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) 2017-2018 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.
*/
#ifndef __ARM_COMPUTE_NEGEMMLOWPAARCH64KERNEL_H__
#define __ARM_COMPUTE_NEGEMMLOWPAARCH64KERNEL_H__
#include "arm_compute/core/NEON/kernels/NEGEMMAssemblyBaseKernel.h"
// Enable only if compiled for AArch64-V8A targets
#ifdef ARM_COMPUTE_AARCH64_V8A
namespace arm_compute
{
class ITensor;
/** AArch64 NEON kernel to multiply two input matrices "A" and "B". */
class NEGEMMLowpAArch64Kernel : public NEGEMMAssemblyBaseKernel
{
public:
const char *name() const override
{
return "NEGEMMLowpAArch64Kernel";
}
/** Default constructor */
NEGEMMLowpAArch64Kernel();
// Inherited methods overridden:
void run(const Window &window, const ThreadInfo &info) override;
protected:
void internal_configure(const ITensor *input0, const ITensor *input1, ITensor *output, ITensor *workspace, float alpha, float beta, bool is_transposed_0, bool is_transposed_1) override;
private:
using NEGEMMLowpAArch64 = void(const ITensor *input0, const ITensor *input1, ITensor *output, ITensor *workspace, float alpha, float beta, bool is_transposed_0,
bool is_transposed_1, const Window &window,
const ThreadInfo &info);
NEGEMMLowpAArch64 *_func;
};
} // namespace arm_compute
#endif /* ARM_COMPUTE_AARCH64_V8A */
#endif /*__ARM_COMPUTE_NEGEMMLOWPAARCH64KERNEL_H__*/
|
