LTOCodeGenerator::LTOCodeGenerator(LLVMContext &Context)
: Context(Context), MergedModule(new Module("ld-temp.o", Context)),
TheLinker(new Linker(*MergedModule)) {
Context.setDiscardValueNames(LTODiscardValueNames);
Context.enableDebugTypeODRUniquing();
initializeLTOPasses();
}
// Main entry point for the ThinLTO processing
void ThinLTOCodeGenerator::run() {
// Sequential linking phase
auto Index = linkCombinedIndex();
// Save temps: index.
if (!SaveTempsDir.empty()) {
auto SaveTempPath = SaveTempsDir + "index.bc";
std::error_code EC;
raw_fd_ostream OS(SaveTempPath, EC, sys::fs::F_None);
if (EC)
report_fatal_error(Twine("Failed to open ") + SaveTempPath +
" to save optimized bitcode\n");
WriteIndexToFile(*Index, OS);
}
// Prepare the resulting object vector
assert(ProducedBinaries.empty() && "The generator should not be reused");
ProducedBinaries.resize(Modules.size());
// Prepare the module map.
auto ModuleMap = generateModuleMap(Modules);
// Parallel optimizer + codegen
{
ThreadPool Pool(ThreadCount);
int count = 0;
for (auto &ModuleBuffer : Modules) {
Pool.async([&](int count) {
LLVMContext Context;
Context.setDiscardValueNames(LTODiscardValueNames);
// Parse module now
auto TheModule = loadModuleFromBuffer(ModuleBuffer, Context, false);
// Save temps: original file.
if (!SaveTempsDir.empty()) {
saveTempBitcode(*TheModule, SaveTempsDir, count, ".0.original.bc");
}
ProducedBinaries[count] = ProcessThinLTOModule(
*TheModule, *Index, ModuleMap, *TMBuilder.create(), CacheOptions,
SaveTempsDir, count);
}, count);
count++;
}
}
// If statistics were requested, print them out now.
if (llvm::AreStatisticsEnabled())
llvm::PrintStatistics();
}
// main - Entry point for the llc compiler.
//
int main(int argc, char **argv) {
sys::PrintStackTraceOnErrorSignal(argv[0]);
PrettyStackTraceProgram X(argc, argv);
// Enable debug stream buffering.
EnableDebugBuffering = true;
LLVMContext Context;
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
// Initialize targets first, so that --version shows registered targets.
InitializeAllTargets();
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
InitializeAllAsmParsers();
// Initialize codegen and IR passes used by llc so that the -print-after,
// -print-before, and -stop-after options work.
PassRegistry *Registry = PassRegistry::getPassRegistry();
initializeCore(*Registry);
initializeCodeGen(*Registry);
initializeLoopStrengthReducePass(*Registry);
initializeLowerIntrinsicsPass(*Registry);
initializeCountingFunctionInserterPass(*Registry);
initializeUnreachableBlockElimLegacyPassPass(*Registry);
initializeConstantHoistingLegacyPassPass(*Registry);
// Register the target printer for --version.
cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
cl::ParseCommandLineOptions(argc, argv, "llvm system compiler\n");
Context.setDiscardValueNames(DiscardValueNames);
// Set a diagnostic handler that doesn't exit on the first error
bool HasError = false;
Context.setDiagnosticHandler(DiagnosticHandler, &HasError);
// Compile the module TimeCompilations times to give better compile time
// metrics.
for (unsigned I = TimeCompilations; I; --I)
if (int RetVal = compileModule(argv, Context))
return RetVal;
return 0;
}
/// Perform the ThinLTO backend on a single module, invoking the LTO and codegen
/// pipelines.
static void thinLTOBackendTask(claimed_file &F, const void *View,
ld_plugin_input_file &File,
raw_fd_ostream *ApiFile,
const ModuleSummaryIndex &CombinedIndex,
raw_fd_ostream *OS, unsigned TaskID) {
// Need to use a separate context for each task
LLVMContext Context;
Context.setDiscardValueNames(options::DiscardValueNames);
Context.enableDebugTypeODRUniquing(); // Merge debug info types.
