#include <stdio.h>
#ifdef _OPENMP
#include <omp.h>
#endif
#define N           100
#define CHUNKSIZE   10
#define MAXTIDS  4



int main (int argc, char *argv[]) {

int nthreads, tid, i, chunk, iter, count[MAXTIDS];
float a[N], b[N], c[N];

/* Some initializations */
for (i=0; i < N; i++) {
  a[i] = b[i] = i * 1.0; }
for (i=0; i < MAXTIDS; i++) {
  count[i] = 0; }
iter = N;
chunk = CHUNKSIZE;

printf("Parallel region starts\n");
#pragma omp parallel private(i,nthreads,tid) 
  {
#ifdef _OPENMP
  tid = omp_get_thread_num();
#else
  tid=0;
#endif
#pragma omp single nowait
{
#ifdef _OPENMP
    nthreads = omp_get_num_threads();
#else
    nthreads = 1;
#endif
    printf("%d: Number of threads = %d\n", tid,nthreads);
}

  #pragma omp for schedule(dynamic,chunk) 
  for (i=0; i < iter; i++) {
    c[i] = a[i] + b[i];
    count[tid]++;
//    printf("tid=%d i=%d  c[i]=%f\n", tid,i,c[i]);
    }
  printf("Thread %d did %d loop iterations. Done.\n",tid,count[tid]);

  }  /* end of parallel region */
  printf("Completed.\n");
  for (i=0; i < iter; i++) {
   if(c[i]!=i*2.0) {
      printf("Error for %d. Is %f should be %f\n",i,c[i],i*2.0);
    } 
   }

}