From: Zachary Turner <zturner@google.com>
Date: Thu, 11 May 2017 00:03:52 +0000 (+0000)
Subject: [Support] Move Parallel algorithms from LLD to LLVM.
X-Git-Url: https://granicus.if.org/sourcecode?a=commitdiff_plain;h=3c1ec57f40978027af0ba6118b11c2ee9e395ef5;p=llvm

[Support] Move Parallel algorithms from LLD to LLVM.

Differential Revision: https://reviews.llvm.org/D33024

git-svn-id: https://llvm.org/svn/llvm-project/llvm/trunk@302748 91177308-0d34-0410-b5e6-96231b3b80d8
---

diff --git a/include/llvm/Support/Parallel.h b/include/llvm/Support/Parallel.h
new file mode 100644
index 00000000000..aca972eb490
--- /dev/null
+++ b/include/llvm/Support/Parallel.h
@@ -0,0 +1,251 @@
+//===- llvm/Support/Parallel.h - Parallel algorithms ----------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#ifndef LLVM_SUPPORT_PARALLEL_H
+#define LLVM_SUPPORT_PARALLEL_H
+
+#include "llvm/ADT/STLExtras.h"
+#include "llvm/Config/llvm-config.h"
+#include "llvm/Support/MathExtras.h"
+
+#include <algorithm>
+#include <condition_variable>
+#include <functional>
+#include <mutex>
+
+#if defined(_MSC_VER) && LLVM_ENABLE_THREADS
+#pragma warning(push)
+#pragma warning(disable : 4530)
+#include <concrt.h>
+#include <ppl.h>
+#pragma warning(pop)
+#endif
+
+namespace llvm {
+
+namespace detail {
+class Latch {
+  uint32_t Count;
+  mutable std::mutex Mutex;
+  mutable std::condition_variable Cond;
+
+public:
+  explicit Latch(uint32_t count = 0) : Count(Count) {}
+  ~Latch() { sync(); }
+
+  void inc() {
+    std::unique_lock<std::mutex> lock(Mutex);
+    ++Count;
+  }
+
+  void dec() {
+    std::unique_lock<std::mutex> lock(Mutex);
+    if (--Count == 0)
+      Cond.notify_all();
+  }
+
+  void sync() const {
+    std::unique_lock<std::mutex> lock(Mutex);
+    Cond.wait(lock, [&] { return Count == 0; });
+  }
+};
+
+class TaskGroup {
+  Latch L;
+
+public:
+  void spawn(std::function<void()> f);
+
+  void sync() const { L.sync(); }
+};
+}
+
+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{};
+
+namespace detail {
+
+#if LLVM_ENABLE_THREADS
+
+#if defined(_MSC_VER)
+template <class RandomAccessIterator, class Comparator>
+void parallel_sort(RandomAccessIterator Start, RandomAccessIterator End,
+                   const Comparator &Comp) {
+  concurrency::parallel_sort(Start, End, Comp);
+}
+template <class IterTy, class FuncTy>
+void parallel_for_each(IterTy Begin, IterTy End, FuncTy Fn) {
+  concurrency::parallel_for_each(Begin, End, Fn);
+}
+
+template <class IndexTy, class FuncTy>
+void parallel_for_each_n(IndexTy Begin, IndexTy End, FuncTy Fn) {
+  concurrency::parallel_for(Begin, End, Fn);
+}
+
+#else
+const ptrdiff_t MinParallelSize = 1024;
+
+/// \brief Inclusive median.
+template <class RandomAccessIterator, class Comparator>
+RandomAccessIterator medianOf3(RandomAccessIterator Start,
+                               RandomAccessIterator End,
+                               const Comparator &Comp) {
+  RandomAccessIterator Mid = Start + (std::distance(Start, End) / 2);
+  return Comp(*Start, *(End - 1))
+             ? (Comp(*Mid, *(End - 1)) ? (Comp(*Start, *Mid) ? Mid : Start)
+                                       : End - 1)
+             : (Comp(*Mid, *Start) ? (Comp(*(End - 1), *Mid) ? Mid : End - 1)
+                                   : Start);
+}
+
+template <class RandomAccessIterator, class Comparator>
+void parallel_quick_sort(RandomAccessIterator Start, RandomAccessIterator End,
+                         const Comparator &Comp, TaskGroup &TG, size_t Depth) {
+  // Do a sequential sort for small inputs.
+  if (std::distance(Start, End) < detail::MinParallelSize || Depth == 0) {
+    std::sort(Start, End, Comp);
+    return;
+  }
+
+  // Partition.
+  auto Pivot = medianOf3(Start, End, Comp);
+  // Move Pivot to End.
+  std::swap(*(End - 1), *Pivot);
+  Pivot = std::partition(Start, End - 1, [&Comp, End](decltype(*Start) V) {
+    return Comp(V, *(End - 1));
+  });
+  // Move Pivot to middle of partition.
