1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
|
//===- llvm/Support/Parallel.cpp - Parallel algorithms --------------------===//
//
// 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
//
//===----------------------------------------------------------------------===//
#include "llvm/Support/Parallel.h"
#include "llvm/Config/llvm-config.h"
#if LLVM_ENABLE_THREADS
#include "llvm/Support/Threading.h"
#include <atomic>
#include <stack>
#include <thread>
namespace llvm {
namespace parallel {
namespace detail {
namespace {
/// 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 defined(_MSC_VER)
/// 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
/// An implementation of an Executor that runs closures on a thread pool
/// in filo order.
class ThreadPoolExecutor : public Executor {
public:
explicit ThreadPoolExecutor(unsigned ThreadCount = 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;
parallel::detail::Latch Done;
};
Executor *Executor::getDefaultExecutor() {
static ThreadPoolExecutor exec;
return &exec;
}
#endif
}
static std::atomic<int> TaskGroupInstances;
// Latch::sync() called by the dtor may cause one thread to block. If is a dead
// lock if all threads in the default executor are blocked. To prevent the dead
// lock, only allow the first TaskGroup to run tasks parallelly. In the scenario
// of nested parallel_for_each(), only the outermost one runs parallelly.
TaskGroup::TaskGroup() : Parallel(TaskGroupInstances++ == 0) {}
TaskGroup::~TaskGroup() { --TaskGroupInstances; }
void TaskGroup::spawn(std::function<void()> F) {
if (Parallel) {
L.inc();
Executor::getDefaultExecutor()->add([&, F] {
F();
L.dec();
});
} else {
F();
}
}
} // namespace detail
} // namespace parallel
} // namespace llvm
#endif // LLVM_ENABLE_THREADS
|
