mirror of
https://github.com/autc04/Retro68.git
synced 2024-12-13 03:29:50 +00:00
142 lines
2.7 KiB
C
142 lines
2.7 KiB
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>
|
||
|
#include "timer.h"
|
||
|
|
||
|
int
|
||
|
main (int argc, char **argv)
|
||
|
{
|
||
|
CUdevice dev;
|
||
|
CUfunction delay;
|
||
|
CUmodule module;
|
||
|
CUresult r;
|
||
|
int N;
|
||
|
int i;
|
||
|
CUstream stream;
|
||
|
unsigned long *a, *d_a, dticks;
|
||
|
int nbytes;
|
||
|
float atime, dtime, hitime, lotime;
|
||
|
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);
|
||
|
|
||
|
N = nprocs;
|
||
|
|
||
|
a = (unsigned long *) malloc (nbytes);
|
||
|
d_a = (unsigned long *) acc_malloc (nbytes);
|
||
|
|
||
|
acc_map_data (a, d_a, nbytes);
|
||
|
|
||
|
stream = (CUstream) acc_get_cuda_stream (0);
|
||
|
if (stream != NULL)
|
||
|
abort ();
|
||
|
|
||
|
r = cuStreamCreate (&stream, CU_STREAM_DEFAULT);
|
||
|
if (r != CUDA_SUCCESS)
|
||
|
{
|
||
|
fprintf (stderr, "cuStreamCreate failed: %d\n", r);
|
||
|
abort ();
|
||
|
}
|
||
|
|
||
|
if (!acc_set_cuda_stream (0, stream))
|
||
|
abort ();
|
||
|
|
||
|
init_timers (1);
|
||
|
|
||
|
kargs[0] = (void *) &d_a;
|
||
|
kargs[1] = (void *) &dticks;
|
||
|
|
||
|
start_timer (0);
|
||
|
|
||
|
for (i = 0; i < N; i++)
|
||
|
{
|
||
|
r = cuLaunchKernel (delay, 1, 1, 1, 1, 1, 1, 0, stream, kargs, 0);
|
||
|
if (r != CUDA_SUCCESS)
|
||
|
{
|
||
|
fprintf (stderr, "cuLaunchKernel failed: %d\n", r);
|
||
|
abort ();
|
||
|
}
|
||
|
|
||
|
acc_wait (0);
|
||
|
}
|
||
|
|
||
|
atime = stop_timer (0);
|
||
|
|
||
|
hitime = dtime * N;
|
||
|
hitime += hitime * 0.02;
|
||
|
|
||
|
lotime = dtime * N;
|
||
|
lotime -= lotime * 0.02;
|
||
|
|
||
|
if (atime > hitime || atime < lotime)
|
||
|
{
|
||
|
fprintf (stderr, "actual time < delay time\n");
|
||
|
abort ();
|
||
|
}
|
||
|
|
||
|
acc_unmap_data (a);
|
||
|
|
||
|
fini_timers ();
|
||
|
|
||
|
free (a);
|
||
|
acc_free (d_a);
|
||
|
|
||
|
acc_shutdown (acc_device_nvidia);
|
||
|
|
||
|
exit (0);
|
||
|
}
|
||
|
|
||
|
/* { dg-output "" } */
|