Home | History | Annotate | Download | only in opencl
      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) 2010-2012, Multicoreware, Inc., 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.
     16 //
     17 // @Authors
     18 //    Peng Xiao, pengxiao (at) multicorewareinc.com
     19 //
     20 // Redistribution and use in source and binary forms, with or without modification,
     21 // are permitted provided that the following conditions are met:
     22 //
     23 //   * Redistribution's of source code must retain the above copyright notice,
     24 //     this list of conditions and the following disclaimer.
     25 //
     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.
     29 //
     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.
     32 //
     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 uintel 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 uinterruption) 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.
     43 //
     44 //M*/
     45 
     46 inline float2 cmulf(float2 a, float2 b)
     47 {
     48     return (float2)(mad(a.x, b.x, - a.y * b.y), mad(a.x, b.y, a.y * b.x));
     49 }
     50 
     51 inline float2 conjf(float2 a)
     52 {
     53     return (float2)(a.x, - a.y);
     54 }
     55 
     56 __kernel void mulAndScaleSpectrums(__global const uchar * src1ptr, int src1_step, int src1_offset,
     57                                    __global const uchar * src2ptr, int src2_step, int src2_offset,
     58                                    __global uchar * dstptr, int dst_step, int dst_offset,
     59                                    int dst_rows, int dst_cols, int rowsPerWI)
     60 {
     61     int x = get_global_id(0);
     62     int y0 = get_global_id(1) * rowsPerWI;
     63 
     64     if (x < dst_cols)
     65     {
     66         int src1_index = mad24(y0, src1_step, mad24(x, (int)sizeof(float2), src1_offset));
     67         int src2_index = mad24(y0, src2_step, mad24(x, (int)sizeof(float2), src2_offset));
     68         int dst_index = mad24(y0, dst_step, mad24(x, (int)sizeof(float2), dst_offset));
     69 
     70         for (int y = y0, y1 = min(dst_rows, y0 + rowsPerWI); y < y1; ++y,
     71             src1_index += src1_step, src2_index += src2_step, dst_index += dst_step)
     72         {
     73             float2 src0 = *(__global const float2 *)(src1ptr + src1_index);
     74             float2 src1 = *(__global const float2 *)(src2ptr + src2_index);
     75             __global float2 * dst = (__global float2 *)(dstptr + dst_index);
     76 
     77 #ifdef CONJ
     78             float2 v = cmulf(src0, conjf(src1));
     79 #else
     80             float2 v = cmulf(src0, src1);
     81 #endif
     82             dst[0] = v;
     83         }
     84     }
     85 }
     86