blob: fda0327461d83d9401ce12167a6ec8da101e8d82 [file] [log] [blame]
Anthony Barbier6ff3b192017-09-04 18:44:23 +01001/*
2 * Copyright (c) 2017 ARM Limited.
3 *
4 * SPDX-License-Identifier: MIT
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a copy
7 * of this software and associated documentation files (the "Software"), to
8 * deal in the Software without restriction, including without limitation the
9 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10 * sell copies of the Software, and to permit persons to whom the Software is
11 * furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in all
14 * copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 */
24#ifndef __ARM_COMPUTE_CLLOCALLYCONNECTEDMATRIXMULTIPLYKERNEL_H__
25#define __ARM_COMPUTE_CLLOCALLYCONNECTEDMATRIXMULTIPLYKERNEL_H__
26
27#include "arm_compute/core/CL/ICLKernel.h"
28
29namespace arm_compute
30{
31class ICLTensor;
32
33/** OpenCL kernel to multiply each row of first tensor with low 2 dimensions of second tensor.
34 *
35 * @attention The second input tensor must have at least 2 dimensions (matrix)
36 *
37 */
38class CLLocallyConnectedMatrixMultiplyKernel : public ICLKernel
39{
40public:
41 /** Default constructor */
42 CLLocallyConnectedMatrixMultiplyKernel();
43 /** Prevent instances of this class from being copied (As this class contains pointers) */
44 CLLocallyConnectedMatrixMultiplyKernel(const CLLocallyConnectedMatrixMultiplyKernel &) = delete;
45 /** Prevent instances of this class from being copied (As this class contains pointers) */
46 CLLocallyConnectedMatrixMultiplyKernel &operator=(const CLLocallyConnectedMatrixMultiplyKernel &) = delete;
47 /** Allow instances of this class to be moved */
48 CLLocallyConnectedMatrixMultiplyKernel(CLLocallyConnectedMatrixMultiplyKernel &&) = default;
49 /** Allow instances of this class to be moved */
50 CLLocallyConnectedMatrixMultiplyKernel &operator=(CLLocallyConnectedMatrixMultiplyKernel &&) = default;
51 /** Initialise the kernel's input, output and alpha
52 *
53 * @param[in] input0 First input tensor. Data types supported: F32
54 * @param[in] input1 Second input tensor. Data type supported: same as @p input0
55 * @param[out] output Output tensor to store the result. Data type supported: same as @p input0
56 */
57 void configure(const ICLTensor *input0, const ICLTensor *input1, ICLTensor *output);
58
59 // Inherited methods overridden:
60 void run(const Window &window, cl::CommandQueue &queue) override;
61
62private:
63 const ICLTensor *_input0;
64 const ICLTensor *_input1;
65 ICLTensor *_output;
66};
67}
68#endif /* __ARM_COMPUTE_CLLOCALLYCONNECTEDMATRIXMULTIPLYKERNEL_H__ */