndex.isGUIDLive(GV->getGUID())) {
+ if (Function *F = dyn_cast<Function>(GV)) {
+ OptimizationRemarkEmitter ORE(F);
+ ORE.emit(OptimizationRemark(DEBUG_TYPE, "deadfunction", F)
+ << ore::NV("Function", F)
+ << " not added to the combined module ");
+ }
continue;
+ }
if (!GV->hasAvailableExternallyLinkage()) {
Keep.push_back(GV);
@@ -849,12 +871,28 @@ Error LTO::addThinLTO(BitcodeModule BM, ArrayRef<InputFile::Symbol> Syms,
"Expected at most one ThinLTO module per bitcode file",
inconvertibleErrorCode());
+ if (!Conf.ThinLTOModulesToCompile.empty()) {
+ if (!ThinLTO.ModulesToCompile)
+ ThinLTO.ModulesToCompile = ModuleMapType();
+ // This is a fuzzy name matching where only modules with name containing the
+ // specified switch values are going to be compiled.
+ for (const std::string &Name : Conf.ThinLTOModulesToCompile) {
+ if (BM.getModuleIdentifier().contains(Name)) {
+ ThinLTO.ModulesToCompile->insert({BM.getModuleIdentifier(), BM});
+ llvm::errs() << "[ThinLTO] Selecting " << BM.getModuleIdentifier()
+ << " to compile\n";
+ }
+ }
+ }
+
return Error::success();
}
unsigned LTO::getMaxTasks() const {
CalledGetMaxTasks = true;
- return RegularLTO.ParallelCodeGenParallelismLevel + ThinLTO.ModuleMap.size();
+ auto ModuleCount = ThinLTO.ModulesToCompile ? ThinLTO.ModulesToCompile->size()
+ : ThinLTO.ModuleMap.size();
+ return RegularLTO.ParallelCodeGenParallelismLevel + ModuleCount;
}
// If only some of the modules were split, we cannot correctly handle
@@ -931,17 +969,6 @@ Error LTO::run(AddStreamFn AddStream, NativeObjectCache Cache) {
return StatsFileOrErr.takeError();
std::unique_ptr<ToolOutputFile> StatsFile = std::move(StatsFileOrErr.get());
- // 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;
-
- // Ensure we don't have inconsistently split LTO units with type tests.
- if (Error Err = checkPartiallySplit())
- return Err;
-
Error Result = runRegularLTO(AddStream);
if (!Result)
Result = runThinLTO(AddStream, Cache, GUIDPreservedSymbols);
@@ -953,6 +980,27 @@ Error LTO::run(AddStreamFn AddStream, NativeObjectCache Cache) {
}
Error LTO::runRegularLTO(AddStreamFn AddStream) {
+ // Setup optimization remarks.
+ auto DiagFileOrErr = lto::setupLLVMOptimizationRemarks(
+ RegularLTO.CombinedModule->getContext(), Conf.RemarksFilename,
+ Conf.RemarksPasses, Conf.RemarksFormat, Conf.RemarksWithHotness);
+ if (!DiagFileOrErr)
+ return DiagFileOrErr.takeError();
+
+ // 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;
+
+ // 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
+ // this path both cases but eventually this should be split into two and
+ // do the ThinLTO checks in `runThinLTO`.
+ if (Error Err = checkPartiallySplit())
+ return Err;
+
// Make sure commons have the right size/alignment: we kept the largest from
// all the prevailing when adding the inputs, and we apply it here.
const DataLayout &DL = RegularLTO.CombinedModule->getDataLayout();
@@ -982,6 +1030,11 @@ Error LTO::runRegularLTO(AddStreamFn AddStream) {
}
}
+ // If allowed, upgrade public vcall visibility metadata to linkage unit
+ // visibility before whole program devirtualization in the optimizer.
