2014-02-18 07:22:49 +08:00
|
|
|
//===- llvm-profdata.cpp - LLVM profile data tool -------------------------===//
|
|
|
|
//
|
2019-01-19 16:50:56 +08:00
|
|
|
// Part of the LLVM Project, under the Apache License v2.0 with LLVM Exceptions.
|
|
|
|
// See https://llvm.org/LICENSE.txt for license information.
|
|
|
|
// SPDX-License-Identifier: Apache-2.0 WITH LLVM-exception
|
2014-02-18 07:22:49 +08:00
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
//
|
|
|
|
// llvm-profdata merges .profdata files.
|
|
|
|
//
|
|
|
|
//===----------------------------------------------------------------------===//
|
|
|
|
|
2015-11-19 01:10:24 +08:00
|
|
|
#include "llvm/ADT/SmallSet.h"
|
2015-12-16 01:37:09 +08:00
|
|
|
#include "llvm/ADT/SmallVector.h"
|
2014-02-18 07:22:49 +08:00
|
|
|
#include "llvm/ADT/StringRef.h"
|
2015-01-14 19:23:27 +08:00
|
|
|
#include "llvm/IR/LLVMContext.h"
|
2014-03-22 01:24:48 +08:00
|
|
|
#include "llvm/ProfileData/InstrProfReader.h"
|
2014-03-22 01:46:22 +08:00
|
|
|
#include "llvm/ProfileData/InstrProfWriter.h"
|
2016-02-05 07:34:31 +08:00
|
|
|
#include "llvm/ProfileData/ProfileCommon.h"
|
2014-11-01 08:56:55 +08:00
|
|
|
#include "llvm/ProfileData/SampleProfReader.h"
|
|
|
|
#include "llvm/ProfileData/SampleProfWriter.h"
|
2014-02-18 07:22:49 +08:00
|
|
|
#include "llvm/Support/CommandLine.h"
|
2015-12-16 01:37:09 +08:00
|
|
|
#include "llvm/Support/Errc.h"
|
2014-04-30 07:26:49 +08:00
|
|
|
#include "llvm/Support/FileSystem.h"
|
2014-03-24 04:43:50 +08:00
|
|
|
#include "llvm/Support/Format.h"
|
2018-04-14 02:26:06 +08:00
|
|
|
#include "llvm/Support/InitLLVM.h"
|
2014-02-18 07:22:49 +08:00
|
|
|
#include "llvm/Support/MemoryBuffer.h"
|
2015-03-24 02:07:13 +08:00
|
|
|
#include "llvm/Support/Path.h"
|
2019-10-22 01:51:54 +08:00
|
|
|
#include "llvm/Support/Threading.h"
|
2016-07-19 09:17:20 +08:00
|
|
|
#include "llvm/Support/ThreadPool.h"
|
2019-02-21 15:42:31 +08:00
|
|
|
#include "llvm/Support/WithColor.h"
|
2014-02-18 07:22:49 +08:00
|
|
|
#include "llvm/Support/raw_ostream.h"
|
2015-12-16 01:37:09 +08:00
|
|
|
#include <algorithm>
|
2014-02-18 07:22:49 +08:00
|
|
|
|
|
|
|
using namespace llvm;
|
|
|
|
|
2018-06-12 06:40:43 +08:00
|
|
|
enum ProfileFormat {
|
|
|
|
PF_None = 0,
|
|
|
|
PF_Text,
|
|
|
|
PF_Compact_Binary,
|
2019-08-24 03:05:30 +08:00
|
|
|
PF_Ext_Binary,
|
2018-06-12 06:40:43 +08:00
|
|
|
PF_GCC,
|
2018-06-12 13:53:49 +08:00
|
|
|
PF_Binary
|
2018-06-12 06:40:43 +08:00
|
|
|
};
|
2015-11-24 04:47:38 +08:00
|
|
|
|
2018-04-18 22:42:33 +08:00
|
|
|
static void warn(Twine Message, std::string Whence = "",
|
2017-11-18 05:18:32 +08:00
|
|
|
std::string Hint = "") {
|
2018-04-18 22:42:33 +08:00
|
|
|
WithColor::warning();
|
2014-03-22 01:24:48 +08:00
|
|
|
if (!Whence.empty())
|
|
|
|
errs() << Whence << ": ";
|
|
|
|
errs() << Message << "\n";
|
2015-11-13 11:47:58 +08:00
|
|
|
if (!Hint.empty())
|
2018-04-18 22:42:33 +08:00
|
|
|
WithColor::note() << Hint << "\n";
|
2017-11-18 05:18:32 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void exitWithError(Twine Message, std::string Whence = "",
|
|
|
|
std::string Hint = "") {
|
2018-04-18 22:42:33 +08:00
|
|
|
WithColor::error();
|
|
|
|
if (!Whence.empty())
|
|
|
|
errs() << Whence << ": ";
|
|
|
|
errs() << Message << "\n";
|
|
|
|
if (!Hint.empty())
|
|
|
|
WithColor::note() << Hint << "\n";
|
2014-03-13 06:00:57 +08:00
|
|
|
::exit(1);
|
2014-02-18 07:22:49 +08:00
|
|
|
}
|
|
|
|
|
2016-05-19 11:54:45 +08:00
|
|
|
static void exitWithError(Error E, StringRef Whence = "") {
|
|
|
|
if (E.isA<InstrProfError>()) {
|
|
|
|
handleAllErrors(std::move(E), [&](const InstrProfError &IPE) {
|
|
|
|
instrprof_error instrError = IPE.get();
|
|
|
|
StringRef Hint = "";
|
|
|
|
if (instrError == instrprof_error::unrecognized_format) {
|
2020-01-20 20:52:12 +08:00
|
|
|
// Hint for common error of forgetting --sample for sample profiles.
|
|
|
|
Hint = "Perhaps you forgot to use the --sample option?";
|
2016-05-19 11:54:45 +08:00
|
|
|
}
|
2020-01-29 03:23:46 +08:00
|
|
|
exitWithError(IPE.message(), std::string(Whence), std::string(Hint));
|
2016-05-19 11:54:45 +08:00
|
|
|
});
|
2015-11-13 11:47:58 +08:00
|
|
|
}
|
2016-05-19 11:54:45 +08:00
|
|
|
|
2020-01-29 03:23:46 +08:00
|
|
|
exitWithError(toString(std::move(E)), std::string(Whence));
|
2016-05-19 11:54:45 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
static void exitWithErrorCode(std::error_code EC, StringRef Whence = "") {
|
2020-01-29 03:23:46 +08:00
|
|
|
exitWithError(EC.message(), std::string(Whence));
|
2015-11-13 11:47:58 +08:00
|
|
|
}
|
|
|
|
|
2015-06-16 08:43:04 +08:00
|
|
|
namespace {
|
2015-12-15 04:37:15 +08:00
|
|
|
enum ProfileKinds { instr, sample };
|
2019-09-04 06:23:16 +08:00
|
|
|
enum FailureMode { failIfAnyAreInvalid, failIfAllAreInvalid };
|
|
|
|
}
|
|
|
|
|
|
|
|
static void warnOrExitGivenError(FailureMode FailMode, std::error_code EC,
|
|
|
|
StringRef Whence = "") {
|
|
|
|
if (FailMode == failIfAnyAreInvalid)
|
|
|
|
exitWithErrorCode(EC, Whence);
|
|
|
|
else
|
2020-01-29 03:23:46 +08:00
|
|
|
warn(EC.message(), std::string(Whence));
|
2015-06-16 08:43:04 +08:00
|
|
|
}
|
2014-02-18 07:22:49 +08:00
|
|
|
|
2016-05-19 11:54:45 +08:00
|
|
|
static void handleMergeWriterError(Error E, StringRef WhenceFile = "",
|
2015-11-18 06:08:53 +08:00
|
|
|
StringRef WhenceFunction = "",
|
2015-12-15 04:37:15 +08:00
|
|
|
bool ShowHint = true) {
|
2015-11-18 06:08:53 +08:00
|
|
|
if (!WhenceFile.empty())
|
|
|
|
errs() << WhenceFile << ": ";
|
|
|
|
if (!WhenceFunction.empty())
|
|
|
|
errs() << WhenceFunction << ": ";
|
2016-05-19 11:54:45 +08:00
|
|
|
|
|
|
|
auto IPE = instrprof_error::success;
|
|
|
|
E = handleErrors(std::move(E),
|
|
|
|
[&IPE](std::unique_ptr<InstrProfError> E) -> Error {
|
|
|
|
IPE = E->get();
|
|
|
|
return Error(std::move(E));
|
|
|
|
});
|
|
|
|
errs() << toString(std::move(E)) << "\n";
|
2015-11-18 06:08:53 +08:00
|
|
|
|
|
|
|
if (ShowHint) {
|
|
|
|
StringRef Hint = "";
|
2016-05-19 11:54:45 +08:00
|
|
|
if (IPE != instrprof_error::success) {
|
|
|
|
switch (IPE) {
|
2015-11-18 07:37:09 +08:00
|
|
|
case instrprof_error::hash_mismatch:
|
|
|
|
case instrprof_error::count_mismatch:
|
|
|
|
case instrprof_error::value_site_count_mismatch:
|
2015-12-15 04:37:15 +08:00
|
|
|
Hint = "Make sure that all profile data to be merged is generated "
|
2015-11-18 06:08:53 +08:00
|
|
|
"from the same binary.";
|
2015-11-18 07:37:09 +08:00
|
|
|
break;
|
2015-11-18 08:52:45 +08:00
|
|
|
default:
|
|
|
|
break;
|
2015-11-18 06:08:53 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (!Hint.empty())
|
|
|
|
errs() << Hint << "\n";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2018-09-14 04:22:02 +08:00
|
|
|
namespace {
|
|
|
|
/// A remapper from original symbol names to new symbol names based on a file
|
|
|
|
/// containing a list of mappings from old name to new name.
|
|
|
|
class SymbolRemapper {
|
|
|
|
std::unique_ptr<MemoryBuffer> File;
|
|
|
|
DenseMap<StringRef, StringRef> RemappingTable;
|
|
|
|
|
|
|
|
public:
|
|
|
|
/// Build a SymbolRemapper from a file containing a list of old/new symbols.