Context.setDiagnosticHandler(diagnosticHandlerForContext, nullptr, true);
std::unique_ptr<llvm::Module> NewModule(new llvm::Module(File.name, Context));
IRMover L(*NewModule.get());
StringSet<> Dummy;
if (linkInModule(Context, L, F, View, File, ApiFile, Dummy, Dummy))
message(LDPL_FATAL, "Failed to rename module for ThinLTO");
if (renameModuleForThinLTO(*NewModule, CombinedIndex))
message(LDPL_FATAL, "Failed to rename module for ThinLTO");
CodeGen codeGen(std::move(NewModule), OS, TaskID, &CombinedIndex, File.name);
codeGen.runAll();
}
// main - Entry point for the llc compiler.
//
int main(int argc, char **argv) {
sys::PrintStackTraceOnErrorSignal(argv[0]);
PrettyStackTraceProgram X(argc, argv);
// Enable debug stream buffering.
EnableDebugBuffering = true;
LLVMContext Context;
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
// Initialize targets first, so that --version shows registered targets.
InitializeAllTargets();
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
InitializeAllAsmParsers();
// Initialize codegen and IR passes used by llc so that the -print-after,
// -print-before, and -stop-after options work.
PassRegistry *Registry = PassRegistry::getPassRegistry();
initializeCore(*Registry);
initializeCodeGen(*Registry);
initializeLoopStrengthReducePass(*Registry);
initializeLowerIntrinsicsPass(*Registry);
initializeCountingFunctionInserterPass(*Registry);
initializeUnreachableBlockElimLegacyPassPass(*Registry);
initializeConstantHoistingLegacyPassPass(*Registry);
initializeScalarOpts(*Registry);
initializeVectorization(*Registry);
// Register the target printer for --version.
cl::AddExtraVersionPrinter(TargetRegistry::printRegisteredTargetsForVersion);
cl::ParseCommandLineOptions(argc, argv, "llvm system compiler\n");
Context.setDiscardValueNames(DiscardValueNames);
// Set a diagnostic handler that doesn't exit on the first error
bool HasError = false;
Context.setDiagnosticHandler(DiagnosticHandler, &HasError);
Context.setInlineAsmDiagnosticHandler(InlineAsmDiagHandler, &HasError);
if (PassRemarksWithHotness)
Context.setDiagnosticHotnessRequested(true);
std::unique_ptr<tool_output_file> YamlFile;
if (RemarksFilename != "") {
std::error_code EC;
YamlFile = llvm::make_unique<tool_output_file>(RemarksFilename, EC,
sys::fs::F_None);
if (EC) {
errs() << EC.message() << '\n';
return 1;
}
Context.setDiagnosticsOutputFile(
llvm::make_unique<yaml::Output>(YamlFile->os()));
}
// Compile the module TimeCompilations times to give better compile time
// metrics.
for (unsigned I = TimeCompilations; I; --I)
if (int RetVal = compileModule(argv, Context))
return RetVal;
if (YamlFile)
YamlFile->keep();
return 0;
}
/// gold informs us that all symbols have been read. At this point, we use
/// get_symbols to see if any of our definitions have been overridden by a
/// native object file. Then, perform optimization and codegen.
static ld_plugin_status allSymbolsReadHook(raw_fd_ostream *ApiFile) {
if (Modules.empty())
return LDPS_OK;
if (unsigned NumOpts = options::extra.size())
cl::ParseCommandLineOptions(NumOpts, &options::extra[0]);
// If we are doing ThinLTO compilation, simply build the combined
// module index/summary and emit it. We don't need to parse the modules
// and link them in this case.
if (options::thinlto) {
ModuleSummaryIndex CombinedIndex;
uint64_t NextModuleId = 0;
for (claimed_file &F : Modules) {
PluginInputFile InputFile(F.handle);
std::unique_ptr<ModuleSummaryIndex> Index =
getModuleSummaryIndexForFile(F, InputFile.file());
// Skip files without a module summary.
if (Index)
CombinedIndex.mergeFrom(std::move(Index), ++NextModuleId);
}
std::error_code EC;
raw_fd_ostream OS(output_name + ".thinlto.bc", EC,
sys::fs::OpenFlags::F_None);
if (EC)
message(LDPL_FATAL, "Unable to open %s.thinlto.bc for writing: %s",
output_name.data(), EC.message().c_str());
WriteIndexToFile(CombinedIndex, OS);
OS.close();
if (options::thinlto_index_only) {
cleanup_hook();
exit(0);
}
thinLTOBackends(ApiFile, CombinedIndex);
return LDPS_OK;
}
LLVMContext Context;
Context.setDiscardValueNames(options::DiscardValueNames);
Context.enableDebugTypeODRUniquing(); // Merge debug info types.
