aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/runtime/NEON/functions/NEPixelWiseMultiplication.h
blob: 29677b74621fdcd7a797139c491ba12116c49921 (plain)
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
205
206
207
208
209
210
211
212
213
214
215
216
217
218
219
220
221
222
223
224
225
226
227
228
229
230
231
232
233
234
235
236
237
238
239
240
241
242
243
244
245
246
247
248
249
250
251
252
253
254
255
256
257
258
/*
 * 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_NEPIXELWISEMULTIPLICATION_H
#define ARM_COMPUTE_NEPIXELWISEMULTIPLICATION_H

#include "arm_compute/core/Types.h"
#include "arm_compute/runtime/IFunction.h"
#include "arm_compute/runtime/NEON/INEOperator.h"

namespace arm_compute
{
class ITensor;

namespace experimental
{
/** Basic function to run @ref NEPixelWiseMultiplicationKernel */
class NEPixelWiseMultiplication : public INEOperator
{
public:
    /** Initialise the kernel's inputs, output and convertion policy.
     *
     * 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
     *
     * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
     *       For all other scale values only round to zero (implemented as round towards minus infinity) is supported.
     *
     * @param[in, out] input1          First input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32
     *                                 This input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[in, out] input2          Second input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32
     *                                 This input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[out]     output          Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32
     * @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. ConvertPolicy cannot be WRAP if datatype is QASYMM8, QASYMM8_SIGNED or QSYMM16.
     * @param[in]      rounding_policy Rounding policy.
     * @param[in]      act_info        (Optional) Activation layer information in case of a fused activation. Currently not supported.
     */
    void configure(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 NEPixelWiseMultiplication
     *
     * 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
     *
     * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
     *       For all other scale values only round to zero (implemented as round towards minus infinity) is supported.
     *
     * @param[in] input1          First input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32
     * @param[in] input2          Second input tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32
     * @param[in] output          Output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32/S32
     * @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. ConvertPolicy cannot be WRAP if datatype is QASYMM8, QASYMM8_SIGNED or QSYMM16.
     * @param[in] rounding_policy Rounding policy.
     * @param[in] act_info        (Optional) Activation layer information in case of a fused activation. Currently not supported.
     *
     * @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:
    MemoryRequirements workspace() const override;
};

/** Basic function to run @ref NEComplexPixelWiseMultiplicationKernel. */
class NEComplexPixelWiseMultiplication : public INEOperator
{
public:
    /** Initialise the kernel's inputs, output.
     *
     * @param[in, out] input1   An input tensor. Data types supported: F32. Number of channels supported: 2 (complex tensor).
     *                          The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[in, out] input2   An input tensor. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
     *                          The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[out]     output   The output tensor. Data types supported: same as @p input1. Number of channels: same as @p input1.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
     */
    void configure(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 NEComplexPixelWiseMultiplication
     *
     * @param[in] input1   An input tensor info. Data types supported: F32. Number of channels supported: 2 (complex tensor).
     * @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. Currently not supported.
     */
    static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());

    // Inherited methods overridden:
    MemoryRequirements workspace() const override;
};
} // namespace experimental