|
|
|
|
static std::unique_ptr<SymbolRemapper> create(StringRef InputFile) {
|
|
|
|
auto BufOrError = MemoryBuffer::getFileOrSTDIN(InputFile);
|
|
|
|
if (!BufOrError)
|
|
|
|
exitWithErrorCode(BufOrError.getError(), InputFile);
|
|
|
|
|
2019-08-15 23:54:37 +08:00
|
|
|
auto Remapper = std::make_unique<SymbolRemapper>();
|
2018-09-14 04:22:02 +08:00
|
|
|
Remapper->File = std::move(BufOrError.get());
|
|
|
|
|
|
|
|
for (line_iterator LineIt(*Remapper->File, /*SkipBlanks=*/true, '#');
|
|
|
|
!LineIt.is_at_eof(); ++LineIt) {
|
|
|
|
std::pair<StringRef, StringRef> Parts = LineIt->split(' ');
|
|
|
|
if (Parts.first.empty() || Parts.second.empty() ||
|
|
|
|
Parts.second.count(' ')) {
|
|
|
|
exitWithError("unexpected line in remapping file",
|
|
|
|
(InputFile + ":" + Twine(LineIt.line_number())).str(),
|
|
|
|
"expected 'old_symbol new_symbol'");
|
|
|
|
}
|
|
|
|
Remapper->RemappingTable.insert(Parts);
|
|
|
|
}
|
|
|
|
return Remapper;
|
|
|
|
}
|
|
|
|
|
|
|
|
/// Attempt to map the given old symbol into a new symbol.
|
|
|
|
///
|
|
|
|
/// \return The new symbol, or \p Name if no such symbol was found.
|
|
|
|
StringRef operator()(StringRef Name) {
|
|
|
|
StringRef New = RemappingTable.lookup(Name);
|
|
|
|
return New.empty() ? Name : New;
|
|
|
|
}
|
|
|
|
};
|
|
|
|
}
|
|
|
|
|
2015-12-16 01:37:09 +08:00
|
|
|
struct WeightedFile {
|
2016-07-21 06:24:52 +08:00
|
|
|
std::string Filename;
|
2015-12-16 01:37:09 +08:00
|
|
|
uint64_t Weight;
|
|
|
|
};
|
|
|
|
typedef SmallVector<WeightedFile, 5> WeightedFileVector;
|
|
|
|
|
2016-07-19 09:17:20 +08:00
|
|
|
/// Keep track of merged data and reported errors.
|
|
|
|
struct WriterContext {
|
|
|
|
std::mutex Lock;
|
|
|
|
InstrProfWriter Writer;
|
2019-09-04 06:23:16 +08:00
|
|
|
std::vector<std::pair<Error, std::string>> Errors;
|
2016-07-19 09:17:20 +08:00
|
|
|
std::mutex &ErrLock;
|
|
|
|
SmallSet<instrprof_error, 4> &WriterErrorCodes;
|
|
|
|
|
|
|
|
WriterContext(bool IsSparse, std::mutex &ErrLock,
|
|
|
|
SmallSet<instrprof_error, 4> &WriterErrorCodes)
|
2019-09-04 06:23:16 +08:00
|
|
|
: Lock(), Writer(IsSparse), Errors(), ErrLock(ErrLock),
|
|
|
|
WriterErrorCodes(WriterErrorCodes) {}
|
2016-07-19 09:17:20 +08:00
|
|
|
};
|
|
|
|
|
2019-05-01 05:19:12 +08:00
|
|
|
/// Computer the overlap b/w profile BaseFilename and TestFileName,
|
|
|
|
/// and store the program level result to Overlap.
|
|
|
|
static void overlapInput(const std::string &BaseFilename,
|
|
|
|
const std::string &TestFilename, WriterContext *WC,
|
|
|
|
OverlapStats &Overlap,
|
|
|
|
const OverlapFuncFilters &FuncFilter,
|
|
|
|
raw_fd_ostream &OS, bool IsCS) {
|
|
|
|
auto ReaderOrErr = InstrProfReader::create(TestFilename);
|
|
|
|
if (Error E = ReaderOrErr.takeError()) {
|
|
|
|
// Skip the empty profiles by returning sliently.
|
|
|
|
instrprof_error IPE = InstrProfError::take(std::move(E));
|
|
|
|
if (IPE != instrprof_error::empty_raw_profile)
|
2019-09-04 06:23:16 +08:00
|
|
|
WC->Errors.emplace_back(make_error<InstrProfError>(IPE), TestFilename);
|
2019-05-01 05:19:12 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
auto Reader = std::move(ReaderOrErr.get());
|
|
|
|
for (auto &I : *Reader) {
|
|
|
|
OverlapStats FuncOverlap(OverlapStats::FunctionLevel);
|
|
|
|
FuncOverlap.setFuncInfo(I.Name, I.Hash);
|
|
|
|
|
|
|
|
WC->Writer.overlapRecord(std::move(I), Overlap, FuncOverlap, FuncFilter);
|
|
|
|
FuncOverlap.dump(OS);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-07-19 09:17:20 +08:00
|
|
|
/// Load an input into a writer context.
|
2018-09-14 04:22:02 +08:00
|
|
|
static void loadInput(const WeightedFile &Input, SymbolRemapper *Remapper,
|
|
|
|
WriterContext *WC) {
|
2016-07-19 09:17:20 +08:00
|
|
|
std::unique_lock<std::mutex> CtxGuard{WC->Lock};
|
|
|
|
|
2017-11-17 10:58:23 +08:00
|
|
|
// Copy the filename, because llvm::ThreadPool copied the input "const
|
|
|
|
// WeightedFile &" by value, making a reference to the filename within it
|
|
|
|
// invalid outside of this packaged task.
|
2019-09-04 06:23:16 +08:00
|
|
|
std::string Filename = Input.Filename;
|
2016-07-19 09:17:20 +08:00
|
|
|
|
|
|
|
auto ReaderOrErr = InstrProfReader::create(Input.Filename);
|
2016-10-20 06:51:17 +08:00
|
|
|
if (Error E = ReaderOrErr.takeError()) {
|
|
|
|
// Skip the empty profiles by returning sliently.
|
|
|
|
instrprof_error IPE = InstrProfError::take(std::move(E));
|
|
|
|
if (IPE != instrprof_error::empty_raw_profile)
|
2019-09-04 06:23:16 +08:00
|
|
|
WC->Errors.emplace_back(make_error<InstrProfError>(IPE), Filename);
|
2016-07-19 09:17:20 +08:00
|
|
|
return;
|
2016-10-20 06:51:17 +08:00
|
|
|
}
|
2016-07-19 09:17:20 +08:00
|
|
|
|
|
|
|
auto Reader = std::move(ReaderOrErr.get());
|
|
|
|
bool IsIRProfile = Reader->isIRLevelProfile();
|
2019-03-01 03:55:07 +08:00
|
|
|
bool HasCSIRProfile = Reader->hasCSIRLevelProfile();
|
|
|
|
if (WC->Writer.setIsIRLevelProfile(IsIRProfile, HasCSIRProfile)) {
|
2019-09-04 06:23:16 +08:00
|
|
|
WC->Errors.emplace_back(
|
|
|
|
make_error<StringError>(
|
|
|
|
"Merge IR generated profile with Clang generated profile.",
|
|
|
|
std::error_code()),
|
|
|
|
Filename);
|
2016-07-19 09:17:20 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
for (auto &I : *Reader) {
|
2018-09-14 04:22:02 +08:00
|
|
|
if (Remapper)
|
|
|
|
I.Name = (*Remapper)(I.Name);
|
2016-10-20 07:31:59 +08:00
|
|
|
const StringRef FuncName = I.Name;
|
2017-07-10 11:04:59 +08:00
|
|
|
bool Reported = false;
|
|
|
|
WC->Writer.addRecord(std::move(I), Input.Weight, [&](Error E) {
|
|
|
|
if (Reported) {
|
|
|
|
consumeError(std::move(E));
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
Reported = true;
|
2016-07-19 09:17:20 +08:00
|
|
|
// Only show hint the first time an error occurs.
|
|
|
|
instrprof_error IPE = InstrProfError::take(std::move(E));
|
|
|
|
std::unique_lock<std::mutex> ErrGuard{WC->ErrLock};
|
|
|
|
bool firstTime = WC->WriterErrorCodes.insert(IPE).second;
|
|
|
|
handleMergeWriterError(make_error<InstrProfError>(IPE), Input.Filename,
|
2016-10-20 07:31:59 +08:00
|
|
|
FuncName, firstTime);
|
2017-07-10 11:04:59 +08:00
|
|
|
});
|
2016-07-19 09:17:20 +08:00
|
|
|
}
|
2019-09-04 06:23:16 +08:00
|
|
|
if (Reader->hasError())
|
|
|
|
if (Error E = Reader->getError())
|
|
|
|
WC->Errors.emplace_back(std::move(E), Filename);
|
2016-07-19 09:17:20 +08:00
|
|
|
}
|
|
|
|
|
|
|
|
/// Merge the \p Src writer context into \p Dst.
|
|
|
|
static void mergeWriterContexts(WriterContext *Dst, WriterContext *Src) {
|
2019-09-04 06:23:16 +08:00
|
|
|
for (auto &ErrorPair : Src->Errors)
|
|
|
|
Dst->Errors.push_back(std::move(ErrorPair));
|
|
|
|
Src->Errors.clear();
|
2017-11-17 10:58:23 +08:00
|
|
|
|
2017-07-10 11:04:59 +08:00
|
|
|
Dst->Writer.mergeRecordsFromWriter(std::move(Src->Writer), [&](Error E) {
|
2019-09-04 06:23:16 +08:00
|
|
|
instrprof_error IPE = InstrProfError::take(std::move(E));
|
|
|
|
std::unique_lock<std::mutex> ErrGuard{Dst->ErrLock};
|
|
|
|
bool firstTime = Dst->WriterErrorCodes.insert(IPE).second;
|
|
|
|
if (firstTime)
|
|
|
|
warn(toString(make_error<InstrProfError>(IPE)));
|
2017-07-10 11:04:59 +08:00
|
|
|
});
|
2016-07-19 09:17:20 +08:00
|
|
|
}
|
|
|
|
|
2015-12-16 01:37:09 +08:00
|
|
|
static void mergeInstrProfile(const WeightedFileVector &Inputs,
|
2018-09-14 04:22:02 +08:00
|
|
|
SymbolRemapper *Remapper,
|
2015-11-24 04:47:38 +08:00
|
|
|
StringRef OutputFilename,
|
2016-07-19 09:17:20 +08:00
|
|
|
ProfileFormat OutputFormat, bool OutputSparse,
|
2019-09-04 06:23:16 +08:00
|
|
|
unsigned NumThreads, FailureMode FailMode) {
|
2014-04-19 05:48:40 +08:00
|
|
|
if (OutputFilename.compare("-") == 0)
|
|
|
|
exitWithError("Cannot write indexed profdata format to stdout.");
|
2014-02-18 07:22:49 +08:00
|
|
|
|
2018-06-12 13:53:49 +08:00
|
|
|
if (OutputFormat != PF_Binary && OutputFormat != PF_Compact_Binary &&
|
2019-08-24 03:05:30 +08:00
|
|
|
OutputFormat != PF_Ext_Binary && OutputFormat != PF_Text)
|
2015-11-24 04:47:38 +08:00
|
|
|
exitWithError("Unknown format is specified.");
|
|
|
|
|
2016-07-19 09:17:20 +08:00
|
|
|
std::mutex ErrorLock;
|
2016-05-19 11:54:45 +08:00
|
|
|
SmallSet<instrprof_error, 4> WriterErrorCodes;
|
2016-07-19 09:17:20 +08:00
|
|
|
|
|
|
|
// If NumThreads is not specified, auto-detect a good default.
|
|
|
|
if (NumThreads == 0)
|
[Support] On Windows, ensure hardware_concurrency() extends to all CPU sockets and all NUMA groups
The goal of this patch is to maximize CPU utilization on multi-socket or high core count systems, so that parallel computations such as LLD/ThinLTO can use all hardware threads in the system. Before this patch, on Windows, a maximum of 64 hardware threads could be used at most, in some cases dispatched only on one CPU socket.
