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 99 100 101 102 103 104 105 106 107 108 109 110 111 112 113 114 115 116 117 118 119 120 121 122 123 124 125 126 127 128 129 130 131 132 133 134 135 136 137 138 139 140 141 142 143 144 145 146 147 148 149 150 151 152 153 154 155 156 157 158 159 160 161 162 163 164 165 166 167 168 169 170 171 172 173 174 175 176 177 178 179 180 181 182 183 184 185 186 187 188 189 190 191 192 193 194 195 196 197 198 199 200 201 202 203 204 205 206 207 208 209 210 211 212 213 214 215 216 217 218 219 220 221 222 223 224 225 226 227 228 229 230 231 232 233 234 235 236 237 238 239 240 241 242 243 244 245 246 247 248 249 250 251 252 253 254 255 256 257 258 259 260 261 262 263 264 265 266 267 268 269 270 271 272 273 274 275 276 277 278 279 280 281 282 283 284 285 286 287 288 289
|
#include <boost/asio/execution.hpp>
#include <boost/asio/static_thread_pool.hpp>
#include <algorithm>
#include <condition_variable>
#include <memory>
#include <mutex>
#include <queue>
#include <thread>
#include <numeric>
using boost::asio::static_thread_pool;
namespace execution = boost::asio::execution;
// A fixed-size thread pool used to implement fork/join semantics. Functions
// are scheduled using a simple FIFO queue. Implementing work stealing, or
// using a queue based on atomic operations, are left as tasks for the reader.
class fork_join_pool
{
public:
// The constructor starts a thread pool with the specified number of threads.
// Note that the thread_count is not a fixed limit on the pool's concurrency.
// Additional threads may temporarily be added to the pool if they join a
// fork_executor.
explicit fork_join_pool(
std::size_t thread_count = std::max(std::thread::hardware_concurrency(), 1u) * 2)
: use_count_(1),
threads_(thread_count)
{
try
{
// Ask each thread in the pool to dequeue and execute functions until
// it is time to shut down, i.e. the use count is zero.
for (thread_count_ = 0; thread_count_ < thread_count; ++thread_count_)
{
threads_.executor().execute(
[this]
{
std::unique_lock<std::mutex> lock(mutex_);
while (use_count_ > 0)
if (!execute_next(lock))
condition_.wait(lock);
});
}
}
catch (...)
{
stop_threads();
threads_.wait();
throw;
}
}
// The destructor waits for the pool to finish executing functions.
~fork_join_pool()
{
stop_threads();
threads_.wait();
}
private:
friend class fork_executor;
// The base for all functions that are queued in the pool.
struct function_base
{
std::shared_ptr<std::size_t> work_count_;
void (*execute_)(std::shared_ptr<function_base>& p);
};
// Execute the next function from the queue, if any. Returns true if a
// function was executed, and false if the queue was empty.
bool execute_next(std::unique_lock<std::mutex>& lock)
{
if (queue_.empty())
return false;
auto p(queue_.front());
queue_.pop();
lock.unlock();
execute(lock, p);
return true;
}
// Execute a function and decrement the outstanding work.
void execute(std::unique_lock<std::mutex>& lock,
std::shared_ptr<function_base>& p)
{
std::shared_ptr<std::size_t> work_count(std::move(p->work_count_));
try
{
p->execute_(p);
lock.lock();
do_work_finished(work_count);
}
catch (...)
{
lock.lock();
do_work_finished(work_count);
throw;
}
}
// Increment outstanding work.
void do_work_started(const std::shared_ptr<std::size_t>& work_count) noexcept
{
if (++(*work_count) == 1)
++use_count_;
}
// Decrement outstanding work. Notify waiting threads if we run out.
void do_work_finished(const std::shared_ptr<std::size_t>& work_count) noexcept
{
if (--(*work_count) == 0)
{
--use_count_;
condition_.notify_all();
}
}
// Dispatch a function, executing it immediately if the queue is already
// loaded. Otherwise adds the function to the queue and wakes a thread.
