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
|
/*
* Copyright (c) 2017-2018 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_CLGEMMINTERLEAVE4X4KERNEL_H__
#define __ARM_COMPUTE_CLGEMMINTERLEAVE4X4KERNEL_H__
#include "arm_compute/core/CL/ICLKernel.h"
namespace arm_compute
{
class ICLTensor;
/** OpenCL kernel which interleaves the elements of a matrix A in chunk of 4x4
*
* This function puts the values in a 4x4 block of Matrix A on the same row (Interleaved values)
*
* @f[
* \left( \begin{array}{cccc}
* a00 & a01 & a02 & a03 \\
* a10 & a11 & a12 & a13 \\
* a20 & a21 & a22 & a23 \\
* a30 & a31 & a32 & a33 \\
* \end{array} \right)
* \rightarrow
* \left( \begin{array}{ccccccccccccccccc}
* a00 & a10 & a20 & a30 & a01 & a11 & a21 & a31 & a02 & a12 & a22 & a32 & a03 & a13 & a23 & a33 \\
* \end{array} \right)
* @f]
*
* After this operation, the output matrix will have the following shape: [ height * W, ceil(width / W) ] where W = 4 * mult_interleave4x4_height
*/
class CLGEMMInterleave4x4Kernel : public ICLKernel
{
public:
/** Default constructor */
CLGEMMInterleave4x4Kernel();
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLGEMMInterleave4x4Kernel(const CLGEMMInterleave4x4Kernel &) = delete;
/** Prevent instances of this class from being copied (As this class contains pointers) */
CLGEMMInterleave4x4Kernel &operator=(const CLGEMMInterleave4x4Kernel &) = delete;
/** Allow instances of this class to be moved */
CLGEMMInterleave4x4Kernel(CLGEMMInterleave4x4Kernel &&) = default;
/** Allow instances of this class to be moved */
CLGEMMInterleave4x4Kernel &operator=(CLGEMMInterleave4x4Kernel &&) = default;
/** Initialise the kernel's input and output.
*
* @param[in] input Input tensor. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
* @param[out] output Output tensor. Data type supported: same as @p input
* @param[in] mult_interleave4x4_height (Optional) Multiplication factor for the height of the 4x4 interleave block
* @param[in] reinterpret_input_as_3d (Optional) True if the input has to be reinterpreted as 3D tensor
* @param[in] unroll_block (Optional) True if the 4x4 block has to be unrolled rather than transposed
*/
void configure(const ICLTensor *input, ICLTensor *output, int mult_interleave4x4_height = 1, bool reinterpret_input_as_3d = false, bool unroll_block = false);
/** Static function to check if given info will lead to a valid configuration of @ref CLGEMMInterleave4x4Kernel
*
* @param[in] input Input tensor info. Data types supported: U8/S8/QASYMM8/U16/S16/F16/U32/S32/F32
* @param[in] output Output tensor info which stores the interleaved matrix. Data type supported: same as @p input.
* @param[in] mult_interleave4x4_height Multiplication factor for the height of the 4x4 interleave block
* @param[in] reinterpret_input_as_3d True if the input has to be reinterpreted as 3D tensor
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *output, int mult_interleave4x4_height, bool reinterpret_input_as_3d);
// Inherited methods overridden
void run(const Window &window, cl::CommandQueue &queue) override;
private:
const ICLTensor *_input;
ICLTensor *_output;
bool _reinterpret_input_as_3d;
};
} // namespace arm_compute
#endif /* __ARM_COMPUTE_CLGEMMINTERLEAVE4X4KERNEL_H__ */
|