Context.setDiagnosticHandler(diagnosticHandlerForContext, nullptr, true);
std::unique_ptr<Module> Combined(new Module("ld-temp.o", Context));
IRMover L(*Combined);
StringSet<> Internalize;
StringSet<> Maybe;
for (claimed_file &F : Modules) {
PluginInputFile InputFile(F.handle);
const void *View = getSymbolsAndView(F);
if (!View)
continue;
if (linkInModule(Context, L, F, View, InputFile.file(), ApiFile,
Internalize, Maybe))
message(LDPL_FATAL, "Failed to link module");
}
for (const auto &Name : Internalize) {
GlobalValue *GV = Combined->getNamedValue(Name.first());
if (GV)
internalize(*GV);
}
for (const auto &Name : Maybe) {
GlobalValue *GV = Combined->getNamedValue(Name.first());
if (!GV)
continue;
GV->setLinkage(GlobalValue::LinkOnceODRLinkage);
if (canBeOmittedFromSymbolTable(GV))
internalize(*GV);
}
if (options::TheOutputType == options::OT_DISABLE)
return LDPS_OK;
if (options::TheOutputType != options::OT_NORMAL) {
std::string path;
if (options::TheOutputType == options::OT_BC_ONLY)
path = output_name;
else
path = output_name + ".bc";
saveBCFile(path, *Combined);
if (options::TheOutputType == options::OT_BC_ONLY)
return LDPS_OK;
}
CodeGen codeGen(std::move(Combined));
codeGen.runAll();
if (!options::extra_library_path.empty() &&
set_extra_library_path(options::extra_library_path.c_str()) != LDPS_OK)
message(LDPL_FATAL, "Unable to set the extra library path.");
return LDPS_OK;
}
//===----------------------------------------------------------------------===//
// main for opt
//
int main(int argc, char **argv) {
sys::PrintStackTraceOnErrorSignal();
llvm::PrettyStackTraceProgram X(argc, argv);
// Enable debug stream buffering.
EnableDebugBuffering = true;
llvm_shutdown_obj Y; // Call llvm_shutdown() on exit.
LLVMContext Context;
InitializeAllTargets();
InitializeAllTargetMCs();
InitializeAllAsmPrinters();
// Initialize passes
PassRegistry &Registry = *PassRegistry::getPassRegistry();
initializeCore(Registry);
initializeScalarOpts(Registry);
initializeObjCARCOpts(Registry);
initializeVectorization(Registry);
initializeIPO(Registry);
initializeAnalysis(Registry);
initializeTransformUtils(Registry);
initializeInstCombine(Registry);
initializeInstrumentation(Registry);
initializeTarget(Registry);
// For codegen passes, only passes that do IR to IR transformation are
// supported.
initializeCodeGenPreparePass(Registry);
initializeAtomicExpandPass(Registry);
initializeRewriteSymbolsPass(Registry);
initializeWinEHPreparePass(Registry);
initializeDwarfEHPreparePass(Registry);
initializeSafeStackPass(Registry);
initializeSjLjEHPreparePass(Registry);
#ifdef LINK_POLLY_INTO_TOOLS
polly::initializePollyPasses(Registry);
#endif
cl::ParseCommandLineOptions(argc, argv,
"llvm .bc -> .bc modular optimizer and analysis printer\n");
if (AnalyzeOnly && NoOutput) {
errs() << argv[0] << ": analyze mode conflicts with no-output mode.\n";
return 1;
}
SMDiagnostic Err;
Context.setDiscardValueNames(DiscardValueNames);
if (!DisableDITypeMap)
Context.enableDebugTypeODRUniquing();
// Load the input module...