void do_execute(std::shared_ptr<function_base> p,
const std::shared_ptr<std::size_t>& work_count)
{
std::unique_lock<std::mutex> lock(mutex_);
if (queue_.size() > thread_count_ * 16)
{
do_work_started(work_count);
lock.unlock();
execute(lock, p);
}
else
{
queue_.push(p);
do_work_started(work_count);
condition_.notify_one();
}
}
// Ask all threads to shut down.
void stop_threads()
{
std::lock_guard<std::mutex> lock(mutex_);
--use_count_;
condition_.notify_all();
}
std::mutex mutex_;
std::condition_variable condition_;
std::queue<std::shared_ptr<function_base>> queue_;
std::size_t use_count_;
std::size_t thread_count_;
static_thread_pool threads_;
};
// A class that satisfies the Executor requirements. Every function or piece of
// work associated with a fork_executor is part of a single, joinable group.
class fork_executor
{
public:
fork_executor(fork_join_pool& ctx)
: context_(ctx),
work_count_(std::make_shared<std::size_t>(0))
{
}
fork_join_pool& query(execution::context_t) const noexcept
{
return context_;
}
template <class Func>
void execute(Func f) const
{
auto p(std::make_shared<function<Func>>(std::move(f), work_count_));
context_.do_execute(p, work_count_);
}
friend bool operator==(const fork_executor& a,
const fork_executor& b) noexcept
{
return a.work_count_ == b.work_count_;
}
friend bool operator!=(const fork_executor& a,
const fork_executor& b) noexcept
{
return a.work_count_ != b.work_count_;
}
// Block until all work associated with the executor is complete. While it is
// waiting, the thread may be borrowed to execute functions from the queue.
void join() const
{
std::unique_lock<std::mutex> lock(context_.mutex_);
while (*work_count_ > 0)
if (!context_.execute_next(lock))
context_.condition_.wait(lock);
}
private:
template <class Func>
struct function : fork_join_pool::function_base
{
explicit function(Func f, const std::shared_ptr<std::size_t>& w)
: function_(std::move(f))
{
work_count_ = w;
execute_ = [](std::shared_ptr<fork_join_pool::function_base>& p)
{
Func tmp(std::move(static_cast<function*>(p.get())->function_));
p.reset();
tmp();
};
}
Func function_;
};
fork_join_pool& context_;
std::shared_ptr<std::size_t> work_count_;
};
// Helper class to automatically join a fork_executor when exiting a scope.
class join_guard
{
public:
explicit join_guard(const fork_executor& ex) : ex_(ex) {}
join_guard(const join_guard&) = delete;
join_guard(join_guard&&) = delete;
~join_guard() { ex_.join(); }
private:
fork_executor ex_;
};
//------------------------------------------------------------------------------
#include <algorithm>
#include <iostream>
#include <random>
#include <vector>
fork_join_pool pool;
template <class Iterator>
void fork_join_sort(Iterator begin, Iterator end)
{
std::size_t n = end - begin;
if (n > 32768)
{
{
fork_executor fork(pool);
join_guard join(fork);
fork.execute([=]{ fork_join_sort(begin, begin + n / 2); });
fork.execute([=]{ fork_join_sort(begin + n / 2, end); });
}
std::inplace_merge(begin, begin + n / 2, end);
}
else
{
std::sort(begin, end);
}
}
int main(int argc, char* argv[])
{
if (argc != 2)
{
std::cerr << "Usage: fork_join <size>\n";
return 1;
}
std::vector<double> vec(std::atoll(argv[1]));
std::iota(vec.begin(), vec.end(), 0);
std::random_device rd;
std::mt19937 g(rd());
std::shuffle(vec.begin(), vec.end(), g);
std::chrono::steady_clock::time_point start = std::chrono::steady_clock::now();
fork_join_sort(vec.begin(), vec.end());
std::chrono::steady_clock::duration elapsed = std::chrono::steady_clock::now() - start;
std::cout << "sort took ";
std::cout << std::chrono::duration_cast<std::chrono::microseconds>(elapsed).count();
std::cout << " microseconds" << std::endl;
}
|