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
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
|
/*
* Copyright (c) 2021-2023 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 ACL_SRC_CPU_OPERATORS_CPUWINOGRADCONV2D_H
#define ACL_SRC_CPU_OPERATORS_CPUWINOGRADCONV2D_H
#include "arm_compute/core/TensorInfo.h"
#include "arm_compute/runtime/FunctionDescriptors.h"
#include "src/core/common/Macros.h"
#include "src/cpu/ICpuOperator.h"
#include "src/cpu/kernels/assembly/gemm_common.hpp"
#include "src/cpu/kernels/CpuWinogradConv2dKernel.h"
#include "src/cpu/operators/CpuActivation.h"
#include "src/cpu/operators/CpuGemm.h"
#include "src/cpu/operators/CpuPermute.h"
#include "src/cpu/operators/internal/CpuGemmAssemblyDispatch.h"
namespace arm_compute
{
namespace cpu
{
class CpuWinogradConv2d : public ICpuOperator
{
public:
/** Constructor */
CpuWinogradConv2d();
ARM_COMPUTE_DISALLOW_COPY_ALLOW_MOVE(CpuWinogradConv2d);
/** Destructor */
~CpuWinogradConv2d();
/** Set the input and output tensors.
*
* Valid data layouts:
* - NHWC
* - NCHW
*
* Valid data type configurations:
* |src0 |src1 |src2 |dst |
* |:--------------|:--------------|:------|:--------------|
* |F16 |F16 |F16 |F16 |
* |F32 |F32 |F32 |F32 |
*
* @param[in] src Source tensor Info. 3 lower dimensions represent a single input [width, height, IFM],
* while every optional dimension from 4 and above represent a batch of inputs.
* Data types supported: F16/F32.
* @param[in] weights Weights tensor Info. Weights are 4D tensor with dimensions [kernel_x, kernel_y, IFM, OFM]. Data type supported: Same as @p input.
* For supported kernel sizes, see @ref arm_compute::NEWinogradConvolutionLayer
* @param[in] biases Biases tensor Info. Shared biases supported. Biases are 1D tensor with dimensions [OFM]. Data type supported: Same as @p weights.
* @param[out] dst Destination tensor Info. 3 lower dimensions represent a single output [width, height, OFM], while the rest represent batch of outputs.
* Data types supported: Same as @p input.
* @param[in] conv_info Contains padding and stride information described in @ref PadStrideInfo. Currently only unit strides are supported.
* @param[in] act_info (Optional) Activation layer information in case of a fused activation.
* @param[in] enable_fast_math (Optional) Enable fast math computation. In case this flag were set, the function could dispatch the fastest implementation
* available which may introduce a drop of accuracy as well. Default is false
*/
void configure(const ITensorInfo *src,
const ITensorInfo *weights,
const ITensorInfo *biases,
ITensorInfo *dst,
const PadStrideInfo &conv_info,
const ActivationLayerInfo &act_info = ActivationLayerInfo(),
bool enable_fast_math = false);
/** Static function to check if given info will lead to a valid configuration of @ref CpuWinogradConv2d
*
* Similar to CpuWinogradConv2d::configure()
*
* @return a status
*/
static Status validate(const ITensorInfo *src,
const ITensorInfo *weights,
const ITensorInfo *biases,
const ITensorInfo *dst,
const PadStrideInfo &conv_info,
const ActivationLayerInfo &act_info = ActivationLayerInfo(),
bool enable_fast_math = false);
// Inherited methods overridden:
void run(ITensorPack &tensors) override;
void prepare(ITensorPack &constants) override;
experimental::MemoryRequirements workspace() const override;
private:
enum AuxTensorIdx
{
/** Slot 0 - 6 reserved for CpuGemm */
TransformedInput = 7,
TransformedOutput,
WorkspaceIO,
TransformedWeights,
PermutedWeights,
Count,
PermutedInput = TransformedOutput,
PermutedOutput = TransformedInput
};
std::unique_ptr<CpuGemm> _gemm_function;
std::unique_ptr<CpuActivation> _activation_func;
std::unique_ptr<ICPPKernel> _transform_input_kernel;
std::unique_ptr<ICPPKernel> _transform_output_kernel;
std::unique_ptr<CpuPermute> _permute_input;
std::unique_ptr<CpuPermute> _permute_output;
std::unique_ptr<CpuPermute> _permute_weights;
experimental::MemoryRequirements _aux_mem{Count};
std::unique_ptr<arm_conv::ConvolutionArgs>
_conv_args; // Make it unique ptr because this type does not have a default constructor
arm_conv::winograd::WinogradImpl _winograd_impl;
DataLayout _data_layout;
TensorInfo _winograd_transformed_input;
TensorInfo _winograd_transformed_output;
TensorInfo _winograd_transformed_weights;
TensorInfo _input_workspace;
TensorInfo _output_workspace;
TensorInfo _weights_hwio;
TensorInfo _input_nhwc;
TensorInfo _output_nhwc;
bool _is_prepared;
bool _run_activation;
};
} // namespace cpu
} // namespace arm_compute
#endif // ACL_SRC_CPU_OPERATORS_CPUWINOGRADCONV2D_H
|
