异步调用std::async实现并行计算

一 std::async

template< class Function, class... Args>
std::future<std::result_of_t<std::decay_t<Function>(std::decay_t<Args>...)>>
    async( Function&& f, Args&&... args );

std::async返回一个future对象，可通过get方法异步获取执行结果，如下所示：

#include <iostream>
#include <string>
#include <future>
 
std::string helloFunction(const std::string& s) {
    return "Hello C++11 from " + s + ".";
}
 
class HelloFunctionObject {
public:
    std::string operator()(const std::string& s) const {
        return "Hello C++11 from " + s + ".";
    }
};
 
int main() {
    // 带函数的future
    auto futureFunction = std::async(helloFunction, "function");
    // 带函数对象的future
    HelloFunctionObject helloFunctionObject;
    auto futureFunctionObject = std::async(helloFunctionObject, "function object");
    // 带匿名函数的future
    auto futureLambda = std::async([](const std::string& s) {return "Hello C++11 from " + s + "."; }, "lambda function");
    std::cout << futureFunction.get() << std::endl;
    std::cout << futureFunctionObject.get() << std::endl;
    std::cout << futureLambda.get() << std::endl;
}

二 std::async实现并行计算

1.主程序：

#include <iostream>
#include <vector>
#include <future>
#include <random>
#include <numeric>
#include <cassert>
#include "time_elapse.hpp"
static const int NUM = 100000000;
long long parallel_inner_product(std::vector<int>&v, std::vector<int>&w) {
    if (v.size() != w.size()) {
        return 0;
    }
    if (v.size() < 100) {
        return std::inner_product(begin(v), end(v), begin(w), 0LL);
    }
 
    auto future1 = std::async([&] { return std::inner_product(&v[0], &v[v.size() / 4], &w[0], 0LL); });
    auto future2 = std::async([&] { return std::inner_product(&v[v.size() / 4], &v[v.size() / 2], &w[v.size() / 4], 0LL); });
    auto future3 = std::async([&] { return std::inner_product(&v[v.size() / 2], &v[v.size() * 3 / 4], &w[v.size() / 2], 0LL); });
    auto future4 = std::async([&] { return std::inner_product(&v[v.size() * 3 / 4], &v[v.size()], &w[v.size() * 3 / 4], 0LL); });
 
    return future1.get() + future2.get() + future3.get() + future4.get();
}
long long serial_inner_product(std::vector<int>&v, std::vector<int>&w) {
    if (v.size() != w.size()) {
        return 0;
    }
    return std::inner_product(begin(v), end(v), begin(w), 0LL);
}
int main() {
    std::random_device seed;
    std::mt19937 engine(seed());
    std::uniform_int_distribution<int> dist(0, 100);
    std::vector<int> v, w;
    v.reserve(NUM);
    w.reserve(NUM);
    time_elapse te;
    te.start();
    for (int i = 0; i < NUM; ++i) {
        v.push_back(dist(engine));
        w.push_back(dist(engine));
    }
    std::cout << "load vector elapse = " << te.end() << "s" << std::endl;
    te.start();
    auto res1 = parallel_inner_product(v, w);
    std::cout << "parallel inner_product elapse = " << te.end() << "s" << std::endl;
 
    te.start();
    auto res2 = serial_inner_product(v, w);
    std::cout << "serial inner_product elapse = " << te.end() << "s" << std::endl;
  
    assert(res1 == res2);
 
    return 0;
}

2.time_elapse.hpp

#include <chrono>
struct time_elapse {
    void start() {
        start_ = std::chrono::steady_clock::now();
    }
    double end() {
        std::chrono::duration<double>dura = std::chrono::steady_clock::now() - start_;
        return dura.count();
    }
private:
    std::chrono::time_point<std::chrono::steady_clock> start_ = std::chrono::steady_clock::now();
};

3.编译脚本make.sh

g++ -std=c++11 -g -o Test test.cpp -pthread

三 程序性能测试

1.测试环境：

（1）国产环境（实体机）

CPU：

OS：

（2）Intel环境（虚拟机）

CPU:

 OS：

2.测试结果对比：

（1）国产环境测试结果（执行两次）

 

（2）Interl环境测试结果（执行两次）

 

3.测试结论

（1）使用std::async优化后的并行计算比串行更节省时间；

（2）国产化环境并没有太多优势，反而调用C++相关库更慢。

https://github.com/wangzhicheng2013/async_parallel