aboutsummaryrefslogtreecommitdiff
path: root/src/cpu/kernels/gemm_matrix_mul/generic/neon/fp32.cpp
blob: e12a312280d13730094ac965ed30130ab3a991ab (plain)
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
/*
 * Copyright (c) 2022 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/gemm_matrix_mul/generic/neon/impl.h"

namespace arm_compute
{
namespace cpu
{
void neon_fp32_gemm_matrix_mul(const ITensor    *lhs,
                               const ITensor    *rhs,
                               ITensor          *dst,
                               const Window     &window,
                               const ThreadInfo &info,
                               float             alpha,
                               const bool        is_dst_vector)
{
    return (is_dst_vector) ? vector_matrix_multiply_f32(lhs, rhs, dst, window, info, alpha)
                           : matrix_matrix_multiply_f32(lhs, rhs, dst, window, info, alpha);
}
} // namespace cpu
} // namespace arm_compute