== Background ==
Windows doesn't have a flat cpu_set_t like Linux. Instead, it projects hardware CPUs (or NUMA nodes) to applications through a concept of "processor groups". A "processor" is the smallest unit of execution on a CPU, that is, an hyper-thread if SMT is active; a core otherwise. There's a limit of 32-bit processors on older 32-bit versions of Windows, which later was raised to 64-processors with 64-bit versions of Windows. This limit comes from the affinity mask, which historically is represented by the sizeof(void*). Consequently, the concept of "processor groups" was introduced for dealing with systems with more than 64 hyper-threads.
By default, the Windows OS assigns only one "processor group" to each starting application, in a round-robin manner. If the application wants to use more processors, it needs to programmatically enable it, by assigning threads to other "processor groups". This also means that affinity cannot cross "processor group" boundaries; one can only specify a "preferred" group on start-up, but the application is free to allocate more groups if it wants to.
This creates a peculiar situation, where newer CPUs like the AMD EPYC 7702P (64-cores, 128-hyperthreads) are projected by the OS as two (2) "processor groups". This means that by default, an application can only use half of the cores. This situation could only get worse in the years to come, as dies with more cores will appear on the market.
== The problem ==
The heavyweight_hardware_concurrency() API was introduced so that only *one hardware thread per core* was used. Once that API returns, that original intention is lost, only the number of threads is retained. Consider a situation, on Windows, where the system has 2 CPU sockets, 18 cores each, each core having 2 hyper-threads, for a total of 72 hyper-threads. Both heavyweight_hardware_concurrency() and hardware_concurrency() currently return 36, because on Windows they are simply wrappers over std::thread::hardware_concurrency() -- which can only return processors from the current "processor group".
== The changes in this patch ==
To solve this situation, we capture (and retain) the initial intention until the point of usage, through a new ThreadPoolStrategy class. The number of threads to use is deferred as late as possible, until the moment where the std::threads are created (ThreadPool in the case of ThinLTO).
When using hardware_concurrency(), setting ThreadCount to 0 now means to use all the possible hardware CPU (SMT) threads. Providing a ThreadCount above to the maximum number of threads will have no effect, the maximum will be used instead.
The heavyweight_hardware_concurrency() is similar to hardware_concurrency(), except that only one thread per hardware *core* will be used.
When LLVM_ENABLE_THREADS is OFF, the threading APIs will always return 1, to ensure any caller loops will be exercised at least once.
Differential Revision: https://reviews.llvm.org/D71775
2020-02-14 11:49:57 +08:00
|
|
|
NumThreads = std::min(hardware_concurrency().compute_thread_count(),
|
|
|
|
unsigned((Inputs.size() + 1) / 2));
|
|
|
|
// FIXME: There's a bug here, where setting NumThreads = Inputs.size() fails
|
|
|
|
// the merge_empty_profile.test because the InstrProfWriter.ProfileKind isn't
|
|
|
|
// merged, thus the emitted file ends up with a PF_Unknown kind.
|
2016-07-19 09:17:20 +08:00
|
|
|
|
|
|
|
// Initialize the writer contexts.
|
|
|
|
SmallVector<std::unique_ptr<WriterContext>, 4> Contexts;
|
|
|
|
for (unsigned I = 0; I < NumThreads; ++I)
|
2019-08-15 23:54:37 +08:00
|
|
|
Contexts.emplace_back(std::make_unique<WriterContext>(
|
2016-07-19 09:17:20 +08:00
|
|
|
OutputSparse, ErrorLock, WriterErrorCodes));
|
|
|
|
|
|
|
|
if (NumThreads == 1) {
|
|
|
|
for (const auto &Input : Inputs)
|
2018-09-14 04:22:02 +08:00
|
|
|
loadInput(Input, Remapper, Contexts[0].get());
|
2016-07-19 09:17:20 +08:00
|
|
|
} else {
|
[Support] On Windows, ensure hardware_concurrency() extends to all CPU sockets and all NUMA groups
The goal of this patch is to maximize CPU utilization on multi-socket or high core count systems, so that parallel computations such as LLD/ThinLTO can use all hardware threads in the system. Before this patch, on Windows, a maximum of 64 hardware threads could be used at most, in some cases dispatched only on one CPU socket.
== Background ==
Windows doesn't have a flat cpu_set_t like Linux. Instead, it projects hardware CPUs (or NUMA nodes) to applications through a concept of "processor groups". A "processor" is the smallest unit of execution on a CPU, that is, an hyper-thread if SMT is active; a core otherwise. There's a limit of 32-bit processors on older 32-bit versions of Windows, which later was raised to 64-processors with 64-bit versions of Windows. This limit comes from the affinity mask, which historically is represented by the sizeof(void*). Consequently, the concept of "processor groups" was introduced for dealing with systems with more than 64 hyper-threads.
By default, the Windows OS assigns only one "processor group" to each starting application, in a round-robin manner. If the application wants to use more processors, it needs to programmatically enable it, by assigning threads to other "processor groups". This also means that affinity cannot cross "processor group" boundaries; one can only specify a "preferred" group on start-up, but the application is free to allocate more groups if it wants to.
This creates a peculiar situation, where newer CPUs like the AMD EPYC 7702P (64-cores, 128-hyperthreads) are projected by the OS as two (2) "processor groups". This means that by default, an application can only use half of the cores. This situation could only get worse in the years to come, as dies with more cores will appear on the market.
== The problem ==
The heavyweight_hardware_concurrency() API was introduced so that only *one hardware thread per core* was used. Once that API returns, that original intention is lost, only the number of threads is retained. Consider a situation, on Windows, where the system has 2 CPU sockets, 18 cores each, each core having 2 hyper-threads, for a total of 72 hyper-threads. Both heavyweight_hardware_concurrency() and hardware_concurrency() currently return 36, because on Windows they are simply wrappers over std::thread::hardware_concurrency() -- which can only return processors from the current "processor group".
== The changes in this patch ==
To solve this situation, we capture (and retain) the initial intention until the point of usage, through a new ThreadPoolStrategy class. The number of threads to use is deferred as late as possible, until the moment where the std::threads are created (ThreadPool in the case of ThinLTO).
When using hardware_concurrency(), setting ThreadCount to 0 now means to use all the possible hardware CPU (SMT) threads. Providing a ThreadCount above to the maximum number of threads will have no effect, the maximum will be used instead.
The heavyweight_hardware_concurrency() is similar to hardware_concurrency(), except that only one thread per hardware *core* will be used.
When LLVM_ENABLE_THREADS is OFF, the threading APIs will always return 1, to ensure any caller loops will be exercised at least once.
Differential Revision: https://reviews.llvm.org/D71775
2020-02-14 11:49:57 +08:00
|
|
|
ThreadPool Pool(hardware_concurrency(NumThreads));
|
2016-07-19 09:17:20 +08:00
|
|
|
|
|
|
|
// Load the inputs in parallel (N/NumThreads serial steps).
|
|
|
|
unsigned Ctx = 0;
|
|
|
|
for (const auto &Input : Inputs) {
|
2018-09-14 04:22:02 +08:00
|
|
|
Pool.async(loadInput, Input, Remapper, Contexts[Ctx].get());
|
2016-07-19 09:17:20 +08:00
|
|
|
Ctx = (Ctx + 1) % NumThreads;
|
2015-11-18 06:08:53 +08:00
|
|
|
}
|
2016-07-19 09:17:20 +08:00
|
|
|
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);
|
2014-03-13 06:00:57 +08:00
|
|
|
}
|
2016-07-19 09:17:20 +08:00
|
|
|
|
2019-09-04 06:23:16 +08:00
|
|
|
// Handle deferred errors encountered during merging. If the number of errors
|
|
|
|
// is equal to the number of inputs the merge failed.
|
|
|
|
unsigned NumErrors = 0;
|
2017-11-18 05:18:32 +08:00
|
|
|
for (std::unique_ptr<WriterContext> &WC : Contexts) {
|
2019-09-04 06:23:16 +08:00
|
|
|
for (auto &ErrorPair : WC->Errors) {
|
|
|
|
++NumErrors;
|
|
|
|
warn(toString(std::move(ErrorPair.first)), ErrorPair.second);
|
|
|
|
}
|
2017-11-18 05:18:32 +08:00
|
|
|
}
|
2019-09-04 06:23:16 +08:00
|
|
|
if (NumErrors == Inputs.size() ||
|
|
|
|
(NumErrors > 0 && FailMode == failIfAnyAreInvalid))
|
|
|
|
exitWithError("No profiles could be merged.");
|
2017-11-18 05:18:32 +08:00
|
|
|
|
2019-07-09 05:03:12 +08:00
|
|
|
std::error_code EC;
|
2019-08-05 13:43:48 +08:00
|
|
|
raw_fd_ostream Output(OutputFilename.data(), EC, sys::fs::OF_None);
|
2019-07-09 05:03:12 +08:00
|
|
|
if (EC)
|
|
|
|
exitWithErrorCode(EC, OutputFilename);
|
|
|
|
|
2016-07-19 09:17:20 +08:00
|
|
|
InstrProfWriter &Writer = Contexts[0]->Writer;
|
2017-06-20 09:38:56 +08:00
|
|
|
if (OutputFormat == PF_Text) {
|
|
|
|
if (Error E = Writer.writeText(Output))
|
|
|
|
exitWithError(std::move(E));
|
|
|
|
} else {
|
2015-11-24 04:47:38 +08:00
|
|
|
Writer.write(Output);
|
2017-06-20 09:38:56 +08:00
|
|
|
}
|
2014-02-18 07:22:49 +08:00
|
|
|
}
|
2014-03-19 10:20:46 +08:00
|
|
|
|
2018-09-14 04:22:02 +08:00
|
|
|
/// Make a copy of the given function samples with all symbol names remapped
|
|
|
|
/// by the provided symbol remapper.
