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
199
200
201
202
203
204
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
259
260
261
262
|
/*
* Copyright 2008-2013 NVIDIA Corporation
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
/*! \file inner_product.h
* \brief Mathematical inner product between ranges
*/
#pragma once
#include <thrust/detail/config.h>
#include <thrust/detail/execution_policy.h>
THRUST_NAMESPACE_BEGIN
/*! \addtogroup reductions
* \{
* \addtogroup transformed_reductions Transformed Reductions
* \ingroup reductions
* \{
*/
/*! \p inner_product calculates an inner product of the ranges
* <tt>[first1, last1)</tt> and <tt>[first2, first2 + (last1 - first1))</tt>.
*
* Specifically, this version of \p inner_product computes the sum
* <tt>init + (*first1 * *first2) + (*(first1+1) * *(first2+1)) + ... </tt>
*
* The algorithm's execution is parallelized as determined by \p exec.
*
* \param exec The execution policy to use for parallelization.
* \param first1 The beginning of the first sequence.
* \param last1 The end of the first sequence.
* \param first2 The beginning of the second sequence.
* \param init Initial value of the result.
* \return The inner product of sequences <tt>[first1, last1)</tt>
* and <tt>[first2, last2)</tt> plus \p init.
*
* \tparam DerivedPolicy The name of the derived execution policy.
* \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>,
* \tparam InputIterator2 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>,
* \tparam OutputType is a model of <a href="https://en.cppreference.com/w/cpp/named_req/CopyAssignable">Assignable</a>,
* and if \c x is an object of type \p OutputType, and \c y is an object of \p InputIterator1's \c value_type,
* and \c z is an object of \p InputIterator2's \c value_type, then <tt>x + y * z</tt> is defined
* and is convertible to \p OutputType.
*
* The following code demonstrates how to use \p inner_product to
* compute the dot product of two vectors using the \p thrust::host execution policy for parallelization.
*
* \code
* #include <thrust/inner_product.h>
* #include <thrust/execution_policy.h>
* ...
* float vec1[3] = {1.0f, 2.0f, 5.0f};
* float vec2[3] = {4.0f, 1.0f, 5.0f};
*
* float result = thrust::inner_product(thrust::host, vec1, vec1 + 3, vec2, 0.0f);
*
* // result == 31.0f
* \endcode
*
* \see https://en.cppreference.com/w/cpp/algorithm/inner_product
*/
template<typename DerivedPolicy,
typename InputIterator1,
typename InputIterator2,
typename OutputType>
__host__ __device__
OutputType inner_product(const thrust::detail::execution_policy_base<DerivedPolicy> &exec,
InputIterator1 first1,
InputIterator1 last1,
InputIterator2 first2,
OutputType init);
/*! \p inner_product calculates an inner product of the ranges
* <tt>[first1, last1)</tt> and <tt>[first2, first2 + (last1 - first1))</tt>.
*
* Specifically, this version of \p inner_product computes the sum
* <tt>init + (*first1 * *first2) + (*(first1+1) * *(first2+1)) + ... </tt>
*
* Unlike the C++ Standard Template Library function <tt>std::inner_product</tt>,
* this version offers no guarantee on order of execution.
*
* \param first1 The beginning of the first sequence.
* \param last1 The end of the first sequence.
* \param first2 The beginning of the second sequence.
* \param init Initial value of the result.
* \return The inner product of sequences <tt>[first1, last1)</tt>
* and <tt>[first2, last2)</tt> plus \p init.
*
* \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>,
* \tparam InputIterator2 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>,
* \tparam OutputType is a model of <a href="https://en.cppreference.com/w/cpp/named_req/CopyAssignable">Assignable</a>,
* and if \c x is an object of type \p OutputType, and \c y is an object of \p InputIterator1's \c value_type,
* and \c z is an object of \p InputIterator2's \c value_type, then <tt>x + y * z</tt> is defined
* and is convertible to \p OutputType.
*
* The following code demonstrates how to use \p inner_product to
* compute the dot product of two vectors.
*
* \code
* #include <thrust/inner_product.h>
* ...
* float vec1[3] = {1.0f, 2.0f, 5.0f};
* float vec2[3] = {4.0f, 1.0f, 5.0f};
*
* float result = thrust::inner_product(vec1, vec1 + 3, vec2, 0.0f);
*
* // result == 31.0f
* \endcode
*
* \see https://en.cppreference.com/w/cpp/algorithm/inner_product
*/
template<typename InputIterator1, typename InputIterator2, typename OutputType>
OutputType inner_product(InputIterator1 first1, InputIterator1 last1,
InputIterator2 first2, OutputType init);
/*! \p inner_product calculates an inner product of the ranges
* <tt>[first1, last1)</tt> and <tt>[first2, first2 + (last1 - first1))</tt>.
*
* This version of \p inner_product is identical to the first, except that is uses
* two user-supplied function objects instead of \c operator+ and \c operator*.
*
* Specifically, this version of \p inner_product computes the sum
* <tt>binary_op1( init, binary_op2(*first1, *first2) ), ... </tt>
*
* The algorithm's execution is parallelized as determined by \p exec.
*
* \param exec The execution policy to use for parallelization.
* \param first1 The beginning of the first sequence.
* \param last1 The end of the first sequence.
* \param first2 The beginning of the second sequence.
* \param init Initial value of the result.
* \param binary_op1 Generalized addition operation.
