1 // -*- C++ -*-
2 
3 // Copyright (C) 2007-2018 Free Software Foundation, Inc.
4 //
5 // This file is part of the GNU ISO C++ Library.  This library is free
6 // software; you can redistribute it and/or modify it under the terms
7 // of the GNU General Public License as published by the Free Software
8 // Foundation; either version 3, or (at your option) any later
9 // version.
10 
11 // This library is distributed in the hope that it will be useful, but
12 // WITHOUT ANY WARRANTY; without even the implied warranty of
13 // MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the GNU
14 // General Public License for more details.
15 
16 // Under Section 7 of GPL version 3, you are granted additional
17 // permissions described in the GCC Runtime Library Exception, version
18 // 3.1, as published by the Free Software Foundation.
19 
20 // You should have received a copy of the GNU General Public License and
21 // a copy of the GCC Runtime Library Exception along with this program;
22 // see the files COPYING3 and COPYING.RUNTIME respectively.  If not, see
23 // <http://www.gnu.org/licenses/>.
24 
25 /** @file parallel/omp_loop.h
26  *  @brief Parallelization of embarrassingly parallel execution by
27  *  means of an OpenMP for loop.
28  *  This file is a GNU parallel extension to the Standard C++ Library.
29  */
30 
31 // Written by Felix Putze.
32 
33 #ifndef _GLIBCXX_PARALLEL_OMP_LOOP_H
34 #define _GLIBCXX_PARALLEL_OMP_LOOP_H 1
35 
36 #include <omp.h>
37 
38 #include <parallel/settings.h>
39 #include <parallel/basic_iterator.h>
40 #include <parallel/base.h>
41 
42 namespace __gnu_parallel
43 {
44   /** @brief Embarrassingly parallel algorithm for random access
45    * iterators, using an OpenMP for loop.
46    *
47    *  @param __begin Begin iterator of element sequence.
48    *  @param __end End iterator of element sequence.
49    *  @param __o User-supplied functor (comparator, predicate, adding
50    *  functor, etc.).
51    *  @param __f Functor to @a process an element with __op (depends on
52    *  desired functionality, e. g. for std::for_each(), ...).
53    *  @param __r Functor to @a add a single __result to the already
54    *  processed elements (depends on functionality).
55    *  @param __base Base value for reduction.
56    *  @param __output Pointer to position where final result is written to
57    *  @param __bound Maximum number of elements processed (e. g. for
58    *  std::count_n()).
59    *  @return User-supplied functor (that may contain a part of the result).
60    */
61   template<typename _RAIter,
62 	   typename _Op,
63 	   typename _Fu,
64 	   typename _Red,
65 	   typename _Result>
66     _Op
__for_each_template_random_access_omp_loop(_RAIter __begin,_RAIter __end,_Op __o,_Fu & __f,_Red __r,_Result __base,_Result & __output,typename std::iterator_traits<_RAIter>::difference_type __bound)67     __for_each_template_random_access_omp_loop(_RAIter __begin, _RAIter __end,
68 					       _Op __o, _Fu& __f, _Red __r,
69 					       _Result __base,
70 					       _Result& __output,
71       typename std::iterator_traits<_RAIter>::difference_type __bound)
72     {
73       typedef typename std::iterator_traits<_RAIter>::difference_type
74         _DifferenceType;
75 
76       _DifferenceType __length = __end - __begin;
77       _ThreadIndex __num_threads = __gnu_parallel::min<_DifferenceType>
78 	(__get_max_threads(), __length);
79 
80       _Result *__thread_results;
81 
82 #     pragma omp parallel num_threads(__num_threads)
83       {
84 #       pragma omp single
85 	{
86 	  __num_threads = omp_get_num_threads();
87 	  __thread_results = new _Result[__num_threads];
88 
89 	  for (_ThreadIndex __i = 0; __i < __num_threads; ++__i)
90 	    __thread_results[__i] = _Result();
91 	}
92 
93         _ThreadIndex __iam = omp_get_thread_num();
94 
95 #pragma omp for schedule(dynamic, _Settings::get().workstealing_chunk_size)
96         for (_DifferenceType __pos = 0; __pos < __length; ++__pos)
97           __thread_results[__iam] = __r(__thread_results[__iam],
98 					__f(__o, __begin+__pos));
99       } //parallel
100 
101       for (_ThreadIndex __i = 0; __i < __num_threads; ++__i)
102         __output = __r(__output, __thread_results[__i]);
103 
104       delete [] __thread_results;
105 
106       // Points to last element processed (needed as return value for
107       // some algorithms like transform).
108       __f._M_finish_iterator = __begin + __length;
109 
110       return __o;
111     }
112 
113 } // end namespace
114 
115 #endif /* _GLIBCXX_PARALLEL_OMP_LOOP_H */
116