ubuntu OpenMP parallel for

最新推荐文章于 2024-10-09 17:03:19 发布

llcdefgab

最新推荐文章于 2024-10-09 17:03:19 发布

阅读量3.1k

点赞数 1

CC 4.0 BY-SA版权

分类专栏： linux 文章标签： ubuntu parallel openmp 并行计算

本文链接：https://blog.youkuaiyun.com/u011773995/article/details/58131303

linux 专栏收录该内容

8 篇文章

订阅专栏

本文介绍了在Ubuntu操作系统中使用OpenMP进行并行计算for循环的实践过程，引用了Stack Overflow上的建议，强调了-fopenmp编译选项的重要性，并提到OMP_NUM_THREADS环境变量用于设置线程数量。实验结果显示，特定类型的for循环不适用于OpenMP并行化，需要转换为常规int遍历。

摘要生成于 C知道，由 DeepSeek-R1 满血版支持，前往体验 >

ubuntu OpenMP parallel for

OpenMP并行计算for循环

test.cpp

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

using namespace std;

int main(){
    vector<int> a={1,2,3,4,5,6,7,8};
    vector<int> b={1,2,1,2,1,2,1,2};
    vector<int> c(8);

    #pragma omp parallel for 
    for(int i = 0; i < 8; i++)
    {
           c[i] = a[i] + b[i];
           printf("c[%d]=%d\n",i,c[i]);
    }
}

From Stack Overflow[1] :

The OpenMP pragmas are only enabled when compiled with -fopenmp. Otherwise they are completely ignored by the compiler.

Therefore, you will need to add -fopenmp to the compilation of every single module that uses OpenMP. (As opposed to just the final linking step.)

g++ -std=c++11 -c test.cpp -o test.o -fopenmp
g++ test.o -o test -fopenmp -lpthread

Environment Variable OMP_NUM_THREADS sets the number of threads[2]

export OMP_NUM_THREADS=4
./test

My Results

c[0]=2
c[6]=8
c[5]=8
c[3]=6
c[2]=4
c[7]=10
c[1]=4
c[4]=6

for (auto &vi : vec) 这种for不能够用#pragma omp parallel for 来并行。要改成普通的int遍历。