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
|
/*
* Copyright (c) 2022-2023 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.
*/
#include "src/cpu/kernels/directconv2d/impl.h"
#include "src/cpu/kernels/directconv2d/nchw/impl.h"
namespace arm_compute
{
namespace cpu
{
namespace kernels
{
#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
void neon_fp16_nchw_directconv2d(
const Window &window, const ITensor *src, const ITensor *weights, ITensor *dst, const PadStrideInfo &conv_info)
{
convolve_nchw<float16_t>(window, src, weights, dst, conv_info);
}
#endif //defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
void run_im2col_fp16_nchw_pad(const ITensor *src,
ITensor *dst,
const Window &window,
DataLayout data_layout,
const PadStrideInfo &conv_info,
std::pair<unsigned int, unsigned int> convolved_dims,
const Size2D &kernel_dims,
const Size2D &dilation,
uint32_t input_pad_right,
bool has_bias)
{
#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
arm_compute::cpu::kernels::run_im2col<float16_t, true, true>(
src, dst, window, data_layout, conv_info, convolved_dims, kernel_dims, dilation, input_pad_right, has_bias);
#else // defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
ARM_COMPUTE_UNUSED(src, dst, window, data_layout, conv_info, convolved_dims, kernel_dims, dilation, input_pad_right,
has_bias);
#endif // defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
}
void run_im2col_fp16_nchw_nopad(const ITensor *src,
ITensor *dst,
const Window &window,
DataLayout data_layout,
const PadStrideInfo &conv_info,
std::pair<unsigned int, unsigned int> convolved_dims,
const Size2D &kernel_dims,
const Size2D &dilation,
uint32_t input_pad_right,
bool has_bias)
{
#if defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
arm_compute::cpu::kernels::run_im2col<float16_t, false, true>(
src, dst, window, data_layout, conv_info, convolved_dims, kernel_dims, dilation, input_pad_right, has_bias);
#else // defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
ARM_COMPUTE_UNUSED(src, dst, window, data_layout, conv_info, convolved_dims, kernel_dims, dilation, input_pad_right,
has_bias);
#endif // defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC) && defined(ENABLE_FP16_KERNELS)
}
} // namespace kernels
} // namespace cpu
} // namespace arm_compute
|
