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
|
/*
* Copyright 2011, Ben Langmead <langmea@cs.jhu.edu>
*
* This file is part of Bowtie 2.
*
* Bowtie 2 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 of the License, or
* (at your option) any later version.
*
* Bowtie 2 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.
*
* You should have received a copy of the GNU General Public License
* along with Bowtie 2. If not, see <http://www.gnu.org/licenses/>.
*/
#ifndef THREADING_H_
#define THREADING_H_
#include <cstdio>
#include <cstdlib>
#include <cstring>
#include <iostream>
#include <mutex>
#include "bt2_locks.h"
#ifdef WITH_QUEUELOCK
#define MUTEX_T mcs_lock
#elif defined(NO_SPINLOCK)
#define MUTEX_T std::mutex
#else
#define MUTEX_T spin_lock
#endif
struct thread_tracking_pair {
int tid;
std::atomic<int>* done;
};
#if defined(_TTHREAD_WIN32_)
#define SLEEP(x) Sleep(x)
#else
#define SLEEP(x) do { \
const static timespec ts_tmp_ = {0, 1000000 * x}; \
nanosleep(&ts_tmp_, NULL); \
} while(false)
#endif
#ifdef NO_SPINLOCK
# ifdef WITH_QUEUELOCK
# define MUTEX_T mcs_lock
# else
# define MUTEX_T std::mutex
# endif
#else
# ifdef WITH_TBB
# define MUTEX_T spin_lock
# endif
#endif /* NO_SPINLOCK */
/**
* Wrap a lock; obtain lock upon construction, release upon destruction.
*/
class ThreadSafe {
public:
ThreadSafe(MUTEX_T& mutex) :
#if NO_SPINLOCK && WITH_QUEUELOCK
node_{},
#endif
mutex_(mutex) {
#if NO_SPINLOCK && WITH_QUEUELOCK
mutex_.lock(node_);
#else
mutex_.lock();
#endif
}
~ThreadSafe() {
#if NO_SPINLOCK && WITH_QUEUELOCK
mutex_.unlock(node_);
#else
mutex_.unlock();
#endif
}
private:
#if NO_SPINLOCK && WITH_QUEUELOCK
MUTEX_T::mcs_node node_;
#endif
MUTEX_T& mutex_;
};
#ifdef WITH_TBB
#ifdef WITH_AFFINITY
//ripped entirely from;
//https://software.intel.com/en-us/blogs/2013/10/31/applying-intel-threading-building-blocks-observers-for-thread-affinity-on-intel
class concurrency_tracker: public tbb::task_scheduler_observer {
std::atomic<int> num_threads;
public:
concurrency_tracker() : num_threads() { observe(true); }
/*override*/ void on_scheduler_entry( bool ) { ++num_threads; }
/*override*/ void on_scheduler_exit( bool ) { --num_threads; }
int get_concurrency() { return num_threads; }
};
class pinning_observer: public tbb::task_scheduler_observer {
cpu_set_t *mask;
int ncpus;
const int pinning_step;
std::atomic<int> thread_index;
public:
pinning_observer( int pinning_step=1 ) : pinning_step(pinning_step), thread_index() {
for ( ncpus = sizeof(cpu_set_t)/CHAR_BIT; ncpus < 16*1024 /* some reasonable limit */; ncpus <<= 1 ) {
mask = CPU_ALLOC( ncpus );
if ( !mask ) break;
const size_t size = CPU_ALLOC_SIZE( ncpus );
CPU_ZERO_S( size, mask );
const int err = sched_getaffinity( 0, size, mask );
if ( !err ) break;
CPU_FREE( mask );
mask = NULL;
if ( errno != EINVAL ) break;
}
if ( !mask )
std::cout << "Warning: Failed to obtain process affinity mask. Thread affinitization is disabled." << std::endl;
}
/*override*/ void on_scheduler_entry( bool ) {
if ( !mask ) return;
const size_t size = CPU_ALLOC_SIZE( ncpus );
const int num_cpus = CPU_COUNT_S( size, mask );
int thr_idx =
//cwilks: we're one interface version lower than what
//is required for task arena (7000 vs. 7001)
#if USE_TASK_ARENA_CURRENT_SLOT
tbb::task_arena::current_slot();
#else
thread_index++;
#endif
#if __MIC__
thr_idx += 1; // To avoid logical thread zero for the master thread on Intel(R) Xeon Phi(tm)
#endif
thr_idx %= num_cpus; // To limit unique number in [0; num_cpus-1] range
// Place threads with specified step
int cpu_idx = 0;
for ( int i = 0, offset = 0; i<thr_idx; ++i ) {
cpu_idx += pinning_step;
if ( cpu_idx >= num_cpus )
cpu_idx = ++offset;
}
// Find index of 'cpu_idx'-th bit equal to 1
int mapped_idx = -1;
while ( cpu_idx >= 0 ) {
if ( CPU_ISSET_S( ++mapped_idx, size, mask ) )
--cpu_idx;
}
cpu_set_t *target_mask = CPU_ALLOC( ncpus );
CPU_ZERO_S( size, target_mask );
CPU_SET_S( mapped_idx, size, target_mask );
const int err = sched_setaffinity( 0, size, target_mask );
//std::cout << "Just set affinity for thread " << thr_idx << "\n";
if ( err ) {
std::cout << "Failed to set thread affinity!n";
exit( EXIT_FAILURE );
}
#if LOG_PINNING
else {
std::stringstream ss;
ss << "Set thread affinity: Thread " << thr_idx << ": CPU " << mapped_idx << std::endl;
std::cerr << ss.str();
}
#endif
CPU_FREE( target_mask );
}
~pinning_observer() {
if ( mask )
CPU_FREE( mask );
}
};
#endif
#endif
#endif
|
