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
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
178
179
180
181
182
183
184
185
186
187
188
189
190
191
192
193
194
195
196
197
198
199
200
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
// Third party copyrights are property of their respective owners.
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other materials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors "as is" and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this software, even if advised of the possibility of such damage.
//
//M*/
#ifndef __OPENCV_internal_shared_HPP__
#define __OPENCV_internal_shared_HPP__
#include "opencv2/gpu/devmem2d.hpp"
#include "safe_call.hpp"
#include "cuda_runtime.h"
#include "npp.h"
#include "NPP_staging.hpp"
#ifndef CV_PI_F
#ifndef CV_PI
#define CV_PI_F 3.14159265f
#else
#define CV_PI_F ((float)CV_PI)
#endif
#endif
namespace cv
{
namespace gpu
{
typedef unsigned char uchar;
typedef signed char schar;
typedef unsigned short ushort;
typedef unsigned int uint;
enum
{
BORDER_REFLECT101_GPU = 0,
BORDER_REPLICATE_GPU,
BORDER_CONSTANT_GPU
};
// Converts CPU border extrapolation mode into GPU internal analogue.
// Returns true if the GPU analogue exists, false otherwise.
bool tryConvertToGpuBorderType(int cpuBorderType, int& gpuBorderType);
static inline int divUp(int total, int grain) { return (total + grain - 1) / grain; }
template<class T> static inline void uploadConstant(const char* name, const T& value)
{
cudaSafeCall( cudaMemcpyToSymbol(name, &value, sizeof(T)) );
}
template<class T> static inline void uploadConstant(const char* name, const T& value, cudaStream_t stream)
{
cudaSafeCall( cudaMemcpyToSymbolAsync(name, &value, sizeof(T), 0, cudaMemcpyHostToDevice, stream) );
}
template<class T> static inline void bindTexture(const char* name, const DevMem2D_<T>& img/*, bool normalized = false,
enum cudaTextureFilterMode filterMode = cudaFilterModePoint, enum cudaTextureAddressMode addrMode = cudaAddressModeClamp*/)
{
//!!!! const_cast is disabled!
//!!!! Please use constructor of 'class texture' instead.
//textureReference* tex;
//cudaSafeCall( cudaGetTextureReference((const textureReference**)&tex, name) );
//tex->normalized = normalized;
//tex->filterMode = filterMode;
//tex->addressMode[0] = addrMode;
//tex->addressMode[1] = addrMode;
const textureReference* tex;
cudaSafeCall( cudaGetTextureReference(&tex, name) );
cudaChannelFormatDesc desc = cudaCreateChannelDesc<T>();
cudaSafeCall( cudaBindTexture2D(0, tex, img.ptr(), &desc, img.cols, img.rows, img.step) );
}
static inline void unbindTexture(const char *name)
{
const textureReference* tex;
cudaSafeCall( cudaGetTextureReference(&tex, name) );
cudaSafeCall( cudaUnbindTexture(tex) );
}
class TextureBinder
{
public:
TextureBinder() : tex_(0) {}
template <typename T> TextureBinder(const textureReference* tex, const DevMem2D_<T>& img) : tex_(0)
{
bind(tex, img);
}
template <typename T> TextureBinder(const char* tex_name, const DevMem2D_<T>& img) : tex_(0)
{
bind(tex_name, img);
}
~TextureBinder() { unbind(); }
template <typename T> void bind(const textureReference* tex, const DevMem2D_<T>& img)
{
unbind();
cudaChannelFormatDesc desc = cudaCreateChannelDesc<T>();
cudaSafeCall( cudaBindTexture2D(0, tex, img.ptr(), &desc, img.cols, img.rows, img.step) );
tex_ = tex;
}
template <typename T> void bind(const char* tex_name, const DevMem2D_<T>& img)
{
const textureReference* tex;
cudaSafeCall( cudaGetTextureReference(&tex, tex_name) );
bind(tex, img);
}
void unbind()
{
if (tex_)
{
cudaUnbindTexture(tex_);
tex_ = 0;
}
}
private:
const textureReference* tex_;
};
class NppStreamHandler
{
public:
inline explicit NppStreamHandler(cudaStream_t newStream = 0)
{
oldStream = nppGetStream();
nppSetStream(newStream);
}
inline ~NppStreamHandler()
{
nppSetStream(oldStream);
}
private:
cudaStream_t oldStream;
};
class NppStStreamHandler
{
public:
inline explicit NppStStreamHandler(cudaStream_t newStream = 0)
{
oldStream = nppStSetActiveCUDAstream(newStream);
}
inline ~NppStStreamHandler()
{
nppStSetActiveCUDAstream(oldStream);
}
private:
cudaStream_t oldStream;
};
}
}
#endif /* __OPENCV_internal_shared_HPP__ */