* \param binary_op2 Generalized multiplication operation.
* \return The inner product of sequences <tt>[first1, last1)</tt> and <tt>[first2, last2)</tt>.
*
* \tparam DerivedPolicy The name of the derived execution policy.
* \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>,
* and \p InputIterator1's \c value_type is convertible to \p BinaryFunction2's \c first_argument_type.
* \tparam InputIterator2 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>.
* and \p InputIterator2's \c value_type is convertible to \p BinaryFunction2's \c second_argument_type.
* \tparam OutputType is a model of <a href="https://en.cppreference.com/w/cpp/named_req/CopyAssignable">Assignable</a>,
* and \p OutputType is convertible to \p BinaryFunction1's \c first_argument_type.
* \tparam BinaryFunction1 is a model of <a href="https://en.cppreference.com/w/cpp/utility/functional/binary_function">Binary Function</a>,
* and \p BinaryFunction1's \c return_type is convertible to \p OutputType.
* \tparam BinaryFunction2 is a model of <a href="https://en.cppreference.com/w/cpp/utility/functional/binary_function">Binary Function</a>,
* and \p BinaryFunction2's \c return_type is convertible to \p BinaryFunction1's \c second_argument_type.
*
* \code
* #include <thrust/inner_product.h>
* #include <thrust/execution_policy.h>
* ...
* float vec1[3] = {1.0f, 2.0f, 5.0f};
* float vec2[3] = {4.0f, 1.0f, 5.0f};
*
* float init = 0.0f;
* thrust::plus<float> binary_op1;
* thrust::multiplies<float> binary_op2;
*
* float result = thrust::inner_product(thrust::host, vec1, vec1 + 3, vec2, init, binary_op1, binary_op2);
*
* // result == 31.0f
* \endcode
*
* \see https://en.cppreference.com/w/cpp/algorithm/inner_product
*/
template<typename DerivedPolicy,
typename InputIterator1,
typename InputIterator2,
typename OutputType,
typename BinaryFunction1,
typename BinaryFunction2>
__host__ __device__
OutputType inner_product(const thrust::detail::execution_policy_base<DerivedPolicy> &exec,
InputIterator1 first1,
InputIterator1 last1,
InputIterator2 first2,
OutputType init,
BinaryFunction1 binary_op1,
BinaryFunction2 binary_op2);
/*! \p inner_product calculates an inner product of the ranges
* <tt>[first1, last1)</tt> and <tt>[first2, first2 + (last1 - first1))</tt>.
*
* This version of \p inner_product is identical to the first, except that is uses
* two user-supplied function objects instead of \c operator+ and \c operator*.
*
* Specifically, this version of \p inner_product computes the sum
* <tt>binary_op1( init, binary_op2(*first1, *first2) ), ... </tt>
*
* Unlike the C++ Standard Template Library function <tt>std::inner_product</tt>,
* this version offers no guarantee on order of execution.
*
* \param first1 The beginning of the first sequence.
* \param last1 The end of the first sequence.
* \param first2 The beginning of the second sequence.
* \param init Initial value of the result.
* \param binary_op1 Generalized addition operation.
* \param binary_op2 Generalized multiplication operation.
* \return The inner product of sequences <tt>[first1, last1)</tt> and <tt>[first2, last2)</tt>.
*
* \tparam InputIterator1 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>,
* and \p InputIterator1's \c value_type is convertible to \p BinaryFunction2's \c first_argument_type.
* \tparam InputIterator2 is a model of <a href="https://en.cppreference.com/w/cpp/iterator/input_iterator">Input Iterator</a>.
* and \p InputIterator2's \c value_type is convertible to \p BinaryFunction2's \c second_argument_type.
* \tparam OutputType is a model of <a href="https://en.cppreference.com/w/cpp/named_req/CopyAssignable">Assignable</a>,
* and \p OutputType is convertible to \p BinaryFunction1's \c first_argument_type.
* \tparam BinaryFunction1 is a model of <a href="https://en.cppreference.com/w/cpp/utility/functional/binary_function">Binary Function</a>,
* and \p BinaryFunction1's \c return_type is convertible to \p OutputType.
* \tparam BinaryFunction2 is a model of <a href="https://en.cppreference.com/w/cpp/utility/functional/binary_function">Binary Function</a>,
* and \p BinaryFunction2's \c return_type is convertible to \p BinaryFunction1's \c second_argument_type.
*
* \code
* #include <thrust/inner_product.h>
* ...
* float vec1[3] = {1.0f, 2.0f, 5.0f};
* float vec2[3] = {4.0f, 1.0f, 5.0f};
*
* float init = 0.0f;
* thrust::plus<float> binary_op1;
* thrust::multiplies<float> binary_op2;
*
* float result = thrust::inner_product(vec1, vec1 + 3, vec2, init, binary_op1, binary_op2);
*
* // result == 31.0f
* \endcode
*
* \see https://en.cppreference.com/w/cpp/algorithm/inner_product
*/
template<typename InputIterator1, typename InputIterator2, typename OutputType,
typename BinaryFunction1, typename BinaryFunction2>
OutputType inner_product(InputIterator1 first1, InputIterator1 last1,
InputIterator2 first2, OutputType init,
BinaryFunction1 binary_op1, BinaryFunction2 binary_op2);
/*! \} // end transformed_reductions
* \} // end reductions
*/
THRUST_NAMESPACE_END
#include <thrust/detail/inner_product.inl>
|
