1
2
3
4
5
6
7
8
9
10
11
12
13
14
15
16
17
18
19
20
21
22
23
24
25
26
27
28
29
30
31
32
33
34
35
36
37
38
39
40
41
42
43
44
45
46
47
48
49
50
51
52
53
54
55
56
57
58
59
60
61
62
63
64
65
66
67
68
69
70
71
72
73
74
75
76
77
78
79
80
81
82
83
84
85
86
87
88
89
90
91
92
93
94
95
96
97
98
99
100
101
102
103
104
105
106
107
108
109
110
111
112
113
114
115
116
117
118
119
120
121
122
123
124
125
126
127
128
129
130
131
132
133
134
135
136
137
138
139
140
141
142
143
144
145
146
147
148
149
150
151
152
153
154
155
156
157
158
159
160
161
162
163
164
165
166
167
168
169
170
171
172
173
174
175
176
177
/*M///////////////////////////////////////////////////////////////////////////////////////
//
// IMPORTANT: READ BEFORE DOWNLOADING, COPYING, INSTALLING OR USING.
//
// By downloading, copying, installing or using the software you agree to this license.
// If you do not agree to this license, do not download, install,
// copy or use the software.
//
//
// License Agreement
// For Open Source Computer Vision Library
//
// Copyright (C) 2010-2012, Institute Of Software Chinese Academy Of Science, all rights reserved.
// Copyright (C) 2010-2012, Advanced Micro Devices, Inc., all rights reserved.
// Third party copyrights are property of their respective owners.
//
// @Authors
// Jia Haipeng, jiahaipeng95@gmail.com
//
// Redistribution and use in source and binary forms, with or without modification,
// are permitted provided that the following conditions are met:
//
// * Redistribution's of source code must retain the above copyright notice,
// this list of conditions and the following disclaimer.
//
// * Redistribution's in binary form must reproduce the above copyright notice,
// this list of conditions and the following disclaimer in the documentation
// and/or other oclMaterials provided with the distribution.
//
// * The name of the copyright holders may not be used to endorse or promote products
// derived from this software without specific prior written permission.
//
// This software is provided by the copyright holders and contributors as is and
// any express or implied warranties, including, but not limited to, the implied
// warranties of merchantability and fitness for a particular purpose are disclaimed.
// In no event shall the Intel Corporation or contributors be liable for any direct,
// indirect, incidental, special, exemplary, or consequential damages
// (including, but not limited to, procurement of substitute goods or services;
// loss of use, data, or profits; or business interruption) however caused
// and on any theory of liability, whether in contract, strict liability,
// or tort (including negligence or otherwise) arising in any way out of
// the use of this softwareif advised of the possibility of such damage.
//
//M*/
#if defined (DOUBLE_SUPPORT)
#pragma OPENCL EXTENSION cl_khr_fp64:enable
#endif
//////////////////////////////////////////////////////////////////////////////////////////////////////
/////////////////////////////////////////////magnitudeSqr//////////////////////////////////////////////
///////////////////////////////////////////////////////////////////////////////////////////////////////
__kernel void magnitudeSqr_C1_D5 (__global float *src1,int src1_step,int src1_offset,
__global float *src2, int src2_step,int src2_offset,
__global float *dst, int dst_step,int dst_offset,
int rows, int cols,int dst_step1)
{
int x = get_global_id(0);
int y = get_global_id(1);
if (x < cols && y < rows)
{
x = x << 2;
#define dst_align ((dst_offset >> 2) & 3)