|
|
|
|
static sampleprof::FunctionSamples
|
|
|
|
remapSamples(const sampleprof::FunctionSamples &Samples,
|
|
|
|
SymbolRemapper &Remapper, sampleprof_error &Error) {
|
|
|
|
sampleprof::FunctionSamples Result;
|
|
|
|
Result.setName(Remapper(Samples.getName()));
|
|
|
|
Result.addTotalSamples(Samples.getTotalSamples());
|
|
|
|
Result.addHeadSamples(Samples.getHeadSamples());
|
|
|
|
for (const auto &BodySample : Samples.getBodySamples()) {
|
|
|
|
Result.addBodySamples(BodySample.first.LineOffset,
|
|
|
|
BodySample.first.Discriminator,
|
|
|
|
BodySample.second.getSamples());
|
|
|
|
for (const auto &Target : BodySample.second.getCallTargets()) {
|
|
|
|
Result.addCalledTargetSamples(BodySample.first.LineOffset,
|
|
|
|
BodySample.first.Discriminator,
|
|
|
|
Remapper(Target.first()), Target.second);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
for (const auto &CallsiteSamples : Samples.getCallsiteSamples()) {
|
|
|
|
sampleprof::FunctionSamplesMap &Target =
|
|
|
|
Result.functionSamplesAt(CallsiteSamples.first);
|
|
|
|
for (const auto &Callsite : CallsiteSamples.second) {
|
|
|
|
sampleprof::FunctionSamples Remapped =
|
|
|
|
remapSamples(Callsite.second, Remapper, Error);
|
2020-01-29 03:23:46 +08:00
|
|
|
MergeResult(Error,
|
|
|
|
Target[std::string(Remapped.getName())].merge(Remapped));
|
2018-09-14 04:22:02 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
return Result;
|
|
|
|
}
|
|
|
|
|
2015-11-24 04:47:38 +08:00
|
|
|
static sampleprof::SampleProfileFormat FormatMap[] = {
|
2019-08-24 03:05:30 +08:00
|
|
|
sampleprof::SPF_None,
|
|
|
|
sampleprof::SPF_Text,
|
|
|
|
sampleprof::SPF_Compact_Binary,
|
|
|
|
sampleprof::SPF_Ext_Binary,
|
|
|
|
sampleprof::SPF_GCC,
|
|
|
|
sampleprof::SPF_Binary};
|
2015-11-24 04:47:38 +08:00
|
|
|
|
2019-08-31 10:27:26 +08:00
|
|
|
static std::unique_ptr<MemoryBuffer>
|
|
|
|
getInputFileBuf(const StringRef &InputFile) {
|
|
|
|
if (InputFile == "")
|
|
|
|
return {};
|
|
|
|
|
|
|
|
auto BufOrError = MemoryBuffer::getFileOrSTDIN(InputFile);
|
|
|
|
if (!BufOrError)
|
|
|
|
exitWithErrorCode(BufOrError.getError(), InputFile);
|
|
|
|
|
|
|
|
return std::move(*BufOrError);
|
|
|
|
}
|
|
|
|
|
|
|
|
static void populateProfileSymbolList(MemoryBuffer *Buffer,
|
|
|
|
sampleprof::ProfileSymbolList &PSL) {
|
|
|
|
if (!Buffer)
|
|
|
|
return;
|
|
|
|
|
|
|
|
SmallVector<StringRef, 32> SymbolVec;
|
|
|
|
StringRef Data = Buffer->getBuffer();
|
|
|
|
Data.split(SymbolVec, '\n', /*MaxSplit=*/-1, /*KeepEmpty=*/false);
|
|
|
|
|
|
|
|
for (StringRef symbol : SymbolVec)
|
|
|
|
PSL.add(symbol);
|
|
|
|
}
|
|
|
|
|
2019-10-08 00:12:37 +08:00
|
|
|
static void handleExtBinaryWriter(sampleprof::SampleProfileWriter &Writer,
|
|
|
|
ProfileFormat OutputFormat,
|
|
|
|
MemoryBuffer *Buffer,
|
|
|
|
sampleprof::ProfileSymbolList &WriterList,
|
|
|
|
bool CompressAllSections) {
|
|
|
|
populateProfileSymbolList(Buffer, WriterList);
|
|
|
|
if (WriterList.size() > 0 && OutputFormat != PF_Ext_Binary)
|
|
|
|
warn("Profile Symbol list is not empty but the output format is not "
|
|
|
|
"ExtBinary format. The list will be lost in the output. ");
|
|
|
|
|
|
|
|
Writer.setProfileSymbolList(&WriterList);
|
|
|
|
|
|
|
|
if (CompressAllSections) {
|
|
|
|
if (OutputFormat != PF_Ext_Binary) {
|
|
|
|
warn("-compress-all-section is ignored. Specify -extbinary to enable it");
|
|
|
|
} else {
|
|
|
|
auto ExtBinaryWriter =
|
|
|
|
static_cast<sampleprof::SampleProfileWriterExtBinary *>(&Writer);
|
|
|
|
ExtBinaryWriter->setToCompressAllSections();
|
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2019-09-04 06:23:16 +08:00
|
|
|
static void mergeSampleProfile(const WeightedFileVector &Inputs,
|
|
|
|
SymbolRemapper *Remapper,
|
|
|
|
StringRef OutputFilename,
|
|
|
|
ProfileFormat OutputFormat,
|
|
|
|
StringRef ProfileSymbolListFile,
|
2019-10-08 00:12:37 +08:00
|
|
|
bool CompressAllSections, FailureMode FailMode) {
|
2014-11-01 08:56:55 +08:00
|
|
|
using namespace sampleprof;
|
|
|
|
StringMap<FunctionSamples> ProfileMap;
|
2015-10-09 03:40:37 +08:00
|
|
|
SmallVector<std::unique_ptr<sampleprof::SampleProfileReader>, 5> Readers;
|
2016-04-15 05:59:01 +08:00
|
|
|
LLVMContext Context;
|
2019-08-31 10:27:26 +08:00
|
|
|
sampleprof::ProfileSymbolList WriterList;
|
2015-12-16 01:37:09 +08:00
|
|
|
for (const auto &Input : Inputs) {
|
2016-04-15 05:59:01 +08:00
|
|
|
auto ReaderOrErr = SampleProfileReader::create(Input.Filename, Context);
|
2019-09-04 06:23:16 +08:00
|
|
|
if (std::error_code EC = ReaderOrErr.getError()) {
|
|
|
|
warnOrExitGivenError(FailMode, EC, Input.Filename);
|
|
|
|
continue;
|
|
|
|
}
|
2014-11-01 08:56:55 +08:00
|
|
|
|
2015-10-09 03:40:37 +08:00
|
|
|
// We need to keep the readers around until after all the files are
|
|
|
|
// read so that we do not lose the function names stored in each
|
|
|
|
// reader's memory. The function names are needed to write out the
|
|
|
|
// merged profile map.
|
|
|
|
Readers.push_back(std::move(ReaderOrErr.get()));
|
|
|
|
const auto Reader = Readers.back().get();
|
2019-09-04 06:23:16 +08:00
|
|
|
if (std::error_code EC = Reader->read()) {
|
|
|
|
warnOrExitGivenError(FailMode, EC, Input.Filename);
|
|
|
|
Readers.pop_back();
|
|
|
|
continue;
|
|
|
|
}
|
2014-11-01 08:56:55 +08:00
|
|
|
|
|
|
|
StringMap<FunctionSamples> &Profiles = Reader->getProfiles();
|
|
|
|
for (StringMap<FunctionSamples>::iterator I = Profiles.begin(),
|
|
|
|
E = Profiles.end();
|
|
|
|
I != E; ++I) {
|
2018-09-14 04:22:02 +08:00
|
|
|
sampleprof_error Result = sampleprof_error::success;
|
|
|
|
FunctionSamples Remapped =
|
|
|
|
Remapper ? remapSamples(I->second, *Remapper, Result)
|
|
|
|
: FunctionSamples();
|
|
|
|
FunctionSamples &Samples = Remapper ? Remapped : I->second;
|
|
|
|
StringRef FName = Samples.getName();
|
|
|
|
MergeResult(Result, ProfileMap[FName].merge(Samples, Input.Weight));
|
2015-12-17 05:45:43 +08:00
|
|
|
if (Result != sampleprof_error::success) {
|
|
|
|
std::error_code EC = make_error_code(Result);
|
2016-05-19 11:54:45 +08:00
|
|
|
handleMergeWriterError(errorCodeToError(EC), Input.Filename, FName);
|
2015-12-17 05:45:43 +08:00
|
|
|
}
|
2014-11-01 08:56:55 +08:00
|
|
|
}
|
2019-08-31 10:27:26 +08:00
|
|
|
|
|
|
|
std::unique_ptr<sampleprof::ProfileSymbolList> ReaderList =
|
|
|
|
Reader->getProfileSymbolList();
|
|
|
|
if (ReaderList)
|
|
|
|
WriterList.merge(*ReaderList);
|
2014-11-01 08:56:55 +08:00
|
|
|
}
|
2019-07-09 05:03:12 +08:00
|
|
|
auto WriterOrErr =
|
|
|
|
SampleProfileWriter::create(OutputFilename, FormatMap[OutputFormat]);
|
|
|
|
if (std::error_code EC = WriterOrErr.getError())
|
|
|
|
exitWithErrorCode(EC, OutputFilename);
|
|
|
|
|
2019-10-08 00:12:37 +08:00
|
|
|
auto Writer = std::move(WriterOrErr.get());
|
2019-08-31 10:27:26 +08:00
|
|
|
// WriterList will have StringRef refering to string in Buffer.
|
|
|
|
// Make sure Buffer lives as long as WriterList.
|
|
|
|
auto Buffer = getInputFileBuf(ProfileSymbolListFile);
|
2019-10-08 00:12:37 +08:00
|
|
|
handleExtBinaryWriter(*Writer, OutputFormat, Buffer.get(), WriterList,
|
|
|
|
CompressAllSections);
|
2014-11-01 08:56:55 +08:00
|
|
|
Writer->write(ProfileMap);
|
|
|
|
}
|
|
|
|
|
2015-12-16 01:37:09 +08:00
|
|
|
static WeightedFile parseWeightedFile(const StringRef &WeightedFilename) {
|
2016-06-07 07:43:56 +08:00
|
|
|
StringRef WeightStr, FileName;
|
|
|
|
std::tie(WeightStr, FileName) = WeightedFilename.split(',');
|
2015-12-16 01:37:09 +08:00
|
|
|
|
|
|
|
uint64_t Weight;
|
|
|
|
if (WeightStr.getAsInteger(10, Weight) || Weight < 1)
|
|
|
|
exitWithError("Input weight must be a positive integer.");
|
|
|
|
|
2020-01-29 03:23:46 +08:00
|
|
|
return {std::string(FileName), Weight};
|
2015-12-16 01:37:09 +08:00
|
|
|
}
|
|
|
|
|
2016-07-21 06:24:52 +08:00
|
|
|
static void addWeightedInput(WeightedFileVector &WNI, const WeightedFile &WF) {
|
|
|
|
StringRef Filename = WF.Filename;
|
|
|
|
uint64_t Weight = WF.Weight;
|
2016-07-22 20:39:55 +08:00
|
|
|
|
|
|
|
// If it's STDIN just pass it on.
