ARM Compute Library
17.03.1
Main Page
Namespaces
Data Structures
Files
File List
Globals
NEGEMM.h
Go to the documentation of this file.
1
/*
2
* Copyright (c) 2017 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 __ARM_COMPUTE_NEGEMM_H__
25
#define __ARM_COMPUTE_NEGEMM_H__
26
27
#include "
arm_compute/core/NEON/kernels/NEFillBorderKernel.h
"
28
#include "
arm_compute/core/NEON/kernels/NEGEMMInterleave4x4Kernel.h
"
29
#include "
arm_compute/core/NEON/kernels/NEGEMMMatrixAdditionKernel.h
"
30
#include "
arm_compute/core/NEON/kernels/NEGEMMMatrixMultiplyKernel.h
"
31
#include "
arm_compute/core/NEON/kernels/NEGEMMTranspose1xWKernel.h
"
32
#include "
arm_compute/runtime/IFunction.h
"
33
#include "
arm_compute/runtime/Tensor.h
"
34
35
namespace
arm_compute
36
{
45
class
NEGEMM
:
public
IFunction
46
{
47
public
:
49
NEGEMM
();
62
void
configure
(
const
ITensor
*a,
const
ITensor
*b,
const
ITensor
*c,
ITensor
*d,
float
alpha,
float
beta);
63
64
// Inherited methods overridden:
65
void
run
()
override
;
66
67
private
:
68
NEGEMMInterleave4x4Kernel
_interleave_kernel;
69
NEGEMMTranspose1xWKernel
_transpose_kernel;
70
NEGEMMMatrixMultiplyKernel
_mm_kernel;
71
NEGEMMMatrixAdditionKernel
_ma_kernel;
72
Tensor
_tmp_a;
73
Tensor
_tmp_b;
74
bool
_run_vector_matrix_multiplication;
75
bool
_run_addition;
76
};
77
}
78
#endif
/*__ARM_COMPUTE_NEGEMM_H__ */
NEGEMMInterleave4x4Kernel.h
NEGEMMMatrixMultiplyKernel.h
arm_compute::IFunction
Base class for all functions.
Definition:
IFunction.h:30
arm_compute::NEGEMM
Basic function to execute GEMM on NEON.
Definition:
NEGEMM.h:45
arm_compute::ITensor
Interface for NEON tensor.
Definition:
ITensor.h:36
arm_compute
Definition:
arm_compute.dox:1
NEFillBorderKernel.h
NEGEMMTranspose1xWKernel.h
arm_compute::NEGEMMInterleave4x4Kernel
NEON kernel to interleave the elements of a matrix.
Definition:
NEGEMMInterleave4x4Kernel.h:52
arm_compute::NEGEMM::NEGEMM
NEGEMM()
Constructor.
arm_compute::NEGEMM::run
void run() override
Run the kernels contained in the function.
Tensor.h
arm_compute::NEGEMMTranspose1xWKernel
NEON kernel which transposes the elements of a matrix in chunks of 1x4 if the input data type is F32 ...
Definition:
NEGEMMTranspose1xWKernel.h:69
arm_compute::Tensor
Basic implementation of the tensor interface.
Definition:
Tensor.h:37
arm_compute::NEGEMMMatrixAdditionKernel
NEON kernel to perform the in-place matrix addition between 2 matrices taking into account that the s...
Definition:
NEGEMMMatrixAdditionKernel.h:41
IFunction.h
arm_compute::NEGEMM::configure
void configure(const ITensor *a, const ITensor *b, const ITensor *c, ITensor *d, float alpha, float beta)
Initialise the kernel's inputs, output.
arm_compute::NEGEMMMatrixMultiplyKernel
NEON kernel to multiply two input matrices "A" and "B".
Definition:
NEGEMMMatrixMultiplyKernel.h:39
NEGEMMMatrixAdditionKernel.h
arm_compute
runtime
NEON
functions
NEGEMM.h
Generated on Fri Mar 24 2017 17:23:49 for ARM Compute Library by
1.8.11