+ updateVCallVisibilityInModule(*RegularLTO.CombinedModule,
+ Conf.HasWholeProgramVisibility);
+
if (Conf.PreOptModuleHook &&
!Conf.PreOptModuleHook(0, *RegularLTO.CombinedModule))
return Error::success();
@@ -1012,8 +1065,15 @@ Error LTO::runRegularLTO(AddStreamFn AddStream) {
!Conf.PostInternalizeModuleHook(0, *RegularLTO.CombinedModule))
return Error::success();
}
- return backend(Conf, AddStream, RegularLTO.ParallelCodeGenParallelismLevel,
- std::move(RegularLTO.CombinedModule), ThinLTO.CombinedIndex);
+
+ if (!RegularLTO.EmptyCombinedModule || Conf.AlwaysEmitRegularLTOObj) {
+ if (Error Err = backend(
+ Conf, AddStream, RegularLTO.ParallelCodeGenParallelismLevel,
+ std::move(RegularLTO.CombinedModule), ThinLTO.CombinedIndex))
+ return Err;
+ }
+
+ return finalizeOptimizationRemarks(std::move(*DiagFileOrErr));
}
static const char *libcallRoutineNames[] = {
@@ -1063,12 +1123,12 @@ class InProcessThinBackend : public ThinBackendProc {
public:
InProcessThinBackend(
const Config &Conf, ModuleSummaryIndex &CombinedIndex,
- unsigned ThinLTOParallelismLevel,
+ ThreadPoolStrategy ThinLTOParallelism,
const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
AddStreamFn AddStream, NativeObjectCache Cache)
: ThinBackendProc(Conf, CombinedIndex, ModuleToDefinedGVSummaries),
- BackendThreadPool(ThinLTOParallelismLevel),
- AddStream(std::move(AddStream)), Cache(std::move(Cache)) {
+ BackendThreadPool(ThinLTOParallelism), AddStream(std::move(AddStream)),
+ Cache(std::move(Cache)) {
for (auto &Name : CombinedIndex.cfiFunctionDefs())
CfiFunctionDefs.insert(
GlobalValue::getGUID(GlobalValue::dropLLVMManglingEscape(Name)));
@@ -1133,6 +1193,9 @@ public:
&ResolvedODR,
const GVSummaryMapTy &DefinedGlobals,
MapVector<StringRef, BitcodeModule> &ModuleMap) {
+ if (LLVM_ENABLE_THREADS && Conf.TimeTraceEnabled)
+ timeTraceProfilerInitialize(Conf.TimeTraceGranularity,
+ "thin backend");
Error E = runThinLTOBackendThread(
AddStream, Cache, Task, BM, CombinedIndex, ImportList, ExportList,
ResolvedODR, DefinedGlobals, ModuleMap);
@@ -1143,6 +1206,8 @@ public:
else
Err = std::move(E);
}
+ if (LLVM_ENABLE_THREADS && Conf.TimeTraceEnabled)
+ timeTraceProfilerFinishThread();
},
BM, std::ref(CombinedIndex), std::ref(ImportList), std::ref(ExportList),
std::ref(ResolvedODR), std::ref(DefinedGlobals), std::ref(ModuleMap));
@@ -1159,13 +1224,13 @@ public:
};
} // end anonymous namespace
-ThinBackend lto::createInProcessThinBackend(unsigned ParallelismLevel) {
+ThinBackend lto::createInProcessThinBackend(ThreadPoolStrategy Parallelism) {
return [=](const Config &Conf, ModuleSummaryIndex &CombinedIndex,
const StringMap<GVSummaryMapTy> &ModuleToDefinedGVSummaries,
AddStreamFn AddStream, NativeObjectCache Cache) {
return std::make_unique<InProcessThinBackend>(
- Conf, CombinedIndex, ParallelismLevel, ModuleToDefinedGVSummaries,
- AddStream, Cache);
+ Conf, CombinedIndex, Parallelism, ModuleToDefinedGVSummaries, AddStream,
+ Cache);
};
}
@@ -1186,7 +1251,7 @@ std::string lto::getThinLTOOutputFile(const std::string &Path,
llvm::errs() << "warning: could not create directory '" << ParentPath
<< "': " << EC.message() << '\n';
}
- return NewPath.str();
+ return std::string(NewPath.str());
}
namespace {
@@ -1215,7 +1280,7 @@ public:
MapVector<StringRef, BitcodeModule> &ModuleMap) override {
StringRef ModulePath = BM.getModuleIdentifier();
std::string NewModulePath =
- getThinLTOOutputFile(ModulePath, OldPrefix, NewPrefix);
+ getThinLTOOutputFile(std::string(ModulePath), OldPrefix, NewPrefix);
if (LinkedObjectsFile)
*LinkedObjectsFile << NewModulePath << '\n';
@@ -1239,7 +1304,7 @@ public:
}
if (OnWrite)
- OnWrite(ModulePath);
+ OnWrite(std::string(ModulePath));
return Error::success();
}
@@ -1264,6 +1329,11 @@ Error LTO::runThinLTO(AddStreamFn AddStream, NativeObjectCache Cache,
if (ThinLTO.ModuleMap.empty())
return Error::success();
+ if (ThinLTO.ModulesToCompile && ThinLTO.ModulesToCompile->empty()) {
+ llvm::errs() << "warning: [ThinLTO] No module compiled\n";
+ return Error::success();
+ }
+
if (Conf.CombinedIndexHook &&
!Conf.CombinedIndexHook(ThinLTO.CombinedIndex, GUIDPreservedSymbols))
return Error::success();
@@ -1299,6 +1369,11 @@ Error LTO::runThinLTO(AddStreamFn AddStream, NativeObjectCache Cache,
std::set<GlobalValue::GUID> ExportedGUIDs;
+ // If allowed, upgrade public vcall visibility to linkage unit visibility in
+ // the summaries before whole program devirtualization below.
+ updateVCallVisibilityInIndex(ThinLTO.CombinedIndex,
+ Conf.HasWholeProgramVisibility);
+
// Perform index-based WPD. This will return immediately if there are
// no index entries in the typeIdMetadata map (e.g. if we are instead
// performing IR-based WPD in hybrid regular/thin LTO mode).
