如何使用 OpenMP 正确并行化 for 循环？

Question

我正在为 C++ 测试 OpenMP，因为我的软件将严重依赖处理器并行化的速度。

当运行以下代码时，我得到了奇怪的结果。

并行化的速度没有我预期的那么快
不使用 -O 标志时，代码运行较慢。

我在 i5-8600 CPU 和 16 GB RAM 上使用 g++ 编译器，版本 7.3.0 和 Ubuntu 18.04 OS。

输出：

Output 1 (Not allowed to embed yet since I'm a new member)

转录：

.../OpenMPTest$ g++ -O3 -o openmp main.cpp -fopenmp
.../OpenMPTest$ ./openmp
6 processors used.
Linear action took: 2.87415 seconds.
Parallel action took: 0.99954 seconds.

Output 2

.../OpenMPTest$ g++ -o openmp main.cpp -fopenmp
.../OpenMPTest$ ./openmp
6 processors used.
Linear action took: 25.7037 seconds.
Parallel action took: 68.0485 seconds.

如您所见，对于 6 个处理器，我的速度仅提高了约 2.9 倍，除非我省略了 -O 标志，在这种情况下，程序运行速度要慢得多，但仍以 100 使用所有 6 个处理器利用率百分比（使用 htop 测试）。

这是为什么？另外，我可以做些什么来实现 6 倍的性能提升？

源代码：

#include <iostream>
#include <ctime>
#include <ratio>
#include <chrono>
#include <array>
#include <omp.h>

int main() {

    using namespace std::chrono;

    const int big_number = 1000000000;
    std::array<double, 6> array = { 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 };

    // Sequential

    high_resolution_clock::time_point start_linear = high_resolution_clock::now();

    for(int i = 0; i < 6; i++) {
        for(int j = 0; j < big_number; j++) {
            array[i]++;
        }   
    }

    high_resolution_clock::time_point end_linear = high_resolution_clock::now();

    // Parallel 

    high_resolution_clock::time_point start_parallel = high_resolution_clock::now();

    array = {0.0, 0.0, 0.0, 0.0, 0.0, 0.0};

    #pragma omp parallel
    {
        #pragma omp for
        for(int i = 0; i < 6; i++) {
            for(int j = 0; j < big_number; j++) {
                array[i]++;
            }   
        }
    }

    high_resolution_clock::time_point end_parallel = high_resolution_clock::now();

    // Stats.

    std::cout << omp_get_num_procs() << " processors used." << std::endl << std::endl;

    duration<double> time_span = duration_cast<duration<double>>(end_linear - start_linear);
    std::cout << "Linear action took: " << time_span.count() << " seconds." << std::endl << std::endl;

    time_span = duration_cast<duration<double>>(end_parallel - start_parallel);
    std::cout << "Parallel action took: " << time_span.count() << " seconds." << std::endl << std::endl;

    return EXIT_SUCCESS;
}

Answer 1

您的代码似乎受到了 false sharing 的影响。

不要让不同的线程访问同一个缓存line.A更好的方法是尽量不要在线程之间共享变量。

#include <iostream>
#include <ctime>
#include <ratio>
#include <chrono>
#include <array>
#include <omp.h>

int main() {

  using namespace std::chrono;

  const int big_number = 1000000000;
  alignas(64) std::array<double, 6*8> array = { 0.0, 0.0, 0.0, 0.0, 0.0, 0.0 };

  // Sequential

  high_resolution_clock::time_point start_linear = high_resolution_clock::now();

  for(int i = 0; i < 6; i++) {
    for(int j = 0; j < big_number; j++) {
      array[i]++;
    }
  }

  high_resolution_clock::time_point end_linear = high_resolution_clock::now();

  // Parallel

  high_resolution_clock::time_point start_parallel = high_resolution_clock::now();

  array = {0.0, 0.0, 0.0, 0.0, 0.0, 0.0};

      #pragma omp parallel
  {
            #pragma omp for
    for(int i = 0; i < 6; i++) {
      for(int j = 0; j < big_number; j++) {
        array[i*8]++;
      }
    }
  }

  high_resolution_clock::time_point end_parallel = high_resolution_clock::now();

  // Stats.

  std::cout << omp_get_num_procs() << " processors used." << std::endl << std::endl;

  duration<double> time_span = duration_cast<duration<double>>(end_linear - start_linear);
  std::cout << "Linear action took: " << time_span.count() << " seconds." << std::endl << std::endl;

  time_span = duration_cast<duration<double>>(end_parallel - start_parallel);
  std::cout << "Parallel action took: " << time_span.count() << " seconds." << std::endl << std::endl;

  return EXIT_SUCCESS;
}

使用了 8 个处理器。

线性动作耗时：26.9021 秒。

并行操作耗时：6.41319 秒。

你可以阅读 this。

如何使用 OpenMP 正确并行化 for 循环？

How do I properly parallelise a for loop using OpenMP?

c++

parallel-processing

for-loop

openmp