#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Filesystem.h"
#include "lld/Common/Memory.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Timer.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/Optional.h"
#include "llvm/Support/Debug.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MathExtras.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/Process.h"
#include "llvm/Support/TarWriter.h"
#include "Chunks.h"
#include "Symbols.h"
#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Timer.h"
#include "llvm/ADT/Hashing.h"
#include "llvm/Support/Debug.h"
#include "Symbols.h"
#include "Writer.h"
#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Threads.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
#include "Symbols.h"
#include "Writer.h"
#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Timer.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/raw_ostream.h"
#include "TypeMerger.h"
#include "Writer.h"
#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Timer.h"
#include "llvm/DebugInfo/CodeView/DebugFrameDataSubsection.h"
#include "llvm/DebugInfo/CodeView/DebugSubsectionRecord.h"
#include "llvm/Support/Errc.h"
#include "llvm/Support/FormatAdapters.h"
#include "llvm/Support/FormatVariadic.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/ScopedPrinter.h"
#include <memory>
#include "Symbols.h"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Timer.h"
#include "llvm/ADT/DenseMap.h"
#include "llvm/ADT/STLExtras.h"
#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Threads.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/ADT/Twine.h"
#include "llvm/IR/DiagnosticInfo.h"
//===----------------------------------------------------------------------===//
#include "lld/Common/Filesystem.h"
-#include "lld/Common/Threads.h"
#include "llvm/Config/llvm-config.h"
#include "llvm/Support/FileOutputBuffer.h"
#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/Parallel.h"
#if LLVM_ON_UNIX
#include <unistd.h>
#endif
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
#include "lld/Common/TargetOptionsCommandFlags.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/SetVector.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/GlobPattern.h"
#include "llvm/Support/LEB128.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/TarWriter.h"
#include "llvm/Support/TargetSelect.h"
#include "Symbols.h"
#include "SyntheticSections.h"
#include "Writer.h"
-#include "lld/Common/Threads.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/Object/ELF.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/TimeProfiler.h"
#include "llvm/Support/xxhash.h"
#include <algorithm>
}
// Initially, we use hash values to partition sections.
- parallelForEach(sections, [&](InputSection *s) {
- s->eqClass[0] = xxHash64(s->data());
- });
+ parallelForEach(
+ sections, [&](InputSection *s) { s->eqClass[0] = xxHash64(s->data()); });
for (unsigned cnt = 0; cnt != 2; ++cnt) {
parallelForEach(sections, [&](InputSection *s) {
#include "Writer.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "llvm/ADT/STLExtras.h"
#include "llvm/ADT/StringRef.h"
#include "llvm/BinaryFormat/ELF.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/ErrorHandling.h"
#include "llvm/Support/FileSystem.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/Path.h"
#include <algorithm>
#include <cassert>
#include "Symbols.h"
#include "SyntheticSections.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "llvm/ADT/MapVector.h"
#include "llvm/ADT/SetVector.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/raw_ostream.h"
using namespace llvm;
#include "Target.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "llvm/BinaryFormat/Dwarf.h"
#include "llvm/Support/Compression.h"
#include "llvm/Support/MD5.h"
#include "llvm/Support/MathExtras.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/SHA1.h"
#include <regex>
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/SetOperations.h"
#include "llvm/ADT/StringExtras.h"
#include "llvm/Support/Endian.h"
#include "llvm/Support/LEB128.h"
#include "llvm/Support/MD5.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/TimeProfiler.h"
#include <cstdlib>
#include <thread>
#include "lld/Common/Filesystem.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "llvm/ADT/StringMap.h"
#include "llvm/ADT/StringSwitch.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/RandomNumberGenerator.h"
#include "llvm/Support/SHA1.h"
#include "llvm/Support/TimeProfiler.h"
+++ /dev/null
-//===- Threads.h ------------------------------------------------*- C++ -*-===//
-//
-// 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
-//
-//===----------------------------------------------------------------------===//
-//
-// LLD supports threads to distribute workloads to multiple cores. Using
-// multicore is most effective when more than one core are idle. At the
-// last step of a build, it is often the case that a linker is the only
-// active process on a computer. So, we are naturally interested in using
-// threads wisely to reduce latency to deliver results to users.