int src1_index = mad24(y, src1_step, (x << 2) + src1_offset - (dst_align << 2));
int src2_index = mad24(y, src2_step, (x << 2) + src2_offset - (dst_align << 2));
int dst_start = mad24(y, dst_step, dst_offset);
int dst_end = mad24(y, dst_step, dst_offset + dst_step1);
int dst_index = mad24(y, dst_step, dst_offset + (x << 2) -(dst_align << 2));
int src1_index_fix = src1_index < 0 ? 0 : src1_index;
int src2_index_fix = src2_index < 0 ? 0 : src2_index;
float4 src1_data = vload4(0, (__global float *)((__global char *)src1 + src1_index_fix));
float4 src2_data = vload4(0, (__global float *)((__global char *)src2 + src2_index_fix));
if(src1_index < 0)
{
float4 tmp;
tmp.xyzw = (src1_index == -2) ? src1_data.zwxy:src1_data.yzwx;
src1_data.xyzw = (src1_index == -1) ? src1_data.wxyz:tmp.xyzw;
}
if(src2_index < 0)
{
float4 tmp;
tmp.xyzw = (src2_index == -2) ? src2_data.zwxy:src2_data.yzwx;
src2_data.xyzw = (src2_index == -1) ? src2_data.wxyz:tmp.xyzw;
}
float4 dst_data = *((__global float4 *)((__global char *)dst + dst_index));
float4 tmp_data ;
tmp_data.x = src1_data.x * src1_data.x + src2_data.x * src2_data.x;
tmp_data.y = src1_data.y * src1_data.y + src2_data.y * src2_data.y;
tmp_data.z = src1_data.z * src1_data.z + src2_data.z * src2_data.z;
tmp_data.w = src1_data.w * src1_data.w + src2_data.w * src2_data.w;
dst_data.x = ((dst_index + 0 >= dst_start) && (dst_index + 0 < dst_end)) ? tmp_data.x : dst_data.x;
dst_data.y = ((dst_index + 4 >= dst_start) && (dst_index + 4 < dst_end)) ? tmp_data.y : dst_data.y;
dst_data.z = ((dst_index + 8 >= dst_start) && (dst_index + 8 < dst_end)) ? tmp_data.z : dst_data.z;
dst_data.w = ((dst_index + 12 >= dst_start) && (dst_index + 12 < dst_end)) ? tmp_data.w : dst_data.w;
*((__global float4 *)((__global char *)dst + dst_index)) = dst_data;
}
}
#if defined (DOUBLE_SUPPORT)
__kernel void magnitudeSqr_C2_D5 (__global float *src1,int src1_step,int src1_offset,
__global float *dst, int dst_step,int dst_offset,
int rows, int cols,int dst_step1)
{
int x = get_global_id(0);
int y = get_global_id(1);
if (x < cols && y < rows)
{
x = x << 2;
#define dst_align ((dst_offset >> 2) & 3)
int src1_index = mad24(y, src1_step, (x << 3) + src1_offset - (dst_align << 3));
int dst_start = mad24(y, dst_step, dst_offset);
int dst_end = mad24(y, dst_step, dst_offset + dst_step1);
int dst_index = mad24(y, dst_step, dst_offset + (x << 2) -(dst_align << 2));
int src1_index_fix = src1_index < 0 ? 0 : src1_index;
float8 src1_data = vload8(0, (__global float *)((__global char *)src1 + src1_index_fix));
if(src1_index==-6)
src1_data.s01234567 = src1_data.s67012345;
if(src1_index==-4)
src1_data.s01234567 = src1_data.s45670123;
if(src1_index== -2)
src1_data.s01234567 = src1_data.s23456701;
float4 dst_data = *((__global float4 *)((__global char *)dst + dst_index));
float4 tmp_data ;
tmp_data.x = src1_data.s0 * src1_data.s0 + src1_data.s1 * src1_data.s1;
tmp_data.y = src1_data.s2 * src1_data.s2 + src1_data.s3 * src1_data.s3;
tmp_data.z = src1_data.s4 * src1_data.s4 + src1_data.s5 * src1_data.s5;
tmp_data.w = src1_data.s6 * src1_data.s6 + src1_data.s7 * src1_data.s7;
dst_data.x = ((dst_index + 0 >= dst_start) && (dst_index + 0 < dst_end)) ? tmp_data.x : dst_data.x;
dst_data.y = ((dst_index + 4 >= dst_start) && (dst_index + 4 < dst_end)) ? tmp_data.y : dst_data.y;
dst_data.z = ((dst_index + 8 >= dst_start) && (dst_index + 8 < dst_end)) ? tmp_data.z : dst_data.z;
dst_data.w = ((dst_index + 12 >= dst_start) && (dst_index + 12 < dst_end)) ? tmp_data.w : dst_data.w;
*((__global float4 *)((__global char *)dst + dst_index)) = dst_data;
}
}
#endif