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
|
/*
* Copyright (c) 2016-2020 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_CLPIXELWISEMULTIPLICATIONKERNEL_H
#define ARM_COMPUTE_CLPIXELWISEMULTIPLICATIONKERNEL_H
#include "arm_compute/core/CL/ICLKernel.h"
#include "arm_compute/core/Types.h"
namespace arm_compute
{
// Forward declarations
class ICLTensor;
/** Interface for the pixelwise multiplication kernel. */
class CLPixelWiseMultiplicationKernel : public ICLKernel
{
public:
/** Default constructor.*/
CLPixelWiseMultiplicationKernel();
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLPixelWiseMultiplicationKernel(const CLPixelWiseMultiplicationKernel &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLPixelWiseMultiplicationKernel &operator=(const CLPixelWiseMultiplicationKernel &) = delete;
/** Allow instances of this class to be moved */
CLPixelWiseMultiplicationKernel(CLPixelWiseMultiplicationKernel &&) = default;
/** Allow instances of this class to be moved */
CLPixelWiseMultiplicationKernel &operator=(CLPixelWiseMultiplicationKernel &&) = default;
/** Initialise the kernel's input, output and border mode.
*
* Valid configurations (Input1,Input2) -> Output :
*
* - (U8,U8) -> U8
* - (U8,U8) -> S16
* - (U8,S16) -> S16
* - (S16,U8) -> S16
* - (S16,S16) -> S16
* - (F16,F16) -> F16
* - (F32,F32) -> F32
* - (QASYMM8,QASYMM8) -> QASYMM8
* - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
* - (QSYMM16,QSYMM16) -> QSYMM16
* - (QSYMM16,QSYMM16) -> S32
*
* @param[in] input1 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] input2 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[out] output The output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] scale Scale to apply after multiplication.
* Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
* @param[in] overflow_policy Overflow policy. Supported overflow policies: Wrap, Saturate
* @param[in] rounding_policy Rounding policy. Supported rounding modes: to zero, to nearest even.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*/
void configure(ITensorInfo *input1, ITensorInfo *input2, ITensorInfo *output, float scale,
ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
/** Initialise the kernel's input, output and border mode.
*
* Valid configurations (Input1,Input2) -> Output :
*
* - (U8,U8) -> U8
* - (U8,U8) -> S16
* - (U8,S16) -> S16
* - (S16,U8) -> S16
* - (S16,S16) -> S16
* - (F16,F16) -> F16
* - (F32,F32) -> F32
* - (QASYMM8,QASYMM8) -> QASYMM8
* - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
* - (QSYMM16,QSYMM16) -> QSYMM16
* - (QSYMM16,QSYMM16) -> S32
*
* @param[in] compile_context The compile context to be used.
* @param[in] input1 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] input2 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[out] output The output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] scale Scale to apply after multiplication.
* Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
* @param[in] overflow_policy Overflow policy. Supported overflow policies: Wrap, Saturate
* @param[in] rounding_policy Rounding policy. Supported rounding modes: to zero, to nearest even.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*/
void configure(const CLCompileContext &compile_context, ITensorInfo *input1, ITensorInfo *input2, ITensorInfo *output, float scale,
ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
/** Static function to check if given info will lead to a valid configuration of @ref CLPixelWiseMultiplicationKernel
*
* Valid configurations (Input1,Input2) -> Output :
*
* - (U8,U8) -> U8
* - (U8,U8) -> S16
* - (U8,S16) -> S16
* - (S16,U8) -> S16
* - (S16,S16) -> S16
* - (F16,F16) -> F16
* - (F32,F32) -> F32
* - (QASYMM8,QASYMM8) -> QASYMM8
* - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
* - (QSYMM16,QSYMM16) -> QSYMM16
* - (QSYMM16,QSYMM16) -> S32
*
* @param[in] input1 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] input2 An input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] output The output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
* @param[in] scale Scale to apply after multiplication.
* Scale must be positive and its value must be either 1/255 or 1/2^n where n is between 0 and 15.
* @param[in] overflow_policy Overflow policy. Supported overflow policies: Wrap, Saturate
* @param[in] rounding_policy Rounding policy. Supported rounding modes: to zero, to nearest even.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*
* @return a status
*/
static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, float scale,
ConvertPolicy overflow_policy, RoundingPolicy rounding_policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
// Inherited methods overridden:
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
BorderSize border_size() const override;
private:
const ITensorInfo *_input1;
const ITensorInfo *_input2;
ITensorInfo *_output;
};
/** Interface for the complex pixelwise multiplication kernel. */
class CLComplexPixelWiseMultiplicationKernel : public ICLKernel
{
public:
/** Default constructor.*/
CLComplexPixelWiseMultiplicationKernel();
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLComplexPixelWiseMultiplicationKernel(const CLComplexPixelWiseMultiplicationKernel &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLComplexPixelWiseMultiplicationKernel &operator=(const CLComplexPixelWiseMultiplicationKernel &) = delete;
/** Allow instances of this class to be moved */
CLComplexPixelWiseMultiplicationKernel(CLComplexPixelWiseMultiplicationKernel &&) = default;
/** Allow instances of this class to be moved */
CLComplexPixelWiseMultiplicationKernel &operator=(CLComplexPixelWiseMultiplicationKernel &&) = default;
/** Initialise the kernel's input, output and border mode.
*
* @param[in] input1 An input tensor info. Data types supported: F32. Number of channels supported: 2.
* @param[in] input2 An input tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
* @param[out] output The output tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*/
void configure(ITensorInfo *input1, ITensorInfo *input2, ITensorInfo *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
/** Initialise the kernel's input, output and border mode.
*
* @param[in] compile_context The compile context to be used.
* @param[in] input1 An input tensor info. Data types supported: F32. Number of channels supported: 2.
* @param[in] input2 An input tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
* @param[out] output The output tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*/
void configure(const CLCompileContext &compile_context, ITensorInfo *input1, ITensorInfo *input2, ITensorInfo *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
/** Static function to check if given info will lead to a valid configuration of @ref CLComplexPixelWiseMultiplicationKernel
*
* @param[in] input1 An input tensor info. Data types supported: F32. Number of channels supported: 2.
* @param[in] input2 An input tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
* @param[in] output The output tensor info. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
*
* @return a status
*/
static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
// Inherited methods overridden:
void run_op(ITensorPack &tensors, const Window &window, cl::CommandQueue &queue) override;
BorderSize border_size() const override;
private:
const ITensorInfo *_input1;
const ITensorInfo *_input2;
ITensorInfo *_output;
};
} // namespace arm_compute
#endif /*ARM_COMPUTE_CLPIXELWISEMULTIPLICATIONKERNEL_H */
|