@@ -1359,14 +1434,19 @@ Error LTO::runThinLTO(AddStreamFn AddStream, NativeObjectCache Cache,
thinLTOResolvePrevailingInIndex(ThinLTO.CombinedIndex, isPrevailing,
recordNewLinkage, GUIDPreservedSymbols);
+ generateParamAccessSummary(ThinLTO.CombinedIndex);
+
std::unique_ptr<ThinBackendProc> BackendProc =
ThinLTO.Backend(Conf, ThinLTO.CombinedIndex, ModuleToDefinedGVSummaries,
AddStream, Cache);
+ auto &ModuleMap =
+ ThinLTO.ModulesToCompile ? *ThinLTO.ModulesToCompile : ThinLTO.ModuleMap;
+
// Tasks 0 through ParallelCodeGenParallelismLevel-1 are reserved for combined
// module and parallel code generation partitions.
unsigned Task = RegularLTO.ParallelCodeGenParallelismLevel;
- for (auto &Mod : ThinLTO.ModuleMap) {
+ for (auto &Mod : ModuleMap) {
if (Error E = BackendProc->start(Task, Mod.second, ImportLists[Mod.first],
ExportLists[Mod.first],
ResolvedODR[Mod.first], ThinLTO.ModuleMap))
@@ -1377,11 +1457,10 @@ Error LTO::runThinLTO(AddStreamFn AddStream, NativeObjectCache Cache,
return BackendProc->wait();
}
-Expected<std::unique_ptr<ToolOutputFile>>
-lto::setupOptimizationRemarks(LLVMContext &Context, StringRef RemarksFilename,
- StringRef RemarksPasses, StringRef RemarksFormat,
- bool RemarksWithHotness, int Count) {
- std::string Filename = RemarksFilename;
+Expected<std::unique_ptr<ToolOutputFile>> lto::setupLLVMOptimizationRemarks(
+ LLVMContext &Context, StringRef RemarksFilename, StringRef RemarksPasses,
+ StringRef RemarksFormat, bool RemarksWithHotness, int Count) {
+ std::string Filename = std::string(RemarksFilename);
// For ThinLTO, file.opt.<format> becomes
// file.opt.<format>.thin.<num>.<format>.
if (!Filename.empty() && Count != -1)
@@ -1389,7 +1468,7 @@ lto::setupOptimizationRemarks(LLVMContext &Context, StringRef RemarksFilename,
(Twine(Filename) + ".thin." + llvm::utostr(Count) + "." + RemarksFormat)
.str();
- auto ResultOrErr = llvm::setupOptimizationRemarks(
+ auto ResultOrErr = llvm::setupLLVMOptimizationRemarks(
Context, Filename, RemarksPasses, RemarksFormat, RemarksWithHotness);
if (Error E = ResultOrErr.takeError())
return std::move(E);
diff --git a/llvm/lib/LTO/LTOBackend.cpp b/llvm/lib/LTO/LTOBackend.cpp
index dcde7277b820..0c395f9bbf28 100644
--- a/llvm/lib/LTO/LTOBackend.cpp
+++ b/llvm/lib/LTO/LTOBackend.cpp
@@ -16,18 +16,20 @@
#include "llvm/LTO/LTOBackend.h"
#include "llvm/Analysis/AliasAnalysis.h"
#include "llvm/Analysis/CGSCCPassManager.h"
+#include "llvm/Analysis/ModuleSummaryAnalysis.h"
#include "llvm/Analysis/TargetLibraryInfo.h"
#include "llvm/Analysis/TargetTransformInfo.h"
#include "llvm/Bitcode/BitcodeReader.h"
#include "llvm/Bitcode/BitcodeWriter.h"
+#include "llvm/IR/LLVMRemarkStreamer.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/PassManager.h"
-#include "llvm/IR/RemarkStreamer.h"
#include "llvm/IR/Verifier.h"
#include "llvm/LTO/LTO.h"
#include "llvm/MC/SubtargetFeature.h"
#include "llvm/Object/ModuleSymbolTable.h"
#include "llvm/Passes/PassBuilder.h"
+#include "llvm/Passes/PassPlugin.h"
#include "llvm/Passes/StandardInstrumentations.h"
#include "llvm/Support/Error.h"
#include "llvm/Support/FileSystem.h"
@@ -61,8 +63,10 @@ Error Config::addSaveTemps(std::string OutputFileName,
std::error_code EC;
ResolutionFile = std::make_unique<raw_fd_ostream>(
OutputFileName + "resolution.txt", EC, sys::fs::OpenFlags::OF_Text);
- if (EC)
+ if (EC) {
+ ResolutionFile.reset();
return errorCodeToError(EC);
+ }
auto setHook = [&](std::string PathSuffix, ModuleHookFn &Hook) {
// Keep track of the hook provided by the linker, which also needs to run.
