OpenMP编程学习笔记五

critical 使用：

如果代码段只需要一个thread执行，可以使用single标明。如果代码段需要ID为0的thread执行，使用master标明。

那么，如果代码段需要各个CPU互斥执行，也就是要求每个CPU都执行一次，但任何时候只用一个CPU在执行。这种

情况可以使用critical。从宏观上看，该代码段被依次在各个CPU上被执行，各个CPU在执行该代码的时序上没有重叠。

测试代码：

void testCritical()
{
    omp_set_num_threads( 4 );
    clock_t t1 = clock();
#pragma omp parallel
    {
       
        printf("test OpenMP/n");
#pragma omp critical
        {
            clock_t t11 = clock();
            printf("test OpenMP critical/n");
            printf("execute thread ID is %d/n", omp_get_thread_num());
                for (int i = 0; i < 100000000; i++)
             {
                 int a = i+1;
             }

            clock_t t22 = clock();
            printf("thread time = %d/n", t22 - t11);
        }
    }
    clock_t t2 = clock();
    printf("total time = %d/n", t2 - t1);
}

运行结果：

test OpenMP
test OpenMP
test OpenMP
test OpenMP
test OpenMP critical
execute thread ID is 0
thread time = 291
test OpenMP critical
execute thread ID is 2
thread time = 290
test OpenMP critical
execute thread ID is 1
thread time = 294
test OpenMP critical
execute thread ID is 3
thread time = 286
total time = 1164

可以看出，整个运行的时间为1164ms,四个thread不是同步执行critical代码段，而是依次执行的。

为了对比，注释掉critical,

void testCritical()
{
    omp_set_num_threads( 4 );
    clock_t t1 = clock();
#pragma omp parallel
    {
       
        printf("test OpenMP/n");
//#pragma omp critical
        {
            clock_t t11 = clock();
            printf("test OpenMP critical/n");
            printf("execute thread ID is %d/n", omp_get_thread_num());
                for (int i = 0; i < 100000000; i++)
             {
                 int a = i+1;
             }

            clock_t t22 = clock();
            printf("thread time = %d/n", t22 - t11);
        }
    }
    clock_t t2 = clock();
    printf("total time = %d/n", t2 - t1);
}

再运行，结果为：

test OpenMP
test OpenMP critical
execute thread ID is 0
test OpenMP
test OpenMP critical
execute thread ID is 2
test OpenMP
test OpenMP critical
execute thread ID is 3
test OpenMP
test OpenMP critical
execute thread ID is 1
thread time = 224
thread time = 228
thread time = 237
thread time = 248
total time = 250

此时，total time基本上等于一个thread的运行所耗时间。