/* { dg-additional-options "-O2" } */
/* { dg-additional-options "-ftree-parallelize-loops=32" } */
/* { dg-additional-options "-fdump-tree-parloops_oacc_kernels-all" } */

#include <stdlib.h>

#define N (1024 * 512)
#define COUNTERTYPE unsigned int

int
main (void)
{
  unsigned int *__restrict a;
  unsigned int sum = 0;
  unsigned int sum2 = 0;

  a = (unsigned int *)malloc (N * sizeof (unsigned int));

  for (COUNTERTYPE i = 0; i < N; i++)
    a[i] = i * 2;

#pragma acc kernels copy (sum) copyin (a[0:N])
  {
    for (COUNTERTYPE ii = 0; ii < N; ii++)
      sum += a[ii];
  }

  for (COUNTERTYPE i = 0; i < N; i++)
    sum2 += a[i];

  if (sum != sum2)
      abort ();

  free (a);

  return 0;
}

/* Check that only one loop is analyzed, and that it can be parallelized.  */
/* { dg-final { scan-tree-dump-times "SUCCESS: may be parallelized" 1 "parloops_oacc_kernels" } } */
/* { dg-final { scan-tree-dump-not "FAILED:" "parloops_oacc_kernels" } } */

/* { dg-final { cleanup-tree-dump "parloops_oacc_kernels" } } */