|
|
|
|
if (Filename == "-") {
|
2020-01-29 03:23:46 +08:00
|
|
|
WNI.push_back({std::string(Filename), Weight});
|
2016-07-22 20:39:55 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
2016-07-21 06:24:52 +08:00
|
|
|
llvm::sys::fs::file_status Status;
|
|
|
|
llvm::sys::fs::status(Filename, Status);
|
|
|
|
if (!llvm::sys::fs::exists(Status))
|
|
|
|
exitWithErrorCode(make_error_code(errc::no_such_file_or_directory),
|
|
|
|
Filename);
|
|
|
|
// If it's a source file, collect it.
|
|
|
|
if (llvm::sys::fs::is_regular_file(Status)) {
|
2020-01-29 03:23:46 +08:00
|
|
|
WNI.push_back({std::string(Filename), Weight});
|
2016-07-21 06:24:52 +08:00
|
|
|
return;
|
|
|
|
}
|
|
|
|
|
|
|
|
if (llvm::sys::fs::is_directory(Status)) {
|
|
|
|
std::error_code EC;
|
|
|
|
for (llvm::sys::fs::recursive_directory_iterator F(Filename, EC), E;
|
|
|
|
F != E && !EC; F.increment(EC)) {
|
|
|
|
if (llvm::sys::fs::is_regular_file(F->path())) {
|
|
|
|
addWeightedInput(WNI, {F->path(), Weight});
|
|
|
|
}
|
|
|
|
}
|
|
|
|
if (EC)
|
|
|
|
exitWithErrorCode(EC, Filename);
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-08 06:47:31 +08:00
|
|
|
static void parseInputFilenamesFile(MemoryBuffer *Buffer,
|
|
|
|
WeightedFileVector &WFV) {
|
|
|
|
if (!Buffer)
|
|
|
|
return;
|
|
|
|
|
|
|
|
SmallVector<StringRef, 8> Entries;
|
|
|
|
StringRef Data = Buffer->getBuffer();
|
|
|
|
Data.split(Entries, '\n', /*MaxSplit=*/-1, /*KeepEmpty=*/false);
|
|
|
|
for (const StringRef &FileWeightEntry : Entries) {
|
|
|
|
StringRef SanitizedEntry = FileWeightEntry.trim(" \t\v\f\r");
|
|
|
|
// Skip comments.
|
|
|
|
if (SanitizedEntry.startswith("#"))
|
|
|
|
continue;
|
|
|
|
// If there's no comma, it's an unweighted profile.
|
|
|
|
else if (SanitizedEntry.find(',') == StringRef::npos)
|
2020-01-29 03:23:46 +08:00
|
|
|
addWeightedInput(WFV, {std::string(SanitizedEntry), 1});
|
2016-06-08 06:47:31 +08:00
|
|
|
else
|
2016-07-21 06:24:52 +08:00
|
|
|
addWeightedInput(WFV, parseWeightedFile(SanitizedEntry));
|
2016-06-08 06:47:31 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2015-12-16 01:37:09 +08:00
|
|
|
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>"));
|
2016-06-08 06:47:31 +08:00
|
|
|
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"));
|
2018-09-14 04:22:02 +08:00
|
|
|
cl::opt<std::string> RemappingFile("remapping-file", cl::value_desc("file"),
|
|
|
|
cl::desc("Symbol remapping file"));
|
|
|
|
cl::alias RemappingFileA("r", cl::desc("Alias for --remapping-file"),
|
|
|
|
cl::aliasopt(RemappingFile));
|
2014-03-22 01:29:44 +08:00
|
|
|
cl::opt<std::string> OutputFilename("output", cl::value_desc("output"),
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::init("-"), cl::Required,
|
2014-03-22 01:29:44 +08:00
|
|
|
cl::desc("Output file"));
|
|
|
|
cl::alias OutputFilenameA("o", cl::desc("Alias for --output"),
|
|
|
|
cl::aliasopt(OutputFilename));
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::opt<ProfileKinds> ProfileKind(
|
|
|
|
cl::desc("Profile kind:"), cl::init(instr),
|
|
|
|
cl::values(clEnumVal(instr, "Instrumentation profile (default)"),
|
2016-10-09 03:41:06 +08:00
|
|
|
clEnumVal(sample, "Sample profile")));
|
2015-11-24 04:47:38 +08:00
|
|
|
cl::opt<ProfileFormat> OutputFormat(
|
2018-06-12 13:53:49 +08:00
|
|
|
cl::desc("Format of output profile"), cl::init(PF_Binary),
|
2019-08-24 03:05:30 +08:00
|
|
|
cl::values(
|
|
|
|
clEnumValN(PF_Binary, "binary", "Binary encoding (default)"),
|
|
|
|
clEnumValN(PF_Compact_Binary, "compbinary",
|
|
|
|
"Compact binary encoding"),
|
|
|
|
clEnumValN(PF_Ext_Binary, "extbinary", "Extensible binary encoding"),
|
|
|
|
clEnumValN(PF_Text, "text", "Text encoding"),
|
|
|
|
clEnumValN(PF_GCC, "gcc",
|
|
|
|
"GCC encoding (only meaningful for -sample)")));
|
2019-09-04 06:23:16 +08:00
|
|
|
cl::opt<FailureMode> FailureMode(
|
|
|
|
"failure-mode", cl::init(failIfAnyAreInvalid), cl::desc("Failure mode:"),
|
|
|
|
cl::values(clEnumValN(failIfAnyAreInvalid, "any",
|
|
|
|
"Fail if any profile is invalid."),
|
|
|
|
clEnumValN(failIfAllAreInvalid, "all",
|
|
|
|
"Fail only if all profiles are invalid.")));
|
2016-01-30 06:54:45 +08:00
|
|
|
cl::opt<bool> OutputSparse("sparse", cl::init(false),
|
|
|
|
cl::desc("Generate a sparse profile (only meaningful for -instr)"));
|
2016-07-19 09:17:20 +08:00
|
|
|
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));
|
2019-08-31 10:27:26 +08:00
|
|
|
cl::opt<std::string> ProfileSymbolListFile(
|
|
|
|
"prof-sym-list", cl::init(""),
|
|
|
|
cl::desc("Path to file containing the list of function symbols "
|
|
|
|
"used to populate profile symbol list"));
|
2019-10-08 00:12:37 +08:00
|
|
|
cl::opt<bool> CompressAllSections(
|
|
|
|
"compress-all-sections", cl::init(false), cl::Hidden,
|
|
|
|
cl::desc("Compress all sections when writing the profile (only "
|
|
|
|
"meaningful for -extbinary)"));
|
2016-01-30 06:54:45 +08:00
|
|
|
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::ParseCommandLineOptions(argc, argv, "LLVM profile data merger\n");
|
|
|
|
|
2016-06-07 07:43:56 +08:00
|
|
|
WeightedFileVector WeightedInputs;
|
|
|
|
for (StringRef Filename : InputFilenames)
|
2020-01-29 03:23:46 +08:00
|
|
|
addWeightedInput(WeightedInputs, {std::string(Filename), 1});
|
2016-06-07 07:43:56 +08:00
|
|
|
for (StringRef WeightedFilename : WeightedInputFilenames)
|
2016-07-21 06:24:52 +08:00
|
|
|
addWeightedInput(WeightedInputs, parseWeightedFile(WeightedFilename));
|
2016-06-08 06:47:31 +08:00
|
|
|
|
|
|
|
// Make sure that the file buffer stays alive for the duration of the
|
|
|
|
// weighted input vector's lifetime.
|
2019-08-31 10:27:26 +08:00
|
|
|
auto Buffer = getInputFileBuf(InputFilenamesFile);
|
2016-06-08 06:47:31 +08:00
|
|
|
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;
|
|
|
|
}
|
2016-06-04 08:36:28 +08:00
|
|
|
|
2018-09-14 04:22:02 +08:00
|
|
|
std::unique_ptr<SymbolRemapper> Remapper;
|
|
|
|
if (!RemappingFile.empty())
|
|
|
|
Remapper = SymbolRemapper::create(RemappingFile);
|
|
|
|
|
2014-11-01 08:56:55 +08:00
|
|
|
if (ProfileKind == instr)
|
2018-09-14 04:22:02 +08:00
|
|
|
mergeInstrProfile(WeightedInputs, Remapper.get(), OutputFilename,
|
2019-09-04 06:23:16 +08:00
|
|
|
OutputFormat, OutputSparse, NumThreads, FailureMode);
|
2014-11-01 08:56:55 +08:00
|
|
|
else
|
2018-09-14 04:22:02 +08:00
|
|
|
mergeSampleProfile(WeightedInputs, Remapper.get(), OutputFilename,
|
2019-10-08 00:12:37 +08:00
|
|
|
OutputFormat, ProfileSymbolListFile, CompressAllSections,
|
|
|
|
FailureMode);
|
2014-11-01 08:56:55 +08:00
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
2014-03-22 01:29:44 +08:00
|
|
|
|
2019-05-01 05:19:12 +08:00
|
|
|
/// Computer the overlap b/w profile BaseFilename and profile TestFilename.