@@ -125,6 +129,29 @@ Error Config::addSaveTemps(std::string OutputFileName,
return Error::success();
}
+#define HANDLE_EXTENSION(Ext) \
+ llvm::PassPluginLibraryInfo get##Ext##PluginInfo();
+#include "llvm/Support/Extension.def"
+
+static void RegisterPassPlugins(ArrayRef<std::string> PassPlugins,
+ PassBuilder &PB) {
+#define HANDLE_EXTENSION(Ext) \
+ get##Ext##PluginInfo().RegisterPassBuilderCallbacks(PB);
+#include "llvm/Support/Extension.def"
+
+ // Load requested pass plugins and let them register pass builder callbacks
+ for (auto &PluginFN : PassPlugins) {
+ auto PassPlugin = PassPlugin::Load(PluginFN);
+ if (!PassPlugin) {
+ errs() << "Failed to load passes from '" << PluginFN
+ << "'. Request ignored.\n";
+ continue;
+ }
+
+ PassPlugin->registerPassBuilderCallbacks(PB);
+ }
+}
+
namespace {
std::unique_ptr<TargetMachine>
@@ -179,6 +206,8 @@ static void runNewPMPasses(const Config &Conf, Module &Mod, TargetMachine *TM,
if (auto Err = PB.parseAAPipeline(AA, "default"))
report_fatal_error("Error parsing default AA pipeline");
+ RegisterPassPlugins(Conf.PassPlugins, PB);
+
LoopAnalysisManager LAM(Conf.DebugPassManager);
FunctionAnalysisManager FAM(Conf.DebugPassManager);
CGSCCAnalysisManager CGAM(Conf.DebugPassManager);
@@ -203,16 +232,16 @@ static void runNewPMPasses(const Config &Conf, Module &Mod, TargetMachine *TM,
default:
llvm_unreachable("Invalid optimization level");
case 0:
- OL = PassBuilder::O0;
+ OL = PassBuilder::OptimizationLevel::O0;
break;
case 1:
- OL = PassBuilder::O1;
+ OL = PassBuilder::OptimizationLevel::O1;
break;
case 2:
- OL = PassBuilder::O2;
+ OL = PassBuilder::OptimizationLevel::O2;
break;
case 3:
- OL = PassBuilder::O3;
+ OL = PassBuilder::OptimizationLevel::O3;
break;
}
@@ -226,8 +255,8 @@ static void runNewPMPasses(const Config &Conf, Module &Mod, TargetMachine *TM,
// FIXME (davide): verify the output.
}
-static void runNewPMCustomPasses(Module &Mod, TargetMachine *TM,
- std::string PipelineDesc,
+static void runNewPMCustomPasses(const Config &Conf, Module &Mod,
+ TargetMachine *TM, std::string PipelineDesc,
std::string AAPipelineDesc,
bool DisableVerify) {
PassBuilder PB(TM);
@@ -239,6 +268,8 @@ static void runNewPMCustomPasses(Module &Mod, TargetMachine *TM,
report_fatal_error("unable to parse AA pipeline description '" +
AAPipelineDesc + "': " + toString(std::move(Err)));
+ RegisterPassPlugins(Conf.PassPlugins, PB);
+
LoopAnalysisManager LAM;
FunctionAnalysisManager FAM;
CGSCCAnalysisManager CGAM;
@@ -305,7 +336,7 @@ bool opt(const Config &Conf, TargetMachine *TM, unsigned Task, Module &Mod,
const ModuleSummaryIndex *ImportSummary) {
// FIXME: Plumb the combined index into the new pass manager.
if (!Conf.OptPipeline.empty())
- runNewPMCustomPasses(Mod, TM, Conf.OptPipeline, Conf.AAPipeline,
+ runNewPMCustomPasses(Conf, Mod, TM, Conf.OptPipeline, Conf.AAPipeline,
Conf.DisableVerify);
else if (Conf.UseNewPM)
runNewPMPasses(Conf, Mod, TM, Conf.OptLevel, IsThinLTO, ExportSummary,
@@ -333,7 +364,8 @@ static void EmitBitcodeSection(Module &M, const Config &Conf) {
}
void codegen(const Config &Conf, TargetMachine *TM, AddStreamFn AddStream,
- unsigned Task, Module &Mod) {
+ unsigned Task, Module &Mod,
+ const ModuleSummaryIndex &CombinedIndex) {
if (Conf.PreCodeGenModuleHook && !Conf.PreCodeGenModuleHook(Task, Mod))
return;
@@ -349,7 +381,7 @@ void codegen(const Config &Conf, TargetMachine *TM, AddStreamFn AddStream,
DwoFile = Conf.DwoDir;
sys::path::append(DwoFile, std::to_string(Task) + ".dwo");
- TM->Options.MCOptions.SplitDwarfFile = DwoFile.str().str();
+ TM->Options.MCOptions.SplitDwarfFile = std::string(DwoFile);
} else
TM->Options.MCOptions.SplitDwarfFile = Conf.SplitDwarfFile;
@@ -362,6 +394,8 @@ void codegen(const Config &Conf, TargetMachine *TM, AddStreamFn AddStream,
auto Stream = AddStream(Task);
legacy::PassManager CodeGenPasses;
+ CodeGenPasses.add(
+ createImmutableModuleSummaryIndexWrapperPass(&CombinedIndex));
if (TM->addPassesToEmitFile(CodeGenPasses, *Stream->OS,
DwoOut ? &DwoOut->os() : nullptr,
Conf.CGFileType))
@@ -374,8 +408,10 @@ void codegen(const Config &Conf, TargetMachine *TM, AddStreamFn AddStream,
void splitCodeGen(const Config &C, TargetMachine *TM, AddStreamFn AddStream,
unsigned ParallelCodeGenParallelismLevel,
- std::unique_ptr<Module> Mod) {
- ThreadPool CodegenThreadPool(ParallelCodeGenParallelismLevel);
+ std::unique_ptr<Module> Mod,
+ const ModuleSummaryIndex &CombinedIndex) {
+ ThreadPool CodegenThreadPool(
+ heavyweight_hardware_concurrency(ParallelCodeGenParallelismLevel));
unsigned ThreadCount = 0;
const Target *T = &TM->getTarget();
@@ -406,7 +442,8 @@ void splitCodeGen(const Config &C, TargetMachine *TM, AddStreamFn AddStream,
std::unique_ptr<TargetMachine> TM =
createTargetMachine(C, T, *MPartInCtx);
- codegen(C, TM.get(), AddStream, ThreadId, *MPartInCtx);
+ codegen(C, TM.get(), AddStream, ThreadId, *MPartInCtx,
+ CombinedIndex);
},
// Pass BC using std::move to ensure that it get moved rather than
// copied into the thread's context.
