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
|
/*
* Copyright (c) 2020, 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 <cstdint>
#include <cstring>
#ifdef ARM_COMPUTE_ENABLE_BF16
#include "bfloat.hpp"
using arm_gemm::bfloat16;
#endif
namespace arm_conv {
namespace pooling {
template <typename T>
void cpp_nhwc_1x1_stride_any_depthfirst_impl(
uint64_t,
uint64_t,
const uint64_t n_channels,
const T *const *const inptrs,
T *outptr
)
{
std::memcpy(outptr, inptrs[0], n_channels * sizeof(T));
}
template void cpp_nhwc_1x1_stride_any_depthfirst_impl(uint64_t, uint64_t, uint64_t, const float *const *, float *);
#ifdef __ARM_FP16_ARGS
template void cpp_nhwc_1x1_stride_any_depthfirst_impl(uint64_t, uint64_t, uint64_t, const __fp16 *const *, __fp16 *);
#endif
#ifdef ARM_COMPUTE_ENABLE_BF16
template void cpp_nhwc_1x1_stride_any_depthfirst_impl(uint64_t, uint64_t, uint64_t, const bfloat16 *const *, bfloat16 *);
#endif
template void cpp_nhwc_1x1_stride_any_depthfirst_impl(uint64_t, uint64_t, uint64_t, const int8_t *const *, int8_t *);
template void cpp_nhwc_1x1_stride_any_depthfirst_impl(uint64_t, uint64_t, uint64_t, const uint8_t *const *, uint8_t *);
} // namespace pooling
} // namespace arm_conv
|
