1 // -*- C++ -*- 2 3 // Copyright (C) 2007-2014 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