|
|
|
|
static void overlapInstrProfile(const std::string &BaseFilename,
|
|
|
|
const std::string &TestFilename,
|
|
|
|
const OverlapFuncFilters &FuncFilter,
|
|
|
|
raw_fd_ostream &OS, bool IsCS) {
|
|
|
|
std::mutex ErrorLock;
|
|
|
|
SmallSet<instrprof_error, 4> WriterErrorCodes;
|
|
|
|
WriterContext Context(false, ErrorLock, WriterErrorCodes);
|
|
|
|
WeightedFile WeightedInput{BaseFilename, 1};
|
|
|
|
OverlapStats Overlap;
|
2019-10-02 02:06:50 +08:00
|
|
|
Error E = Overlap.accumulateCounts(BaseFilename, TestFilename, IsCS);
|
2019-05-01 05:19:12 +08:00
|
|
|
if (E)
|
|
|
|
exitWithError(std::move(E), "Error in getting profile count sums");
|
|
|
|
if (Overlap.Base.CountSum < 1.0f) {
|
|
|
|
OS << "Sum of edge counts for profile " << BaseFilename << " is 0.\n";
|
|
|
|
exit(0);
|
|
|
|
}
|
|
|
|
if (Overlap.Test.CountSum < 1.0f) {
|
|
|
|
OS << "Sum of edge counts for profile " << TestFilename << " is 0.\n";
|
|
|
|
exit(0);
|
|
|
|
}
|
|
|
|
loadInput(WeightedInput, nullptr, &Context);
|
|
|
|
overlapInput(BaseFilename, TestFilename, &Context, Overlap, FuncFilter, OS,
|
|
|
|
IsCS);
|
|
|
|
Overlap.dump(OS);
|
|
|
|
}
|
|
|
|
|
|
|
|
static int overlap_main(int argc, const char *argv[]) {
|
|
|
|
cl::opt<std::string> BaseFilename(cl::Positional, cl::Required,
|
|
|
|
cl::desc("<base profile file>"));
|
|
|
|
cl::opt<std::string> TestFilename(cl::Positional, cl::Required,
|
|
|
|
cl::desc("<test profile file>"));
|
|
|
|
cl::opt<std::string> Output("output", cl::value_desc("output"), cl::init("-"),
|
|
|
|
cl::desc("Output file"));
|
|
|
|
cl::alias OutputA("o", cl::desc("Alias for --output"), cl::aliasopt(Output));
|
|
|
|
cl::opt<bool> IsCS("cs", cl::init(false),
|
|
|
|
cl::desc("For context sensitive counts"));
|
|
|
|
cl::opt<unsigned long long> ValueCutoff(
|
|
|
|
"value-cutoff", cl::init(-1),
|
|
|
|
cl::desc(
|
|
|
|
"Function level overlap information for every function in test "
|
|
|
|
"profile with max count value greater then the parameter value"));
|
|
|
|
cl::opt<std::string> FuncNameFilter(
|
|
|
|
"function",
|
|
|
|
cl::desc("Function level overlap information for matching functions"));
|
|
|
|
cl::ParseCommandLineOptions(argc, argv, "LLVM profile data overlap tool\n");
|
|
|
|
|
|
|
|
std::error_code EC;
|
2019-08-05 13:43:48 +08:00
|
|
|
raw_fd_ostream OS(Output.data(), EC, sys::fs::OF_Text);
|
2019-05-01 05:19:12 +08:00
|
|
|
if (EC)
|
|
|
|
exitWithErrorCode(EC, Output);
|
|
|
|
|
|
|
|
overlapInstrProfile(BaseFilename, TestFilename,
|
|
|
|
OverlapFuncFilters{ValueCutoff, FuncNameFilter}, OS,
|
|
|
|
IsCS);
|
|
|
|
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2017-03-10 03:03:57 +08:00
|
|
|
typedef struct ValueSitesStats {
|
|
|
|
ValueSitesStats()
|
|
|
|
: TotalNumValueSites(0), TotalNumValueSitesWithValueProfile(0),
|
|
|
|
TotalNumValues(0) {}
|
|
|
|
uint64_t TotalNumValueSites;
|
|
|
|
uint64_t TotalNumValueSitesWithValueProfile;
|
|
|
|
uint64_t TotalNumValues;
|
|
|
|
std::vector<unsigned> ValueSitesHistogram;
|
|
|
|
} ValueSitesStats;
|
|
|
|
|
|
|
|
static void traverseAllValueSites(const InstrProfRecord &Func, uint32_t VK,
|
|
|
|
ValueSitesStats &Stats, raw_fd_ostream &OS,
|
2017-03-17 05:15:48 +08:00
|
|
|
InstrProfSymtab *Symtab) {
|
2017-03-10 03:03:57 +08:00
|
|
|
uint32_t NS = Func.getNumValueSites(VK);
|
|
|
|
Stats.TotalNumValueSites += NS;
|
|
|
|
for (size_t I = 0; I < NS; ++I) {
|
|
|
|
uint32_t NV = Func.getNumValueDataForSite(VK, I);
|
|
|
|
std::unique_ptr<InstrProfValueData[]> VD = Func.getValueForSite(VK, I);
|
|
|
|
Stats.TotalNumValues += NV;
|
|
|
|
if (NV) {
|
|
|
|
Stats.TotalNumValueSitesWithValueProfile++;
|
|
|
|
if (NV > Stats.ValueSitesHistogram.size())
|
|
|
|
Stats.ValueSitesHistogram.resize(NV, 0);
|
|
|
|
Stats.ValueSitesHistogram[NV - 1]++;
|
|
|
|
}
|
2019-01-09 06:41:48 +08:00
|
|
|
|
|
|
|
uint64_t SiteSum = 0;
|
|
|
|
for (uint32_t V = 0; V < NV; V++)
|
|
|
|
SiteSum += VD[V].Count;
|
|
|
|
if (SiteSum == 0)
|
|
|
|
SiteSum = 1;
|
|
|
|
|
2017-03-10 03:03:57 +08:00
|
|
|
for (uint32_t V = 0; V < NV; V++) {
|
2019-01-09 06:41:48 +08:00
|
|
|
OS << "\t[ " << format("%2u", I) << ", ";
|
2017-03-17 05:15:48 +08:00
|
|
|
if (Symtab == nullptr)
|
2019-02-06 02:09:28 +08:00
|
|
|
OS << format("%4" PRIu64, VD[V].Value);
|
2017-03-17 05:15:48 +08:00
|
|
|
else
|
|
|
|
OS << Symtab->getFuncName(VD[V].Value);
|
2019-01-09 06:41:48 +08:00
|
|
|
OS << ", " << format("%10" PRId64, VD[V].Count) << " ] ("
|
|
|
|
<< format("%.2f%%", (VD[V].Count * 100.0 / SiteSum)) << ")\n";
|
2017-03-10 03:03:57 +08:00
|
|
|
}
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
static void showValueSitesStats(raw_fd_ostream &OS, uint32_t VK,
|
|
|
|
ValueSitesStats &Stats) {
|
|
|
|
OS << " Total number of sites: " << Stats.TotalNumValueSites << "\n";
|
|
|
|
OS << " Total number of sites with values: "
|
|
|
|
<< Stats.TotalNumValueSitesWithValueProfile << "\n";
|
|
|
|
OS << " Total number of profiled values: " << Stats.TotalNumValues << "\n";
|
|
|
|
|
|
|
|
OS << " Value sites histogram:\n\tNumTargets, SiteCount\n";
|
|
|
|
for (unsigned I = 0; I < Stats.ValueSitesHistogram.size(); I++) {
|
|
|
|
if (Stats.ValueSitesHistogram[I] > 0)
|
|
|
|
OS << "\t" << I + 1 << ", " << Stats.ValueSitesHistogram[I] << "\n";
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-18 04:41:14 +08:00
|
|
|
static int showInstrProfile(const std::string &Filename, bool ShowCounts,
|
2017-07-12 04:30:43 +08:00
|
|
|
uint32_t TopN, bool ShowIndirectCallTargets,
|
|
|
|
bool ShowMemOPSizes, bool ShowDetailedSummary,
|
2016-01-14 05:44:36 +08:00
|
|
|
std::vector<uint32_t> DetailedSummaryCutoffs,
|
2019-03-01 03:55:07 +08:00
|
|
|
bool ShowAllFunctions, bool ShowCS,
|
|
|
|
uint64_t ValueCutoff, bool OnlyListBelow,
|
|
|
|
const std::string &ShowFunction, bool TextFormat,
|
|
|
|
raw_fd_ostream &OS) {
|
2014-11-03 08:51:45 +08:00
|
|
|
auto ReaderOrErr = InstrProfReader::create(Filename);
|
2016-06-18 04:41:14 +08:00
|
|
|
std::vector<uint32_t> Cutoffs = std::move(DetailedSummaryCutoffs);
|
|
|
|
if (ShowDetailedSummary && Cutoffs.empty()) {
|
2016-01-14 05:44:36 +08:00
|
|
|
Cutoffs = {800000, 900000, 950000, 990000, 999000, 999900, 999990};
|
|
|
|
}
|
2016-06-18 04:41:14 +08:00
|
|
|
InstrProfSummaryBuilder Builder(std::move(Cutoffs));
|
2016-05-19 11:54:45 +08:00
|
|
|
if (Error E = ReaderOrErr.takeError())
|
|
|
|
exitWithError(std::move(E), Filename);
|
2014-03-22 01:29:44 +08:00
|
|
|
|
2014-11-03 08:51:45 +08:00
|
|
|
auto Reader = std::move(ReaderOrErr.get());
|
2016-02-11 01:18:30 +08:00
|
|
|
bool IsIRInstr = Reader->isIRLevelProfile();
|
2016-01-14 05:44:36 +08:00
|
|
|
size_t ShownFunctions = 0;
|
2019-01-09 06:41:48 +08:00
|
|
|
size_t BelowCutoffFunctions = 0;
|
2017-03-10 03:03:57 +08:00
|
|
|
int NumVPKind = IPVK_Last - IPVK_First + 1;
|
|
|
|
std::vector<ValueSitesStats> VPStats(NumVPKind);
|
2017-07-12 04:30:43 +08:00
|
|
|
|
|
|
|
auto MinCmp = [](const std::pair<std::string, uint64_t> &v1,
|
|
|
|
const std::pair<std::string, uint64_t> &v2) {
|
|
|
|
return v1.second > v2.second;
|
|
|
|
};
|
|
|
|
|
|
|
|
std::priority_queue<std::pair<std::string, uint64_t>,
|
|
|
|
std::vector<std::pair<std::string, uint64_t>>,
|
|
|
|
decltype(MinCmp)>
|
|
|
|
HottestFuncs(MinCmp);
|
|
|
|
|
2019-01-09 06:41:48 +08:00
|
|
|
if (!TextFormat && OnlyListBelow) {
|
|
|
|
OS << "The list of functions with the maximum counter less than "
|
|
|
|
<< ValueCutoff << ":\n";
|
|
|
|
}
|
|
|
|
|
2018-08-24 09:34:45 +08:00
|
|
|
// Add marker so that IR-level instrumentation round-trips properly.
