[Support] Move LLD's parallel algorithm wrappers to support

Essentially takes the lld/Common/Threads.h wrappers and moves them to
the llvm/Support/Paralle.h algorithm header.

The changes are:
- Remove policy parameter, since all clients use `par`.
- Rename the methods to `parallelSort` etc to match LLVM style, since
  they are no longer C++17 pstl compatible.
- Move algorithms from llvm::parallel:: to llvm::, since they have
  "parallel" in the name and are no longer overloads of the regular
  algorithms.
- Add range overloads
- Use the sequential algorithm directly when 1 thread is requested
  (skips task grouping)
- Fix the index type of parallelForEachN to size_t. Nobody in LLVM was
  using any other parameter, and it made overload resolution hard for
  for_each_n(par, 0, foo.size(), ...) because 0 is int, not size_t.

Remove Threads.h and update LLD for that.

This is a prerequisite for parallel public symbol processing in the PDB
library, which is in LLVM.

Reviewed By: MaskRay, aganea

Differential Revision: https://reviews.llvm.org/D79390

lld/COFF/Driver.cpp

@@ -21,7 +21,6 @@
 #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"
@@ -39,6 +38,7 @@
 #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"

lld/COFF/ICF.cpp

@@ -21,7 +21,6 @@
 #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"

lld/COFF/LLDMapFile.cpp

@@ -23,7 +23,7 @@
 #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;

lld/COFF/MapFile.cpp

@@ -32,8 +32,8 @@
 #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"
 

lld/COFF/PDB.cpp

@@ -16,7 +16,6 @@
 #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"
@@ -57,6 +56,7 @@
 #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>

lld/COFF/Writer.cpp

@@ -17,7 +17,6 @@
 #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"

lld/Common/ErrorHandler.cpp

@@ -8,7 +8,7 @@
 
 #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"

lld/Common/Filesystem.cpp

@@ -11,10 +11,10 @@
 //===----------------------------------------------------------------------===//
 
 #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

lld/ELF/Driver.cpp

@@ -43,7 +43,6 @@
 #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"
@@ -53,6 +52,7 @@
 #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"

lld/ELF/ICF.cpp

@@ -80,10 +80,10 @@
 #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>
@@ -467,9 +467,8 @@ template <class ELFT> void ICF<ELFT>::run() {
   }
 
   // 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) {

lld/ELF/LinkerScript.cpp

@@ -21,7 +21,6 @@
 #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"
@@ -29,6 +28,7 @@
 #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>

lld/ELF/MapFile.cpp

@@ -26,9 +26,9 @@
 #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;

lld/ELF/OutputSections.cpp

@@ -14,11 +14,11 @@
 #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>
 

lld/ELF/SyntheticSections.cpp

@@ -26,7 +26,6 @@
 #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"
@@ -37,6 +36,7 @@
 #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>

lld/ELF/Writer.cpp

@@ -22,9 +22,9 @@
 #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"

lld/include/lld/Common/Threads.h

@@ -1,90 +0,0 @@
-//===- 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

lld/lib/ReaderWriter/MachO/LayoutPass.cpp

@@ -461,10 +461,11 @@ llvm::Error LayoutPass::perform(SimpleFile &mergedFile) {
   });
 
   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);
 

lld/wasm/Driver.cpp

@@ -19,7 +19,6 @@
 #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"
@@ -27,6 +26,7 @@
 #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"

lld/wasm/OutputSections.cpp

@@ -12,9 +12,9 @@
 #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"
 

lld/wasm/Writer.cpp

@@ -20,7 +20,6 @@
 #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"
@@ -31,6 +30,7 @@
 #include "llvm/Support/Format.h"
 #include "llvm/Support/FormatVariadic.h"
 #include "llvm/Support/LEB128.h"
+#include "llvm/Support/Parallel.h"
 
 #include <cstdarg>
 #include <map>

llvm/include/llvm/Support/Parallel.h

@@ -22,17 +22,6 @@
 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
@@ -169,61 +158,58 @@ void parallel_for_each_n(IndexTy Begin, IndexTy End, FuncTy Fn) {
 
 #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)
+template <class FuncTy>
+void parallelForEachN(size_t Begin, size_t End, FuncTy Fn) {
+#if LLVM_ENABLE_THREADS
+  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);
 }
 
-// Parallel algorithm implementations, only available when LLVM_ENABLE_THREADS
-// is true.
-#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);
+// 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 IterTy, class FuncTy>
-void for_each(parallel_execution_policy policy, IterTy Begin, IterTy End,
-              FuncTy Fn) {
-  detail::parallel_for_each(Begin, End, Fn);
+template <class RangeTy, class FuncTy>
+void parallelForEach(RangeTy &&R, FuncTy Fn) {
+  parallelForEach(std::begin(R), std::end(R), Fn);
 }
 
-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);
-}
-#endif
-
-} // namespace parallel
 } // namespace llvm
 
 #endif // LLVM_SUPPORT_PARALLEL_H

llvm/unittests/Support/ParallelTest.cpp

@@ -30,7 +30,7 @@ TEST(Parallel, sort) {
   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));
 }
 
@@ -40,7 +40,7 @@ TEST(Parallel, parallel_for) {
   // 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);

mlir/docs/Diagnostics.md

@@ -390,8 +390,7 @@ ParallelDiagnosticHandler handler(context);
 
 // 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];

mlir/lib/Pass/Pass.cpp

@@ -493,8 +493,8 @@ void OpToOpPassAdaptor::runOnOperationAsyncImpl() {
 
   // 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) {

mlir/lib/Transforms/Inliner.cpp

@@ -496,9 +496,8 @@ static void canonicalizeSCC(CallGraph &cg, CGUseList &useList,
   // 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);