Hi,
Using CGT-7.4.1 and OpenMP-1.1.2.06, I experience problems with openmp barriers when the number of loop iterations is lower then the core-count:
#include <ti/omp/omp.h>
#include <stdio.h>
void main()
{
int i;
#pragma omp parallel for
for (i=0; i < 6; i++) //8 iterations work
{
printf("Hello before barrier \n");
#pragma omp barrier
printf("Hello after barrier \n");
}
}
The following code hangs forever at the barrier (config taken from mathvec example, except OpenMP.setNumProcessors(8)), however when I increase loop iterations to 8 everything works as expected.
As I am very tight on schedule, I unfourtunately can not try the latest versions.
Regards, Clemens