aboutsummaryrefslogtreecommitdiff
path: root/arm_compute/runtime/CL/functions/CLElementwiseOperations.h
blob: 9cd3c150cc5b2d7eb26d6e9af179aa79441cc6f9 (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
259
260
261
262
263
264
265
266
267
268
269
270
271
272
273
274
275
276
277
278
279
280
281
282
283
284
285
286
287
288
289
290
291
292
293
294
295
296
297
298
299
300
301
302
303
304
305
306
307
308
309
310
311
312
313
314
315
316
317
318
319
320
321
322
323
324
325
326
327
328
329
330
331
332
333
334
335
336
337
338
339
340
341
342
343
344
345
346
347
348
349
350
351
352
353
354
355
356
357
358
359
360
361
362
363
364
365
366
367
368
369
370
371
372
373
374
375
376
377
378
379
380
381
382
383
384
385
386
387
388
389
390
391
392
393
394
395
396
397
398
399
400
401
402
403
404
405
406
407
408
409
410
411
/*
 * Copyright (c) 2018-2020 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_CLELEMENTWISEOPERATIONS_H
#define ARM_COMPUTE_CLELEMENTWISEOPERATIONS_H

#include "arm_compute/core/Types.h"
#include "arm_compute/runtime/CL/ICLSimpleFunction.h"

namespace arm_compute
{
class ICLTensor;

/** Basic function to run @ref CLSaturatedArithmeticOperationKernel for addition
 *
 * @note The tensor data type for the inputs must be U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
 * @note The function performs an arithmetic addition between two tensors.
 */
class CLArithmeticAddition : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * Valid configurations (Input1,Input2) -> Output :
     *
     *   - (U8,U8)           -> U8
     *   - (U8,U8)           -> S16
     *   - (S16,U8)          -> S16
     *   - (U8,S16)          -> S16
     *   - (S16,S16)         -> S16
     *   - (S32,S32)         -> S32
     *   - (F16,F16)         -> F16
     *   - (F32,F32)         -> F32
     *   - (QASYMM8,QASYMM8) -> QASYMM8
     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
     *   - (QSYMM16,QSYMM16) -> QSYMM16
     *
     * @param[in, out] input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                          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   Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                          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   Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in]      policy   Policy to use to handle overflow.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * Valid configurations (Input1,Input2) -> Output :
     *
     *   - (U8,U8)           -> U8
     *   - (U8,U8)           -> S16
     *   - (S16,U8)          -> S16
     *   - (U8,S16)          -> S16
     *   - (S16,S16)         -> S16
     *   - (S32,S32)         -> S32
     *   - (F16,F16)         -> F16
     *   - (F32,F32)         -> F32
     *   - (QASYMM8,QASYMM8) -> QASYMM8
     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
     *   - (QSYMM16,QSYMM16) -> QSYMM16
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                                 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          Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                                 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          Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in]      policy          Policy to use to handle overflow.
     * @param[in]      act_info        (Optional) Activation layer information in case of a fused activation.
     */
    void configure(const CLCompileContext &compile_context, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLSaturatedArithmeticOperationKernel for addition
     *
     * Valid configurations (Input1,Input2) -> Output :
     *
     *   - (U8,U8)           -> U8
     *   - (U8,U8)           -> S16
     *   - (S16,U8)          -> S16
     *   - (U8,S16)          -> S16
     *   - (S16,S16)         -> S16
     *   - (S32,S32)         -> S32
     *   - (F16,F16)         -> F16
     *   - (F32,F32)         -> F32
     *   - (QASYMM8,QASYMM8) -> QASYMM8
     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
     *   - (QSYMM16,QSYMM16) -> QSYMM16
     *
     * @param[in] input1   First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in] output   Output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in] policy   Policy to use to handle overflow.
     * @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, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
};

/** Basic function to run @ref CLSaturatedArithmeticOperationKernel for subtraction
 *
 * @note The tensor data type for the inputs must be U8/QASYMM8/QASYMM8_SIGNED/S16/S32/F16/F32.
 * @note The function performs an arithmetic subtraction between two tensors.
 */
class CLArithmeticSubtraction : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * Valid configurations (Input1,Input2) -> Output :
     *
     *   - (U8,U8)           -> U8
     *   - (U8,U8)           -> S16
     *   - (S16,U8)          -> S16
     *   - (U8,S16)          -> S16
     *   - (S16,S16)         -> S16
     *   - (S32,S32)         -> S32
     *   - (F16,F16)         -> F16
     *   - (F32,F32)         -> F32
     *   - (QASYMM8,QASYMM8) -> QASYMM8
     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
     *   - (QSYMM16,QSYMM16) -> QSYMM16
     *
     * @param[in, out] input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                          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   Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                          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   Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in]      policy   Policy to use to handle overflow.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * Valid configurations (Input1,Input2) -> Output :
     *
     *   - (U8,U8)           -> U8
     *   - (U8,U8)           -> S16
     *   - (S16,U8)          -> S16
     *   - (U8,S16)          -> S16
     *   - (S16,S16)         -> S16
     *   - (S32,S32)         -> S32
     *   - (F16,F16)         -> F16
     *   - (F32,F32)         -> F32
     *   - (QASYMM8,QASYMM8) -> QASYMM8
     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
     *   - (QSYMM16,QSYMM16) -> QSYMM16
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                                 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          Second tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     *                                 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          Output tensor. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in]      policy          Policy to use to handle overflow.
     * @param[in]      act_info        (Optional) Activation layer information in case of a fused activation.
     */
    void configure(const CLCompileContext &compile_context, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLSaturatedArithmeticOperationKernel for subtraction
     *
     * Valid configurations (Input1,Input2) -> Output :
     *
     *   - (U8,U8)           -> U8
     *   - (U8,U8)           -> S16
     *   - (S16,U8)          -> S16
     *   - (U8,S16)          -> S16
     *   - (S16,S16)         -> S16
     *   - (S32,S32)         -> S32
     *   - (F16,F16)         -> F16
     *   - (F32,F32)         -> F32
     *   - (QASYMM8,QASYMM8) -> QASYMM8
     *   - (QASYMM8_SIGNED,QASYMM8_SIGNED) -> QASYMM8_SIGNED
     *   - (QSYMM16,QSYMM16) -> QSYMM16
     *
     * @param[in] input1   First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in] output   Output tensor info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/F16/F32.
     * @param[in] policy   Policy to use to handle overflow.
     * @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, ConvertPolicy policy, const ActivationLayerInfo &act_info = ActivationLayerInfo());
};

