OpenMP parallel computing pI value

After creating a project with vs, you must right-click the project and choose Properties -- C/C ++ -- language. In the dialog box on the right, select YES For OpenMP;

ProgramCodeIs:

# Include<Stdio. h>

# Include<Time. h>

# Include<OMP. h>

 

Static long num_steps= 100000;

Double step, PI;

Void main ()

{

Clock_t T1 = clock ();

Int I;

Double X, sum = 0.0;

Step = 1.0/(double) num_steps;

# Pragma OMP parallel for ction (+: Sum)

For (I = 0; I <num_steps; I ++)

{

X = (I + 0.5) * step;

Sum = sum + 4.0/(1.0 + x * X );

Printf ("% d", omp_get_thread_num ());

}

Pi = Step * sum;

Clock_t t2 = clock ();

Printf ("Pi = % F, time: % d \ n", PI, t2-t1 );

}

The above Code uses the Protocol rduction (OP: List); in this way, each thread will have a private list. After the list calculation of all threads is complete, the private list value of each thread is normalized as a list value by op.