threads.c

void * thread_start(void *arg) {
    while (1) {
        /* for each column. Only run columns the thread_num
            is assigned to */
        for (column_count = thread_num; column_count < dim - 1; column_count+=threads) {
             /* do thread work for data chunk */
        }        

        /* barrier */
        barrier_result = pthread_barrier_wait(barrier);
        
        if (not_finished == 0) {
            /* finished */
            break;
            /* break while loop, end thread. 
               The barrier is now broken because it is no longer 
               getting called by this thread */
        }

        /* we are not finished, loop around and do thread work on next data chunk */
    }
}