Home | History | Annotate | Download | only in cuda
      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 "opencv2/opencv_modules.hpp"
     44 
     45 #ifndef HAVE_OPENCV_CUDEV
     46 
     47 #error "opencv_cudev is required"
     48 
     49 #else
     50 
     51 #include "opencv2/cudaarithm.hpp"
     52 #include "opencv2/cudev.hpp"
     53 #include "opencv2/core/private.cuda.hpp"
     54 
     55 using namespace cv;
     56 using namespace cv::cuda;
     57 using namespace cv::cudev;
     58 
     59 void cv::cuda::transpose(InputArray _src, OutputArray _dst, Stream& stream)
     60 {
     61     GpuMat src = getInputMat(_src, stream);
     62 
     63     const size_t elemSize = src.elemSize();
     64 
     65     CV_Assert( elemSize == 1 || elemSize == 4 || elemSize == 8 );
     66 
     67     GpuMat dst = getOutputMat(_dst, src.cols, src.rows, src.type(), stream);
     68 
     69     if (elemSize == 1)
     70     {
     71         NppStreamHandler h(StreamAccessor::getStream(stream));
     72 
     73         NppiSize sz;
     74         sz.width  = src.cols;
     75         sz.height = src.rows;
     76 
     77         nppSafeCall( nppiTranspose_8u_C1R(src.ptr<Npp8u>(), static_cast<int>(src.step),
     78             dst.ptr<Npp8u>(), static_cast<int>(dst.step), sz) );
     79 
     80         if (!stream)
     81             CV_CUDEV_SAFE_CALL( cudaDeviceSynchronize() );
     82     }
     83     else if (elemSize == 4)
     84     {
     85         gridTranspose(globPtr<int>(src), globPtr<int>(dst), stream);
     86     }
     87     else // if (elemSize == 8)
     88     {
     89         gridTranspose(globPtr<double>(src), globPtr<double>(dst), stream);
     90     }
     91 
     92     syncOutput(dst, _dst, stream);
     93 }
     94 
     95 #endif
     96