1 /*M///////////////////////////////////////////////////////////////////////////////////////
3 // IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
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.
11 // For Open Source Computer Vision Library
13 // Copyright (C) 2010-2012, Institute Of Software Chinese Academy Of Science, all rights reserved.
14 // Copyright (C) 2010-2012, Advanced Micro Devices, Inc., all rights reserved.
15 // Third party copyrights are property of their respective owners.
18 // Jiang Liyuan, jlyuan001.good@163.com
20 // Redistribution and use in source and binary forms, with or without modification,
21 // are permitted provided that the following conditions are met:
23 // * Redistribution's of source code must retain the above copyright notice,
24 // this list of conditions and the following disclaimer.
26 // * Redistribution's in binary form must reproduce the above copyright notice,
27 // this list of conditions and the following disclaimer in the documentation
28 // and/or other materials provided with the distribution.
30 // * The name of the copyright holders may not be used to endorse or promote products
31 // derived from this software without specific prior written permission.
33 // This software is provided by the copyright holders and contributors as is and
34 // any express or implied warranties, including, but not limited to, the implied
35 // warranties of merchantability and fitness for a particular purpose are disclaimed.
36 // In no event shall the Intel Corporation or contributors be liable for any direct,
37 // indirect, incidental, special, exemplary, or consequential damages
38 // (including, but not limited to, procurement of substitute goods or services;
39 // loss of use, data, or profits; or business interruption) however caused
40 // and on any theory of liability, whether in contract, strict liability,
41 // or tort (including negligence or otherwise) arising in any way out of
42 // the use of this software, even if advised of the possibility of such damage.
48 #pragma OPENCL EXTENSION cl_amd_fp64:enable
49 #elif defined (cl_khr_fp64)
50 #pragma OPENCL EXTENSION cl_khr_fp64:enable
54 /************************************** convolve **************************************/
56 __kernel void convolve_D5(__global float *src, __global float *temp1, __global float *dst,
57 int rows, int cols, int src_step, int dst_step,int k_step, int kWidth, int kHeight,
58 int src_offset, int dst_offset, int koffset)
60 __local float smem[16 + 2 * 8][16 + 2 * 8];
62 int x = get_local_id(0);
63 int y = get_local_id(1);
64 int gx = get_global_id(0);
65 int gy = get_global_id(1);
73 smem[y][x] = src[min(max(gy - 8, 0), rows - 1) * src_step + min(max(gx - 8, 0), cols - 1) + src_offset];
81 smem[y][x + 16] = src[min(max(gy - 8, 0), rows - 1) * src_step + min(gx + 8, cols - 1) + src_offset];
89 smem[y + 16][x] = src[min(gy + 8, rows - 1) * src_step + min(max(gx - 8, 0), cols - 1) + src_offset];
97 smem[y + 16][x + 16] = src[min(gy + 8, rows - 1) * src_step + min(gx + 8, cols - 1) + src_offset];
99 barrier(CLK_LOCAL_MEM_FENCE);
101 if (gx < cols && gy < rows)
105 for (int i = 0; i < kHeight; ++i)
106 for (int j = 0; j < kWidth; ++j)
107 res += smem[y + 8 - kHeight / 2 + i][x + 8 - kWidth / 2 + j] * temp1[i * k_step + j + koffset];
109 dst[gy * dst_step + gx + dst_offset] = res;