小编kar*_*kar的帖子

在OpenMP中使用时omp sections,将线程分配到这些块内的部分,或者将每个线程被分配给每个区段？

时间nthreads == 3:

#pragma omp sections
{
    #pragma omp section
    { 
        printf ("id = %d, \n", omp_get_thread_num());
    }

    #pragma omp section
    { 
        printf ("id = %d, \n", omp_get_thread_num());
    }
}

输出:

id=1
id=1

但是当我执行以下代码时:

#pragma omp sections
{
    #pragma omp section
    { 
        printf ("id = %d, \n", omp_get_thread_num());
    }

    #pragma omp section
    { 
        printf ("id = %d, \n", omp_get_thread_num());
    }
}

#pragma omp sections
{
    #pragma omp section
    { 
        printf ("id = …

我已经阅读了CUDA编程指南,我无法理解下面显示的线程分配方法:

dim3 dimGrid( 2, 2, 1 );
dim3 dimBlock( 4, 2, 2 );
KernelFunction<<< dimGrid, dimBlock >>>(. . .);

有人可以解释如何为上述条件分配线程吗？