OpenFPM_pdata  4.1.0
Project that contain the implementation of distributed structures
mutex.cuh
Go to the documentation of this file.
1 /******************************************************************************
2  * Copyright (c) 2011, Duane Merrill. All rights reserved.
3  * Copyright (c) 2011-2018, NVIDIA CORPORATION. All rights reserved.
4  *
5  * Redistribution and use in source and binary forms, with or without
6  * modification, are permitted provided that the following conditions are met:
7  * * Redistributions of source code must retain the above copyright
8  * notice, this list of conditions and the following disclaimer.
9  * * Redistributions in binary form must reproduce the above copyright
10  * notice, this list of conditions and the following disclaimer in the
11  * documentation and/or other materials provided with the distribution.
12  * * Neither the name of the NVIDIA CORPORATION nor the
13  * names of its contributors may be used to endorse or promote products
14  * derived from this software without specific prior written permission.
15  *
16  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
17  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
18  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
19  * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
20  * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
21  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
22  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
23  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
24  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
25  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
26  *
27  ******************************************************************************/
28 
35 #pragma once
36 
37 #if (__cplusplus > 199711L) || (defined(_MSC_VER) && _MSC_VER >= 1800)
38  #include <mutex>
39 #else
40  #if defined(_WIN32) || defined(_WIN64)
41  #include <intrin.h>
42 
43  #define WIN32_LEAN_AND_MEAN
44  #define NOMINMAX
45  #include <windows.h>
46  #undef WIN32_LEAN_AND_MEAN
47  #undef NOMINMAX
48 
52  #pragma intrinsic(_ReadWriteBarrier)
53 
54  #endif
55 #endif
56 
57 #include "../util_namespace.cuh"
58 
59 
61 CUB_NS_PREFIX
62 
64 namespace cub {
65 
66 
72 struct Mutex
73 {
74 #if (__cplusplus > 199711L) || (defined(_MSC_VER) && _MSC_VER >= 1800)
75 
76  std::mutex mtx;
77 
78  void Lock()
79  {
80  mtx.lock();
81  }
82 
83  void Unlock()
84  {
85  mtx.unlock();
86  }
87 
88  void TryLock()
89  {
90  mtx.try_lock();
91  }
92 
93 #else //__cplusplus > 199711L
94 
95  #if defined(_MSC_VER)
96 
97  // Microsoft VC++
98  typedef long Spinlock;
99 
100  #else
101 
102  // GNU g++
103  typedef int Spinlock;
104 
108  __forceinline__ void _ReadWriteBarrier()
109  {
110  __sync_synchronize();
111  }
112 
116  __forceinline__ long _InterlockedExchange(volatile int * const Target, const int Value)
117  {
118  // NOTE: __sync_lock_test_and_set would be an acquire barrier, so we force a full barrier
120  return __sync_lock_test_and_set(Target, Value);
121  }
122 
126  __forceinline__ void YieldProcessor()
127  {
128  }
129 
130  #endif // defined(_MSC_VER)
131 
133  volatile Spinlock lock;
134 
138  Mutex() : lock(0) {}
139 
143  __forceinline__ void Lock()
144  {
145  while (1)
146  {
147  if (!_InterlockedExchange(&lock, 1)) return;
148  while (lock) YieldProcessor();
149  }
150  }
151 
152 
156  __forceinline__ void Unlock()
157  {
159  lock = 0;
160  }
161 
162 #endif // __cplusplus > 199711L
163 
164 };
165 
166 
167 
168 
169 } // CUB namespace
170 CUB_NS_POSTFIX // Optional outer namespace(s)
171 
__forceinline__ void Lock()
Definition: mutex.cuh:143
Optional outer namespace(s)
__forceinline__ void _ReadWriteBarrier()
Definition: mutex.cuh:108
volatile Spinlock lock
Lock member.
Definition: mutex.cuh:133
__forceinline__ void Unlock()
Definition: mutex.cuh:156
__forceinline__ void YieldProcessor()
Definition: mutex.cuh:126
__forceinline__ long _InterlockedExchange(volatile int *const Target, const int Value)
Definition: mutex.cuh:116