TEST_F(ThreadPoolTest, Async) {
CHECK_UNSUPPORTED();
ThreadPool Pool;
std::atomic_int i{0};
Pool.async([this, &i] {
waitForMainThread();
++i;
});
Pool.async([&i] { ++i; });
ASSERT_NE(2, i.load());
setMainThreadReady();
Pool.wait();
ASSERT_EQ(2, i.load());
}
TEST_F(ThreadPoolTest, AsyncBarrierArgs) {
CHECK_UNSUPPORTED();
// Test that async works with a function requiring multiple parameters.
std::atomic_int checked_in{0};
ThreadPool Pool;
for (size_t i = 0; i < 5; ++i) {
Pool.async(TestFunc, std::ref(checked_in), i);
}
Pool.wait();
ASSERT_EQ(10, checked_in);
}
TEST_F(ThreadPoolTest, PoolDestruction) {
CHECK_UNSUPPORTED();
// Test that we are waiting on destruction
std::atomic_int checked_in{0};
{
ThreadPool Pool;
for (size_t i = 0; i < 5; ++i) {
Pool.async([this, &checked_in, i] {
waitForMainThread();
++checked_in;
});
}
ASSERT_EQ(0, checked_in);
setMainThreadReady();
}
ASSERT_EQ(5, checked_in);
}
TEST_F(ThreadPoolTest, AsyncBarrier) {
CHECK_UNSUPPORTED();
// test that async & barrier work together properly.
std::atomic_int checked_in{0};
ThreadPool Pool;
for (size_t i = 0; i < 5; ++i) {
Pool.async([this, &checked_in, i] {
waitForMainThread();
++checked_in;
});
}
ASSERT_EQ(0, checked_in);
setMainThreadReady();
Pool.wait();
ASSERT_EQ(5, checked_in);
}
int CodeCoverageTool::show(int argc, const char **argv,
CommandLineParserType commandLineParser) {
cl::OptionCategory ViewCategory("Viewing options");
cl::opt<bool> ShowLineExecutionCounts(
"show-line-counts", cl::Optional,
cl::desc("Show the execution counts for each line"), cl::init(true),
cl::cat(ViewCategory));
cl::opt<bool> ShowRegions(
"show-regions", cl::Optional,
cl::desc("Show the execution counts for each region"),
cl::cat(ViewCategory));
cl::opt<bool> ShowBestLineRegionsCounts(
"show-line-counts-or-regions", cl::Optional,
cl::desc("Show the execution counts for each line, or the execution "
"counts for each region on lines that have multiple regions"),
cl::cat(ViewCategory));
cl::opt<bool> ShowExpansions("show-expansions", cl::Optional,
cl::desc("Show expanded source regions"),
cl::cat(ViewCategory));
cl::opt<bool> ShowInstantiations("show-instantiations", cl::Optional,
cl::desc("Show function instantiations"),
cl::cat(ViewCategory));
cl::opt<std::string> ShowOutputDirectory(
"output-dir", cl::init(""),
cl::desc("Directory in which coverage information is written out"));
cl::alias ShowOutputDirectoryA("o", cl::desc("Alias for --output-dir"),
cl::aliasopt(ShowOutputDirectory));
cl::opt<uint32_t> TabSize(
"tab-size", cl::init(2),
cl::desc(
"Set tab expansion size for html coverage reports (default = 2)"));
cl::opt<std::string> ProjectTitle(
"project-title", cl::Optional,
cl::desc("Set project title for the coverage report"));
auto Err = commandLineParser(argc, argv);
if (Err)
return Err;
ViewOpts.ShowLineNumbers = true;
ViewOpts.ShowLineStats = ShowLineExecutionCounts.getNumOccurrences() != 0 ||
!ShowRegions || ShowBestLineRegionsCounts;
ViewOpts.ShowRegionMarkers = ShowRegions || ShowBestLineRegionsCounts;
ViewOpts.ShowLineStatsOrRegionMarkers = ShowBestLineRegionsCounts;
ViewOpts.ShowExpandedRegions = ShowExpansions;
ViewOpts.ShowFunctionInstantiations = ShowInstantiations;
ViewOpts.ShowOutputDirectory = ShowOutputDirectory;
ViewOpts.TabSize = TabSize;
ViewOpts.ProjectTitle = ProjectTitle;
if (ViewOpts.hasOutputDirectory()) {
if (auto E = sys::fs::create_directories(ViewOpts.ShowOutputDirectory)) {
error("Could not create output directory!", E.message());
return 1;
}
}
sys::fs::file_status Status;
if (sys::fs::status(PGOFilename, Status)) {
error("profdata file error: can not get the file status. \n");
return 1;
}
auto ModifiedTime = Status.getLastModificationTime();
std::string ModifiedTimeStr = to_string(ModifiedTime);
size_t found = ModifiedTimeStr.rfind(":");
ViewOpts.CreatedTimeStr = (found != std::string::npos)
? "Created: " + ModifiedTimeStr.substr(0, found)
: "Created: " + ModifiedTimeStr;
auto Coverage = load();
if (!Coverage)
return 1;
auto Printer = CoveragePrinter::create(ViewOpts);
if (!Filters.empty()) {
auto OSOrErr = Printer->createViewFile("functions", /*InToplevel=*/true);
if (Error E = OSOrErr.takeError()) {
error("Could not create view file!", toString(std::move(E)));
return 1;
}
auto OS = std::move(OSOrErr.get());
// Show functions.
for (const auto &Function : Coverage->getCoveredFunctions()) {
if (!Filters.matches(Function))
continue;
auto mainView = createFunctionView(Function, *Coverage);
if (!mainView) {
warning("Could not read coverage for '" + Function.Name + "'.");
continue;
}
mainView->print(*OS.get(), /*WholeFile=*/false, /*ShowSourceName=*/true);
}
Printer->closeViewFile(std::move(OS));
return 0;
}
// Show files
bool ShowFilenames =
(SourceFiles.size() != 1) || ViewOpts.hasOutputDirectory() ||
(ViewOpts.Format == CoverageViewOptions::OutputFormat::HTML);
if (SourceFiles.empty())
// Get the source files from the function coverage mapping.
for (StringRef Filename : Coverage->getUniqueSourceFiles())
SourceFiles.push_back(Filename);
// Create an index out of the source files.
if (ViewOpts.hasOutputDirectory()) {
if (Error E = Printer->createIndexFile(SourceFiles, *Coverage)) {
error("Could not create index file!", toString(std::move(E)));
return 1;
}
}
// FIXME: Sink the hardware_concurrency() == 1 check into ThreadPool.
if (!ViewOpts.hasOutputDirectory() ||
std::thread::hardware_concurrency() == 1) {
for (const std::string &SourceFile : SourceFiles)
writeSourceFileView(SourceFile, Coverage.get(), Printer.get(),
ShowFilenames);
} else {
// In -output-dir mode, it's safe to use multiple threads to print files.
ThreadPool Pool;
for (const std::string &SourceFile : SourceFiles)
Pool.async(&CodeCoverageTool::writeSourceFileView, this, SourceFile,
Coverage.get(), Printer.get(), ShowFilenames);
Pool.wait();
}
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();
}