Retro68/gcc/libgomp/testsuite/libgomp.oacc-c-c++-common/lib-73.c

/* { dg-do run { target openacc_nvidia_accel_selected } } */
/* { dg-additional-options "-lcuda" } */

#include <stdio.h>
#include <unistd.h>
#include <stdlib.h>
#include <openacc.h>
#include <cuda.h>

int
main (int argc, char **argv)
{
  CUdevice dev;
  CUfunction delay;
  CUmodule module;
  CUresult r;
  const int N = 10;
  int i;
  CUstream streams[N];
  unsigned long *a, *d_a, dticks;
  int nbytes;
  float dtime;
  void *kargs[2];
  int clkrate;
  int devnum, nprocs;

  acc_init (acc_device_nvidia);

  devnum = acc_get_device_num (acc_device_nvidia);

  r = cuDeviceGet (&dev, devnum);
  if (r != CUDA_SUCCESS)
    {
      fprintf (stderr, "cuDeviceGet failed: %d\n", r);
      abort ();
    }

  r =
    cuDeviceGetAttribute (&nprocs, CU_DEVICE_ATTRIBUTE_MULTIPROCESSOR_COUNT,
			  dev);
  if (r != CUDA_SUCCESS)
    {
      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
      abort ();
    }

  r = cuDeviceGetAttribute (&clkrate, CU_DEVICE_ATTRIBUTE_CLOCK_RATE, dev);
  if (r != CUDA_SUCCESS)
    {
      fprintf (stderr, "cuDeviceGetAttribute failed: %d\n", r);
      abort ();
    }

  r = cuModuleLoad (&module, "subr.ptx");
  if (r != CUDA_SUCCESS)
    {
      fprintf (stderr, "cuModuleLoad failed: %d\n", r);
      abort ();
    }

  r = cuModuleGetFunction (&delay, module, "delay");
  if (r != CUDA_SUCCESS)
    {
      fprintf (stderr, "cuModuleGetFunction failed: %d\n", r);
      abort ();
    }

  nbytes = nprocs * sizeof (unsigned long);

  dtime = 200.0;

  dticks = (unsigned long) (dtime * clkrate);

  a = (unsigned long *) malloc (nbytes);
  d_a = (unsigned long *) acc_malloc (nbytes);

  acc_map_data (a, d_a, nbytes);

  kargs[0] = (void *) &d_a;
  kargs[1] = (void *) &dticks;

  for (i = 0; i < N; i++)
    {
      streams[i] = (CUstream) acc_get_cuda_stream (i);
      if (streams[i] != NULL)
	abort ();

      r = cuStreamCreate (&streams[i], CU_STREAM_DEFAULT);
      if (r != CUDA_SUCCESS)
	{
	  fprintf (stderr, "cuStreamCreate failed: %d\n", r);
	  abort ();
	}

        if (!acc_set_cuda_stream (i, streams[i]))
	  abort ();
    }

  for (i = 0; i < N; i++)
    {
      r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, streams[i], kargs, 0);
      if (r != CUDA_SUCCESS)
	{
	  fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
	  abort ();
	}

    }

  if (acc_async_test_all () != 0)
    {
      fprintf (stderr, "asynchronous operation not running\n");
      abort ();
    }

  sleep ((int) (dtime / 1000.0f) + 1);

  if (acc_async_test_all () != 1)
    {
      fprintf (stderr, "asynchronous operation not running\n");
      abort ();
    }

  acc_unmap_data (a);

  free (a);
  acc_free (d_a);

  acc_shutdown (acc_device_nvidia);

  exit (0);
}

/* { dg-output "" } */