xref: /aosp_15_r20/external/ComputeLibrary/src/cpu/kernels/gemm_matrix_mul/generic/neon/impl.h (revision c217d954acce2dbc11938adb493fc0abd69584f3)
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 #ifndef SRC_CORE_KERNELS_GEMMMATRIXMUL_IMPL_H
25 #define SRC_CORE_KERNELS_GEMMMATRIXMUL_IMPL_H
26 #include "arm_compute/core/Helpers.h"
27 #include "src/core/CPP/Validate.h"
28 
29 namespace arm_compute
30 {
31 namespace cpu
32 {
33 #ifdef __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
34 void vector_matrix_multiply_f16(const ITensor *lhs, const ITensor *rhs, ITensor *dst, const Window &window, const ThreadInfo &info, float alpha);
35 
36 void matrix_matrix_multiply_f16(const ITensor *lhs, const ITensor *rhs, ITensor *dst, const Window &window, const ThreadInfo &info, float alpha);
37 
38 #endif // __ARM_FEATURE_FP16_VECTOR_ARITHMETIC
39 
40 void vector_matrix_multiply_f32(const ITensor *lhs, const ITensor *rhs, ITensor *dst, const Window &window, const ThreadInfo &info, float alpha);
41 
42 void matrix_matrix_multiply_f32(const ITensor *lhs, const ITensor *rhs, ITensor *dst, const Window &window, const ThreadInfo &info, float alpha);
43 
44 } // namespace cpu
45 } // namespace arm_compute
46 #endif //define SRC_CORE_KERNELS_GEMMMATRIXMUL_IMPL_H
47