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
|
/*
* Copyright (c) 2019-2020 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_CLARGMINMAXLAYERKERNEL_H
#define ARM_COMPUTE_CLARGMINMAXLAYERKERNEL_H
#include "arm_compute/core/CL/ICLKernel.h"
#include "arm_compute/core/Types.h"
namespace arm_compute
{
class ICLTensor;
/** Interface for the reduction operation kernel
*
* @note The default data type for an uninitialized output tensor is
* signed 32-bit integer (S32). It is the user's responsibility to check
* that the results do not overflow because the indices are computed
* in unsigned 32-bit (U32).
*/
class CLArgMinMaxLayerKernel : public ICLKernel
{
public:
/** Default constructor */
CLArgMinMaxLayerKernel();
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLArgMinMaxLayerKernel(const CLArgMinMaxLayerKernel &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLArgMinMaxLayerKernel &operator=(const CLArgMinMaxLayerKernel &) = delete;
/** Allow instances of this class to be moved */
CLArgMinMaxLayerKernel(CLArgMinMaxLayerKernel &&) = default;
/** Allow instances of this class to be moved */
CLArgMinMaxLayerKernel &operator=(CLArgMinMaxLayerKernel &&) = default;
/** Default destructor */
~CLArgMinMaxLayerKernel() = default;
/** Set the input and output tensors.
*
* @param[in] input Source tensor. Data types supported: QASYMM8/QASYMM8_SIGNED/S32/F16/F32.
* @param[in] prev_output Destination tensor of the previous iterations of @ref CLArgMinMaxLayerKernel. Data types supported: U32/S32
* Has to be nullptr for the first iteration
* @param[out] output Destination tensor. Data types supported: U32/S32
* Output will have the same number of dimensions as input.
* @param[in] axis Axis along which to reduce. Supported reduction axis : 0,1,2,3
* @param[in] op Reduction operation to perform. Only ArgMin and ArgMax are supported.
*/
void configure(const ICLTensor *input, const ICLTensor *prev_output, ICLTensor *output, unsigned int axis, ReductionOperation op);
/** Set the input and output tensors.
*
* @param[in] compile_context The compile context to be used.
* @param[in] input Source tensor. Data types supported: QASYMM8/QASYMM8_SIGNED/S32/F16/F32.
* @param[in] prev_output Destination tensor of the previous iterations of @ref CLArgMinMaxLayerKernel. Data types supported: U32/S32
* Has to be nullptr for the first iteration
* @param[out] output Destination tensor. Data types supported: U32/S32
* Output will have the same number of dimensions as input.
* @param[in] axis Axis along which to reduce. Supported reduction axis : 0,1,2,3
* @param[in] op Reduction operation to perform. Only ArgMin and ArgMax are supported.
*/
void configure(const CLCompileContext &compile_context, const ICLTensor *input, const ICLTensor *prev_output, ICLTensor *output, unsigned int axis, ReductionOperation op);
/** Static function to check if given info will lead to a valid configuration of @ref CLArgMinMaxLayerKernel.
*
* @param[in] input Source tensor info. Data types supported: QASYMM8/QASYMM8_SIGNED/S32/F16/F32.
* @param[in] prev_output Destination tensor info of the previous iterations. Data types supported: U32/S32
* Has to be nullptr for the first iteration
* @param[in] output Destination tensor info. Data types supported: U32/S32
* Output will have the same number of dimensions as input.
* @param[in] axis Axis along which to reduce. Supported reduction axis : 0,1,2,3
* @param[in] op Reduction operation to perform. Only ArgMin and ArgMax are supported.
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *prev_output, const ITensorInfo *output, unsigned int axis, ReductionOperation op);
// Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;
private:
const ICLTensor *_input;
const ICLTensor *_prev_output;
ICLTensor *_output;
unsigned int _reduction_axis;
ReductionOperation _op;
};
} // namespace arm_compute
#endif /* ARM_COMPUTE_CLARGMINMAXLAYERKERNEL_H */
|
