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 // Copyright (C) 2013, OpenCV Foundation, all rights reserved. 16 // Third party copyrights are property of their respective owners. 17 // 18 // Redistribution and use in source and binary forms, with or without modification, 19 // are permitted provided that the following conditions are met: 20 // 21 // * Redistribution's of source code must retain the above copyright notice, 22 // this list of conditions and the following disclaimer. 23 // 24 // * Redistribution's in binary form must reproduce the above copyright notice, 25 // this list of conditions and the following disclaimer in the documentation 26 // and/or other materials provided with the distribution. 27 // 28 // * The name of the copyright holders may not be used to endorse or promote products 29 // derived from this software without specific prior written permission. 30 // 31 // This software is provided by the copyright holders and contributors "as is" and 32 // any express or implied warranties, including, but not limited to, the implied 33 // warranties of merchantability and fitness for a particular purpose are disclaimed. 34 // In no event shall the Intel Corporation or contributors be liable for any direct, 35 // indirect, incidental, special, exemplary, or consequential damages 36 // (including, but not limited to, procurement of substitute goods or services; 37 // loss of use, data, or profits; or business interruption) however caused 38 // and on any theory of liability, whether in contract, strict liability, 39 // or tort (including negligence or otherwise) arising in any way out of 40 // the use of this software, even if advised of the possibility of such damage. 41 // 42 //M*/ 43 44 #pragma once 45 46 #ifndef __OPENCV_CUDEV_GRID_REDUCE_TO_ROW_DETAIL_HPP__ 47 #define __OPENCV_CUDEV_GRID_REDUCE_TO_ROW_DETAIL_HPP__ 48 49 #include "../../common.hpp" 50 #include "../../util/saturate_cast.hpp" 51 #include "../../block/reduce.hpp" 52 53 namespace cv { namespace cudev { 54 55 namespace grid_reduce_to_vec_detail 56 { 57 template <class Reductor, int BLOCK_SIZE_X, int BLOCK_SIZE_Y, class SrcPtr, typename ResType, class MaskPtr> reduceToRow(const SrcPtr src,ResType * dst,const MaskPtr mask,const int rows,const int cols)58 __global__ void reduceToRow(const SrcPtr src, ResType* dst, const MaskPtr mask, const int rows, const int cols) 59 { 60 typedef typename Reductor::work_type work_type; 61 62 __shared__ work_type smem[BLOCK_SIZE_X * BLOCK_SIZE_Y]; 63 64 const int x = blockIdx.x * BLOCK_SIZE_X + threadIdx.x; 65 66 work_type myVal = Reductor::initialValue(); 67 68 Reductor op; 69 70 if (x < cols) 71 { 72 for (int y = threadIdx.y; y < rows; y += BLOCK_SIZE_Y) 73 { 74 if (mask(y, x)) 75 { 76 myVal = op(myVal, saturate_cast<work_type>(src(y, x))); 77 } 78 } 79 } 80 81 smem[threadIdx.x * BLOCK_SIZE_Y + threadIdx.y] = myVal; 82 83 __syncthreads(); 84 85 volatile work_type* srow = smem + threadIdx.y * BLOCK_SIZE_X; 86 87 myVal = srow[threadIdx.x]; 88 blockReduce<BLOCK_SIZE_X>(srow, myVal, threadIdx.x, op); 89 90 if (threadIdx.x == 0) 91 srow[0] = myVal; 92 93 __syncthreads(); 94 95 if (threadIdx.y == 0 && x < cols) 96 dst[x] = saturate_cast<ResType>(Reductor::result(smem[threadIdx.x * BLOCK_SIZE_X], rows)); 97 } 98 99 template <class Reductor, class SrcPtr, typename ResType, class MaskPtr> reduceToRow(const SrcPtr & src,ResType * dst,const MaskPtr & mask,int rows,int cols,cudaStream_t stream)100 __host__ void reduceToRow(const SrcPtr& src, ResType* dst, const MaskPtr& mask, int rows, int cols, cudaStream_t stream) 101 { 102 const int BLOCK_SIZE_X = 16; 103 const int BLOCK_SIZE_Y = 16; 104 105 const dim3 block(BLOCK_SIZE_X, BLOCK_SIZE_Y); 106 const dim3 grid(divUp(cols, block.x)); 107 108 reduceToRow<Reductor, BLOCK_SIZE_X, BLOCK_SIZE_Y><<<grid, block, 0, stream>>>(src, dst, mask, rows, cols); 109 CV_CUDEV_SAFE_CALL( cudaGetLastError() ); 110 111 if (stream == 0) 112 CV_CUDEV_SAFE_CALL( cudaDeviceSynchronize() ); 113 } 114 } 115 116 }} 117 118 #endif 119