/** Basic function to run @ref NEPixelWiseMultiplicationKernel */
class NEPixelWiseMultiplication : public IFunction
{
public:
    /** Default Constructor */
    NEPixelWiseMultiplication();
    /** Default Destructor */
    ~NEPixelWiseMultiplication();
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    NEPixelWiseMultiplication(const NEPixelWiseMultiplication &) = delete;
    /** Default move constructor */
    NEPixelWiseMultiplication(NEPixelWiseMultiplication &&);
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    NEPixelWiseMultiplication &operator=(const NEPixelWiseMultiplication &) = delete;
    /** Default move assignment operator */
    NEPixelWiseMultiplication &operator=(NEPixelWiseMultiplication &&);
    /** Initialise the kernel's inputs, output and convertion policy.
     *
     * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
     *       For all other scale values only round to zero (implemented as round towards minus infinity) is supported.
     *
     * @param[in, out] input1          An input tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32
     *                                 This input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[in, out] input2          An input tensor. Data types supported: U8, QASYMM8 (only if @p input1 is QASYMM8), QASYMM8_SIGNED (only if @p input1 is QASYMM8_SIGNED), S16, QSYMM16 (only if @p input1 is QSYMM16), F16 (only if @p input1 is F16), F32 (only if @p input1 is F32).
     *                                 This input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[out]     output          Output tensor. Data types supported:
     *                                 - U8, only if both inputs are U8.
     *                                 - QASYMM8, only if both inputs are QASYMM8.
     *                                 - QASYMM8_SIGNED, only if @p input1 is QASYMM8_SIGNED.
     *                                 - S16.
     *                                 - QSYMM16, only if both inputs are QSYMM16.
     *                                 - S32, only if both inputs are QSYMM16.
     *                                 - F16, only if @p input1 is F16.
     *                                 - F32, only if both inputs are 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. ConvertPolicy cannot be WRAP if datatype is QASYMM8, QASYMM8_SIGNED or QSYMM16.
     * @param[in]      rounding_policy Rounding policy.
     * @param[in]      act_info        (Optional) Activation layer information in case of a fused activation. Currently not supported.
     */
    void configure(const ITensor *input1, const ITensor *input2, ITensor *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 NEPixelWiseMultiplication
     *
     * @note For @p scale equal to 1/255 only round to nearest even (implemented as round half up) is supported.
     *       For all other scale values only round to zero (implemented as round towards minus infinity) is supported.
     *
     * @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 (only if @p input1 is QASYMM8), QASYMM8_SIGNED (only if @p input1 is QASYMM8_SIGNED), S16, QSYMM16 (only if both inputs are QSYMM16), F16 (only if @p input1 is F16), F32 (only if @p input1 is F32).
     * @param[in] output          Output tensor info. Data types supported:
     *                            - U8, only if both inputs are U8.
     *                            - QASYMM8, only if both inputs are QASYMM8.
     *                            - QASYMM8_SIGNED, only if @p input1 is QASYMM8_SIGNED.
     *                            - S16.
     *                            - QSYMM16, only if both inputs are QSYMM16.
     *                            - S32, only if both inputs are QSYMM16.
     *                            - F16, only if @p input1 is F16.
     *                            - F32, only if both inputs are 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. ConvertPolicy cannot be WRAP if datatype is QASYMM8, QASYMM8_SIGNED or QSYMM16.
     * @param[in] rounding_policy Rounding policy.
     * @param[in] act_info        (Optional) Activation layer information in case of a fused activation. Currently not supported.
     *
     * @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() override;

private:
    struct Impl;
    std::unique_ptr<Impl> _impl;
};

/** Basic function to run @ref NEComplexPixelWiseMultiplicationKernel. */
class NEComplexPixelWiseMultiplication : public IFunction
{
public:
    /** Default Constructor */
    NEComplexPixelWiseMultiplication();
    /** Default Destructor */
    ~NEComplexPixelWiseMultiplication();
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    NEComplexPixelWiseMultiplication(const NEComplexPixelWiseMultiplication &) = delete;
    /** Default move constructor */
    NEComplexPixelWiseMultiplication(NEComplexPixelWiseMultiplication &&);
    /** Prevent instances of this class from being copied (As this class contains pointers) */
    NEComplexPixelWiseMultiplication &operator=(const NEComplexPixelWiseMultiplication &) = delete;
    /** Default move assignment operator */
    NEComplexPixelWiseMultiplication &operator=(NEComplexPixelWiseMultiplication &&);
    /** Initialise the kernel's inputs, output.
     *
     * @param[in, out] input1   An input tensor. Data types supported: F32. Number of channels supported: 2 (complex tensor).
     *                          The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[in, out] input2   An input tensor. Data types supported: same as @p input1. Number of channels supported: same as @p input1.
     *                          The input tensor is [in, out] because its TensorInfo might be modified inside the kernel in case of broadcasting of dimension 0.
     * @param[out]     output   The output tensor. Data types supported: same as @p input1. Number of channels: same as @p input1.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation. Currently not supported.
     */
    void configure(ITensor *input1, ITensor *input2, ITensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref NEComplexPixelWiseMultiplication
     *
     * @param[in] input1   An input tensor info. Data types supported: F32. Number of channels supported: 2 (complex tensor).
     * @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. Currently not supported.
     */
    static Status validate(const ITensorInfo *input1, const ITensorInfo *input2, const ITensorInfo *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());

    // Inherited methods overridden:
    void run() override;

private:
    struct Impl;
    std::unique_ptr<Impl> _impl;
};
}
#endif /*ARM_COMPUTE_NEPIXELWISEMULTIPLICATION_H */