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 // Shengen Yan,yanshengen@gmail.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.
46 #if defined (DOUBLE_SUPPORT)
48 #pragma OPENCL EXTENSION cl_khr_fp64:enable
49 #elif defined (cl_amd_fp64)
50 #pragma OPENCL EXTENSION cl_amd_fp64:enable
55 #define FUNC(a, b) b += a;
57 #define FUNC(a, b) b += a >= (dstT)(0) ? a : -a;
59 #define FUNC(a, b) b += a * a;
61 #error No sum function
64 /**************************************Array buffer SUM**************************************/
66 __kernel void arithm_op_sum(int cols,int invalid_cols,int offset,int elemnum,int groupnum,
67 __global srcT *src, __global dstT *dst)
69 int lid = get_local_id(0);
70 int gid = get_group_id(0);
71 int id = get_global_id(0);
72 int idx = offset + id + (id / cols) * invalid_cols;
74 __local dstT localmem_sum[128];
75 dstT sum = (dstT)(0), temp;
77 for (int grainSize = groupnum << 8; id < elemnum; id += grainSize)
79 idx = offset + id + (id / cols) * invalid_cols;
80 temp = convertToDstT(src[idx]);
85 localmem_sum[lid - 128] = sum;
86 barrier(CLK_LOCAL_MEM_FENCE);
89 localmem_sum[lid] = sum + localmem_sum[lid];
90 barrier(CLK_LOCAL_MEM_FENCE);
92 for (int lsize = 64; lsize > 0; lsize >>= 1)
96 int lid2 = lsize + lid;
97 localmem_sum[lid] = localmem_sum[lid] + localmem_sum[lid2];
99 barrier(CLK_LOCAL_MEM_FENCE);
103 dst[gid] = localmem_sum[0];