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
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
|
/* OpenACC Runtime Library: CUDA support glue.
Copyright (C) 2014-2020 Free Software Foundation, Inc.
Contributed by Mentor Embedded.
This file is part of the GNU Offloading and Multi Processing Library
(libgomp).
Libgomp is free software; you can redistribute it and/or modify it
under the terms of the GNU General Public License as published by
the Free Software Foundation; either version 3, or (at your option)
any later version.
Libgomp is distributed in the hope that it will be useful, but WITHOUT ANY
WARRANTY; without even the implied warranty of MERCHANTABILITY or FITNESS
FOR A PARTICULAR PURPOSE. See the GNU General Public License for
more details.
Under Section 7 of GPL version 3, you are granted additional
permissions described in the GCC Runtime Library Exception, version
3.1, as published by the Free Software Foundation.
You should have received a copy of the GNU General Public License and
a copy of the GCC Runtime Library Exception along with this program;
see the files COPYING3 and COPYING.RUNTIME respectively. If not, see
<http://www.gnu.org/licenses/>. */
#include "openacc.h"
#include "libgomp.h"
#include "oacc-int.h"
#include <assert.h>
void *
acc_get_current_cuda_device (void)
{
struct goacc_thread *thr = goacc_thread ();
void *ret = NULL;
if (thr && thr->dev && thr->dev->openacc.cuda.get_current_device_func)
{
acc_prof_info prof_info;
acc_api_info api_info;
bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
ret = thr->dev->openacc.cuda.get_current_device_func ();
if (profiling_p)
{
thr->prof_info = NULL;
thr->api_info = NULL;
}
}
return ret;
}
void *
acc_get_current_cuda_context (void)
{
struct goacc_thread *thr = goacc_thread ();
void *ret = NULL;
if (thr && thr->dev && thr->dev->openacc.cuda.get_current_context_func)
{
acc_prof_info prof_info;
acc_api_info api_info;
bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
ret = thr->dev->openacc.cuda.get_current_context_func ();
if (profiling_p)
{
thr->prof_info = NULL;
thr->api_info = NULL;
}
}
return ret;
}
void *
acc_get_cuda_stream (int async)
{
struct goacc_thread *thr = goacc_thread ();
if (!async_valid_p (async))
return NULL;
void *ret = NULL;
if (thr && thr->dev && thr->dev->openacc.cuda.get_stream_func)
{
goacc_aq aq = lookup_goacc_asyncqueue (thr, false, async);
if (!aq)
return ret;
acc_prof_info prof_info;
acc_api_info api_info;
bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
if (profiling_p)
{
prof_info.async = async;
prof_info.async_queue = prof_info.async;
}
ret = thr->dev->openacc.cuda.get_stream_func (aq);
if (profiling_p)
{
thr->prof_info = NULL;
thr->api_info = NULL;
}
}
return ret;
}
/* As of OpenACC 2.6, the return code of this function appears to be
unspecified. We choose to return 1 for success, or 0 for failure. */
int
acc_set_cuda_stream (int async, void *stream)
{
struct goacc_thread *thr;
if (!async_valid_p (async) || stream == NULL)
return 0;
goacc_lazy_initialize ();
thr = goacc_thread ();
int ret = 0;
if (thr && thr->dev && thr->dev->openacc.cuda.set_stream_func)
{
acc_prof_info prof_info;
acc_api_info api_info;
bool profiling_p = GOACC_PROFILING_SETUP_P (thr, &prof_info, &api_info);
if (profiling_p)
{
prof_info.async = async;
prof_info.async_queue = prof_info.async;
}
goacc_aq aq = get_goacc_asyncqueue (async);
/* Due to not using an asyncqueue for "acc_async_sync", this cannot be
used to change the CUDA stream associated with "acc_async_sync". */
if (!aq)
{
assert (async == acc_async_sync);
gomp_debug (0, "Refusing request to set CUDA stream associated"
" with \"acc_async_sync\"\n");
ret = 0;
goto out_prof;
}
gomp_mutex_lock (&thr->dev->openacc.async.lock);
ret = thr->dev->openacc.cuda.set_stream_func (aq, stream);
gomp_mutex_unlock (&thr->dev->openacc.async.lock);
out_prof:
if (profiling_p)
{
thr->prof_info = NULL;
thr->api_info = NULL;
}
}
return ret;
}
|
