forked from progschj/ThreadPool
-
Notifications
You must be signed in to change notification settings - Fork 0
Expand file tree
/
Copy pathThreadPool.h
More file actions
232 lines (206 loc) · 7.35 KB
/
Copy pathThreadPool.h
File metadata and controls
232 lines (206 loc) · 7.35 KB
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
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
// Copyright (c) 2012 Jakob Progsch, Václav Zeman
// Copyright (c) 2021 Chengkun Cao
//
// This software is provided 'as-is', without any express or implied
// warranty. In no event will the authors be held liable for any damages
// arising from the use of this software.
//
// Permission is granted to anyone to use this software for any purpose,
// including commercial applications, and to alter it and redistribute it
// freely, subject to the following restrictions:
//
// 1. The origin of this software must not be misrepresented; you must not
// claim that you wrote the original software. If you use this software
// in a product, an acknowledgment in the product documentation would be
// appreciated but is not required.
//
// 2. Altered source versions must be plainly marked as such, and must not be
// misrepresented as being the original software.
//
// 3. This notice may not be removed or altered from any source
// distribution.
//
#pragma once
#include <vector>
#include <queue>
#include <unordered_map>
#include <memory>
#include <thread>
#include <mutex>
#include <condition_variable>
#include <future>
#include <functional>
#include <stdexcept>
#include <string>
#include <iostream>
#if defined(WIN32) || defined(_WIN32) || defined(__WIN32__) || defined(__NT__) || defined(WIN64) || defined(_WIN64)
//define something for Windows (32-bit and 64-bit, this part is common)
#include "windows_cpu.h"
#elif __APPLE__
#include <TargetConditionals.h>
#if TARGET_IPHONE_SIMULATOR
// iOS Simulator
#elif TARGET_OS_MACCATALYST
// Mac's Catalyst (ports iOS API into Mac, like UIKit).
#include "macos_cpu.h"
#elif TARGET_OS_IPHONE
// iOS device
#elif TARGET_OS_MAC
// Other kinds of Mac OS
#include "macos_cpu.h"
#else
# error "Unknown Apple platform"
#endif
#elif __linux__
// linux
#elif __unix__ // all unices not caught above
// Unix
#elif defined(_POSIX_VERSION)
// POSIX
#else
# error "Unknown compiler"
#endif
class ThreadPool {
public:
ThreadPool(size_t);
~ThreadPool();
void pool_bind_core(std::vector<int> core_ids);
template<class F, class... Args>
auto enqueue(F&& f, Args&&... args)
-> std::future<typename std::result_of<F(Args...)>::type>;
template<class F, class... Args>
auto strict_enqueue(int core_id, F&& f, Args&&... args)
-> std::future<typename std::result_of<F(Args...)>::type>;
private:
// need to keep track of threads so we can join them
std::vector< std::thread > workers;
std::unordered_map<int, int> core_ids_to_worker_index_map;
// the task queue
std::queue< std::function<void()> > tasks;
std::unordered_map<int, std::queue<std::function<void()>> > strict_tasks;
// synchronization
std::mutex queue_mutex;
std::condition_variable condition;
bool stop;
};
// the constructor just launches some amount of workers
inline ThreadPool::ThreadPool(size_t threads)
: stop(false)
{
for(size_t i = 0;i<threads;++i)
{
workers.emplace_back(
[this, i]
{
for(;;)
{
std::function<void()> task;
{
std::unique_lock<std::mutex> lock(this->queue_mutex);
this->condition.wait(lock,
[this, i]{ return this->stop || !this->tasks.empty() || !this->strict_tasks[i].empty(); });
if(this->stop && this->tasks.empty() && this->strict_tasks[i].empty())
return;
if(!this->tasks.empty())
{
task = std::move(this->tasks.front());
this->tasks.pop();
//std::cout << "tasks" << std::endl;
}
else if(!this->strict_tasks[i].empty())
{
task = std::move(this->strict_tasks[i].front());
this->strict_tasks[i].pop();
//std::cout << "strict_tasks" << std::endl;
}
else
{
//std::cout << "none" << i << std::endl;
continue;
}
}
task();
}
}
);
}
}
inline void ThreadPool::pool_bind_core(std::vector<int> core_ids)
{
if(core_ids.size() != this->workers.size())
{
auto msg = std::string("Wrong core_ids list size ") + std::to_string(core_ids.size());
throw std::runtime_error(msg);
}
for(int i=0;i<workers.size();i++)
{
const int id = core_ids[i];
core_ids_to_worker_index_map.emplace(id, i);
strict_tasks.emplace(id, std::queue<std::function<void()>>());
cpu_set_t cpuset;
CPU_ZERO(&cpuset);
CPU_SET(id, &cpuset);
int rc = pthread_setaffinity_np(workers[i].native_handle(), sizeof(cpu_set_t), &cpuset);
if (rc != 0) {
auto msg = std::string("Error calling pthread_setaffinity_np: ") + std::to_string(rc) + "\n";
throw std::runtime_error(msg);
}
}
}
// add new work item to the pool
template<class F, class... Args>
auto ThreadPool::enqueue(F&& f, Args&&... args)
-> std::future<typename std::result_of<F(Args...)>::type>
{
using return_type = typename std::result_of<F(Args...)>::type;
auto task = std::make_shared< std::packaged_task<return_type()> >(
std::bind(std::forward<F>(f), std::forward<Args>(args)...)
);
std::future<return_type> res = task->get_future();
{
std::unique_lock<std::mutex> lock(queue_mutex);
// don't allow enqueueing after stopping the pool
if(stop)
throw std::runtime_error("enqueue on stopped ThreadPool");
tasks.emplace([task](){ (*task)(); });
}
condition.notify_one();
return res;
}
// add new work item to the pool, with strict bind core id
template<class F, class... Args>
auto ThreadPool::strict_enqueue(int core_id, F&& f, Args&&... args)
-> std::future<typename std::result_of<F(Args...)>::type>
{
using return_type = typename std::result_of<F(Args...)>::type;
if(this->core_ids_to_worker_index_map.find(core_id) == this->core_ids_to_worker_index_map.end())
throw std::runtime_error("enqueue core id not found!");
int worker_id = core_ids_to_worker_index_map[core_id];
auto task = std::make_shared< std::packaged_task<return_type()> >(
std::bind(std::forward<F>(f), std::forward<Args>(args)...)
);
std::future<return_type> res = task->get_future();
{
std::unique_lock<std::mutex> lock(queue_mutex);
// don't allow enqueueing after stopping the pool
if(stop)
throw std::runtime_error("enqueue on stopped ThreadPool");
strict_tasks[worker_id].emplace([task](){ (*task)(); });
}
condition.notify_all();
return res;
}
// the destructor joins all threads
inline ThreadPool::~ThreadPool()
{
{
std::unique_lock<std::mutex> lock(queue_mutex);
stop = true;
}
condition.notify_all();
for(std::thread &worker: workers)
{
if(worker.joinable())
worker.join();
}
}