/home/docs/checkouts/readthedocs.org/user_builds/advanced-micro-devices-hipcub/checkouts/docs-5.6.0/hipcub/include/hipcub/backend/cub/device/device_segmented_reduce.hpp Source File

• home
• docs
• checkouts
• readthedocs.org
• user_builds
• advanced-micro-devices-hipcub
• checkouts
• docs-5.6.0
• hipcub
• include
• hipcub
• backend
• cub
• device

device_segmented_reduce.hpp

1 /******************************************************************************

2  * Copyright (c) 2010-2011, Duane Merrill. All rights reserved.

3  * Copyright (c) 2011-2018, NVIDIA CORPORATION. All rights reserved.

4  * Modifications Copyright (c) 2017-2020, Advanced Micro Devices, Inc. All rights reserved.

5  *

6  * Redistribution and use in source and binary forms, with or without

7  * modification, are permitted provided that the following conditions are met:

8  * * Redistributions of source code must retain the above copyright

9  * notice, this list of conditions and the following disclaimer.

10  * * Redistributions in binary form must reproduce the above copyright

11  * notice, this list of conditions and the following disclaimer in the

12  * documentation and/or other materials provided with the distribution.

13  * * Neither the name of the NVIDIA CORPORATION nor the

14  * names of its contributors may be used to endorse or promote products

15  * derived from this software without specific prior written permission.

16  *

17  * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND

18  * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED

19  * WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE

20  * DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY

21  * DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES

22  * (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;

23  * LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND

24  * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT

25  * (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS

26  * SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.

27  *

28  ******************************************************************************/

29 

30 #ifndef HIPCUB_CUB_DEVICE_DEVICE_SEGMENTED_REDUCE_HPP_

31 #define HIPCUB_CUB_DEVICE_DEVICE_SEGMENTED_REDUCE_HPP_

32 

33 #include "../../../config.hpp"

34 

35 #include <cub/device/device_segmented_reduce.cuh>

36 

37 BEGIN_HIPCUB_NAMESPACE

38 

39 struct DeviceSegmentedReduce

40 {

41  template<

42  typename InputIteratorT,

43  typename OutputIteratorT,

44  typename OffsetIteratorT,

45  typename ReductionOp,

46  typename T

47  >

48  HIPCUB_RUNTIME_FUNCTION static

49  hipError_t Reduce(void * d_temp_storage,

50  size_t& temp_storage_bytes,

51  InputIteratorT d_in,

52  OutputIteratorT d_out,

53  int num_segments,

54  OffsetIteratorT d_begin_offsets,

55  OffsetIteratorT d_end_offsets,

56  ReductionOp reduction_op,

57  T initial_value,

58  hipStream_t stream = 0,

59  bool debug_synchronous = false)

60  {

61  return hipCUDAErrorTohipError(

62  ::cub::DeviceSegmentedReduce::Reduce(

63  d_temp_storage, temp_storage_bytes,

64  d_in, d_out, num_segments,

65  d_begin_offsets, d_end_offsets,

66  reduction_op, initial_value,

67  stream, debug_synchronous

68  )

69  );

70  }

71 

72  template<

73  typename InputIteratorT,

74  typename OutputIteratorT,

75  typename OffsetIteratorT

76  >

77  HIPCUB_RUNTIME_FUNCTION static

78  hipError_t Sum(void * d_temp_storage,

79  size_t& temp_storage_bytes,

80  InputIteratorT d_in,

81  OutputIteratorT d_out,

82  int num_segments,

83  OffsetIteratorT d_begin_offsets,

84  OffsetIteratorT d_end_offsets,

85  hipStream_t stream = 0,

86  bool debug_synchronous = false)

87  {

88  return hipCUDAErrorTohipError(

89  ::cub::DeviceSegmentedReduce::Sum(

90  d_temp_storage, temp_storage_bytes,

91  d_in, d_out, num_segments,

92  d_begin_offsets, d_end_offsets,

93  stream, debug_synchronous

94  )

95  );