@@ -434,8 +471,8 @@ Expected<const Target *> initAndLookupTarget(const Config &C, Module &Mod) {
}
}
-static Error
-finalizeOptimizationRemarks(std::unique_ptr<ToolOutputFile> DiagOutputFile) {
+Error lto::finalizeOptimizationRemarks(
+ std::unique_ptr<ToolOutputFile> DiagOutputFile) {
// Make sure we flush the diagnostic remarks file in case the linker doesn't
// call the global destructors before exiting.
if (!DiagOutputFile)
@@ -455,27 +492,19 @@ Error lto::backend(const Config &C, AddStreamFn AddStream,
std::unique_ptr<TargetMachine> TM = createTargetMachine(C, *TOrErr, *Mod);
- // Setup optimization remarks.
- auto DiagFileOrErr = lto::setupOptimizationRemarks(
- Mod->getContext(), C.RemarksFilename, C.RemarksPasses, C.RemarksFormat,
- C.RemarksWithHotness);
- if (!DiagFileOrErr)
- return DiagFileOrErr.takeError();
- auto DiagnosticOutputFile = std::move(*DiagFileOrErr);
-
if (!C.CodeGenOnly) {
if (!opt(C, TM.get(), 0, *Mod, /*IsThinLTO=*/false,
/*ExportSummary=*/&CombinedIndex, /*ImportSummary=*/nullptr))
- return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
+ return Error::success();
}
if (ParallelCodeGenParallelismLevel == 1) {
- codegen(C, TM.get(), AddStream, 0, *Mod);
+ codegen(C, TM.get(), AddStream, 0, *Mod, CombinedIndex);
} else {
splitCodeGen(C, TM.get(), AddStream, ParallelCodeGenParallelismLevel,
- std::move(Mod));
+ std::move(Mod), CombinedIndex);
}
- return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
+ return Error::success();
}
static void dropDeadSymbols(Module &Mod, const GVSummaryMapTy &DefinedGlobals,
@@ -511,22 +540,32 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
std::unique_ptr<TargetMachine> TM = createTargetMachine(Conf, *TOrErr, Mod);
// Setup optimization remarks.
- auto DiagFileOrErr = lto::setupOptimizationRemarks(
+ auto DiagFileOrErr = lto::setupLLVMOptimizationRemarks(
Mod.getContext(), Conf.RemarksFilename, Conf.RemarksPasses,
Conf.RemarksFormat, Conf.RemarksWithHotness, Task);
if (!DiagFileOrErr)
return DiagFileOrErr.takeError();
auto DiagnosticOutputFile = std::move(*DiagFileOrErr);
+ // Set the partial sample profile ratio in the profile summary module flag of
+ // the module, if applicable.
+ Mod.setPartialSampleProfileRatio(CombinedIndex);
+
if (Conf.CodeGenOnly) {
- codegen(Conf, TM.get(), AddStream, Task, Mod);
+ codegen(Conf, TM.get(), AddStream, Task, Mod, CombinedIndex);
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
}
if (Conf.PreOptModuleHook && !Conf.PreOptModuleHook(Task, Mod))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
- renameModuleForThinLTO(Mod, CombinedIndex);
+ // When linking an ELF shared object, dso_local should be dropped. We
+ // conservatively do this for -fpic.