|
|
|
|
if (TextFormat && IsIRInstr)
|
|
|
|
OS << ":ir\n";
|
|
|
|
|
2014-03-22 01:29:44 +08:00
|
|
|
for (const auto &Func : *Reader) {
|
2019-03-01 03:55:07 +08:00
|
|
|
if (Reader->isIRLevelProfile()) {
|
|
|
|
bool FuncIsCS = NamedInstrProfRecord::hasCSFlagInHash(Func.Hash);
|
|
|
|
if (FuncIsCS != ShowCS)
|
|
|
|
continue;
|
|
|
|
}
|
2014-11-01 08:56:55 +08:00
|
|
|
bool Show =
|
|
|
|
ShowAllFunctions || (!ShowFunction.empty() &&
|
|
|
|
Func.Name.find(ShowFunction) != Func.Name.npos);
|
2014-03-22 01:29:44 +08:00
|
|
|
|
2018-08-24 09:34:45 +08:00
|
|
|
bool doTextFormatDump = (Show && TextFormat);
|
2015-11-24 04:47:38 +08:00
|
|
|
|
|
|
|
if (doTextFormatDump) {
|
2015-12-20 14:22:13 +08:00
|
|
|
InstrProfSymtab &Symtab = Reader->getSymtab();
|
2017-07-07 03:00:12 +08:00
|
|
|
InstrProfWriter::writeRecordInText(Func.Name, Func.Hash, Func, Symtab,
|
|
|
|
OS);
|
2015-11-24 04:47:38 +08:00
|
|
|
continue;
|
|
|
|
}
|
|
|
|
|
2014-04-25 10:45:33 +08:00
|
|
|
assert(Func.Counts.size() > 0 && "function missing entry counter");
|
2016-05-20 05:07:12 +08:00
|
|
|
Builder.addRecord(Func);
|
2015-11-24 04:47:38 +08:00
|
|
|
|
2019-01-09 06:41:48 +08:00
|
|
|
uint64_t FuncMax = 0;
|
|
|
|
uint64_t FuncSum = 0;
|
|
|
|
for (size_t I = 0, E = Func.Counts.size(); I < E; ++I) {
|
|
|
|
FuncMax = std::max(FuncMax, Func.Counts[I]);
|
|
|
|
FuncSum += Func.Counts[I];
|
|
|
|
}
|
|
|
|
|
|
|
|
if (FuncMax < ValueCutoff) {
|
|
|
|
++BelowCutoffFunctions;
|
|
|
|
if (OnlyListBelow) {
|
|
|
|
OS << " " << Func.Name << ": (Max = " << FuncMax
|
|
|
|
<< " Sum = " << FuncSum << ")\n";
|
|
|
|
}
|
|
|
|
continue;
|
|
|
|
} else if (OnlyListBelow)
|
|
|
|
continue;
|
2019-01-09 06:37:12 +08:00
|
|
|
|
2019-01-09 06:41:48 +08:00
|
|
|
if (TopN) {
|
2017-07-12 04:30:43 +08:00
|
|
|
if (HottestFuncs.size() == TopN) {
|
|
|
|
if (HottestFuncs.top().second < FuncMax) {
|
|
|
|
HottestFuncs.pop();
|
|
|
|
HottestFuncs.emplace(std::make_pair(std::string(Func.Name), FuncMax));
|
|
|
|
}
|
|
|
|
} else
|
|
|
|
HottestFuncs.emplace(std::make_pair(std::string(Func.Name), FuncMax));
|
|
|
|
}
|
|
|
|
|
2014-03-22 01:29:44 +08:00
|
|
|
if (Show) {
|
|
|
|
if (!ShownFunctions)
|
|
|
|
OS << "Counters:\n";
|
2015-11-24 04:47:38 +08:00
|
|
|
|
2014-03-22 01:29:44 +08:00
|
|
|
++ShownFunctions;
|
|
|
|
|
|
|
|
OS << " " << Func.Name << ":\n"
|
2014-03-24 04:43:50 +08:00
|
|
|
<< " Hash: " << format("0x%016" PRIx64, Func.Hash) << "\n"
|
2016-02-11 01:18:30 +08:00
|
|
|
<< " Counters: " << Func.Counts.size() << "\n";
|
|
|
|
if (!IsIRInstr)
|
|
|
|
OS << " Function count: " << Func.Counts[0] << "\n";
|
2015-11-24 04:47:38 +08:00
|
|
|
|
2015-09-30 06:13:58 +08:00
|
|
|
if (ShowIndirectCallTargets)
|
2015-11-02 13:08:23 +08:00
|
|
|
OS << " Indirect Call Site Count: "
|
|
|
|
<< Func.getNumValueSites(IPVK_IndirectCallTarget) << "\n";
|
2014-03-22 01:29:44 +08:00
|
|
|
|
2017-03-17 05:15:48 +08:00
|
|
|
uint32_t NumMemOPCalls = Func.getNumValueSites(IPVK_MemOPSize);
|
|
|
|
if (ShowMemOPSizes && NumMemOPCalls > 0)
|
|
|
|
OS << " Number of Memory Intrinsics Calls: " << NumMemOPCalls
|
|
|
|
<< "\n";
|
|
|
|
|
2015-11-24 04:47:38 +08:00
|
|
|
if (ShowCounts) {
|
|
|
|
OS << " Block counts: [";
|
2016-02-11 01:18:30 +08:00
|
|
|
size_t Start = (IsIRInstr ? 0 : 1);
|
|
|
|
for (size_t I = Start, E = Func.Counts.size(); I < E; ++I) {
|
|
|
|
OS << (I == Start ? "" : ", ") << Func.Counts[I];
|
2015-11-24 04:47:38 +08:00
|
|
|
}
|
|
|
|
OS << "]\n";
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ShowIndirectCallTargets) {
|
2017-03-10 03:03:57 +08:00
|
|
|
OS << " Indirect Target Results:\n";
|
|
|
|
traverseAllValueSites(Func, IPVK_IndirectCallTarget,
|
|
|
|
VPStats[IPVK_IndirectCallTarget], OS,
|
2017-03-17 05:15:48 +08:00
|
|
|
&(Reader->getSymtab()));
|
|
|
|
}
|
|
|
|
|
|
|
|
if (ShowMemOPSizes && NumMemOPCalls > 0) {
|
2017-05-25 01:55:25 +08:00
|
|
|
OS << " Memory Intrinsic Size Results:\n";
|
2017-03-17 05:15:48 +08:00
|
|
|
traverseAllValueSites(Func, IPVK_MemOPSize, VPStats[IPVK_MemOPSize], OS,
|
|
|
|
nullptr);
|
2015-09-30 06:13:58 +08:00
|
|
|
}
|
|
|
|
}
|
2014-03-22 01:29:44 +08:00
|
|
|
}
|
2014-03-24 04:55:53 +08:00
|
|
|
if (Reader->hasError())
|
2016-05-19 11:54:45 +08:00
|
|
|
exitWithError(Reader->getError(), Filename);
|
2014-03-22 01:29:44 +08:00
|
|
|
|
2018-08-24 09:34:45 +08:00
|
|
|
if (TextFormat)
|
2015-11-24 04:47:38 +08:00
|
|
|
return 0;
|
2016-05-20 05:53:28 +08:00
|
|
|
std::unique_ptr<ProfileSummary> PS(Builder.getSummary());
|
2017-11-15 00:59:18 +08:00
|
|
|
OS << "Instrumentation level: "
|
|
|
|
<< (Reader->isIRLevelProfile() ? "IR" : "Front-end") << "\n";
|
2014-03-22 01:29:44 +08:00
|
|
|
if (ShowAllFunctions || !ShowFunction.empty())
|
|
|
|
OS << "Functions shown: " << ShownFunctions << "\n";
|
2016-05-20 05:07:12 +08:00
|
|
|
OS << "Total functions: " << PS->getNumFunctions() << "\n";
|
2019-01-09 06:41:48 +08:00
|
|
|
if (ValueCutoff > 0) {
|
|
|
|
OS << "Number of functions with maximum count (< " << ValueCutoff
|
|
|
|
<< "): " << BelowCutoffFunctions << "\n";
|
|
|
|
OS << "Number of functions with maximum count (>= " << ValueCutoff
|
|
|
|
<< "): " << PS->getNumFunctions() - BelowCutoffFunctions << "\n";
|
|
|
|
}
|
2016-05-20 05:07:12 +08:00
|
|
|
OS << "Maximum function count: " << PS->getMaxFunctionCount() << "\n";
|
2016-05-20 05:53:28 +08:00
|
|
|
OS << "Maximum internal block count: " << PS->getMaxInternalCount() << "\n";
|
2017-03-17 05:15:48 +08:00
|
|
|
|
2017-07-12 04:30:43 +08:00
|
|
|
if (TopN) {
|
|
|
|
std::vector<std::pair<std::string, uint64_t>> SortedHottestFuncs;
|
|
|
|
while (!HottestFuncs.empty()) {
|
|
|
|
SortedHottestFuncs.emplace_back(HottestFuncs.top());
|
|
|
|
HottestFuncs.pop();
|
|
|
|
}
|
|
|
|
OS << "Top " << TopN
|
|
|
|
<< " functions with the largest internal block counts: \n";
|
|
|
|
for (auto &hotfunc : llvm::reverse(SortedHottestFuncs))
|
|
|
|
OS << " " << hotfunc.first << ", max count = " << hotfunc.second << "\n";
|
|
|
|
}
|
|
|
|
|
2016-05-24 00:36:11 +08:00
|
|
|
if (ShownFunctions && ShowIndirectCallTargets) {
|
2017-03-10 03:03:57 +08:00
|
|
|
OS << "Statistics for indirect call sites profile:\n";
|
|
|
|
showValueSitesStats(OS, IPVK_IndirectCallTarget,
|
|
|
|
VPStats[IPVK_IndirectCallTarget]);
|
2016-05-24 00:36:11 +08:00
|
|
|
}
|
2016-01-14 05:44:36 +08:00
|
|
|
|
2017-03-17 05:15:48 +08:00
|
|
|
if (ShownFunctions && ShowMemOPSizes) {
|
|
|
|
OS << "Statistics for memory intrinsic calls sizes profile:\n";
|
|
|
|
showValueSitesStats(OS, IPVK_MemOPSize, VPStats[IPVK_MemOPSize]);
|
|
|
|
}
|
|
|
|
|
2016-01-14 05:44:36 +08:00
|
|
|
if (ShowDetailedSummary) {
|
|
|
|
OS << "Detailed summary:\n";
|
2016-05-20 05:53:28 +08:00
|
|
|
OS << "Total number of blocks: " << PS->getNumCounts() << "\n";
|
2016-05-20 05:07:12 +08:00
|
|
|
OS << "Total count: " << PS->getTotalCount() << "\n";
|
|
|
|
for (auto Entry : PS->getDetailedSummary()) {
|
2016-02-18 02:18:47 +08:00
|
|
|
OS << Entry.NumCounts << " blocks with count >= " << Entry.MinCount
|
2016-01-14 05:44:36 +08:00
|
|
|
<< " account for "
|
|
|
|
<< format("%0.6g", (float)Entry.Cutoff / ProfileSummary::Scale * 100)
|
|
|
|
<< " percentage of the total counts.\n";
|
|
|
|
}
|
|
|
|
}
|
2014-03-22 01:29:44 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2019-09-22 01:23:55 +08:00
|
|
|
static void showSectionInfo(sampleprof::SampleProfileReader *Reader,
|
|
|
|
raw_fd_ostream &OS) {
|
|
|
|
if (!Reader->dumpSectionInfo(OS)) {
|
|
|
|
WithColor::warning() << "-show-sec-info-only is only supported for "
|
|
|
|
<< "sample profile in extbinary format and is "
|
|
|
|
<< "ignored for other formats.\n";
|
|
|
|
return;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
2016-06-18 04:41:14 +08:00
|
|
|
static int showSampleProfile(const std::string &Filename, bool ShowCounts,
|
|
|
|
bool ShowAllFunctions,
|
|
|
|
const std::string &ShowFunction,
|