+  std::swap(*Pivot, *(End - 1));
+
+  // Recurse.
+  TG.spawn([=, &Comp, &TG] {
+    parallel_quick_sort(Start, Pivot, Comp, TG, Depth - 1);
+  });
+  parallel_quick_sort(Pivot + 1, End, Comp, TG, Depth - 1);
+}
+
+template <class RandomAccessIterator, class Comparator>
+void parallel_sort(RandomAccessIterator Start, RandomAccessIterator End,
+                   const Comparator &Comp) {
+  TaskGroup TG;
+  parallel_quick_sort(Start, End, Comp, TG,
+                      llvm::Log2_64(std::distance(Start, End)) + 1);
+}
+
+template <class IterTy, class FuncTy>
+void parallel_for_each(IterTy Begin, IterTy End, FuncTy Fn) {
+  // TaskGroup has a relatively high overhead, so we want to reduce
+  // the number of spawn() calls. We'll create up to 1024 tasks here.
+  // (Note that 1024 is an arbitrary number. This code probably needs
+  // improving to take the number of available cores into account.)
+  ptrdiff_t TaskSize = std::distance(Begin, End) / 1024;
+  if (TaskSize == 0)
+    TaskSize = 1;
+
+  TaskGroup TG;
+  while (TaskSize <= std::distance(Begin, End)) {
+    TG.spawn([=, &Fn] { std::for_each(Begin, Begin + TaskSize, Fn); });
+    Begin += TaskSize;
+  }
+  TG.spawn([=, &Fn] { std::for_each(Begin, End, Fn); });
+}
+
+template <class IndexTy, class FuncTy>
+void parallel_for_each_n(IndexTy Begin, IndexTy End, FuncTy Fn) {
+  ptrdiff_t TaskSize = (End - Begin) / 1024;
+  if (TaskSize == 0)
+    TaskSize = 1;
+
+  TaskGroup TG;
+  IndexTy I = Begin;
+  for (; I + TaskSize < End; I += TaskSize) {
+    TG.spawn([=, &Fn] {
+      for (IndexTy J = I, E = I + TaskSize; J != E; ++J)
+        Fn(J);
+    });
+  }
+  TG.spawn([=, &Fn] {
+    for (IndexTy J = I; J < End; ++J)
+      Fn(J);
+  });
+}
+
+#endif
+
+#endif
+
+template <typename Iter>
+using DefComparator =
+    std::less<typename std::iterator_traits<Iter>::value_type>;
+
+} // namespace detail
+
+// 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!");
+  std::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!");
+  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.
+#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);
+}
+
+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 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
diff --git a/lib/Support/CMakeLists.txt b/lib/Support/CMakeLists.txt
index 63c440037c2..83376284548 100644
--- a/lib/Support/CMakeLists.txt
+++ b/lib/Support/CMakeLists.txt
@@ -81,6 +81,7 @@ add_llvm_library(LLVMSupport
   MD5.cpp
   NativeFormatting.cpp
   Options.cpp
+  Parallel.cpp
   PluginLoader.cpp
   PrettyStackTrace.cpp
   RandomNumberGenerator.cpp
diff --git a/lib/Support/Parallel.cpp b/lib/Support/Parallel.cpp
new file mode 100644
index 00000000000..04fb1c95533
--- /dev/null
+++ b/lib/Support/Parallel.cpp
@@ -0,0 +1,136 @@
+//===- llvm/Support/Parallel.cpp - Parallel algorithms --------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/Parallel.h"
+#include "llvm/Config/llvm-config.h"
+
+#include <atomic>
+#include <stack>
+#include <thread>
+
+using namespace llvm;
+
+namespace {
+
+/// \brief An abstract class that takes closures and runs them asynchronously.
+class Executor {
+public:
+  virtual ~Executor() = default;
+  virtual void add(std::function<void()> func) = 0;
+
+  static Executor *getDefaultExecutor();
+};
+
+#if !LLVM_ENABLE_THREADS
+class SyncExecutor : public Executor {
+public:
+  virtual void add(std::function<void()> F) { F(); }
+};
+
+Executor *Executor::getDefaultExecutor() {
+  static SyncExecutor Exec;
+  return &Exec;
+}
+
+#elif defined(_MSC_VER)
+/// \brief An Executor that runs tasks via ConcRT.
+class ConcRTExecutor : public Executor {
+  struct Taskish {
+    Taskish(std::function<void()> Task) : Task(Task) {}
+
+    std::function<void()> Task;
+
+    static void run(void *P) {
+      Taskish *Self = static_cast<Taskish *>(P);
+      Self->Task();
+      concurrency::Free(Self);
+    }
+  };
+
+public:
+  virtual void add(std::function<void()> F) {
+    Concurrency::CurrentScheduler::ScheduleTask(
+        Taskish::run, new (concurrency::Alloc(sizeof(Taskish))) Taskish(F));
+  }
+};
+
+Executor *Executor::getDefaultExecutor() {
+  static ConcRTExecutor exec;
+  return &exec;
+}
+
+#else
+/// \brief An implementation of an Executor that runs closures on a thread pool
+///   in filo order.
