通过多个并行区域的 OpenMP 线程亲和性

Question

这个问题是关于特定情况下的线程关联。假设我们有如下代码。

int main(){
omp_set_num_threads(NTHREADS);
somestruct *array = (somestruct*)malloc(sizeof(somestruct) * NTHREADS);
#pragma omp parallel default(none) shared(array)
{
    // each thread initializes their corresponding struct data
    int tid = omp_get_thread_num();
    initialize_struct(array, tid);
    // ...
}

// some sequential computation
// ....
// ....

// parallel region again
#pragma omp parallel default(none) shared(array)
{
    int tid = omp_get_thread_num();
    // each thread does some computation on their corresponding struct
    do_computation(array, tid);
}

return 0;
}

线程亲和性是否会像上例中那样在多个并行区域中保持不变？也就是说，如果第一个parallel region中tid0映射到CPU0的core0，是否保证tid0在第二个parallel region中映射到CPU0的同一个core0？

Answer 1

是。该规范要求所谓的 "threadprivate persistence"，这使得运行时在随后的并行区域中重用相同的线程，如解释的那样 here：threadprivate 数据可以在某些条件下跨活动并行区域持续存在：

The values of data in the threadprivate variables of non-initial threads are guaranteed to persist between two consecutive active parallel regions only if all the following conditions hold:

• Neither parallel region is nested inside another explicit parallel region.

• The number of threads used to execute both parallel regions is the same.

• The value of the dyn-var internal control variable in the enclosing task region is false at entry to both parallel regions.

If these conditions all hold, and if a threadprivate variable is referenced in both regions, then threads with the same thread number in their respective regions will reference the same copy of that variable.

通过多个并行区域的 OpenMP 线程亲和性

OpenMP thread Affinity through multiple parallel regions

c++

parallel-processing

openmp