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
|
/*
* Copyright (c) 2018-2019 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_CLGEMMRESHAPERHSMATRIXKERNEL_H__
#define __ARM_COMPUTE_CLGEMMRESHAPERHSMATRIXKERNEL_H__
#include "arm_compute/core/CL/ICLKernel.h"
namespace arm_compute
{
class ICLTensor;
/** OpenCL kernel to reshape the RHS matrix when performing the matrix multiplication
* In particular, this kernel splits the input matrix in blocks of size K0xN0 and stores each one in
* the output matrix unrolling the values */
class CLGEMMReshapeRHSMatrixKernel : public ICLKernel
{
public:
/** Default constructor */
CLGEMMReshapeRHSMatrixKernel();
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLGEMMReshapeRHSMatrixKernel(const CLGEMMReshapeRHSMatrixKernel &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLGEMMReshapeRHSMatrixKernel &operator=(const CLGEMMReshapeRHSMatrixKernel &) = delete;
/** Allow instances of this class to be moved */
CLGEMMReshapeRHSMatrixKernel(CLGEMMReshapeRHSMatrixKernel &&) = default;
/** Allow instances of this class to be moved */
CLGEMMReshapeRHSMatrixKernel &operator=(CLGEMMReshapeRHSMatrixKernel &&) = default;
/** Initialise the kernel's input and output.
*
* @param[in] input Input tensor. Data types supported: All
* @param[out] output Output tensor. Data type supported: same as @p input
* @param[in] rhs_info RHS matrix information to be used for reshaping. This object contains all the necessary
* information to reshape the input tensor. Only the following values are supported:
* rhs_info.n0: 2,3,4,8,16
* rhs_info.k0: 1,2,3,4,8,16 (k0 = 1 only if rhs_info.transpose = false)
* rhs_info.h0: greater than 0
* rhs_info.transpose: true, false
* rhs_info.interleave: true, false
*/
void configure(const ICLTensor *input, ICLTensor *output, const GEMMRHSMatrixInfo &rhs_info);
/** Static function to check if given info will lead to a valid configuration of @ref CLGEMMReshapeRHSMatrixKernel
*
* @param[in] input Input tensor info. Data types supported: All
* @param[in] output Output tensor info which stores the interleaved matrix. Data type supported: same as @p input.
* @param[in] rhs_info RHS matrix information to be used for reshaping. This object contains all the necessary
* information to reshape the input tensor. Only the following values are supported:
* rhs_info.n0: 2,3,4,8,16
* rhs_info.k0: 1,2,3,4,8,16 (k0 = 1 only if rhs_info.transpose = false)
* rhs_info.h0: greater than 0
* rhs_info.transpose: true, false
* rhs_info.interleave: true, false
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *output, const GEMMRHSMatrixInfo &rhs_info);
// Inherited methods overridden
void run(const Window &window, cl::CommandQueue &queue) override;
private:
const ICLTensor *_input;
ICLTensor *_output;
};
} // namespace arm_compute
#endif /* __ARM_COMPUTE_CLGEMMRESHAPERHSMATRIXKERNEL_H__ */
|
