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
|
/* 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. */
#ifndef GOMP_BARRIER_H
#define GOMP_BARRIER_H 1
#include "mutex.h"
typedef struct
{
/* Make sure total/generation is in a mostly read cacheline, while
awaited in a separate cacheline. */
unsigned total __attribute__((aligned (64)));
unsigned generation;
unsigned awaited __attribute__((aligned (64)));
unsigned awaited_final;
} gomp_barrier_t;
typedef unsigned int gomp_barrier_state_t;
/* The generation field contains a counter in the high bits, with a few
low bits dedicated to flags. Note that TASK_PENDING and WAS_LAST can
share space because WAS_LAST is never stored back to generation. */
#define BAR_TASK_PENDING 1
#define BAR_WAS_LAST 1
#define BAR_WAITING_FOR_TASK 2
#define BAR_CANCELLED 4
#define BAR_INCR 8
static inline void gomp_barrier_init (gomp_barrier_t *bar, unsigned count)
{
bar->total = count;
bar->awaited = count;
bar->awaited_final = count;
bar->generation = 0;
}
static inline void gomp_barrier_reinit (gomp_barrier_t *bar, unsigned count)
{
__atomic_add_fetch (&bar->awaited, count - bar->total, MEMMODEL_ACQ_REL);
bar->total = count;
}
static inline void gomp_barrier_destroy (gomp_barrier_t *bar)
{
}
extern void gomp_barrier_wait (gomp_barrier_t *);
extern void gomp_barrier_wait_last (gomp_barrier_t *);
extern void gomp_barrier_wait_end (gomp_barrier_t *, gomp_barrier_state_t);
extern void gomp_team_barrier_wait (gomp_barrier_t *);
extern void gomp_team_barrier_wait_final (gomp_barrier_t *);
extern void gomp_team_barrier_wait_end (gomp_barrier_t *,
gomp_barrier_state_t);
extern bool gomp_team_barrier_wait_cancel (gomp_barrier_t *);
extern bool gomp_team_barrier_wait_cancel_end (gomp_barrier_t *,
gomp_barrier_state_t);
extern void gomp_team_barrier_wake (gomp_barrier_t *, int);
struct gomp_team;
extern void gomp_team_barrier_cancel (struct gomp_team *);
static inline gomp_barrier_state_t
gomp_barrier_wait_start (gomp_barrier_t *bar)
{
unsigned int ret = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
ret &= -BAR_INCR | BAR_CANCELLED;
/* A memory barrier is needed before exiting from the various forms
of gomp_barrier_wait, to satisfy OpenMP API version 3.1 section
2.8.6 flush Construct, which says there is an implicit flush during
a barrier region. This is a convenient place to add the barrier,
so we use MEMMODEL_ACQ_REL here rather than MEMMODEL_ACQUIRE. */
if (__atomic_add_fetch (&bar->awaited, -1, MEMMODEL_ACQ_REL) == 0)
ret |= BAR_WAS_LAST;
return ret;
}
static inline gomp_barrier_state_t
gomp_barrier_wait_cancel_start (gomp_barrier_t *bar)
{
return gomp_barrier_wait_start (bar);
}
/* This is like gomp_barrier_wait_start, except it decrements
bar->awaited_final rather than bar->awaited and should be used
for the gomp_team_end barrier only. */
static inline gomp_barrier_state_t
gomp_barrier_wait_final_start (gomp_barrier_t *bar)
{
unsigned int ret = __atomic_load_n (&bar->generation, MEMMODEL_ACQUIRE);
ret &= -BAR_INCR | BAR_CANCELLED;
/* See above gomp_barrier_wait_start comment. */
if (__atomic_add_fetch (&bar->awaited_final, -1, MEMMODEL_ACQ_REL) == 0)
ret |= BAR_WAS_LAST;
return ret;
}
static inline bool
gomp_barrier_last_thread (gomp_barrier_state_t state)
{
return state & BAR_WAS_LAST;
}
/* All the inlines below must be called with team->task_lock
held. */
static inline void
gomp_team_barrier_set_task_pending (gomp_barrier_t *bar)
{
bar->generation |= BAR_TASK_PENDING;
}
static inline void
gomp_team_barrier_clear_task_pending (gomp_barrier_t *bar)
{
bar->generation &= ~BAR_TASK_PENDING;
}
static inline void
gomp_team_barrier_set_waiting_for_tasks (gomp_barrier_t *bar)
{
bar->generation |= BAR_WAITING_FOR_TASK;
}
static inline bool
gomp_team_barrier_waiting_for_tasks (gomp_barrier_t *bar)
{
return (bar->generation & BAR_WAITING_FOR_TASK) != 0;
}
static inline bool
gomp_team_barrier_cancelled (gomp_barrier_t *bar)
{
return __builtin_expect ((bar->generation & BAR_CANCELLED) != 0, 0);
}
static inline void
gomp_team_barrier_done (gomp_barrier_t *bar, gomp_barrier_state_t state)
{
bar->generation = (state & -BAR_INCR) + BAR_INCR;
}
#endif /* GOMP_BARRIER_H */
|