-//
-// That said, we don't want to do "too clever" things using threads.
-// Complex multi-threaded algorithms are sometimes extremely hard to
-// reason about and can easily mess up the entire design.
-//
-// Fortunately, when a linker links large programs (when the link time is
-// most critical), it spends most of the time to work on massive number of
-// small pieces of data of the same kind, and there are opportunities for
-// large parallelism there. Here are examples:
-//
-// - We have hundreds of thousands of input sections that need to be
-// copied to a result file at the last step of link. Once we fix a file
-// layout, each section can be copied to its destination and its
-// relocations can be applied independently.
-//
-// - We have tens of millions of small strings when constructing a
-// mergeable string section.
-//
-// For the cases such as the former, we can just use parallelForEach
-// instead of std::for_each (or a plain for loop). Because tasks are
-// completely independent from each other, we can run them in parallel
-// without any coordination between them. That's very easy to understand
-// and reason about.
-//
-// For the cases such as the latter, we can use parallel algorithms to
-// deal with massive data. We have to write code for a tailored algorithm
-// for each problem, but the complexity of multi-threading is isolated in
-// a single pass and doesn't affect the linker's overall design.
-//
-// The above approach seems to be working fairly well. As an example, when
-// linking Chromium (output size 1.6 GB), using 4 cores reduces latency to
-// 75% compared to single core (from 12.66 seconds to 9.55 seconds) on my
-// Ivy Bridge Xeon 2.8 GHz machine. Using 40 cores reduces it to 63% (from
-// 12.66 seconds to 7.95 seconds). Because of the Amdahl's law, the
-// speedup is not linear, but as you add more cores, it gets faster.
-//
-// On a final note, if you are trying to optimize, keep the axiom "don't
-// guess, measure!" in mind. Some important passes of the linker are not
-// that slow. For example, resolving all symbols is not a very heavy pass,
-// although it would be very hard to parallelize it. You want to first
-// identify a slow pass and then optimize it.
-//
-//===----------------------------------------------------------------------===//
-
-#ifndef LLD_COMMON_THREADS_H
-#define LLD_COMMON_THREADS_H
-
-#include "llvm/Support/Parallel.h"
-#include <functional>
-
-namespace lld {
-
-template <typename R, class FuncTy> void parallelForEach(R &&range, FuncTy fn) {
- if (llvm::parallel::strategy.ThreadsRequested != 1)
- for_each(llvm::parallel::par, std::begin(range), std::end(range), fn);
- else
- for_each(llvm::parallel::seq, std::begin(range), std::end(range), fn);
-}
-
-inline void parallelForEachN(size_t begin, size_t end,
- llvm::function_ref<void(size_t)> fn) {
- if (llvm::parallel::strategy.ThreadsRequested != 1)
- for_each_n(llvm::parallel::par, begin, end, fn);
- else
- for_each_n(llvm::parallel::seq, begin, end, fn);
-}
-
-template <typename R, class FuncTy> void parallelSort(R &&range, FuncTy fn) {
- if (llvm::parallel::strategy.ThreadsRequested != 1)
- sort(llvm::parallel::par, std::begin(range), std::end(range), fn);
- else
- sort(llvm::parallel::seq, std::begin(range), std::end(range), fn);
-}
-
-} // namespace lld
-
-#endif
});
std::vector<LayoutPass::SortKey> vec = decorate(atomRange);
- sort(llvm::parallel::par, vec.begin(), vec.end(),
- [&](const LayoutPass::SortKey &l, const LayoutPass::SortKey &r) -> bool {
- return compareAtoms(l, r, _customSorter);
- });
+ llvm::parallelSort(
+ vec,