std::unique_ptr<Module> M = parseIRFile(InputFilename, Err, Context);
if (!M) {
Err.print(argv[0], errs());
return 1;
}
// Strip debug info before running the verifier.
if (StripDebug)
StripDebugInfo(*M);
// Immediately run the verifier to catch any problems before starting up the
// pass pipelines. Otherwise we can crash on broken code during
// doInitialization().
if (!NoVerify && verifyModule(*M, &errs())) {
errs() << argv[0] << ": " << InputFilename
<< ": error: input module is broken!\n";
return 1;
}
// If we are supposed to override the target triple, do so now.
if (!TargetTriple.empty())
M->setTargetTriple(Triple::normalize(TargetTriple));
// Figure out what stream we are supposed to write to...
std::unique_ptr<tool_output_file> Out;
if (NoOutput) {
if (!OutputFilename.empty())
errs() << "WARNING: The -o (output filename) option is ignored when\n"
"the --disable-output option is used.\n";
} else {
// Default to standard output.
if (OutputFilename.empty())
OutputFilename = "-";
std::error_code EC;
Out.reset(new tool_output_file(OutputFilename, EC, sys::fs::F_None));
if (EC) {
errs() << EC.message() << '\n';
return 1;
}
}
Triple ModuleTriple(M->getTargetTriple());
std::string CPUStr, FeaturesStr;
TargetMachine *Machine = nullptr;
const TargetOptions Options = InitTargetOptionsFromCodeGenFlags();
if (ModuleTriple.getArch()) {
CPUStr = getCPUStr();
FeaturesStr = getFeaturesStr();
Machine = GetTargetMachine(ModuleTriple, CPUStr, FeaturesStr, Options);
}
std::unique_ptr<TargetMachine> TM(Machine);
// Override function attributes based on CPUStr, FeaturesStr, and command line
// flags.
setFunctionAttributes(CPUStr, FeaturesStr, *M);
// If the output is set to be emitted to standard out, and standard out is a
// console, print out a warning message and refuse to do it. We don't
// impress anyone by spewing tons of binary goo to a terminal.
if (!Force && !NoOutput && !AnalyzeOnly && !OutputAssembly)
if (CheckBitcodeOutputToConsole(Out->os(), !Quiet))
NoOutput = true;
if (PassPipeline.getNumOccurrences() > 0) {
OutputKind OK = OK_NoOutput;
if (!NoOutput)
OK = OutputAssembly ? OK_OutputAssembly : OK_OutputBitcode;
VerifierKind VK = VK_VerifyInAndOut;
if (NoVerify)
VK = VK_NoVerifier;
else if (VerifyEach)
VK = VK_VerifyEachPass;
// The user has asked to use the new pass manager and provided a pipeline
// string. Hand off the rest of the functionality to the new code for that
// layer.
return runPassPipeline(argv[0], Context, *M, TM.get(), Out.get(),
PassPipeline, OK, VK, PreserveAssemblyUseListOrder,
PreserveBitcodeUseListOrder)
? 0
: 1;
}
// Create a PassManager to hold and optimize the collection of passes we are
// about to build.
//
legacy::PassManager Passes;
// Add an appropriate TargetLibraryInfo pass for the module's triple.
TargetLibraryInfoImpl TLII(ModuleTriple);
// The -disable-simplify-libcalls flag actually disables all builtin optzns.
if (DisableSimplifyLibCalls)
TLII.disableAllFunctions();
Passes.add(new TargetLibraryInfoWrapperPass(TLII));
// Add an appropriate DataLayout instance for this module.
const DataLayout &DL = M->getDataLayout();
if (DL.isDefault() && !DefaultDataLayout.empty()) {
M->setDataLayout(DefaultDataLayout);
}
// Add internal analysis passes from the target machine.