+ bool ClearDSOLocalOnDeclarations =
+ TM->getTargetTriple().isOSBinFormatELF() &&
+ TM->getRelocationModel() != Reloc::Static &&
+ Mod.getPIELevel() == PIELevel::Default;
+ renameModuleForThinLTO(Mod, CombinedIndex, ClearDSOLocalOnDeclarations);
dropDeadSymbols(Mod, DefinedGlobals, CombinedIndex);
@@ -552,7 +591,8 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
/*IsImporting*/ true);
};
- FunctionImporter Importer(CombinedIndex, ModuleLoader);
+ FunctionImporter Importer(CombinedIndex, ModuleLoader,
+ ClearDSOLocalOnDeclarations);
if (Error Err = Importer.importFunctions(Mod, ImportList).takeError())
return Err;
@@ -563,6 +603,6 @@ Error lto::thinBackend(const Config &Conf, unsigned Task, AddStreamFn AddStream,
/*ExportSummary=*/nullptr, /*ImportSummary=*/&CombinedIndex))
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
- codegen(Conf, TM.get(), AddStream, Task, Mod);
+ codegen(Conf, TM.get(), AddStream, Task, Mod, CombinedIndex);
return finalizeOptimizationRemarks(std::move(DiagnosticOutputFile));
}
diff --git a/llvm/lib/LTO/LTOCodeGenerator.cpp b/llvm/lib/LTO/LTOCodeGenerator.cpp
index 5fef14230a9b..25ab1404b4e1 100644
--- a/llvm/lib/LTO/LTOCodeGenerator.cpp
+++ b/llvm/lib/LTO/LTOCodeGenerator.cpp
@@ -29,11 +29,11 @@
#include "llvm/IR/DiagnosticInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/LLVMRemarkStreamer.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/Module.h"
#include "llvm/IR/PassTimingInfo.h"
-#include "llvm/IR/RemarkStreamer.h"
#include "llvm/IR/Verifier.h"
#include "llvm/InitializePasses.h"
#include "llvm/LTO/LTO.h"
@@ -57,6 +57,7 @@
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/IPO/Internalize.h"
#include "llvm/Transforms/IPO/PassManagerBuilder.h"
+#include "llvm/Transforms/IPO/WholeProgramDevirt.h"
#include "llvm/Transforms/ObjCARC.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
#include <system_error>
@@ -133,10 +134,12 @@ void LTOCodeGenerator::initializeLTOPasses() {
initializeSimpleInlinerPass(R);
initializePruneEHPass(R);
initializeGlobalDCELegacyPassPass(R);
+ initializeOpenMPOptLegacyPassPass(R);
initializeArgPromotionPass(R);
initializeJumpThreadingPass(R);
initializeSROALegacyPassPass(R);
initializeAttributorLegacyPassPass(R);
+ initializeAttributorCGSCCLegacyPassPass(R);
initializePostOrderFunctionAttrsLegacyPassPass(R);
initializeReversePostOrderFunctionAttrsLegacyPassPass(R);
initializeGlobalsAAWrapperPassPass(R);
@@ -526,8 +529,8 @@ bool LTOCodeGenerator::optimize(bool DisableVerify, bool DisableInline,
return false;
auto DiagFileOrErr =
- lto::setupOptimizationRemarks(Context, RemarksFilename, RemarksPasses,
- RemarksFormat, RemarksWithHotness);
+ lto::setupLLVMOptimizationRemarks(Context, RemarksFilename, RemarksPasses,
+ RemarksFormat, RemarksWithHotness);
if (!DiagFileOrErr) {
errs() << "Error: " << toString(DiagFileOrErr.takeError()) << "\n";
report_fatal_error("Can't get an output file for the remarks");
@@ -542,6 +545,13 @@ bool LTOCodeGenerator::optimize(bool DisableVerify, bool DisableInline,
}
StatsFile = std::move(StatsFileOrErr.get());
+ // Currently there is no support for enabling whole program visibility via a
+ // linker option in the old LTO API, but this call allows it to be specified
+ // via the internal option. Must be done before WPD invoked via the optimizer
+ // pipeline run below.
+ updateVCallVisibilityInModule(*MergedModule,
+ /* WholeProgramVisibilityEnabledInLTO */ false);
+
// We always run the verifier once on the merged module, the `DisableVerify`
// parameter only applies to subsequent verify.
verifyMergedModuleOnce();
@@ -622,9 +632,9 @@ bool LTOCodeGenerator::compileOptimized(ArrayRef<raw_pwrite_stream *> Out) {
return true;
}
-void LTOCodeGenerator::setCodeGenDebugOptions(ArrayRef<const char *> Options) {
+void LTOCodeGenerator::setCodeGenDebugOptions(ArrayRef<StringRef> Options) {
for (StringRef Option : Options)
- CodegenOptions.push_back(Option);
+ CodegenOptions.push_back(Option.str());
}
void LTOCodeGenerator::parseCodeGenDebugOptions() {
diff --git a/llvm/lib/LTO/LTOModule.cpp b/llvm/lib/LTO/LTOModule.cpp
index 587b332e7064..ebe779aea62e 100644
--- a/llvm/lib/LTO/LTOModule.cpp
+++ b/llvm/lib/LTO/LTOModule.cpp
@@ -28,6 +28,7 @@
#include "llvm/MC/MCSymbol.h"
#include "llvm/MC/SubtargetFeature.h"
#include "llvm/Object/IRObjectFile.h"
+#include "llvm/Object/MachO.h"
#include "llvm/Object/ObjectFile.h"
#include "llvm/Support/FileSystem.h"
#include "llvm/Support/Host.h"
@@ -413,9 +414,8 @@ void LTOModule::addDefinedFunctionSymbol(StringRef Name, const Function *F) {
void LTOModule::addDefinedSymbol(StringRef Name, const GlobalValue *def,
bool isFunction) {
- // set alignment part log2() can have rounding errors
- uint32_t align = def->getAlignment();
- uint32_t attr = align ? countTrailingZeros(align) : 0;
+ const GlobalObject *go = dyn_cast<GlobalObject>(def);
+ uint32_t attr = go ? Log2(go->getAlign().valueOrOne()) : 0;
// set permissions part
if (isFunction) {
@@ -676,3 +676,11 @@ const char *LTOModule::getDependentLibrary(lto::InputFile *input, size_t index,
*size = S.size();
return S.data();
}
+
+Expected<uint32_t> LTOModule::getMachOCPUType() const {
+ return MachO::getCPUType(Triple(Mod->getTargetTriple()));
+}
+
+Expected<uint32_t> LTOModule::getMachOCPUSubType() const {
+ return MachO::getCPUSubType(Triple(Mod->getTargetTriple()));
+}
diff --git a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
index a9e27832917c..d0a1e1889c61 100644
--- a/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
+++ b/llvm/lib/LTO/ThinLTOCodeGenerator.cpp
@@ -27,10 +27,10 @@
#include "llvm/IR/DebugInfo.h"
#include "llvm/IR/DiagnosticPrinter.h"
#include "llvm/IR/LLVMContext.h"
+#include "llvm/IR/LLVMRemarkStreamer.h"
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/IR/PassTimingInfo.h"
-#include "llvm/IR/RemarkStreamer.h"
#include "llvm/IR/Verifier.h"
#include "llvm/IRReader/IRReader.h"
#include "llvm/LTO/LTO.h"
@@ -48,7 +48,6 @@
#include "llvm/Support/ThreadPool.h"
#include "llvm/Support/Threading.h"
#include "llvm/Support/ToolOutputFile.h"
-#include "llvm/Support/VCSRevision.h"
#include "llvm/Target/TargetMachine.h"
#include "llvm/Transforms/IPO.h"
#include "llvm/Transforms/IPO/FunctionImport.h"
@@ -81,8 +80,10 @@ extern cl::opt<std::string> RemarksFormat;
namespace {
-static cl::opt<int>
- ThreadCount("threads", cl::init(llvm::heavyweight_hardware_concurrency()));
+// Default to using all available threads in the system, but using only one
+// thred per core, as indicated by the usage of
+// heavyweight_hardware_concurrency() below.
