采用std::thread 替换 openmp

内容转换的，具体详见博客：https://cloud.tencent.com/developer/article/1094617 及对应的code：https://github.com/cpuimage/ParallelFor/blob/master/ParallelFor.cpp

#include <stdio.h>
#include <stdlib.h>
#include <iostream>

#if defined(_OPENMP)
// compile with: /openmp
#include <omp.h>
auto const epoch = omp_get_wtime();
double now() {
    return omp_get_wtime() - epoch;
};
#else
#include <chrono>
auto const epoch = std::chrono::steady_clock::now();
double now() {
    return std::chrono::duration_cast<std::chrono::milliseconds>(std::chrono::steady_clock::now() - epoch).count() / 1000.0;
};
#endif

template<typename FN>
double bench(const FN &fn) {
    auto took = -now();
    return (fn(), took + now());
}

#include <functional>

#if defined(_OPENMP)
#    include <omp.h>
#else
#include <thread>

#include <vector>
#endif

#ifdef _OPENMP
static int processorCount = static_cast<int>(omp_get_num_procs());
#else
static int processorCount = static_cast<int>(std::thread::hardware_concurrency());
#endif

static void ParallelFor(int inclusiveFrom, int exclusiveTo, std::function<void(size_t)> func)
{
#if defined(_OPENMP)
#pragma omp parallel for num_threads(processorCount)
    for (int i = inclusiveFrom; i < exclusiveTo; ++i)
    {
        func(i);
    }
    return;
#else
    if (inclusiveFrom >= exclusiveTo)
        return;

    static    size_t thread_cnt = ;
    if (thread_cnt == )
    {
        thread_cnt = std::thread::hardware_concurrency();
    }
    size_t entry_per_thread = (exclusiveTo - inclusiveFrom) / thread_cnt;

    if (entry_per_thread < )
    {
        for (int i = inclusiveFrom; i < exclusiveTo; ++i)
        {
            func(i);
        }
        return;
    }
    std::vector<std::thread> threads;
    int start_idx, end_idx;

    for (start_idx = inclusiveFrom; start_idx < exclusiveTo; start_idx += entry_per_thread)
    {
        end_idx = start_idx + entry_per_thread;
        if (end_idx > exclusiveTo)
            end_idx = exclusiveTo;

        threads.emplace_back([&](size_t from, size_t to)
        {
            for (size_t entry_idx = from; entry_idx < to; ++entry_idx)
                func(entry_idx);
        }, start_idx, end_idx);
    }

    for (auto& t : threads)
    {
        t.join();
    }
#endif
}

void test_scale(int i, double* a, double* b) {
    a[i] =  * b[i];
}

int main()
{
    int N = ;
    double* a2 = (double*)calloc(N, sizeof(double));
    double* a1 = (double*)calloc(N, sizeof(double));
    double* b = (double*)calloc(N, sizeof(double));
    if (a1 == NULL || a2 == NULL || b == NULL)
    {
        if (a1)
        {
            free(a1);
        }if (a2)
        {
            free(a2);
        }if (b)
        {
            free(b);
        }
        return -;
    }
    for (int i = ; i < N; i++)
    {
        a1[i] = i;
        a2[i] = i;
        b[i] = i;
    }
    double beforeTime = bench([&] {
        for (int i = ; i < N; i++)
        {
            test_scale(i, a1, b);
        }
    });

    std::cout << " \nbefore: " << int(beforeTime * ) << "ms" << std::endl;
    double afterTime = bench([&] {
        ParallelFor(, N, [a2, b](size_t i)
        {
            test_scale(i, a2, b);
        });
    });
    std::cout << " \nafter: " << int(afterTime * ) << "ms" << std::endl;

    for (int i = ; i < N; i++)
    {
        if (a1[i] != a2[i]) {
            printf("error %f : %f \t", a1[i], a2[i]);
            getchar();
        }
    }
    free(a1);
    free(a2);
    free(b);
    getchar();
    return ;
}

要使用OPENMP,加个编译选项/openmp  或者定义一下 _OPENMP 即可。

建议c++11编译。

示例代码比较简单。

这里举例的是ncnn代码修改例子，具体如下：

   #pragma omp parallel for
        for (int q=; q<channels; q++)
        {
            const Mat m = src.channel(q);
            Mat borderm = dst.channel(q);

            copy_make_border_image(m, borderm, top, left, type, v);
        }

替换为：

    ParallelFor(, channels, [&](int  q) {
                {
                    const Mat m = src.channel(q);
                    Mat borderm = dst.channel(q);

                    copy_make_border_image(m, borderm, top, left, type, v);
                }});