Passes.add(createTargetTransformInfoWrapperPass(TM ? TM->getTargetIRAnalysis()
: TargetIRAnalysis()));
std::unique_ptr<legacy::FunctionPassManager> FPasses;
if (OptLevelO1 || OptLevelO2 || OptLevelOs || OptLevelOz || OptLevelO3) {
FPasses.reset(new legacy::FunctionPassManager(M.get()));
FPasses->add(createTargetTransformInfoWrapperPass(
TM ? TM->getTargetIRAnalysis() : TargetIRAnalysis()));
}
if (PrintBreakpoints) {
// Default to standard output.
if (!Out) {
if (OutputFilename.empty())
OutputFilename = "-";
std::error_code EC;
Out = llvm::make_unique<tool_output_file>(OutputFilename, EC,
sys::fs::F_None);
if (EC) {
errs() << EC.message() << '\n';
return 1;
}
}
Passes.add(createBreakpointPrinter(Out->os()));
NoOutput = true;
}
// Create a new optimization pass for each one specified on the command line
for (unsigned i = 0; i < PassList.size(); ++i) {
if (StandardLinkOpts &&
StandardLinkOpts.getPosition() < PassList.getPosition(i)) {
AddStandardLinkPasses(Passes);
StandardLinkOpts = false;
}
if (OptLevelO1 && OptLevelO1.getPosition() < PassList.getPosition(i)) {
AddOptimizationPasses(Passes, *FPasses, 1, 0);
OptLevelO1 = false;
}
if (OptLevelO2 && OptLevelO2.getPosition() < PassList.getPosition(i)) {
AddOptimizationPasses(Passes, *FPasses, 2, 0);
OptLevelO2 = false;
}
if (OptLevelOs && OptLevelOs.getPosition() < PassList.getPosition(i)) {
AddOptimizationPasses(Passes, *FPasses, 2, 1);
OptLevelOs = false;
}
if (OptLevelOz && OptLevelOz.getPosition() < PassList.getPosition(i)) {
AddOptimizationPasses(Passes, *FPasses, 2, 2);
OptLevelOz = false;
}
if (OptLevelO3 && OptLevelO3.getPosition() < PassList.getPosition(i)) {
AddOptimizationPasses(Passes, *FPasses, 3, 0);
OptLevelO3 = false;
}
const PassInfo *PassInf = PassList[i];
Pass *P = nullptr;
if (PassInf->getTargetMachineCtor())
P = PassInf->getTargetMachineCtor()(TM.get());
else if (PassInf->getNormalCtor())
P = PassInf->getNormalCtor()();
else
errs() << argv[0] << ": cannot create pass: "******"\n";
if (P) {
PassKind Kind = P->getPassKind();
addPass(Passes, P);
if (AnalyzeOnly) {
switch (Kind) {
case PT_BasicBlock:
Passes.add(createBasicBlockPassPrinter(PassInf, Out->os(), Quiet));
break;
case PT_Region:
Passes.add(createRegionPassPrinter(PassInf, Out->os(), Quiet));
break;
case PT_Loop:
Passes.add(createLoopPassPrinter(PassInf, Out->os(), Quiet));
break;
case PT_Function:
Passes.add(createFunctionPassPrinter(PassInf, Out->os(), Quiet));
break;
case PT_CallGraphSCC:
Passes.add(createCallGraphPassPrinter(PassInf, Out->os(), Quiet));
break;
default:
Passes.add(createModulePassPrinter(PassInf, Out->os(), Quiet));
break;
}
}
}
if (PrintEachXForm)
Passes.add(
createPrintModulePass(errs(), "", PreserveAssemblyUseListOrder));
}
if (StandardLinkOpts) {
AddStandardLinkPasses(Passes);
StandardLinkOpts = false;
}
if (OptLevelO1)
AddOptimizationPasses(Passes, *FPasses, 1, 0);
if (OptLevelO2)
AddOptimizationPasses(Passes, *FPasses, 2, 0);
if (OptLevelOs)
AddOptimizationPasses(Passes, *FPasses, 2, 1);
if (OptLevelOz)
AddOptimizationPasses(Passes, *FPasses, 2, 2);
if (OptLevelO3)
AddOptimizationPasses(Passes, *FPasses, 3, 0);
if (OptLevelO1 || OptLevelO2 || OptLevelOs || OptLevelOz || OptLevelO3) {
FPasses->doInitialization();
for (Function &F : *M)
FPasses->run(F);
FPasses->doFinalization();
}
// Check that the module is well formed on completion of optimization
if (!NoVerify && !VerifyEach)
Passes.add(createVerifierPass());
// In run twice mode, we want to make sure the output is bit-by-bit
// equivalent if we run the pass manager again, so setup two buffers and
// a stream to write to them. Note that llc does something similar and it
// may be worth to abstract this out in the future.