2019-09-22 01:23:55 +08:00
|
|
|
bool ShowProfileSymbolList,
|
|
|
|
bool ShowSectionInfoOnly, raw_fd_ostream &OS) {
|
2014-11-01 08:56:55 +08:00
|
|
|
using namespace sampleprof;
|
2016-04-15 05:59:01 +08:00
|
|
|
LLVMContext Context;
|
|
|
|
auto ReaderOrErr = SampleProfileReader::create(Filename, Context);
|
2014-11-03 08:51:45 +08:00
|
|
|
if (std::error_code EC = ReaderOrErr.getError())
|
2015-11-13 11:47:58 +08:00
|
|
|
exitWithErrorCode(EC, Filename);
|
2014-11-01 08:56:55 +08:00
|
|
|
|
2014-11-03 08:51:45 +08:00
|
|
|
auto Reader = std::move(ReaderOrErr.get());
|
2019-09-22 01:23:55 +08:00
|
|
|
|
|
|
|
if (ShowSectionInfoOnly) {
|
|
|
|
showSectionInfo(Reader.get(), OS);
|
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-09-17 08:17:21 +08:00
|
|
|
if (std::error_code EC = Reader->read())
|
2015-11-13 11:47:58 +08:00
|
|
|
exitWithErrorCode(EC, Filename);
|
2015-09-17 08:17:21 +08:00
|
|
|
|
2014-11-01 08:56:55 +08:00
|
|
|
if (ShowAllFunctions || ShowFunction.empty())
|
|
|
|
Reader->dump(OS);
|
|
|
|
else
|
|
|
|
Reader->dumpFunctionProfile(ShowFunction, OS);
|
|
|
|
|
2019-08-31 10:27:26 +08:00
|
|
|
if (ShowProfileSymbolList) {
|
|
|
|
std::unique_ptr<sampleprof::ProfileSymbolList> ReaderList =
|
|
|
|
Reader->getProfileSymbolList();
|
|
|
|
ReaderList->dump(OS);
|
|
|
|
}
|
|
|
|
|
2014-11-01 08:56:55 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
|
2015-03-10 00:23:46 +08:00
|
|
|
static int show_main(int argc, const char *argv[]) {
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::opt<std::string> Filename(cl::Positional, cl::Required,
|
|
|
|
cl::desc("<profdata-file>"));
|
|
|
|
|
|
|
|
cl::opt<bool> ShowCounts("counts", cl::init(false),
|
|
|
|
cl::desc("Show counter values for shown functions"));
|
2015-11-24 04:47:38 +08:00
|
|
|
cl::opt<bool> TextFormat(
|
|
|
|
"text", cl::init(false),
|
|
|
|
cl::desc("Show instr profile data in text dump format"));
|
2015-09-30 06:13:58 +08:00
|
|
|
cl::opt<bool> ShowIndirectCallTargets(
|
|
|
|
"ic-targets", cl::init(false),
|
|
|
|
cl::desc("Show indirect call site target values for shown functions"));
|
2017-03-17 05:15:48 +08:00
|
|
|
cl::opt<bool> ShowMemOPSizes(
|
|
|
|
"memop-sizes", cl::init(false),
|
|
|
|
cl::desc("Show the profiled sizes of the memory intrinsic calls "
|
|
|
|
"for shown functions"));
|
2016-01-14 05:44:36 +08:00
|
|
|
cl::opt<bool> ShowDetailedSummary("detailed-summary", cl::init(false),
|
|
|
|
cl::desc("Show detailed profile summary"));
|
|
|
|
cl::list<uint32_t> DetailedSummaryCutoffs(
|
|
|
|
cl::CommaSeparated, "detailed-summary-cutoffs",
|
|
|
|
cl::desc(
|
|
|
|
"Cutoff percentages (times 10000) for generating detailed summary"),
|
|
|
|
cl::value_desc("800000,901000,999999"));
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::opt<bool> ShowAllFunctions("all-functions", cl::init(false),
|
|
|
|
cl::desc("Details for every function"));
|
2019-03-01 03:55:07 +08:00
|
|
|
cl::opt<bool> ShowCS("showcs", cl::init(false),
|
|
|
|
cl::desc("Show context sensitive counts"));
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::opt<std::string> ShowFunction("function",
|
|
|
|
cl::desc("Details for matching functions"));
|
|
|
|
|
|
|
|
cl::opt<std::string> OutputFilename("output", cl::value_desc("output"),
|
|
|
|
cl::init("-"), 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)"),
|
2016-10-09 03:41:06 +08:00
|
|
|
clEnumVal(sample, "Sample profile")));
|
2017-07-12 04:30:43 +08:00
|
|
|
cl::opt<uint32_t> TopNFunctions(
|
|
|
|
"topn", cl::init(0),
|
|
|
|
cl::desc("Show the list of functions with the largest internal counts"));
|
2019-01-09 06:41:48 +08:00
|
|
|
cl::opt<uint32_t> ValueCutoff(
|
|
|
|
"value-cutoff", cl::init(0),
|
|
|
|
cl::desc("Set the count value cutoff. Functions with the maximum count "
|
|
|
|
"less than this value will not be printed out. (Default is 0)"));
|
|
|
|
cl::opt<bool> OnlyListBelow(
|
|
|
|
"list-below-cutoff", cl::init(false),
|
|
|
|
cl::desc("Only output names of functions whose max count values are "
|
|
|
|
"below the cutoff value"));
|
2019-08-31 10:27:26 +08:00
|
|
|
cl::opt<bool> ShowProfileSymbolList(
|
|
|
|
"show-prof-sym-list", cl::init(false),
|
|
|
|
cl::desc("Show profile symbol list if it exists in the profile. "));
|
2019-09-22 01:23:55 +08:00
|
|
|
cl::opt<bool> ShowSectionInfoOnly(
|
|
|
|
"show-sec-info-only", cl::init(false),
|
|
|
|
cl::desc("Show the information of each section in the sample profile. "
|
|
|
|
"The flag is only usable when the sample profile is in "
|
|
|
|
"extbinary format"));
|
2019-08-31 10:27:26 +08:00
|
|
|
|
2014-11-01 08:56:55 +08:00
|
|
|
cl::ParseCommandLineOptions(argc, argv, "LLVM profile data summary\n");
|
|
|
|
|
|
|
|
if (OutputFilename.empty())
|
|
|
|
OutputFilename = "-";
|
|
|
|
|
2019-07-09 05:03:12 +08:00
|
|
|
if (!Filename.compare(OutputFilename)) {
|
|
|
|
errs() << sys::path::filename(argv[0])
|
|
|
|
<< ": Input file name cannot be the same as the output file name!\n";
|
|
|
|
return 1;
|
|
|
|
}
|
|
|
|
|
2014-11-01 08:56:55 +08:00
|
|
|
std::error_code EC;
|
2019-08-05 13:43:48 +08:00
|
|
|
raw_fd_ostream OS(OutputFilename.data(), EC, sys::fs::OF_Text);
|
2014-11-01 08:56:55 +08:00
|
|
|
if (EC)
|
2015-11-24 04:47:38 +08:00
|
|
|
exitWithErrorCode(EC, OutputFilename);
|
2014-11-01 08:56:55 +08:00
|
|
|
|
|
|
|
if (ShowAllFunctions && !ShowFunction.empty())
|
2018-04-18 22:42:33 +08:00
|
|
|
WithColor::warning() << "-function argument ignored: showing all functions\n";
|
2014-11-01 08:56:55 +08:00
|
|
|
|
|
|
|
if (ProfileKind == instr)
|
2017-07-12 04:30:43 +08:00
|
|
|
return showInstrProfile(Filename, ShowCounts, TopNFunctions,
|
|
|
|
ShowIndirectCallTargets, ShowMemOPSizes,
|
|
|
|
ShowDetailedSummary, DetailedSummaryCutoffs,
|
2019-03-01 03:55:07 +08:00
|
|
|
ShowAllFunctions, ShowCS, ValueCutoff,
|
|
|
|
OnlyListBelow, ShowFunction, TextFormat, OS);
|
2014-11-01 08:56:55 +08:00
|
|
|
else
|
|
|
|
return showSampleProfile(Filename, ShowCounts, ShowAllFunctions,
|
2019-09-22 01:23:55 +08:00
|
|
|
ShowFunction, ShowProfileSymbolList,
|
|
|
|
ShowSectionInfoOnly, OS);
|
2014-11-01 08:56:55 +08:00
|
|
|
}
|
|
|
|
|
2014-03-19 10:20:46 +08:00
|
|
|
int main(int argc, const char *argv[]) {
|
2018-04-14 02:26:06 +08:00
|
|
|
InitLLVM X(argc, argv);
|
2014-03-19 10:20:46 +08:00
|
|
|
|
|
|
|
StringRef ProgName(sys::path::filename(argv[0]));
|
|
|
|
if (argc > 1) {
|
2014-04-25 12:24:47 +08:00
|
|
|
int (*func)(int, const char *[]) = nullptr;
|
2014-03-19 10:20:46 +08:00
|
|
|
|
|
|
|
if (strcmp(argv[1], "merge") == 0)
|
|
|
|
func = merge_main;
|
2014-03-22 01:29:44 +08:00
|
|
|
else if (strcmp(argv[1], "show") == 0)
|
|
|
|
func = show_main;
|
2019-05-01 05:19:12 +08:00
|
|
|
else if (strcmp(argv[1], "overlap") == 0)
|
|
|
|
func = overlap_main;
|
2014-03-19 10:20:46 +08:00
|
|
|
|
|
|
|
if (func) {
|
|
|
|
std::string Invocation(ProgName.str() + " " + argv[1]);
|
|
|
|
argv[1] = Invocation.c_str();
|
|
|
|
return func(argc - 1, argv + 1);
|
|
|
|
}
|
|
|
|
|
2015-12-15 04:37:15 +08:00
|
|
|
if (strcmp(argv[1], "-h") == 0 || strcmp(argv[1], "-help") == 0 ||
|
2014-03-19 10:20:46 +08:00
|
|
|
strcmp(argv[1], "--help") == 0) {
|
|
|
|
|
|
|
|
errs() << "OVERVIEW: LLVM profile data tools\n\n"
|
|
|
|
<< "USAGE: " << ProgName << " <command> [args...]\n"
|
|
|
|
<< "USAGE: " << ProgName << " <command> -help\n\n"
|
2016-08-04 07:10:51 +08:00
|
|
|
<< "See each individual command --help for more details.\n"
|
2019-05-01 05:19:12 +08:00
|
|
|
<< "Available commands: merge, show, overlap\n";
|
2014-03-19 10:20:46 +08:00
|
|
|
return 0;
|
|
|
|
}
|
|
|
|
}
|
|
|
|
|
|
|
|
if (argc < 2)
|
|
|
|
errs() << ProgName << ": No command specified!\n";
|
|
|
|
else
|
|
|
|
errs() << ProgName << ": Unknown command!\n";
|
|
|
|
|
2019-05-01 05:19:12 +08:00
|
|
|
errs() << "USAGE: " << ProgName << " <merge|show|overlap> [args...]\n";
|
2014-03-19 10:20:46 +08:00
|
|
|
return 1;
|
|
|
|
}
|