/** Basic function to run @ref CLSaturatedArithmeticOperationKernel for division
 *
 * @note The tensor data type for the inputs must be F16/F32.
 * @note The function performs an arithmetic division between two tensors.
 */
class CLArithmeticDivision : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output.
     *
     * @param[in, out] input1   First tensor input. Data types supported: F16/F32.
     *                          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   Second tensor input. 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   Output tensor. Data types supported: Same as @p input1.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output.
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: F16/F32.
     *                                 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          Second tensor input. 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          Output tensor. Data types 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, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLArithmeticDivision
     *
     * @param[in] input1   First tensor input info. Data types supported: F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: Same as @p input1.
     * @param[in] output   Output tensor info. Data types 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());
};

/** Basic function to run @ref CLArithmeticOperationKernel for max
 *
 * @note The tensor data type for the inputs must be U8/QASYMM8/S16/QSYMM16/S32/U32/F16/F32.
 * @note The function performs a max operation between two tensors.
 */
class CLElementwiseMax : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in, out] input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
     *                          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   Second tensor input. Data types 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   Output tensor. Data types supported: same as @p input1.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
     *                                 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          Second tensor input. Data types 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          Output tensor. Data types 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, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLArithmeticOperationKernel for max
     *
     * @param[in] input1   First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: same as @p input1.
     * @param[in] output   Output tensor info. Data types 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());
};

/** Basic function to run @ref CLArithmeticOperationKernel for min
 *
 * @note The tensor data type for the inputs must be U8/QASYMM8/S16/QSYMM16/S32/U32/F16/F32.
 * @note The function performs a max operation between two tensors.
 */
class CLElementwiseMin : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in, out] input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
     *                          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   Second tensor input. Data types 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   Output tensor. Data types supported: same as @p input1.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
     *                                 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          Second tensor input. Data types 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          Output tensor. Data types 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, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLArithmeticOperationKernel for min
     *
     * @param[in] input1   First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/S32/U32/F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: same as @p input1.
     * @param[in] output   Output tensor info. Data types 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());
};

/** Basic function to run @ref CLArithmeticOperationKernel for squared difference
 *
 * @note The tensor data type for the inputs must be QASYMM8/U8/S16/QSYMM16/F16/F32.
 * @note The function performs a squared different operation between two tensors (i.e., out[i] = (in1[i] - in2[i])^2
 */
class CLElementwiseSquaredDiff : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in, out] input1   First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
     *                          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   Second tensor input. Data types 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   Output tensor. Data types supported: same as @p input1.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
     *                                 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          Second tensor input. Data types 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          Output tensor. Data types 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, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLArithmeticOperationKernel for squared difference
     *
     * @param[in] input1   First tensor input info. Data types supported: U8/QASYMM8/QASYMM8_SIGNED/S16/QSYMM16/F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: same as @p input1.
     * @param[in] output   Output tensor info. Data types 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());
};

/** Basic function to run @ref CLArithmeticOperationKernel for power
 *
 * @note The tensor data type for the inputs must be F16/F32.
 * @note The function performs an elementwise power of in1 to in2 (i.e., out[i] = in1[i] ^ in2[i])
 */
class CLElementwisePower : public ICLSimpleFunction
{
public:
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in, out] input1   First tensor input. Data types supported: F16/F32.
     *                          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   Second tensor input. Data types supported: F16/F32.
     *                          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   Output tensor. Data types supported:F16/F32.
     * @param[in]      act_info (Optional) Activation layer information in case of a fused activation.
     */
    void configure(ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Initialise the kernel's inputs, output and conversion policy.
     *
     * @param[in]      compile_context The compile context to be used.
     * @param[in, out] input1          First tensor input. Data types supported: F16/F32.
     *                                 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          Second tensor input. Data types supported: F16/F32.
     *                                 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          Output tensor. Data types supported:F16/F32.
     * @param[in]      act_info        (Optional) Activation layer information in case of a fused activation.
     */
    void configure(const CLCompileContext &compile_context, ICLTensor *input1, ICLTensor *input2, ICLTensor *output, const ActivationLayerInfo &act_info = ActivationLayerInfo());
    /** Static function to check if given info will lead to a valid configuration of @ref CLArithmeticOperationKernel for power
     *
     * @param[in] input1   First tensor input info. Data types supported: F16/F32.
     * @param[in] input2   Second tensor input info. Data types supported: F16/F32.
     * @param[in] output   Output tensor info. Data types supported: F16/F32.
     * @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());
};
} // namespace arm_compute
#endif /* ARM_COMPUTE_CLELEMENTWISEOPERATIONS_H */