SmallVector<char, 0> Buffer;
SmallVector<char, 0> CompileTwiceBuffer;
std::unique_ptr<raw_svector_ostream> BOS;
raw_ostream *OS = nullptr;
// Write bitcode or assembly to the output as the last step...
if (!NoOutput && !AnalyzeOnly) {
assert(Out);
OS = &Out->os();
if (RunTwice) {
BOS = make_unique<raw_svector_ostream>(Buffer);
OS = BOS.get();
}
if (OutputAssembly) {
if (EmitSummaryIndex)
report_fatal_error("Text output is incompatible with -module-summary");
if (EmitModuleHash)
report_fatal_error("Text output is incompatible with -module-hash");
Passes.add(createPrintModulePass(*OS, "", PreserveAssemblyUseListOrder));
} else
Passes.add(createBitcodeWriterPass(*OS, PreserveBitcodeUseListOrder,
EmitSummaryIndex, EmitModuleHash));
}
// Before executing passes, print the final values of the LLVM options.
cl::PrintOptionValues();
// If requested, run all passes again with the same pass manager to catch
// bugs caused by persistent state in the passes
if (RunTwice) {
std::unique_ptr<Module> M2(CloneModule(M.get()));
Passes.run(*M2);
CompileTwiceBuffer = Buffer;
Buffer.clear();
}
// Now that we have all of the passes ready, run them.
Passes.run(*M);
// Compare the two outputs and make sure they're the same
if (RunTwice) {
assert(Out);
if (Buffer.size() != CompileTwiceBuffer.size() ||
(memcmp(Buffer.data(), CompileTwiceBuffer.data(), Buffer.size()) !=
0)) {
errs() << "Running the pass manager twice changed the output.\n"
"Writing the result of the second run to the specified output.\n"
"To generate the one-run comparison binary, just run without\n"
"the compile-twice option\n";
Out->os() << BOS->str();
Out->keep();
return 1;
}
Out->os() << BOS->str();
}
// Declare success.
if (!NoOutput || PrintBreakpoints)
Out->keep();
return 0;
}
// Main entry point for the ThinLTO processing
void ThinLTOCodeGenerator::run() {
if (CodeGenOnly) {
// Perform only parallel codegen and return.
ThreadPool Pool;
assert(ProducedBinaries.empty() && "The generator should not be reused");
ProducedBinaries.resize(Modules.size());
int count = 0;
for (auto &ModuleBuffer : Modules) {
Pool.async([&](int count) {
LLVMContext Context;
Context.setDiscardValueNames(LTODiscardValueNames);
// Parse module now
auto TheModule = loadModuleFromBuffer(ModuleBuffer, Context, false);
// CodeGen
ProducedBinaries[count] = codegen(*TheModule);
}, count++);
}
return;
}
// Sequential linking phase
auto Index = linkCombinedIndex();
// Save temps: index.
if (!SaveTempsDir.empty()) {
auto SaveTempPath = SaveTempsDir + "index.bc";
std::error_code EC;
raw_fd_ostream OS(SaveTempPath, EC, sys::fs::F_None);
if (EC)
report_fatal_error(Twine("Failed to open ") + SaveTempPath +
" to save optimized bitcode\n");
WriteIndexToFile(*Index, OS);
}
// Prepare the resulting object vector
assert(ProducedBinaries.empty() && "The generator should not be reused");
ProducedBinaries.resize(Modules.size());
// Prepare the module map.
auto ModuleMap = generateModuleMap(Modules);
auto ModuleCount = Modules.size();
// Collect for each module the list of function it defines (GUID -> Summary).
StringMap<GVSummaryMapTy> ModuleToDefinedGVSummaries(ModuleCount);
Index->collectDefinedGVSummariesPerModule(ModuleToDefinedGVSummaries);
// Collect the import/export lists for all modules from the call-graph in the
// combined index.