96  }

97 

98  template<

99  typename InputIteratorT,

100  typename OutputIteratorT,

101  typename OffsetIteratorT

102  >

103  HIPCUB_RUNTIME_FUNCTION static

104  hipError_t Min(void * d_temp_storage,

105  size_t& temp_storage_bytes,

106  InputIteratorT d_in,

107  OutputIteratorT d_out,

108  int num_segments,

109  OffsetIteratorT d_begin_offsets,

110  OffsetIteratorT d_end_offsets,

111  hipStream_t stream = 0,

112  bool debug_synchronous = false)

113  {

114  return hipCUDAErrorTohipError(

115  ::cub::DeviceSegmentedReduce::Min(

116  d_temp_storage, temp_storage_bytes,

117  d_in, d_out, num_segments,

118  d_begin_offsets, d_end_offsets,

119  stream, debug_synchronous

120  )

121  );

122  }

123 

124  template<

125  typename InputIteratorT,

126  typename OutputIteratorT,

127  typename OffsetIteratorT

128  >

129  HIPCUB_RUNTIME_FUNCTION static

130  hipError_t ArgMin(void * d_temp_storage,

131  size_t& temp_storage_bytes,

132  InputIteratorT d_in,

133  OutputIteratorT d_out,

134  int num_segments,

135  OffsetIteratorT d_begin_offsets,

136  OffsetIteratorT d_end_offsets,

137  hipStream_t stream = 0,

138  bool debug_synchronous = false)

139  {

140  return hipCUDAErrorTohipError(

141  ::cub::DeviceSegmentedReduce::ArgMin(

142  d_temp_storage, temp_storage_bytes,

143  d_in, d_out, num_segments,

144  d_begin_offsets, d_end_offsets,

145  stream, debug_synchronous

146  )

147  );

148  }

149 

150  template<

151  typename InputIteratorT,

152  typename OutputIteratorT,

153  typename OffsetIteratorT

154  >

155  HIPCUB_RUNTIME_FUNCTION static

156  hipError_t Max(void * d_temp_storage,

157  size_t& temp_storage_bytes,

158  InputIteratorT d_in,

159  OutputIteratorT d_out,

160  int num_segments,

161  OffsetIteratorT d_begin_offsets,

162  OffsetIteratorT d_end_offsets,

163  hipStream_t stream = 0,

164  bool debug_synchronous = false)

165  {

166  return hipCUDAErrorTohipError(

167  ::cub::DeviceSegmentedReduce::Max(

168  d_temp_storage, temp_storage_bytes,

169  d_in, d_out, num_segments,

170  d_begin_offsets, d_end_offsets,

171  stream, debug_synchronous

172  )

173  );

174  }

175 

176  template<

177  typename InputIteratorT,

178  typename OutputIteratorT,

179  typename OffsetIteratorT

180  >

181  HIPCUB_RUNTIME_FUNCTION static

182  hipError_t ArgMax(void * d_temp_storage,

183  size_t& temp_storage_bytes,

184  InputIteratorT d_in,

185  OutputIteratorT d_out,

186  int num_segments,

187  OffsetIteratorT d_begin_offsets,

188  OffsetIteratorT d_end_offsets,

189  hipStream_t stream = 0,

190  bool debug_synchronous = false)

191  {

192  return hipCUDAErrorTohipError(

193  ::cub::DeviceSegmentedReduce::ArgMax(

194  d_temp_storage, temp_storage_bytes,

195  d_in, d_out, num_segments,

196  d_begin_offsets, d_end_offsets,

197  stream, debug_synchronous

198  )

199  );

200  }

201 };

202 

203 END_HIPCUB_NAMESPACE

204 

205 #endif // HIPCUB_CUB_DEVICE_DEVICE_SEGMENTED_REDUCE_HPP_

hipcub::ArgMax

Definition: thread_operators.hpp:126

hipcub::ArgMin

Definition: thread_operators.hpp:141

hipcub::DeviceSegmentedReduce

Definition: device_segmented_reduce.hpp:40

hipcub::Max

Definition: thread_operators.hpp:106

hipcub::Min

Definition: thread_operators.hpp:116

hipcub::Sum

Definition: thread_operators.hpp:76