+class ThreadPoolExecutor : public Executor {
+public:
+  explicit ThreadPoolExecutor(
+      unsigned ThreadCount = std::thread::hardware_concurrency())
+      : Done(ThreadCount) {
+    // Spawn all but one of the threads in another thread as spawning threads
+    // can take a while.
+    std::thread([&, ThreadCount] {
+      for (size_t i = 1; i < ThreadCount; ++i) {
+        std::thread([=] { work(); }).detach();
+      }
+      work();
+    }).detach();
+  }
+
+  ~ThreadPoolExecutor() override {
+    std::unique_lock<std::mutex> Lock(Mutex);
+    Stop = true;
+    Lock.unlock();
+    Cond.notify_all();
+    // Wait for ~Latch.
+  }
+
+  void add(std::function<void()> F) override {
+    std::unique_lock<std::mutex> Lock(Mutex);
+    WorkStack.push(F);
+    Lock.unlock();
+    Cond.notify_one();
+  }
+
+private:
+  void work() {
+    while (true) {
+      std::unique_lock<std::mutex> Lock(Mutex);
+      Cond.wait(Lock, [&] { return Stop || !WorkStack.empty(); });
+      if (Stop)
+        break;
+      auto Task = WorkStack.top();
+      WorkStack.pop();
+      Lock.unlock();
+      Task();
+    }
+    Done.dec();
+  }
+
+  std::atomic<bool> Stop{false};
+  std::stack<std::function<void()>> WorkStack;
+  std::mutex Mutex;
+  std::condition_variable Cond;
+  Latch Done;
+};
+
+Executor *Executor::getDefaultExecutor() {
+  static ThreadPoolExecutor exec;
+  return &exec;
+}
+#endif
+}
+
+void detail::TaskGroup::spawn(std::function<void()> F) {
+  L.inc();
+  Executor::getDefaultExecutor()->add([&, F] {
+    F();
+    L.dec();
+  });
+}
diff --git a/unittests/Support/CMakeLists.txt b/unittests/Support/CMakeLists.txt
index 1f677100dce..f8d3c1c9a8c 100644
--- a/unittests/Support/CMakeLists.txt
+++ b/unittests/Support/CMakeLists.txt
@@ -36,6 +36,7 @@ add_llvm_unittest(SupportTests
   MemoryBufferTest.cpp
   MemoryTest.cpp
   NativeFormatTests.cpp
+  ParallelTest.cpp
   Path.cpp
   ProcessTest.cpp
   ProgramTest.cpp
diff --git a/unittests/Support/ParallelTest.cpp b/unittests/Support/ParallelTest.cpp
new file mode 100644
index 00000000000..f381631ac3a
--- /dev/null
+++ b/unittests/Support/ParallelTest.cpp
@@ -0,0 +1,48 @@
+//===- llvm/unittest/Support/ParallelTest.cpp -----------------------------===//
+//
+//                     The LLVM Compiler Infrastructure
+//
+// This file is distributed under the University of Illinois Open Source
+// License. See LICENSE.TXT for details.
+//
+//===----------------------------------------------------------------------===//
+///
+/// \file
+/// \brief Parallel.h unit tests.
+///
+//===----------------------------------------------------------------------===//
+
+#include "llvm/Support/Parallel.h"
+#include "gtest/gtest.h"
+#include <array>
+#include <random>
+
+uint32_t array[1024 * 1024];
+
+using namespace llvm;
+
+TEST(Parallel, sort) {
+  std::mt19937 randEngine;
+  std::uniform_int_distribution<uint32_t> dist;
+
+  for (auto &i : array)
+    i = dist(randEngine);
+
+  sort(parallel::par, std::begin(array), std::end(array));
+  ASSERT_TRUE(std::is_sorted(std::begin(array), std::end(array)));
+}
+
+TEST(Parallel, parallel_for) {
+  // We need to test the case with a TaskSize > 1. We are white-box testing
+  // here. The TaskSize is calculated as (End - Begin) / 1024 at the time of
+  // writing.
+  uint32_t range[2050];
+  std::fill(range, range + 2050, 1);
+  for_each_n(parallel::par, 0, 2049, [&range](size_t I) { ++range[I]; });
+
+  uint32_t expected[2049];
+  std::fill(expected, expected + 2049, 2);
+  ASSERT_TRUE(std::equal(range, range + 2049, expected));
+  // Check that we don't write past the end of the requested range.
+  ASSERT_EQ(range[2049], 1u);
+}