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
|
/*
* Copyright (c) 2016-2019 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_NEGEMMINTERLEAVE4x4KERNEL_H
#define ARM_COMPUTE_NEGEMMINTERLEAVE4x4KERNEL_H
#include "arm_compute/core/NEON/INESimpleKernel.h"
namespace arm_compute
{
class ITensor;
/** NEON kernel to interleave the elements of a matrix
*
* 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 * 4, ceil(width / 4.0f) ]
*/
class NEGEMMInterleave4x4Kernel : public INESimpleKernel
{
public:
const char *name() const override
{
return "NEGEMMInterleave4x4Kernel";
}
/* Constructor */
NEGEMMInterleave4x4Kernel();
/** Initialise the kernel's input and output.
*
* @param[in] input Input tensor. Data types supported: All
* @param[out] output Output tensor which stores the interleaved matrix. Data type supported: same as @p input.
*/
void configure(const ITensor *input, ITensor *output);
/** Static function to check if given info will lead to a valid configuration of @ref NEGEMMInterleave4x4Kernel
*
* @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.
*
* @return a status
*/
static Status validate(const ITensorInfo *input, const ITensorInfo *output);
// Inherited methods overridden:
void run(const Window &window, const ThreadInfo &info) override;
private:
/** Common signature for all the transpose functions
*
* @param[in] input An input tensor. Data types supported: All
* @param[out] output The output tensor. Data type supported: same as @p input
* @param[in] window Region on which to execute the kernel.
*/
using GEMMInterleaveFunction = void(const ITensor *input, ITensor *output, const Window &window);
GEMMInterleaveFunction *_func; /**< GEMM interleave function to use for the particular tensor types passed to configure() */
};
} // namespace arm_compute
#endif /*ARM_COMPUTE_NEGEMMINTERLEAVE4x4KERNEL_H*/
|
