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
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
|
/*
-----------------------------------------------------------------------
Copyright 2012 iMinds-Vision Lab, University of Antwerp
Contact: astra@ua.ac.be
Website: http://astra.ua.ac.be
This file is part of the
All Scale Tomographic Reconstruction Antwerp Toolbox ("ASTRA Toolbox").
The ASTRA Toolbox 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.
The ASTRA Toolbox 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 the ASTRA Toolbox. If not, see <http://www.gnu.org/licenses/>.
-----------------------------------------------------------------------
$Id$
*/
#include "util.h"
#include "dataop.h"
#include "arith.h"
#include <cassert>
namespace astraCUDA {
void operationVolumeMult(float* data1, float* data2, unsigned int width, unsigned int height)
{
float* D_data1;
float* D_data2;
unsigned int pitch;
allocateVolume(D_data1, width+2, height+2, pitch);
copyVolumeToDevice(data1, width, width, height, D_data1, pitch);
allocateVolume(D_data2, width+2, height+2, pitch);
copyVolumeToDevice(data2, width, width, height, D_data2, pitch);
processVol<opMul, VOL>(D_data1, D_data2, pitch, width, height);
copyVolumeFromDevice(data1, width, width, height, D_data1, pitch);
cudaFree(D_data1);
cudaFree(D_data2);
}
void operationVolumeMultScalarMask(float* data, float* mask, float scalar, unsigned int width, unsigned int height)
{
float* D_data;
float* D_mask;
unsigned int pitch;
allocateVolume(D_data, width+2, height+2, pitch);
copyVolumeToDevice(data, width, width, height, D_data, pitch);
allocateVolume(D_mask, width+2, height+2, pitch);
copyVolumeToDevice(mask, width, width, height, D_mask, pitch);
processVol<opMulMask, VOL>(D_data, D_mask, scalar, pitch, width, height);
copyVolumeFromDevice(data, width, width, height, D_data, pitch);
cudaFree(D_data);
cudaFree(D_mask);
}
void operationVolumeMultScalar(float* data, float scalar, unsigned int width, unsigned int height)
{
float* D_data;
unsigned int pitch;
allocateVolume(D_data, width+2, height+2, pitch);
copyVolumeToDevice(data, width, width, height, D_data, pitch);
processVol<opMul, VOL>(D_data, scalar, pitch, width, height);
copyVolumeFromDevice(data, width, width, height, D_data, pitch);
cudaFree(D_data);
}
void operationVolumeAdd(float* data1, float* data2, unsigned int width, unsigned int height)
{
float* D_data1;
float* D_data2;
unsigned int pitch;
allocateVolume(D_data1, width+2, height+2, pitch);
copyVolumeToDevice(data1, width, width, height, D_data1, pitch);
allocateVolume(D_data2, width+2, height+2, pitch);
copyVolumeToDevice(data2, width, width, height, D_data2, pitch);
processVol<opAdd, VOL>(D_data1, D_data2, pitch, width, height);
copyVolumeFromDevice(data1, width, width, height, D_data1, pitch);
cudaFree(D_data1);
cudaFree(D_data2);
}
void operationVolumeAddScalar(float* data, float scalar, unsigned int width, unsigned int height)
{
float* D_data;
unsigned int pitch;
allocateVolume(D_data, width+2, height+2, pitch);
copyVolumeToDevice(data, width, width, height, D_data, pitch);
processVol<opAdd, VOL>(D_data, scalar, pitch, width, height);
copyVolumeFromDevice(data, width, width, height, D_data, pitch);
cudaFree(D_data);
}
}
|
