1 /*
2 * Copyright (c) 2022 Arm Limited.
3 *
4 * SPDX-License-Identifier: MIT
5 *
6 * Permission is hereby granted, free of charge, to any person obtaining a copy
7 * of this software and associated documentation files (the "Software"), to
8 * deal in the Software without restriction, including without limitation the
9 * rights to use, copy, modify, merge, publish, distribute, sublicense, and/or
10 * sell copies of the Software, and to permit persons to whom the Software is
11 * furnished to do so, subject to the following conditions:
12 *
13 * The above copyright notice and this permission notice shall be included in all
14 * copies or substantial portions of the Software.
15 *
16 * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
17 * IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
18 * FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL THE
19 * AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
20 * LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM,
21 * OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE
22 * SOFTWARE.
23 */
24
25 #if defined(__aarch64__) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)
26
27 #include "winograd_implementations.hpp"
28 #include "weight_transform.hpp"
29
30 namespace arm_conv {
31 namespace winograd {
32 namespace weight_transform {
33
34 void *a64_fp16_4x4_3x3(unsigned int, const __fp16 *, size_t, size_t, __fp16 *, size_t);
35
36 #define IMPL(KERN_ROWS, KERN_COLS, TRANS_ROWS, TRANS_COLS, KERN) \
37 new Transform<__fp16>(#KERN, KERN_ROWS, KERN_COLS, TRANS_ROWS, TRANS_COLS, KERN)
38
39 static const TransformImplementation<__fp16> transforms_fp16[] = {
40 { IMPL(3, 3, 6, 6, a64_fp16_4x4_3x3) },
41 { nullptr }
42 };
43
44 template <>
implementation_list(void)45 const TransformImplementation<__fp16> *implementation_list(void)
46 {
47 return transforms_fp16;
48 }
49
50 } // namespace weight_transform
51 } // namespace winograd
52 } // namespace arm_conv
53
54 #endif // defined(__aarch64__) && defined(__ARM_FEATURE_FP16_VECTOR_ARITHMETIC)
55