c++积累2 -运行时决定线程数量

1、获取cpu核个数

    unsigned long const hardware_threads = std::thread::hardware_concurrency();

2、demo示例

将一个数组中的元素进行累加计算，通过并行处理

#include <iostream>
#include <numeric>
#include <thread>
#include <vector>

template<typename Iterator, typename T>
struct accumulate_block {
    void operator()(Iterator first, Iterator last, T &result) {
        result = std::accumulate(first, last, result);
    }
};


template<typename Iterator, typename T>
T parallel_accumulate(Iterator first, Iterator last, T init) {

    // 开始结束元素个数
    unsigned long const length = std::distance(first, last);

    if (!length) {
        return init;
    }

    // 按照每个线程最少处理25个数
    unsigned long const min_per_thread = 25;

    // 不考虑cpu个数下，期望的最大线程数
    unsigned long const max_threads = (length + min_per_thread - 1) / min_per_thread;

    // 获取cpu核个数
    unsigned long const hardware_threads = std::thread::hardware_concurrency();

    std::cout << "cpu num: " << hardware_threads << std::endl;

    // 结合cpu核个数，取最小值。如果获取不到cpu核个数，则默认为2个线程
    unsigned long const num_threads = std::min(hardware_threads != 0 ? hardware_threads : 2, max_threads);

    // 每个线程平均分配需要计算的元素个数
    unsigned long const block_size = length / num_threads;

    // 多线程结果
    std::vector<T> results(num_threads);
    // 多线程数组
    std::vector<std::thread> threads(num_threads - 1);
    Iterator block_start = first;
    // 并行启动多线程进行计算
    for (unsigned long i = 0; i < (num_threads - 1); ++i) {
        Iterator block_end = block_start;
        std::advance(block_end, block_size);
        threads[i] = std::thread(
                accumulate_block<Iterator, T>(),
                        block_start,block_end, std::ref(results[i]));
        block_start = block_end;
    }

    accumulate_block<Iterator, T>()(block_start,last,results[num_threads -1]);
    // 等待多线程执行完成
    std::for_each(threads.begin(), threads.end(), std::mem_fn(&std::thread::join));

    // 累加多线程计算结果并返回
    return std::accumulate(results.begin(), results.end(), init);
}


int main() {
    std::vector<int> ivec = {10, 29,10,10,30,20};
    int res = parallel_accumulate(ivec.begin(), ivec.end(), 0);
    std::cout << res << std::endl;
    return 0;
}

运行结果：

cpu num: 8
109