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
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
201
202
203
204
205
206
207
208
209
210
211
|
/* Copyright (C) 2015-2022 Free Software Foundation, Inc.
Contributed by Alexander Monakov <amonakov@ispras.ru>
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/>. */
/* This file handles maintenance of threads on NVPTX. */
#if defined __nvptx_softstack__ && defined __nvptx_unisimt__
#include "libgomp.h"
#include <stdlib.h>
#include <string.h>
struct gomp_thread *nvptx_thrs __attribute__((shared,nocommon));
int __gomp_team_num __attribute__((shared,nocommon));
/* Number of active target threads in team, used in ACC mode. */
unsigned int __nvptx_omp_num_threads __attribute__((shared,nocommon));
static void gomp_thread_start (struct gomp_thread_pool *);
/* There should be some .shared space reserved for us. There's no way to
express this magic extern sizeless array in C so use asm. */
asm (".extern .shared .u8 __nvptx_lowlat_pool[];\n");
/* Defined in basic-allocator.c via config/nvptx/allocator.c. */
void __nvptx_lowlat_init (void *heap, size_t size);
/* This externally visible function handles target region entry. It
sets up a per-team thread pool and transfers control by calling FN (FN_DATA)
in the master thread or gomp_thread_start in other threads.
The name of this function is part of the interface with the compiler: for
each target region, GCC emits a PTX .kernel function that sets up soft-stack
and uniform-simt state and calls this function, passing in FN the original
function outlined for the target region. */
void
gomp_nvptx_main (void (*fn) (void *), void *fn_data)
{
int tid, ntids;
asm ("mov.u32 %0, %%tid.y;" : "=r" (tid));
asm ("mov.u32 %0, %%ntid.y;" : "=r" (ntids));
if (tid == 0)
{
gomp_global_icv.nthreads_var = ntids;
gomp_global_icv.thread_limit_var = ntids;
/* Starting additional threads is not supported. */
gomp_global_icv.dyn_var = true;
__gomp_team_num = 0;
nvptx_thrs = alloca (ntids * sizeof (*nvptx_thrs));
memset (nvptx_thrs, 0, ntids * sizeof (*nvptx_thrs));
/* Find the low-latency heap details .... */
uint32_t *shared_pool;
uint32_t shared_pool_size = 0;
asm ("cvta.shared.u64\t%0, __nvptx_lowlat_pool;" : "=r"(shared_pool));
#if __PTX_ISA_VERSION_MAJOR__ > 4 \
|| (__PTX_ISA_VERSION_MAJOR__ == 4 && __PTX_ISA_VERSION_MINOR__ >= 1)
asm ("mov.u32\t%0, %%dynamic_smem_size;\n"
: "=r"(shared_pool_size));
#endif
__nvptx_lowlat_init (shared_pool, shared_pool_size);
/* Initialize the thread pool. */
struct gomp_thread_pool *pool = alloca (sizeof (*pool));
pool->threads = alloca (ntids * sizeof (*pool->threads));
for (tid = 0; tid < ntids; tid++)
pool->threads[tid] = nvptx_thrs + tid;
pool->threads_size = ntids;
pool->threads_used = ntids;
pool->threads_busy = 1;
pool->last_team = NULL;
gomp_simple_barrier_init (&pool->threads_dock, ntids);
nvptx_thrs[0].thread_pool = pool;
asm ("bar.sync 0;");
fn (fn_data);
gomp_free_thread (nvptx_thrs);
}
else
{
asm ("bar.sync 0;");
gomp_thread_start (nvptx_thrs[0].thread_pool);
}
}
/* This function contains the idle loop in which a thread waits
to be called up to become part of a team. */
static void
gomp_thread_start (struct gomp_thread_pool *pool)
{
struct gomp_thread *thr = gomp_thread ();
gomp_sem_init (&thr->release, 0);
thr->thread_pool = pool;
do
{
gomp_simple_barrier_wait (&pool->threads_dock);
if (!thr->fn)
continue;
thr->fn (thr->data);
thr->fn = NULL;
struct gomp_task *task = thr->task;
gomp_team_barrier_wait_final (&thr->ts.team->barrier);
gomp_finish_task (task);
}
/* Work around an NVIDIA driver bug: when generating sm_50 machine code,
it can trash stack pointer R1 in loops lacking exit edges. Add a cheap
artificial exit that the driver would not be able to optimize out. */
while (nvptx_thrs);
}
/* Launch a team. */
void
gomp_team_start (void (*fn) (void *), void *data, unsigned nthreads,
unsigned flags, struct gomp_team *team,
struct gomp_taskgroup *taskgroup)
{
struct gomp_thread *thr, *nthr;
struct gomp_task *task;
struct gomp_task_icv *icv;
struct gomp_thread_pool *pool;
unsigned long nthreads_var;
thr = gomp_thread ();
pool = thr->thread_pool;
task = thr->task;
icv = task ? &task->icv : &gomp_global_icv;
/* Always save the previous state, even if this isn't a nested team.
In particular, we should save any work share state from an outer
orphaned work share construct. */
team->prev_ts = thr->ts;
thr->ts.team = team;
thr->ts.team_id = 0;
++thr->ts.level;
if (nthreads > 1)
++thr->ts.active_level;
thr->ts.work_share = &team->work_shares[0];
thr->ts.last_work_share = NULL;
thr->ts.single_count = 0;
thr->ts.static_trip = 0;
thr->task = &team->implicit_task[0];
nthreads_var = icv->nthreads_var;
gomp_init_task (thr->task, task, icv);
team->implicit_task[0].icv.nthreads_var = nthreads_var;
team->implicit_task[0].taskgroup = taskgroup;
if (nthreads == 1)
return;
/* Release existing idle threads. */
for (unsigned i = 1; i < nthreads; ++i)
{
nthr = pool->threads[i];
nthr->ts.team = team;
nthr->ts.work_share = &team->work_shares[0];
nthr->ts.last_work_share = NULL;
nthr->ts.team_id = i;
nthr->ts.level = team->prev_ts.level + 1;
nthr->ts.active_level = thr->ts.active_level;
nthr->ts.single_count = 0;
nthr->ts.static_trip = 0;
nthr->task = &team->implicit_task[i];
gomp_init_task (nthr->task, task, icv);
team->implicit_task[i].icv.nthreads_var = nthreads_var;
team->implicit_task[i].taskgroup = taskgroup;
nthr->fn = fn;
nthr->data = data;
team->ordered_release[i] = &nthr->release;
}
gomp_simple_barrier_wait (&pool->threads_dock);
}
int
gomp_pause_host (void)
{
return -1;
}
#include "../../team.c"
#endif
|
