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
|
/******************************************************************************
* Copyright (c) 2011, Duane Merrill. All rights reserved.
* Copyright (c) 2011-2018, NVIDIA CORPORATION. All rights reserved.
*
* Redistribution and use in source and binary forms, with or without
* modification, are permitted provided that the following conditions are met:
* * Redistributions of source code must retain the above copyright
* notice, this list of conditions and the following disclaimer.
* * Redistributions in binary form must reproduce the above copyright
* notice, this list of conditions and the following disclaimer in the
* documentation and/or other materials provided with the distribution.
* * Neither the name of the NVIDIA CORPORATION nor the
* names of its contributors may be used to endorse or promote products
* derived from this software without specific prior written permission.
*
* THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" AND
* ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE IMPLIED
* WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE ARE
* DISCLAIMED. IN NO EVENT SHALL NVIDIA CORPORATION BE LIABLE FOR ANY
* DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES
* (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES;
* LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND
* ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, OR TORT
* (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT OF THE USE OF THIS
* SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF SUCH DAMAGE.
*
******************************************************************************/
/**
* @file
* Thread utilities for sequential search
*/
#pragma once
#include <cub/config.cuh>
#if defined(_CCCL_IMPLICIT_SYSTEM_HEADER_GCC)
# pragma GCC system_header
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_CLANG)
# pragma clang system_header
#elif defined(_CCCL_IMPLICIT_SYSTEM_HEADER_MSVC)
# pragma system_header
#endif // no system header
#include <iterator>
#include <cub/util_namespace.cuh>
#include <cub/util_type.cuh>
#include <nv/target>
CUB_NAMESPACE_BEGIN
/**
* Computes the begin offsets into A and B for the specific diagonal
*/
template <
typename AIteratorT,
typename BIteratorT,
typename OffsetT,
typename CoordinateT>
__host__ __device__ __forceinline__ void MergePathSearch(
OffsetT diagonal,
AIteratorT a,
BIteratorT b,
OffsetT a_len,
OffsetT b_len,
CoordinateT& path_coordinate)
{
/// The value type of the input iterator
using T = cub::detail::value_t<AIteratorT>;
OffsetT split_min = CUB_MAX(diagonal - b_len, 0);
OffsetT split_max = CUB_MIN(diagonal, a_len);
while (split_min < split_max)
{
OffsetT split_pivot = (split_min + split_max) >> 1;
if (a[split_pivot] <= b[diagonal - split_pivot - 1])
{
// Move candidate split range up A, down B
split_min = split_pivot + 1;
}
else
{
// Move candidate split range up B, down A
split_max = split_pivot;
}
}
path_coordinate.x = CUB_MIN(split_min, a_len);
path_coordinate.y = diagonal - split_min;
}
/**
* @brief Returns the offset of the first value within @p input which does not compare
* less than @p val
*
* @param[in] input
* Input sequence
*
* @param[in] num_items
* Input sequence length
*
* @param[in] val
* Search key
*/
template <typename InputIteratorT, typename OffsetT, typename T>
__device__ __forceinline__ OffsetT LowerBound(InputIteratorT input, OffsetT num_items, T val)
{
OffsetT retval = 0;
while (num_items > 0)
{
OffsetT half = num_items >> 1;
if (input[retval + half] < val)
{
retval = retval + (half + 1);
num_items = num_items - (half + 1);
}
else
{
num_items = half;
}
}
return retval;
}
/**
* @brief Returns the offset of the first value within @p input which compares
* greater than @p val
*
* @param[in] input
* Input sequence
*
* @param[in] num_items
* Input sequence length
*
* @param[in] val
* Search key
*/
template <typename InputIteratorT, typename OffsetT, typename T>
__device__ __forceinline__ OffsetT UpperBound(InputIteratorT input, OffsetT num_items, T val)
{
OffsetT retval = 0;
while (num_items > 0)
{
OffsetT half = num_items >> 1;
if (val < input[retval + half])
{
num_items = half;
}
else
{
retval = retval + (half + 1);
num_items = num_items - (half + 1);
}
}
return retval;
}
#if defined(__CUDA_FP16_TYPES_EXIST__)
/**
* @param[in] input
* Input sequence
*
* @param[in] num_items
* Input sequence length
*
* @param[in] val
* Search key
*/
template <typename InputIteratorT, typename OffsetT>
__device__ __forceinline__ OffsetT UpperBound(InputIteratorT input, OffsetT num_items, __half val)
{
OffsetT retval = 0;
while (num_items > 0)
{
OffsetT half = num_items >> 1;
bool lt;
NV_IF_TARGET(NV_PROVIDES_SM_53,
(lt = val < input[retval + half];),
(lt = __half2float(val) < __half2float(input[retval + half]);));
if (lt)
{
num_items = half;
}
else
{
retval = retval + (half + 1);
num_items = num_items - (half + 1);
}
}
return retval;
}
#endif
CUB_NAMESPACE_END
|
