1/*M///////////////////////////////////////////////////////////////////////////////////////
2//
3//  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
4//
5//  By downloading, copying, installing or using the software you agree to this license.
6//  If you do not agree to this license, do not download, install,
7//  copy or use the software.
8//
9//
10//                           License Agreement
11//                For Open Source Computer Vision Library
12//
13// Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
14// Copyright (C) 2009, Willow Garage Inc., all rights reserved.
15// Third party copyrights are property of their respective owners.
16//
17// Redistribution and use in source and binary forms, with or without modification,
18// are permitted provided that the following conditions are met:
19//
20//   * Redistribution's of source code must retain the above copyright notice,
21//     this list of conditions and the following disclaimer.
22//
23//   * Redistribution's in binary form must reproduce the above copyright notice,
24//     this list of conditions and the following disclaimer in the documentation
25//     and/or other materials provided with the distribution.
26//
27//   * The name of the copyright holders may not be used to endorse or promote products
28//     derived from this software without specific prior written permission.
29//
30// This software is provided by the copyright holders and contributors "as is" and
31// any express or implied warranties, including, but not limited to, the implied
32// warranties of merchantability and fitness for a particular purpose are disclaimed.
33// In no event shall the Intel Corporation or contributors be liable for any direct,
34// indirect, incidental, special, exemplary, or consequential damages
35// (including, but not limited to, procurement of substitute goods or services;
36// loss of use, data, or profits; or business interruption) however caused
37// and on any theory of liability, whether in contract, strict liability,
38// or tort (including negligence or otherwise) arising in any way out of
39// the use of this software, even if advised of the possibility of such damage.
40//
41//M*/
42
43#include "precomp.hpp"
44
45using namespace cv;
46using namespace cv::cuda;
47
48#if !defined (HAVE_CUDA) || defined (CUDA_DISABLER)
49
50void cv::cuda::merge(const GpuMat*, size_t, OutputArray, Stream&) { throw_no_cuda(); }
51void cv::cuda::merge(const std::vector<GpuMat>&, OutputArray, Stream&) { throw_no_cuda(); }
52
53void cv::cuda::split(InputArray, GpuMat*, Stream&) { throw_no_cuda(); }
54void cv::cuda::split(InputArray, std::vector<GpuMat>&, Stream&) { throw_no_cuda(); }
55
56void cv::cuda::transpose(InputArray, OutputArray, Stream&) { throw_no_cuda(); }
57
58void cv::cuda::flip(InputArray, OutputArray, int, Stream&) { throw_no_cuda(); }
59
60Ptr<LookUpTable> cv::cuda::createLookUpTable(InputArray) { throw_no_cuda(); return Ptr<LookUpTable>(); }
61
62void cv::cuda::copyMakeBorder(InputArray, OutputArray, int, int, int, int, int, Scalar, Stream&) { throw_no_cuda(); }
63
64#else /* !defined (HAVE_CUDA) */
65
66////////////////////////////////////////////////////////////////////////
67// flip
68
69namespace
70{
71    template<int DEPTH> struct NppTypeTraits;
72    template<> struct NppTypeTraits<CV_8U>  { typedef Npp8u npp_t; };
73    template<> struct NppTypeTraits<CV_8S>  { typedef Npp8s npp_t; };
74    template<> struct NppTypeTraits<CV_16U> { typedef Npp16u npp_t; };
75    template<> struct NppTypeTraits<CV_16S> { typedef Npp16s npp_t; };
76    template<> struct NppTypeTraits<CV_32S> { typedef Npp32s npp_t; };
77    template<> struct NppTypeTraits<CV_32F> { typedef Npp32f npp_t; };
78    template<> struct NppTypeTraits<CV_64F> { typedef Npp64f npp_t; };
79
80    template <int DEPTH> struct NppMirrorFunc
81    {
82        typedef typename NppTypeTraits<DEPTH>::npp_t npp_t;
83
84        typedef NppStatus (*func_t)(const npp_t* pSrc, int nSrcStep, npp_t* pDst, int nDstStep, NppiSize oROI, NppiAxis flip);
85    };
86
87    template <int DEPTH, typename NppMirrorFunc<DEPTH>::func_t func> struct NppMirror
88    {
89        typedef typename NppMirrorFunc<DEPTH>::npp_t npp_t;
90
91        static void call(const GpuMat& src, GpuMat& dst, int flipCode, cudaStream_t stream)
92        {
93            NppStreamHandler h(stream);
94
95            NppiSize sz;
96            sz.width  = src.cols;
97            sz.height = src.rows;
98
99            nppSafeCall( func(src.ptr<npp_t>(), static_cast<int>(src.step),
100                dst.ptr<npp_t>(), static_cast<int>(dst.step), sz,
101                (flipCode == 0 ? NPP_HORIZONTAL_AXIS : (flipCode > 0 ? NPP_VERTICAL_AXIS : NPP_BOTH_AXIS))) );
102
103            if (stream == 0)
104                cudaSafeCall( cudaDeviceSynchronize() );
105        }
106    };
107}
108
109void cv::cuda::flip(InputArray _src, OutputArray _dst, int flipCode, Stream& stream)
110{
111    typedef void (*func_t)(const GpuMat& src, GpuMat& dst, int flipCode, cudaStream_t stream);
112    static const func_t funcs[6][4] =
113    {
114        {NppMirror<CV_8U, nppiMirror_8u_C1R>::call, 0, NppMirror<CV_8U, nppiMirror_8u_C3R>::call, NppMirror<CV_8U, nppiMirror_8u_C4R>::call},
115        {0,0,0,0},
116        {NppMirror<CV_16U, nppiMirror_16u_C1R>::call, 0, NppMirror<CV_16U, nppiMirror_16u_C3R>::call, NppMirror<CV_16U, nppiMirror_16u_C4R>::call},
117        {0,0,0,0},
118        {NppMirror<CV_32S, nppiMirror_32s_C1R>::call, 0, NppMirror<CV_32S, nppiMirror_32s_C3R>::call, NppMirror<CV_32S, nppiMirror_32s_C4R>::call},
119        {NppMirror<CV_32F, nppiMirror_32f_C1R>::call, 0, NppMirror<CV_32F, nppiMirror_32f_C3R>::call, NppMirror<CV_32F, nppiMirror_32f_C4R>::call}
120    };
121
122    GpuMat src = getInputMat(_src, stream);
123
124    CV_Assert(src.depth() == CV_8U || src.depth() == CV_16U || src.depth() == CV_32S || src.depth() == CV_32F);
125    CV_Assert(src.channels() == 1 || src.channels() == 3 || src.channels() == 4);
126
127    _dst.create(src.size(), src.type());
128    GpuMat dst = getOutputMat(_dst, src.size(), src.type(), stream);
129
130    funcs[src.depth()][src.channels() - 1](src, dst, flipCode, StreamAccessor::getStream(stream));
131
132    syncOutput(dst, _dst, stream);
133}
134
135#endif /* !defined (HAVE_CUDA) */
136