+ [&](const LayoutPass::SortKey &l, const LayoutPass::SortKey &r) -> bool {
+ return compareAtoms(l, r, _customSorter);
+ });
LLVM_DEBUG(checkTransitivity(vec, _customSorter));
undecorate(atomRange, vec);
#include "lld/Common/Memory.h"
#include "lld/Common/Reproduce.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "lld/Common/Version.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Object/Wasm.h"
#include "llvm/Option/ArgList.h"
#include "llvm/Support/CommandLine.h"
#include "llvm/Support/Host.h"
+#include "llvm/Support/Parallel.h"
#include "llvm/Support/Path.h"
#include "llvm/Support/Process.h"
#include "llvm/Support/TarWriter.h"
#include "OutputSegment.h"
#include "WriterUtils.h"
#include "lld/Common/ErrorHandler.h"
-#include "lld/Common/Threads.h"
#include "llvm/ADT/Twine.h"
#include "llvm/Support/LEB128.h"
+#include "llvm/Support/Parallel.h"
#define DEBUG_TYPE "lld"
#include "lld/Common/ErrorHandler.h"
#include "lld/Common/Memory.h"
#include "lld/Common/Strings.h"
-#include "lld/Common/Threads.h"
#include "llvm/ADT/DenseSet.h"
#include "llvm/ADT/SmallSet.h"
#include "llvm/ADT/SmallVector.h"
#include "llvm/Support/Format.h"
#include "llvm/Support/FormatVariadic.h"
#include "llvm/Support/LEB128.h"
+#include "llvm/Support/Parallel.h"
#include <cstdarg>
#include <map>
namespace llvm {
namespace parallel {
-struct sequential_execution_policy {};
-struct parallel_execution_policy {};
-
-template <typename T>
-struct is_execution_policy
- : public std::integral_constant<
- bool, llvm::is_one_of<T, sequential_execution_policy,
- parallel_execution_policy>::value> {};
-
-constexpr sequential_execution_policy seq{};
-constexpr parallel_execution_policy par{};
// Strategy for the default executor used by the parallel routines provided by
// this file. It defaults to using all hardware threads and should be
#endif
-template <typename Iter>
-using DefComparator =
- std::less<typename std::iterator_traits<Iter>::value_type>;
-
} // namespace detail
+} // namespace parallel
-// sequential algorithm implementations.
-template <class Policy, class RandomAccessIterator,
- class Comparator = detail::DefComparator<RandomAccessIterator>>
-void sort(Policy policy, RandomAccessIterator Start, RandomAccessIterator End,
- const Comparator &Comp = Comparator()) {
- static_assert(is_execution_policy<Policy>::value,
- "Invalid execution policy!");
+template <class RandomAccessIterator,
+ class Comparator = std::less<
+ typename std::iterator_traits<RandomAccessIterator>::value_type>>
+void parallelSort(RandomAccessIterator Start, RandomAccessIterator End,
+ const Comparator &Comp = Comparator()) {
+#if LLVM_ENABLE_THREADS
+ if (parallel::strategy.ThreadsRequested != 1) {
+ parallel::detail::parallel_sort(Start, End, Comp);
+ return;
+ }
+#endif
llvm::sort(Start, End, Comp);
}
-template <class Policy, class IterTy, class FuncTy>
-void for_each(Policy policy, IterTy Begin, IterTy End, FuncTy Fn) {
- static_assert(is_execution_policy<Policy>::value,
- "Invalid execution policy!");
+template <class IterTy, class FuncTy>
+void parallelForEach(IterTy Begin, IterTy End, FuncTy Fn) {
+#if LLVM_ENABLE_THREADS
+ if (parallel::strategy.ThreadsRequested != 1) {
+ parallel::detail::parallel_for_each(Begin, End, Fn);
+ return;
+ }
+#endif
std::for_each(Begin, End, Fn);
}
-template <class Policy, class IndexTy, class FuncTy>
-void for_each_n(Policy policy, IndexTy Begin, IndexTy End, FuncTy Fn) {
- static_assert(is_execution_policy<Policy>::value,
- "Invalid execution policy!");
- for (IndexTy I = Begin; I != End; ++I)
- Fn(I);
-}
-
-// Parallel algorithm implementations, only available when LLVM_ENABLE_THREADS
-// is true.
