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
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
// **************************************************************************
//
// PARALUTION www.paralution.com
//
// Copyright (C) 2015 PARALUTION Labs UG (haftungsbeschränkt) & Co. KG
// Am Hasensprung 6, 76571 Gaggenau
// Handelsregister: Amtsgericht Mannheim, HRA 706051
// Vertreten durch:
// PARALUTION Labs Verwaltungs UG (haftungsbeschränkt)
// Am Hasensprung 6, 76571 Gaggenau
// Handelsregister: Amtsgericht Mannheim, HRB 721277
// Geschäftsführer: Dimitar Lukarski, Nico Trost
//
// This program is free software: you can redistribute it and/or modify
// it under the terms of the GNU General Public License as published by
// the Free Software Foundation, either version 3 of the License, or
// (at your option) any later version.
//
// This program is distributed in the hope that it will be useful,
// but WITHOUT ANY WARRANTY; without even the implied warranty of
// MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the
// GNU General Public License for more details.
//
// You should have received a copy of the GNU General Public License
// along with this program. If not, see <http://www.gnu.org/licenses/>.
//
// **************************************************************************
// PARALUTION version 1.1.0
#ifndef PARALUTION_GPU_MATRIX_ELL_HPP_
#define PARALUTION_GPU_MATRIX_ELL_HPP_
#include "../base_matrix.hpp"
#include "../base_vector.hpp"
#include "../matrix_formats.hpp"
namespace paralution {
template <typename ValueType>
class GPUAcceleratorMatrixELL : public GPUAcceleratorMatrix<ValueType> {
public:
GPUAcceleratorMatrixELL();
GPUAcceleratorMatrixELL(const Paralution_Backend_Descriptor local_backend);
virtual ~GPUAcceleratorMatrixELL();
inline int get_max_row(void) const { return mat_.max_row; }
virtual void info(void) const;
virtual unsigned int get_mat_format(void) const { return ELL; }
virtual void Clear(void);
virtual void AllocateELL(const int nnz, const int nrow, const int ncol, const int max_row);
virtual void SetDataPtrELL(int **col, ValueType **val,
const int nnz, const int nrow, const int ncol, const int max_row);
virtual void LeaveDataPtrELL(int **col, ValueType **val, int &max_row);
virtual bool ConvertFrom(const BaseMatrix<ValueType> &mat);
virtual void CopyFrom(const BaseMatrix<ValueType> &mat);
virtual void CopyFromAsync(const BaseMatrix<ValueType> &mat);
virtual void CopyTo(BaseMatrix<ValueType> *mat) const;
virtual void CopyToAsync(BaseMatrix<ValueType> *mat) const;
virtual void CopyFromHost(const HostMatrix<ValueType> &src);
virtual void CopyFromHostAsync(const HostMatrix<ValueType> &src);
virtual void CopyToHost(HostMatrix<ValueType> *dst) const;
virtual void CopyToHostAsync(HostMatrix<ValueType> *dst) const;
virtual void Apply(const BaseVector<ValueType> &in, BaseVector<ValueType> *out) const;
virtual void ApplyAdd(const BaseVector<ValueType> &in, const ValueType scalar,
BaseVector<ValueType> *out) const;
private:
MatrixELL<ValueType, int> mat_;
friend class BaseVector<ValueType>;
friend class AcceleratorVector<ValueType>;
friend class GPUAcceleratorVector<ValueType>;
};
}
#endif // PARALUTION_GPU_MATRIX_ELL_HPP_