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
|
/*
* Copyright (c) 2018 Samsung Electronics Co., Ltd. All Rights Reserved
*
* Licensed under the Apache License, Version 2.0 (the "License");
* you may not use this file except in compliance with the License.
* You may obtain a copy of the License at
*
* http://www.apache.org/licenses/LICENSE-2.0
*
* Unless required by applicable law or agreed to in writing, software
* distributed under the License is distributed on an "AS IS" BASIS,
* WITHOUT WARRANTIES OR CONDITIONS OF ANY KIND, either express or implied.
* See the License for the specific language governing permissions and
* limitations under the License.
*/
#include "internal/layers/SimpleCastLayer.h"
#include <arm_compute/runtime/CL/CLScheduler.h>
void SimpleCastLayer::castData(::arm_compute::ITensor *in, ::arm_compute::ITensor *out,
const arm_compute::Coordinates &id)
{
switch (in->info()->data_type())
{
case ::arm_compute::DataType::F32:
{
copyCast(*reinterpret_cast<float *>(in->ptr_to_element(id)), out, id);
break;
}
case ::arm_compute::DataType::S32:
{
copyCast(*reinterpret_cast<int32_t *>(in->ptr_to_element(id)), out, id);
break;
}
case ::arm_compute::DataType::U32:
{
copyCast(*reinterpret_cast<uint32_t *>(in->ptr_to_element(id)), out, id);
break;
}
case ::arm_compute::DataType::QASYMM8:
{
const uint8_t quantizedValue = *(in->ptr_to_element(id));
copyCast(in->info()->quantization_info().dequantize(quantizedValue), out, id);
break;
}
default:
throw std::runtime_error("Not supported, yet");
break;
}
}
void SimpleCastLayer::configure(::arm_compute::ITensor *in, ::arm_compute::ITensor *out)
{
_in = in;
_out = out;
}
void SimpleCastLayer::run(void)
{
if (::internal::arm_compute::isGpuMode())
{
auto &q = ::arm_compute::CLScheduler::get().queue();
CAST_CL(_in)->map(q);
CAST_CL(_out)->map(q);
}
arm_compute::Window window;
window.use_tensor_dimensions(_out->info()->tensor_shape());
execute_window_loop(window,
[this](const arm_compute::Coordinates &id) { castData(_in, _out, id); });
if (::internal::arm_compute::isGpuMode())
{
auto &q = ::arm_compute::CLScheduler::get().queue();
CAST_CL(_out)->unmap(q);
CAST_CL(_in)->unmap(q);
}
}
|