StringMap<FunctionImporter::ImportMapTy> ImportLists(ModuleCount);
StringMap<FunctionImporter::ExportSetTy> ExportLists(ModuleCount);
ComputeCrossModuleImport(*Index, ModuleToDefinedGVSummaries, ImportLists,
ExportLists);
// Convert the preserved symbols set from string to GUID, this is needed for
// computing the caching hash and the internalization.
auto GUIDPreservedSymbols =
computeGUIDPreservedSymbols(PreservedSymbols, TMBuilder.TheTriple);
// We use a std::map here to be able to have a defined ordering when
// producing a hash for the cache entry.
// FIXME: we should be able to compute the caching hash for the entry based
// on the index, and nuke this map.
StringMap<std::map<GlobalValue::GUID, GlobalValue::LinkageTypes>> ResolvedODR;
// Resolve LinkOnce/Weak symbols, this has to be computed early because it
// impacts the caching.
resolveWeakForLinkerInIndex(*Index, ResolvedODR);
auto isExported = [&](StringRef ModuleIdentifier, GlobalValue::GUID GUID) {
const auto &ExportList = ExportLists.find(ModuleIdentifier);
return (ExportList != ExportLists.end() &&
ExportList->second.count(GUID)) ||
GUIDPreservedSymbols.count(GUID);
};
// Use global summary-based analysis to identify symbols that can be
// internalized (because they aren't exported or preserved as per callback).
// Changes are made in the index, consumed in the ThinLTO backends.
thinLTOInternalizeAndPromoteInIndex(*Index, isExported);
// Make sure that every module has an entry in the ExportLists and
// ResolvedODR maps to enable threaded access to these maps below.
for (auto &DefinedGVSummaries : ModuleToDefinedGVSummaries) {
ExportLists[DefinedGVSummaries.first()];
ResolvedODR[DefinedGVSummaries.first()];
}
// Compute the ordering we will process the inputs: the rough heuristic here
// is to sort them per size so that the largest module get schedule as soon as
// possible. This is purely a compile-time optimization.
std::vector<int> ModulesOrdering;
ModulesOrdering.resize(Modules.size());
std::iota(ModulesOrdering.begin(), ModulesOrdering.end(), 0);
std::sort(ModulesOrdering.begin(), ModulesOrdering.end(),
[&](int LeftIndex, int RightIndex) {
auto LSize = Modules[LeftIndex].getBufferSize();
auto RSize = Modules[RightIndex].getBufferSize();
return LSize > RSize;
});
// Parallel optimizer + codegen
{
ThreadPool Pool(ThreadCount);
for (auto IndexCount : ModulesOrdering) {
auto &ModuleBuffer = Modules[IndexCount];
Pool.async([&](int count) {
auto ModuleIdentifier = ModuleBuffer.getBufferIdentifier();
auto &ExportList = ExportLists[ModuleIdentifier];
auto &DefinedFunctions = ModuleToDefinedGVSummaries[ModuleIdentifier];
// The module may be cached, this helps handling it.
ModuleCacheEntry CacheEntry(CacheOptions.Path, *Index, ModuleIdentifier,
ImportLists[ModuleIdentifier], ExportList,
ResolvedODR[ModuleIdentifier],
DefinedFunctions, GUIDPreservedSymbols);
{
auto ErrOrBuffer = CacheEntry.tryLoadingBuffer();
DEBUG(dbgs() << "Cache " << (ErrOrBuffer ? "hit" : "miss") << " '"
<< CacheEntry.getEntryPath() << "' for buffer " << count
<< " " << ModuleIdentifier << "\n");
if (ErrOrBuffer) {
// Cache Hit!