+static cl::opt<int> ThreadCount("threads", cl::init(0));
// Simple helper to save temporary files for debug.
static void saveTempBitcode(const Module &TheModule, StringRef TempDir,
@@ -151,8 +152,9 @@ generateModuleMap(std::vector<std::unique_ptr<lto::InputFile>> &Modules) {
return ModuleMap;
}
-static void promoteModule(Module &TheModule, const ModuleSummaryIndex &Index) {
- if (renameModuleForThinLTO(TheModule, Index))
+static void promoteModule(Module &TheModule, const ModuleSummaryIndex &Index,
+ bool ClearDSOLocalOnDeclarations) {
+ if (renameModuleForThinLTO(TheModule, Index, ClearDSOLocalOnDeclarations))
report_fatal_error("renameModuleForThinLTO failed");
}
@@ -204,15 +206,16 @@ static std::unique_ptr<Module> loadModuleFromInput(lto::InputFile *Input,
static void
crossImportIntoModule(Module &TheModule, const ModuleSummaryIndex &Index,
- StringMap<lto::InputFile*> &ModuleMap,
- const FunctionImporter::ImportMapTy &ImportList) {
+ StringMap<lto::InputFile *> &ModuleMap,
+ const FunctionImporter::ImportMapTy &ImportList,
+ bool ClearDSOLocalOnDeclarations) {
auto Loader = [&](StringRef Identifier) {
auto &Input = ModuleMap[Identifier];
return loadModuleFromInput(Input, TheModule.getContext(),
/*Lazy=*/true, /*IsImporting*/ true);
};
- FunctionImporter Importer(Index, Loader);
+ FunctionImporter Importer(Index, Loader, ClearDSOLocalOnDeclarations);
Expected<bool> Result = Importer.importFunctions(TheModule, ImportList);
if (!Result) {
handleAllErrors(Result.takeError(), [&](ErrorInfoBase &EIB) {
@@ -410,8 +413,15 @@ ProcessThinLTOModule(Module &TheModule, ModuleSummaryIndex &Index,
// "Benchmark"-like optimization: single-source case
bool SingleModule = (ModuleMap.size() == 1);
+ // When linking an ELF shared object, dso_local should be dropped. We
+ // conservatively do this for -fpic.
+ bool ClearDSOLocalOnDeclarations =
+ TM.getTargetTriple().isOSBinFormatELF() &&
+ TM.getRelocationModel() != Reloc::Static &&
+ TheModule.getPIELevel() == PIELevel::Default;
+
if (!SingleModule) {
- promoteModule(TheModule, Index);
+ promoteModule(TheModule, Index, ClearDSOLocalOnDeclarations);
// Apply summary-based prevailing-symbol resolution decisions.
thinLTOResolvePrevailingInModule(TheModule, DefinedGlobals);
@@ -431,7 +441,8 @@ ProcessThinLTOModule(Module &TheModule, ModuleSummaryIndex &Index,
saveTempBitcode(TheModule, SaveTempsDir, count, ".2.internalized.bc");
if (!SingleModule) {
- crossImportIntoModule(TheModule, Index, ModuleMap, ImportList);
+ crossImportIntoModule(TheModule, Index, ModuleMap, ImportList,
+ ClearDSOLocalOnDeclarations);
// Save temps: after cross-module import.
saveTempBitcode(TheModule, SaveTempsDir, count, ".3.imported.bc");
@@ -672,7 +683,8 @@ void ThinLTOCodeGenerator::promote(Module &TheModule, ModuleSummaryIndex &Index,
Index, IsExported(ExportLists, GUIDPreservedSymbols),
IsPrevailing(PrevailingCopy));
- promoteModule(TheModule, Index);
+ // FIXME Set ClearDSOLocalOnDeclarations.
