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
|
/*
* Copyright (c) 2019 Samsung Electronics Co., Ltd. All Rights Reserved
* Copyright (c) 2019 ARM Limited.
*
* SPDX-License-Identifier: MIT
*
* Permission is hereby granted, free of charge, to any person obtaining a copy
* of this software and associated documentation files (the "Software"), to
* deal in the Software without restriction, including without limitation the
* rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
* sell copies of the Software, and to permit persons to whom the Software is
* furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice shall be included in all
* copies or substantial portions of the Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
* AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
* OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
* SOFTWARE.
*/
#ifndef __ARM_COMPUTE_NEGATHERKERNELEX_H__
#define __ARM_COMPUTE_NEGATHERKERNELEX_H__
#include "arm_compute/core/NEON/INEKernel.h"
#include "arm_compute/core/Types.h"
namespace arm_compute
{
class ITensor;
/** Kernel to perform other operation on NEON */
class NEGatherKernelEx : public INEKernel
{
public:
/** Default constructor. */
NEGatherKernelEx();
/** Prevent instances of this class from being copied (As this class contains pointers). */
NEGatherKernelEx(const NEGatherKernelEx &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers). */
NEGatherKernelEx &operator=(const NEGatherKernelEx &) = delete;
/** Allow instances of this class to be moved. */
NEGatherKernelEx(NEGatherKernelEx &&) = default;
/** Allow instances of this class to be moved. */
NEGatherKernelEx &operator=(NEGatherKernelEx &&) = default;
/** Default detructor */
~NEGatherKernelEx() = default;
/** Name of the kernel
*
* @return Kernel name
*/
const char *name() const override { return "NEGatherKernelEx"; }
/** Initialise the kernel's inputs and outputs
*
* @param[in] input Source tensor. Supported tensor rank: up to 4. Data type supported:
* U8/S8/QASYMM8/U16/S16/U32/S32/F16/F32
* @param[in] indices Indices tensor. Supported tensor rank: up to 3. Must be one of the
* following type: U32/S32. Each value Must be in range [0, input.shape[@p axis])
* @param[out] output Destination tensor. Data type supported: Same as @p input
* @param[in] axis (Optional) The axis in @p input to gather @p indices from. Negative values
* wrap around. Defaults to 0
*/
void configure(const ITensor *input, const ITensor *indices, ITensor *output, int axis = 0);
/** Static function to check if given info will lead to a valid configuration of @ref
* NEGatherKernelEx
*
* @param[in] input Source tensor info. Supported tensor rank: up to 4. Data type supported:
* U8/S8/QASYMM8/U16/S16/U32/S32/F16/F32
* @param[in] indices Indices tensor info. Supported tensor rank: up to 3. Must be one of the
* following type: U32/S32. Each value Must be in range [0, input.shape[@p axis])
* @param[in] output Destination tensor info. Data type supported: Same as @p input
* @param[in] axis (Optional) The axis in @p input to gather @p indices from. Negative values
* wrap around. Defaults to 0
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *indices,
const ITensorInfo *output, int axis);
// Inherited methods overridden:
void run(const Window &window, const ThreadInfo &info) override;
private:
/** Implementation of the gather operation for 0 axis.
*
* For gather on the 0 axis an element by element copy is performed.
*
* @param[in] window Region on which to execute the kernel. (Must be a region of the window
* returned by window())
* @param[in] info Info about executing thread and CPU.
*/
template <typename U> void gather_0_axis(const Window &window, const ThreadInfo &info);
/** Implementation of the gather operation.
*
* For 1<=axis a row-wise copy is taking place.
*
* @param[in] window Region on which to execute the kernel. (Must be a region of the window
* returned by window())
* @param[in] info Info about executing thread and CPU.
*/
template <typename U> void gather_n_axis(const Window &window, const ThreadInfo &info);
using kernel_ptr = void (NEGatherKernelEx::*)(const Window &window, const ThreadInfo &info);
const ITensor *_input;
const ITensor *_indices;
int _axis;
ITensor *_output;
kernel_ptr _func;
};
} // namespace arm_compute
#endif /* __ARM_COMPUTE_NEGATHERKERNELEX_H__ */
|
