随着线程数量的增加,“temp”的计数减少了。 当我发送线程数为“1”时,它给出了正确答案,但随着线程数量的增加,运行时间缩短但给出了错误的答案
#include <stdio.h>
#include <mpi.h>
#include <complex.h>
#include <time.h>
#include <omp.h>
#define MAXITERS 1000
// globals
int count = 0;
int nptsside;
float side2;
float side4;
int temp = 0;
int inset(double complex c) {
int iters;
float rl,im;
double complex z = c;
for (iters = 0; iters < MAXITERS; iters++) {
z = z*z + c;
rl = creal(z);
im = cimag(z);
if (rl*rl + im*im > 4) return 0;
}
return 1;
}
int main(int argc, char **argv)
{
nptsside = atoi(argv[1]);
side2 = nptsside / 2.0;
side4 = nptsside / 4.0;
//struct timespec bgn,nd;
//clock_gettime(CLOCK_REALTIME, &bgn);
int x,y; float xv,yv;
double complex z;
int i;
int mystart, myend;
int nrows;
int nprocs, mype;
int data;
MPI_Status status;
MPI_Init(&argc,&argv);
MPI_Comm_size(MPI_COMM_WORLD, &nprocs);
MPI_Comm_rank(MPI_COMM_WORLD, &mype);
nrows = nptsside/nprocs;
printf("%d\n", nprocs);
mystart = mype*nrows;
myend = mystart + nrows - 1;
#pragma omp parallel shared(mystart, myend, temp)
{
int nth = omp_get_num_threads();
printf("%d\n", nth);
#ifdef STATIC
#pragma omp for reduction(+:temp) schedule(static)
#elif defined DYNAMIC
#pragma omp for reduction(+:temp) schedule(dynamic)
#elif defined GUIDED
#pragma omp for reduction(+:temp) schedule(guided)
#endif
for (x=mystart; x<=myend; x++) {
for ( y=0; y<nptsside; y++) {
xv = (x - side2) / side4;
yv = (y - side2) / side4;
z = xv + yv*I;
if (inset(z)) {
temp++;
}
}
}
}
if(mype==0) {
count += temp;
printf("%d\n", temp);
for (i = 1; i < nprocs; i++) {
MPI_Recv(&temp, 1, MPI_INT, i, 0, MPI_COMM_WORLD, &status);
count += temp;
printf("%d\n", temp);
}
}
else{
MPI_Send(&temp, 1, MPI_INT, 0, 0, MPI_COMM_WORLD);
}
MPI_Finalize();
if(mype==0) {
printf("%d\n", count);
}
//clock_gettime(CLOCK_REALTIME, &nd);
//printf("%f\n",timediff(bgn,nd));
}
答案 0 :(得分:0)
当您进入OpenMP循环时,您没有定义任何私有变量。
首先,您必须始终声明OpenMP循环的循环计数器(以及OpenMP循环内嵌套循环的任何循环计数器)私有。
其次,您有三个变量(xv
,yv
和z
),每个变量都依赖于这些循环中的迭代。因此,每个线程也需要拥有自己的这些变量的私有副本。将并行语句更改为
#pragma omp parallel shared(mystart, myend, temp) private(x, y, xv, yv, z)
应修复您的OpenMP问题。
看到你说将线程数设置为1会产生正确的答案,我没有查看你的MPI代码。
编辑:好的,我说谎,我现在简要地查看了你的MPI代码。而不是所有的发送和接收,你应该写一个单一的减少。这个集体将比您当前设置的阻止通信快得多。MPI_Reduce(&temp, &count, 1, MPI_INT, MPI_SUM, 0, MPI_COMM_WORLD);