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
|
/*
* Copyright (c) 2017-2019 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_CLGEMMLOWPOFFSETCONTRIBUTIONKERNEL_H
#define ARM_COMPUTE_CLGEMMLOWPOFFSETCONTRIBUTIONKERNEL_H
#include "arm_compute/core/CL/ICLKernel.h"
namespace arm_compute
{
class ICLTensor;
/** OpenCL kernel used to add the offset contribution after @ref CLGEMMLowpMatrixMultiplyKernel. The computation is performed in-place
*
* This kernel takes a final int32 accumulator value (the output of @ref CLGEMMLowpMatrixMultiplyKernel),
* and adds to it the offset contribution of matrix A and matrix B in-place.
*
* The final result is:
*
* mm_result[i][k] = mm_result[i][k] +
* (vector_sum_col[k] * a_offset) +
* (vector_sum_row[i] * b_offset) +
* (a_offset * b_offset * k)
*
*/
class CLGEMMLowpOffsetContributionKernel : public ICLKernel
{
public:
/** Constructor */
CLGEMMLowpOffsetContributionKernel();
/** Prevent instances of this class from being copied (As this class contains pointers)*/
CLGEMMLowpOffsetContributionKernel(const CLGEMMLowpOffsetContributionKernel &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers)*/
CLGEMMLowpOffsetContributionKernel &operator=(const CLGEMMLowpOffsetContributionKernel &) = delete;
/** Allow instances of this class to be moved */
CLGEMMLowpOffsetContributionKernel(CLGEMMLowpOffsetContributionKernel &&) = default;
/** Allow instances of this class to be moved */
CLGEMMLowpOffsetContributionKernel &operator=(CLGEMMLowpOffsetContributionKernel &&) = default;
/** Initialise the kernel's input and output.
*
* @param[in, out] mm_result Input tensor containing the result of @ref CLGEMMLowpMatrixMultiplyKernel. Data type supported: S32
* @param[in] vector_sum_col Input row-vector of sums of all the entries in each column of matrix B.
* Note: vector_sum_col can be a nullptr in case a_offset = 0. Data type supported: same as @p mm_result
* @param[in] vector_sum_row Input row-vector of sums of all the entries in each row of matrix A.
* Note: vector_sum_row can be a nullptr in case b_offset = 0. Data type supported: same as @p mm_result
* @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the addition of biases is not required.
* Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input.
* @param[in] k Number of matrix A columns or Matrix B rows
* @param[in] a_offset Offset to be added to each element of the matrix A.
* @param[in] b_offset Offset to be added to each element of the matrix B.
*/
void configure(ICLTensor *mm_result, const ICLTensor *vector_sum_col, const ICLTensor *vector_sum_row, const ICLTensor *bias, int32_t k, int32_t a_offset, int32_t b_offset);
/** Static function to check if given info will lead to a valid configuration of @ref CLGEMMLowpOffsetContributionKernel
*
* @param[in] mm_result Input tensor containing the result of @ref CLGEMMLowpOffsetContributionKernel. Data type supported: S32
* @param[in] vector_sum_col Input row-vector of sums of all the entries in each column of matrix B.
* Note: vector_sum_col can be a nullptr in case a_offset = 0. Data type supported: same as @p mm_result
* @param[in] vector_sum_row Input row-vector of sums of all the entries in each row of matrix A.
* Note: vector_sum_row can be a nullptr in case b_offset = 0. Data type supported: same as @p mm_result
* @param[in] bias Biases tensor. Only shared biases supported and it can be a nullptr if the addition of biases is not required.
* Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p input.
* @param[in] a_offset Offset to be added to each element of the matrix A.
* @param[in] b_offset Offset to be added to each element of the matrix B.
*
* @return a status
*/
static Status validate(const ITensorInfo *mm_result, const ITensorInfo *vector_sum_col, const ITensorInfo *vector_sum_row, const ITensorInfo *bias, int32_t a_offset, int32_t b_offset);
// Inherited methods overridden:
void run(const Window &window, cl::CommandQueue &queue) override;
private:
const ICLTensor *_vector_sum_col;
const ICLTensor *_vector_sum_row;
ICLTensor *_mm_result;
const ICLTensor *_bias;
};
} // namespace arm_compute
#endif /* ARM_COMPUTE_CLGEMMLOWPOFFSETCONTRIBUTIONKERNEL_H */
|