+ promoteModule(TheModule, Index, /*ClearDSOLocalOnDeclarations=*/false);
}
/**
@@ -704,7 +716,9 @@ void ThinLTOCodeGenerator::crossModuleImport(Module &TheModule,
ExportLists);
auto &ImportList = ImportLists[TheModule.getModuleIdentifier()];
- crossImportIntoModule(TheModule, Index, ModuleMap, ImportList);
+ // FIXME Set ClearDSOLocalOnDeclarations.
+ crossImportIntoModule(TheModule, Index, ModuleMap, ImportList,
+ /*ClearDSOLocalOnDeclarations=*/false);
}
/**
@@ -831,7 +845,8 @@ void ThinLTOCodeGenerator::internalize(Module &TheModule,
Index, IsExported(ExportLists, GUIDPreservedSymbols),
IsPrevailing(PrevailingCopy));
- promoteModule(TheModule, Index);
+ // FIXME Set ClearDSOLocalOnDeclarations.
+ promoteModule(TheModule, Index, /*ClearDSOLocalOnDeclarations=*/false);
// Internalization
thinLTOResolvePrevailingInModule(
@@ -871,15 +886,15 @@ ThinLTOCodeGenerator::writeGeneratedObject(int count, StringRef CacheEntryPath,
// Cache is enabled, hard-link the entry (or copy if hard-link fails).
auto Err = sys::fs::create_hard_link(CacheEntryPath, OutputPath);
if (!Err)
- return OutputPath.str();
+ return std::string(OutputPath.str());
// Hard linking failed, try to copy.
Err = sys::fs::copy_file(CacheEntryPath, OutputPath);
if (!Err)
- return OutputPath.str();
+ return std::string(OutputPath.str());
// Copy failed (could be because the CacheEntry was removed from the cache
// in the meantime by another process), fall back and try to write down the
// buffer to the output.
- errs() << "error: can't link or copy from cached entry '" << CacheEntryPath
+ errs() << "remark: can't link or copy from cached entry '" << CacheEntryPath
<< "' to '" << OutputPath << "'\n";
}
// No cache entry, just write out the buffer.
@@ -888,7 +903,7 @@ ThinLTOCodeGenerator::writeGeneratedObject(int count, StringRef CacheEntryPath,
if (Err)
report_fatal_error("Can't open output '" + OutputPath + "'\n");
OS << OutputBuffer.getBuffer();
- return OutputPath.str();
+ return std::string(OutputPath.str());
}
// Main entry point for the ThinLTO processing
@@ -970,6 +985,12 @@ void ThinLTOCodeGenerator::run() {
// Synthesize entry counts for functions in the combined index.
computeSyntheticCounts(*Index);
+ // Currently there is no support for enabling whole program visibility via a
+ // linker option in the old LTO API, but this call allows it to be specified
+ // via the internal option. Must be done before WPD below.
+ updateVCallVisibilityInIndex(*Index,
+ /* WholeProgramVisibilityEnabledInLTO */ false);
+
// Perform index-based WPD. This will return immediately if there are
// no index entries in the typeIdMetadata map (e.g. if we are instead
// performing IR-based WPD in hybrid regular/thin LTO mode).
@@ -1037,7 +1058,7 @@ void ThinLTOCodeGenerator::run() {
// Parallel optimizer + codegen
{
- ThreadPool Pool(ThreadCount);
+ ThreadPool Pool(heavyweight_hardware_concurrency(ThreadCount));
for (auto IndexCount : ModulesOrdering) {
auto &Mod = Modules[IndexCount];
Pool.async([&](int count) {
@@ -1074,7 +1095,7 @@ void ThinLTOCodeGenerator::run() {
LLVMContext Context;
Context.setDiscardValueNames(LTODiscardValueNames);
Context.enableDebugTypeODRUniquing();
- auto DiagFileOrErr = lto::setupOptimizationRemarks(
+ auto DiagFileOrErr = lto::setupLLVMOptimizationRemarks(
Context, RemarksFilename, RemarksPasses, RemarksFormat,
RemarksWithHotness, count);
if (!DiagFileOrErr) {
@@ -1113,7 +1134,7 @@ void ThinLTOCodeGenerator::run() {
auto ReloadedBufferOrErr = CacheEntry.tryLoadingBuffer();
if (auto EC = ReloadedBufferOrErr.getError()) {
// On error, keep the preexisting buffer and print a diagnostic.
- errs() << "error: can't reload cached file '" << CacheEntryPath
+ errs() << "remark: can't reload cached file '" << CacheEntryPath
<< "': " << EC.message() << "\n";
} else {
OutputBuffer = std::move(*ReloadedBufferOrErr);
diff --git a/llvm/lib/LTO/UpdateCompilerUsed.cpp b/llvm/lib/LTO/UpdateCompilerUsed.cpp
index 6434f902088d..040e1106523c 100644
--- a/llvm/lib/LTO/UpdateCompilerUsed.cpp
+++ b/llvm/lib/LTO/UpdateCompilerUsed.cpp
@@ -17,6 +17,7 @@
#include "llvm/IR/LegacyPassManager.h"
#include "llvm/IR/Mangler.h"
#include "llvm/Transforms/Utils/ModuleUtils.h"
+#include "llvm/Target/TargetMachine.h"
using namespace llvm;
generated by cgit v1.2.3 (git 2.25.1) at 2025-11-04 06:29:38 +0000