1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
|
/* { 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 "" } */
|