ProducedBinaries[count] = std::move(ErrOrBuffer.get());
return;
}
}
LLVMContext Context;
Context.setDiscardValueNames(LTODiscardValueNames);
Context.enableDebugTypeODRUniquing();
auto DiagFileOrErr = setupOptimizationRemarks(Context, count);
if (!DiagFileOrErr) {
errs() << "Error: " << toString(DiagFileOrErr.takeError()) << "\n";
report_fatal_error("ThinLTO: Can't get an output file for the "
"remarks");
}
// Parse module now
auto TheModule = loadModuleFromBuffer(ModuleBuffer, Context, false);
// Save temps: original file.
saveTempBitcode(*TheModule, SaveTempsDir, count, ".0.original.bc");
auto &ImportList = ImportLists[ModuleIdentifier];
// Run the main process now, and generates a binary
auto OutputBuffer = ProcessThinLTOModule(
*TheModule, *Index, ModuleMap, *TMBuilder.create(), ImportList,
ExportList, GUIDPreservedSymbols,
ModuleToDefinedGVSummaries[ModuleIdentifier], CacheOptions,
DisableCodeGen, SaveTempsDir, count);
OutputBuffer = CacheEntry.write(std::move(OutputBuffer));
ProducedBinaries[count] = std::move(OutputBuffer);
}, IndexCount);
}
}
CachePruning(CacheOptions.Path)
.setPruningInterval(std::chrono::seconds(CacheOptions.PruningInterval))
.setEntryExpiration(std::chrono::seconds(CacheOptions.Expiration))
.setMaxSize(CacheOptions.MaxPercentageOfAvailableSpace)
.prune();
// If statistics were requested, print them out now.
if (llvm::AreStatisticsEnabled())
llvm::PrintStatistics();
}
// Main entry point for the ThinLTO processing
void ThinLTOCodeGenerator::run() {
if (CodeGenOnly) {
// Perform only parallel codegen and return.
ThreadPool Pool;
assert(ProducedBinaries.empty() && "The generator should not be reused");
ProducedBinaries.resize(Modules.size());
int count = 0;
for (auto &ModuleBuffer : Modules) {
Pool.async([&](int count) {
LLVMContext Context;
Context.setDiscardValueNames(LTODiscardValueNames);
// Parse module now
auto TheModule = loadModuleFromBuffer(ModuleBuffer, Context, false);
// CodeGen
ProducedBinaries[count] = codegen(*TheModule);
}, count++);
}
return;
}
// Sequential linking phase
auto Index = linkCombinedIndex();
// Save temps: index.
if (!SaveTempsDir.empty()) {
auto SaveTempPath = SaveTempsDir + "index.bc";
std::error_code EC;
raw_fd_ostream OS(SaveTempPath, EC, sys::fs::F_None);
if (EC)
report_fatal_error(Twine("Failed to open ") + SaveTempPath +
" to save optimized bitcode\n");
WriteIndexToFile(*Index, OS);
}
// Prepare the resulting object vector
assert(ProducedBinaries.empty() && "The generator should not be reused");
ProducedBinaries.resize(Modules.size());
// Prepare the module map.
auto ModuleMap = generateModuleMap(Modules);
auto ModuleCount = Modules.size();
// Collect the import/export lists for all modules from the call-graph in the
// combined index.
StringMap<FunctionImporter::ImportMapTy> ImportLists(ModuleCount);
StringMap<FunctionImporter::ExportSetTy> ExportLists(ModuleCount);
ComputeCrossModuleImport(*Index, ImportLists, ExportLists);
// Parallel optimizer + codegen
{
ThreadPool Pool(ThreadCount);
int count = 0;
for (auto &ModuleBuffer : Modules) {
Pool.async([&](int count) {
LLVMContext Context;
Context.setDiscardValueNames(LTODiscardValueNames);
// Parse module now
auto TheModule = loadModuleFromBuffer(ModuleBuffer, Context, false);
// Save temps: original file.
if (!SaveTempsDir.empty()) {
saveTempBitcode(*TheModule, SaveTempsDir, count, ".0.original.bc");
}
auto &ImportList = ImportLists[TheModule->getModuleIdentifier()];
ProducedBinaries[count] = ProcessThinLTOModule(
*TheModule, *Index, ModuleMap, *TMBuilder.create(), ImportList,
CacheOptions, DisableCodeGen, SaveTempsDir, count);
}, count);
count++;
}
}
// If statistics were requested, print them out now.
if (llvm::AreStatisticsEnabled())
llvm::PrintStatistics();
}