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
|
/*
* Copyright (c) 2021-2022 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_CL_WIDTH_CONCATENATE_4TENSORS_KERNEL_H
#define ARM_COMPUTE_CL_WIDTH_CONCATENATE_4TENSORS_KERNEL_H
#include "src/core/common/Macros.h"
#include "src/gpu/cl/ClCompileContext.h"
#include "src/gpu/cl/IClKernel.h"
namespace arm_compute
{
namespace opencl
{
namespace kernels
{
/** Interface for the width concatenate kernel of 4 tensors.
* All source tensors will be concatenated into the destination tensor.
*/
class ClWidthConcatenate4TensorsKernel : public IClKernel
{
public:
ClWidthConcatenate4TensorsKernel();
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(ClWidthConcatenate4TensorsKernel);
/** Initialise the kernel's sources and destination
*
* @param[in] compile_context The compile context to be used.
* @param[in] src1 First source tensor info. Data types supported: All.
* @param[in] src2 Second source tensor info. Data types supported: same as @p src1
* @param[in] src3 Third source tensor info. Data types supported: same as @p src1
* @param[in] src4 Fourth source tensor info. Data types supported: same as @p src1
* @param[out] dst Destination tensor info. Data types supported: same as @p src1.
*/
void configure(const CLCompileContext &compile_context,
ITensorInfo *src1,
ITensorInfo *src2,
ITensorInfo *src3,
ITensorInfo *src4,
ITensorInfo *dst);
/** Static function to check if given info will lead to a valid configuration
*
* Similar to @ref ClWidthConcatenate4TensorsKernel::configure()
*
* @return a status
*/
static Status validate(const ITensorInfo *src1,
const ITensorInfo *src2,
const ITensorInfo *src3,
const ITensorInfo *src4,
const ITensorInfo *dst);
// Inherited methods overridden:
void run_op(ITensorPack &tensors, const Window &window, ::cl::CommandQueue &queue) override;
private:
int32_t _depth{0};
int32_t _input1_width{0};
int32_t _input2_width{0};
int32_t _input3_width{0};
};
} // namespace kernels
} // namespace opencl
} // namespace arm_compute
#endif /* ARM_COMPUTE_CL_WIDTH_CONCATENATE_4TENSORS_KERNEL_H */
|
