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
|
/*
* Copyright (c) 2017-2022 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.
*/
#include "arm_compute/runtime/NEON/functions/NEGEMMConvolutionLayer.h"
#include "arm_compute/core/Size2D.h"
#include "arm_compute/core/Utils.h"
#include "arm_compute/core/Validate.h"
#include "arm_compute/runtime/Tensor.h"
#include "src/core/helpers/MemoryHelpers.h"
#include "src/cpu/operators/CpuGemmConv2d.h"
using namespace arm_compute::experimental;
namespace arm_compute
{
struct NEGEMMConvolutionLayer::Impl
{
const ITensor *weights{nullptr};
std::unique_ptr<cpu::CpuGemmConv2d> op{nullptr};
ITensorPack run_pack{};
MemoryGroup memory_group{};
IWeightsManager *weights_manager{nullptr};
MemoryRequirements aux_mem_req{};
WorkspaceData<Tensor> workspace_tensors{};
bool is_prepared{false};
};
NEGEMMConvolutionLayer::NEGEMMConvolutionLayer(const std::shared_ptr<IMemoryManager> &memory_manager,
IWeightsManager *weights_manager)
: _impl(std::make_unique<Impl>())
{
_impl->weights_manager = weights_manager;
_impl->memory_group = MemoryGroup(memory_manager);
}
NEGEMMConvolutionLayer::~NEGEMMConvolutionLayer() = default;
void NEGEMMConvolutionLayer::configure(const ITensor *input,
const ITensor *weights,
const ITensor *biases,
ITensor *output,
const PadStrideInfo &conv_info,
const WeightsInfo &weights_info,
const Size2D &dilation,
const ActivationLayerInfo &act_info,
bool enable_fast_math,
unsigned int num_groups)
{
ARM_COMPUTE_ERROR_ON_NULLPTR(input, weights, output);
_impl->weights = weights;
_impl->op = std::make_unique<cpu::CpuGemmConv2d>();
_impl->op->configure(input->info(), weights->info(), (biases != nullptr ? biases->info() : nullptr), output->info(),
conv_info, weights_info, dilation, act_info, enable_fast_math, num_groups);
_impl->run_pack = {{TensorType::ACL_SRC_0, input},
{TensorType::ACL_SRC_1, weights},
{TensorType::ACL_SRC_2, biases},
{TensorType::ACL_DST, output}};
_impl->aux_mem_req = _impl->op->workspace();
_impl->workspace_tensors =
manage_workspace<Tensor>(_impl->aux_mem_req, _impl->memory_group, _impl->run_pack, _impl->run_pack);
}
Status NEGEMMConvolutionLayer::validate(const ITensorInfo *input,
const ITensorInfo *weights,
const ITensorInfo *biases,
const ITensorInfo *output,
const PadStrideInfo &conv_info,
const WeightsInfo &weights_info,
const Size2D &dilation,
const ActivationLayerInfo &act_info,
bool enable_fast_math,
unsigned int num_groups)
{
return cpu::CpuGemmConv2d::validate(input, weights, biases, output, conv_info, weights_info, dilation, act_info,
enable_fast_math, num_groups);
}
Status NEGEMMConvolutionLayer::has_opt_impl(arm_compute::WeightFormat &expected_weight_format,
const ITensorInfo *src,
const ITensorInfo *weights,
const ITensorInfo *biases,
const ITensorInfo *dst,
const PadStrideInfo &conv_info,
const WeightsInfo &weights_info,
const Size2D &dilation,
const ActivationLayerInfo &act_info,
const bool enable_fast_math)
{
return cpu::CpuGemmConv2d::has_opt_impl(expected_weight_format, src, weights, biases, dst, conv_info, weights_info,
dilation, act_info, enable_fast_math);
}
void NEGEMMConvolutionLayer::run()
{
prepare();
MemoryGroupResourceScope scope_mg(_impl->memory_group);
_impl->op->run(_impl->run_pack);
}
void NEGEMMConvolutionLayer::prepare()
{
if (!_impl->is_prepared)
{
_impl->op->prepare(_impl->run_pack);
// Release temporary tensors that are only used in prepare stage
release_temporaries<Tensor>(_impl->aux_mem_req, _impl->workspace_tensors);
_impl->is_prepared = true;
}
}
} // namespace arm_compute
|
