static int merge_main(int argc, const char *argv[]) {
cl::list<std::string> InputFilenames(cl::Positional,
cl::desc("<filename...>"));
cl::list<std::string> WeightedInputFilenames("weighted-input",
cl::desc("<weight>,<filename>"));
cl::opt<std::string> InputFilenamesFile(
"input-files", cl::init(""),
cl::desc("Path to file containing newline-separated "
"[<weight>,]<filename> entries"));
cl::alias InputFilenamesFileA("f", cl::desc("Alias for --input-files"),
cl::aliasopt(InputFilenamesFile));
cl::opt<bool> DumpInputFileList(
"dump-input-file-list", cl::init(false), cl::Hidden,
cl::desc("Dump the list of input files and their weights, then exit"));
cl::opt<std::string> OutputFilename("output", cl::value_desc("output"),
cl::init("-"), cl::Required,
cl::desc("Output file"));
cl::alias OutputFilenameA("o", cl::desc("Alias for --output"),
cl::aliasopt(OutputFilename));
cl::opt<ProfileKinds> ProfileKind(
cl::desc("Profile kind:"), cl::init(instr),
cl::values(clEnumVal(instr, "Instrumentation profile (default)"),
clEnumVal(sample, "Sample profile")));
cl::opt<ProfileFormat> OutputFormat(
cl::desc("Format of output profile"), cl::init(PF_Binary),
cl::values(clEnumValN(PF_Binary, "binary", "Binary encoding (default)"),
clEnumValN(PF_Text, "text", "Text encoding"),
clEnumValN(PF_GCC, "gcc",
"GCC encoding (only meaningful for -sample)")));
cl::opt<bool> OutputSparse("sparse", cl::init(false),
cl::desc("Generate a sparse profile (only meaningful for -instr)"));
cl::opt<unsigned> NumThreads(
"num-threads", cl::init(0),
cl::desc("Number of merge threads to use (default: autodetect)"));
cl::alias NumThreadsA("j", cl::desc("Alias for --num-threads"),
cl::aliasopt(NumThreads));
cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
WeightedFileVector WeightedInputs;
for (StringRef Filename : InputFilenames)
addWeightedInput(WeightedInputs, {Filename, 1});
for (StringRef WeightedFilename : WeightedInputFilenames)
addWeightedInput(WeightedInputs, parseWeightedFile(WeightedFilename));
// Make sure that the file buffer stays alive for the duration of the
// weighted input vector's lifetime.
auto Buffer = getInputFilenamesFileBuf(InputFilenamesFile);
parseInputFilenamesFile(Buffer.get(), WeightedInputs);
if (WeightedInputs.empty())
exitWithError("No input files specified. See " +
sys::path::filename(argv[0]) + " -help");
if (DumpInputFileList) {
for (auto &WF : WeightedInputs)
outs() << WF.Weight << "," << WF.Filename << "\n";
return 0;
}
if (ProfileKind == instr)
mergeInstrProfile(WeightedInputs, OutputFilename, OutputFormat,
OutputSparse, NumThreads);
else
mergeSampleProfile(WeightedInputs, OutputFilename, OutputFormat);
return 0;
}
static void mergeInstrProfile(const WeightedFileVector &Inputs,
StringRef OutputFilename,
ProfileFormat OutputFormat, bool OutputSparse,
unsigned NumThreads) {
if (OutputFilename.compare("-") == 0)
exitWithError("Cannot write indexed profdata format to stdout.");
if (OutputFormat != PF_Binary && OutputFormat != PF_Text)
exitWithError("Unknown format is specified.");
std::error_code EC;
raw_fd_ostream Output(OutputFilename.data(), EC, sys::fs::F_None);
if (EC)
exitWithErrorCode(EC, OutputFilename);
std::mutex ErrorLock;
SmallSet<instrprof_error, 4> WriterErrorCodes;
// If NumThreads is not specified, auto-detect a good default.
if (NumThreads == 0)
NumThreads = std::max(1U, std::min(std::thread::hardware_concurrency(),
unsigned(Inputs.size() / 2)));
// Initialize the writer contexts.
SmallVector<std::unique_ptr<WriterContext>, 4> Contexts;
for (unsigned I = 0; I < NumThreads; ++I)
Contexts.emplace_back(llvm::make_unique<WriterContext>(
OutputSparse, ErrorLock, WriterErrorCodes));
if (NumThreads == 1) {
for (const auto &Input : Inputs)
loadInput(Input, Contexts[0].get());
} else {
ThreadPool Pool(NumThreads);
// Load the inputs in parallel (N/NumThreads serial steps).
unsigned Ctx = 0;
for (const auto &Input : Inputs) {
Pool.async(loadInput, Input, Contexts[Ctx].get());
Ctx = (Ctx + 1) % NumThreads;
}
Pool.wait();
// Merge the writer contexts together (~ lg(NumThreads) serial steps).
unsigned Mid = Contexts.size() / 2;
unsigned End = Contexts.size();
assert(Mid > 0 && "Expected more than one context");
do {
for (unsigned I = 0; I < Mid; ++I)
Pool.async(mergeWriterContexts, Contexts[I].get(),
Contexts[I + Mid].get());
Pool.wait();
if (End & 1) {
Pool.async(mergeWriterContexts, Contexts[0].get(),
Contexts[End - 1].get());
Pool.wait();
}
End = Mid;
Mid /= 2;
} while (Mid > 0);
}
// Handle deferred hard errors encountered during merging.
for (std::unique_ptr<WriterContext> &WC : Contexts)
if (WC->Err)
exitWithError(std::move(WC->Err), WC->ErrWhence);
InstrProfWriter &Writer = Contexts[0]->Writer;
if (OutputFormat == PF_Text)
Writer.writeText(Output);
else
Writer.write(Output);
}