+template <class FuncTy>
+void parallelForEachN(size_t Begin, size_t End, FuncTy Fn) {
#if LLVM_ENABLE_THREADS
-template <class RandomAccessIterator,
- class Comparator = detail::DefComparator<RandomAccessIterator>>
-void sort(parallel_execution_policy policy, RandomAccessIterator Start,
- RandomAccessIterator End, const Comparator &Comp = Comparator()) {
- detail::parallel_sort(Start, End, Comp);
+ if (parallel::strategy.ThreadsRequested != 1) {
+ parallel::detail::parallel_for_each_n(Begin, End, Fn);
+ return;
+ }
+#endif
+ for (size_t I = Begin; I != End; ++I)
+ Fn(I);
}
-template <class IterTy, class FuncTy>
-void for_each(parallel_execution_policy policy, IterTy Begin, IterTy End,
- FuncTy Fn) {
- detail::parallel_for_each(Begin, End, Fn);
+// Range wrappers.
+template <class RangeTy,
+ class Comparator = std::less<decltype(*std::begin(RangeTy()))>>
+void parallelSort(RangeTy &&R, const Comparator &Comp = Comparator()) {
+ parallelSort(std::begin(R), std::end(R), Comp);
}
-template <class IndexTy, class FuncTy>
-void for_each_n(parallel_execution_policy policy, IndexTy Begin, IndexTy End,
- FuncTy Fn) {
- detail::parallel_for_each_n(Begin, End, Fn);
+template <class RangeTy, class FuncTy>
+void parallelForEach(RangeTy &&R, FuncTy Fn) {
+ parallelForEach(std::begin(R), std::end(R), Fn);
}
-#endif
-} // namespace parallel
} // namespace llvm
#endif // LLVM_SUPPORT_PARALLEL_H
for (auto &i : array)
i = dist(randEngine);
- sort(parallel::par, std::begin(array), std::end(array));
+ parallelSort(std::begin(array), std::end(array));
ASSERT_TRUE(llvm::is_sorted(array));
}
// writing.
uint32_t range[2050];
std::fill(range, range + 2050, 1);
- for_each_n(parallel::par, 0, 2049, [&range](size_t I) { ++range[I]; });
+ parallelForEachN(0, 2049, [&range](size_t I) { ++range[I]; });
uint32_t expected[2049];
std::fill(expected, expected + 2049, 2);
// Process a list of operations in parallel.
std::vector<Operation *> opsToProcess = ...;
-llvm::for_each_n(llvm::parallel::par, 0, opsToProcess.size(),
- [&](size_t i) {
+llvm::parallelForEachN(0, opsToProcess.size(), [&](size_t i) {
// Notify the handler that we are processing the i'th operation.
handler.setOrderIDForThread(i);
auto *op = opsToProcess[i];
// An atomic failure variable for the async executors.
std::atomic<bool> passFailed(false);
- llvm::parallel::for_each(
- llvm::parallel::par, asyncExecutors.begin(),
+ llvm::parallelForEach(
+ asyncExecutors.begin(),
std::next(asyncExecutors.begin(),
std::min(asyncExecutors.size(), opAMPairs.size())),
[&](MutableArrayRef<OpPassManager> pms) {
// be reworked.
if (context->isMultithreadingEnabled()) {
ParallelDiagnosticHandler canonicalizationHandler(context);
- llvm::parallel::for_each_n(
- llvm::parallel::par, /*Begin=*/size_t(0),
- /*End=*/nodesToCanonicalize.size(), [&](size_t index) {
+ llvm::parallelForEachN(
+ /*Begin=*/0, /*End=*/nodesToCanonicalize.size(), [&](size_t index) {
// Set the order for this thread so that diagnostics will be properly
// ordered.
canonicalizationHandler.setOrderIDForThread(index);
projects / platform / upstream / llvm.git / commitdiff