我试图简单地总结一下所有名为" train_hr"的变量。和" test_hr"从所有10个处理器中存储并打印处理器0上的总和。我检查以确保各个总和不是0(它们不是,它们都在1000s)。它保持报告的总和为0.我不知道为什么。我已经看了很多这方面的例子,我完全按照指示完成了。任何帮助将不胜感激。
double train_hr = 0, test_hr = 0;
double train_hr_global = 0, test_hr_global = 0;
//Master processor
if (my_rank == 0) {
// sends a task to each processor
int curr_task = 0;
for(i = 0; i < num_procs; i++) {
if (curr_task < nsamples_all) {
MPI_Send(&curr_task, 1, MPI_INT, i, 1, MPI_COMM_WORLD);
curr_task++;
}
}
int r;
MPI_Status status;
//keeps sending tasks to processors until there are no more tasks
while (curr_task < nsamples_all) {
MPI_Recv(&r, 1, MPI_INT, MPI_ANY_SOURCE, 1, MPI_COMM_WORLD, &status);
MPI_Send(&curr_task, 1, MPI_INT, status.MPI_SOURCE, 1, MPI_COMM_WORLD);
curr_task++;
}
//tell all processors to stop receiving
int a = -1;
for (i = 0; i < num_procs; i++) {
MPI_Send(&a, 1, MPI_INT, i, 1, MPI_COMM_WORLD);
}
}
//Helper processors
else {
int stop = 1;
while(stop != 0){
int i;
//Receives task OR stop alert from master
MPI_Status status;
MPI_Recv(&i, 1, MPI_INT, 0, 1, MPI_COMM_WORLD, &status);
if (i == -1) {
stop = 0;
}
//computations
else{
float r;
//unimportant computations here
train_hr += r;
test_hr += r;
//Tells master processor it is done
MPI_Send(&i, 1, MPI_INT, 0, 1, MPI_COMM_WORLD);
}
}
}
//At this point I checked the current values of train_hr and test_hr on each helper processor. They are all non-zero.
MPI_Reduce(&train_hr, &train_hr_global, 1, MPI_INT, MPI_SUM, 0, MPI_COMM_WORLD);
MPI_Reduce(&test_hr, &test_hr_global, 1, MPI_INT, MPI_SUM, 0, MPI_COMM_WORLD);
//at this point, the vales of train_hr_global and test_hr_global on the master processor (processor 0) are 0 when they should be the sum of all the processors values.
}