warp_reduce.hpp

00001 /*M///////////////////////////////////////////////////////////////////////////////////////
00002 //
00003 //  IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
00004 //
00005 //  By downloading, copying, installing or using the software you agree to this license.
00006 //  If you do not agree to this license, do not download, install,
00007 //  copy or use the software.
00008 //
00009 //
00010 //                           License Agreement
00011 //                For Open Source Computer Vision Library
00012 //
00013 // Copyright (C) 2000-2008, Intel Corporation, all rights reserved.
00014 // Copyright (C) 2009, Willow Garage Inc., all rights reserved.
00015 // Third party copyrights are property of their respective owners.
00016 //
00017 // Redistribution and use in source and binary forms, with or without modification,
00018 // are permitted provided that the following conditions are met:
00019 //
00020 //   * Redistribution's of source code must retain the above copyright notice,
00021 //     this list of conditions and the following disclaimer.
00022 //
00023 //   * Redistribution's in binary form must reproduce the above copyright notice,
00024 //     this list of conditions and the following disclaimer in the documentation
00025 //     and/or other materials provided with the distribution.
00026 //
00027 //   * The name of the copyright holders may not be used to endorse or promote products
00028 //     derived from this software without specific prior written permission.
00029 //
00030 // This software is provided by the copyright holders and contributors "as is" and
00031 // any express or implied warranties, including, but not limited to, the implied
00032 // warranties of merchantability and fitness for a particular purpose are disclaimed.
00033 // In no event shall the Intel Corporation or contributors be liable for any direct,
00034 // indirect, incidental, special, exemplary, or consequential damages
00035 // (including, but not limited to, procurement of substitute goods or services;
00036 // loss of use, data, or profits; or business interruption) however caused
00037 // and on any theory of liability, whether in contract, strict liability,
00038 // or tort (including negligence or otherwise) arising in any way out of
00039 // the use of this software, even if advised of the possibility of such damage.
00040 //
00041 //M*/
00042 
00043 #ifndef OPENCV_CUDA_WARP_REDUCE_HPP__
00044 #define OPENCV_CUDA_WARP_REDUCE_HPP__
00045 
00046 /** @file
00047  * @deprecated Use @ref cudev instead.
00048  */
00049 
00050 //! @cond IGNORED
00051 
00052 namespace cv { namespace cuda { namespace device
00053 {
00054     template <class T>
00055     __device__ __forceinline__ T warp_reduce(volatile T *ptr , const unsigned int tid = threadIdx.x)
00056     {
00057         const unsigned int lane = tid & 31; // index of thread in warp (0..31)
00058 
00059         if (lane < 16)
00060         {
00061             T partial = ptr[tid];
00062 
00063             ptr[tid] = partial = partial + ptr[tid + 16];
00064             ptr[tid] = partial = partial + ptr[tid + 8];
00065             ptr[tid] = partial = partial + ptr[tid + 4];
00066             ptr[tid] = partial = partial + ptr[tid + 2];
00067             ptr[tid] = partial = partial + ptr[tid + 1];
00068         }
00069 
00070         return ptr[tid - lane];
00071     }
00072 }}} // namespace cv { namespace cuda { namespace cudev {
00073 
00074 //! @endcond
00075 
00076 #endif /* OPENCV_CUDA_WARP_REDUCE_HPP__ */
00077