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) 2005-2015 Free Software Foundation, Inc.
Contributed by Richard Henderson <rth@redhat.com>.
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 is a Linux specific implementation of a barrier synchronization
mechanism for libgomp. This type is private to the library. This
implementation uses atomic instructions and the futex syscall. */
#include <limits.h>
#include "wait.h"
void
gomp_barrier_wait_end (gomp_barrier_t *bar, gomp_barrier_state_t state)
{
if (__builtin_expect (state & BAR_WAS_LAST, 0))
{
/* Next time we'll be awaiting TOTAL threads again. */
bar->awaited = bar->total;
__atomic_store_n (&bar->generation, bar->generation + BAR_INCR,
MEMMODEL_RELEASE);
futex_wake ((int *) &bar->generation, INT_MAX);
}
else
{
do
do_wait ((int *) &bar->generation, state);
while (__atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE) == state);
}
}
void
gomp_barrier_wait (gomp_barrier_t *bar)
{
gomp_barrier_wait_end (bar, gomp_barrier_wait_start (bar));
}
/* Like gomp_barrier_wait, except that if the encountering thread
is not the last one to hit the barrier, it returns immediately.
The intended usage is that a thread which intends to gomp_barrier_destroy
this barrier calls gomp_barrier_wait, while all other threads
call gomp_barrier_wait_last. When gomp_barrier_wait returns,
the barrier can be safely destroyed. */
void
gomp_barrier_wait_last (gomp_barrier_t *bar)
{
gomp_barrier_state_t state = gomp_barrier_wait_start (bar);
if (state & BAR_WAS_LAST)
gomp_barrier_wait_end (bar, state);
}
void
gomp_team_barrier_wake (gomp_barrier_t *bar, int count)
{
futex_wake ((int *) &bar->generation, count == 0 ? INT_MAX : count);
}
void
gomp_team_barrier_wait_end (gomp_barrier_t *bar, gomp_barrier_state_t state)
{
unsigned int generation, gen;
if (__builtin_expect (state & BAR_WAS_LAST, 0))
{
/* Next time we'll be awaiting TOTAL threads again. */
struct gomp_thread *thr = gomp_thread ();
struct gomp_team *team = thr->ts.team;
bar->awaited = bar->total;
team->work_share_cancelled = 0;
if (__builtin_expect (team->task_count, 0))
{
gomp_barrier_handle_tasks (state);
state &= ~BAR_WAS_LAST;
}
else
{
state &= ~BAR_CANCELLED;
state += BAR_INCR - BAR_WAS_LAST;
__atomic_store_n (&bar->generation, state, MEMMODEL_RELEASE);
futex_wake ((int *) &bar->generation, INT_MAX);
return;
}
}
generation = state;
state &= ~BAR_CANCELLED;
do
{
do_wait ((int *) &bar->generation, generation);
gen = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
if (__builtin_expect (gen & BAR_TASK_PENDING, 0))
{
gomp_barrier_handle_tasks (state);
gen = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
}
generation |= gen & BAR_WAITING_FOR_TASK;
}
while (gen != state + BAR_INCR);
}
void
gomp_team_barrier_wait (gomp_barrier_t *bar)
{
gomp_team_barrier_wait_end (bar, gomp_barrier_wait_start (bar));
}
void
gomp_team_barrier_wait_final (gomp_barrier_t *bar)
{
gomp_barrier_state_t state = gomp_barrier_wait_final_start (bar);
if (__builtin_expect (state & BAR_WAS_LAST, 0))
bar->awaited_final = bar->total;
gomp_team_barrier_wait_end (bar, state);
}
bool
gomp_team_barrier_wait_cancel_end (gomp_barrier_t *bar,
gomp_barrier_state_t state)
{
unsigned int generation, gen;
if (__builtin_expect (state & BAR_WAS_LAST, 0))
{
/* Next time we'll be awaiting TOTAL threads again. */
/* BAR_CANCELLED should never be set in state here, because
cancellation means that at least one of the threads has been
cancelled, thus on a cancellable barrier we should never see
all threads to arrive. */
struct gomp_thread *thr = gomp_thread ();
struct gomp_team *team = thr->ts.team;
bar->awaited = bar->total;
team->work_share_cancelled = 0;
if (__builtin_expect (team->task_count, 0))
{
gomp_barrier_handle_tasks (state);
state &= ~BAR_WAS_LAST;
}
else
{
state += BAR_INCR - BAR_WAS_LAST;
__atomic_store_n (&bar->generation, state, MEMMODEL_RELEASE);
futex_wake ((int *) &bar->generation, INT_MAX);
return false;
}
}
if (__builtin_expect (state & BAR_CANCELLED, 0))
return true;
generation = state;
do
{
do_wait ((int *) &bar->generation, generation);
gen = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
if (__builtin_expect (gen & BAR_CANCELLED, 0))
return true;
if (__builtin_expect (gen & BAR_TASK_PENDING, 0))
{
gomp_barrier_handle_tasks (state);
gen = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
}
generation |= gen & BAR_WAITING_FOR_TASK;
}
while (gen != state + BAR_INCR);
return false;
}
bool
gomp_team_barrier_wait_cancel (gomp_barrier_t *bar)
{
return gomp_team_barrier_wait_cancel_end (bar, gomp_barrier_wait_start (bar));
}
void
gomp_team_barrier_cancel (struct gomp_team *team)
{
gomp_mutex_lock (&team->task_lock);
if (team->barrier.generation & BAR_CANCELLED)
{
gomp_mutex_unlock (&team->task_lock);
return;
}
team->barrier.generation |= BAR_CANCELLED;
gomp_mutex_unlock (&team->task_lock);
futex_wake ((int *) &team->barrier.generation, INT_MAX);
}
|
