refactored and extended arithm operations add/sub/mul/div/absdiff

modules/ocl/include/opencv2/ocl/ocl.hpp

@@ -409,40 +409,37 @@ namespace cv
         CV_EXPORTS void split(const oclMat &src, vector<oclMat> &dst);
 
         ////////////////////////////// Arithmetics ///////////////////////////////////
+
         //#if defined DOUBLE_SUPPORT
         //typedef double F;
         //#else
         //typedef float F;
         //#endif
+
         //	CV_EXPORTS void addWeighted(const oclMat& a,F  alpha, const oclMat& b,F beta,F gama, oclMat& c);
         CV_EXPORTS void addWeighted(const oclMat &a, double  alpha, const oclMat &b, double beta, double gama, oclMat &c);
+
         //! adds one matrix to another (c = a + b)
         // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
-        CV_EXPORTS void add(const oclMat &a, const oclMat &b, oclMat &c);
-        //! adds one matrix to another (c = a + b)
-        // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
-        CV_EXPORTS void add(const oclMat &a, const oclMat &b, oclMat &c, const oclMat &mask);
+        CV_EXPORTS void add(const oclMat &a, const oclMat &b, oclMat &c, const oclMat &mask = oclMat());
         //! adds scalar to a matrix (c = a + s)
         // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
         CV_EXPORTS void add(const oclMat &a, const Scalar &sc, oclMat &c, const oclMat &mask = oclMat());
+
         //! subtracts one matrix from another (c = a - b)
         // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
-        CV_EXPORTS void subtract(const oclMat &a, const oclMat &b, oclMat &c);
-        //! subtracts one matrix from another (c = a - b)
-        // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
-        CV_EXPORTS void subtract(const oclMat &a, const oclMat &b, oclMat &c, const oclMat &mask);
+        CV_EXPORTS void subtract(const oclMat &a, const oclMat &b, oclMat &c, const oclMat &mask = oclMat());
         //! subtracts scalar from a matrix (c = a - s)
         // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
         CV_EXPORTS void subtract(const oclMat &a, const Scalar &sc, oclMat &c, const oclMat &mask = oclMat());
-        //! subtracts scalar from a matrix (c = a - s)
-        // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
-        CV_EXPORTS void subtract(const Scalar &sc, const oclMat &a, oclMat &c, const oclMat &mask = oclMat());
+
         //! computes element-wise product of the two arrays (c = a * b)
         // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
         CV_EXPORTS void multiply(const oclMat &a, const oclMat &b, oclMat &c, double scale = 1);
         //! multiplies matrix to a number (dst = scalar * src)
         // supports CV_32FC1 only
         CV_EXPORTS void multiply(double scalar, const oclMat &src, oclMat &dst);
+
         //! computes element-wise quotient of the two arrays (c = a / b)
         // supports all types except CV_8SC1,CV_8SC2,CV8SC3 and CV_8SC4
         CV_EXPORTS void divide(const oclMat &a, const oclMat &b, oclMat &c, double scale = 1);

modules/ocl/src/opencl/arithm_add_mask.cl

+/*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 software, even if advised of the possibility of such damage.
+//
+//M*/
+
+#if defined (DOUBLE_SUPPORT)
+#ifdef cl_khr_fp64
+#pragma OPENCL EXTENSION cl_khr_fp64:enable
+#elif defined (cl_amd_fp64)
+#pragma OPENCL EXTENSION cl_amd_fp64:enable
+#endif
+#endif
+
+//////////////////////////////////////////////////////////////////////////////////
+///////////////////////////////// add with mask //////////////////////////////////
+//////////////////////////////////////////////////////////////////////////////////
+
+__kernel void arithm_binary_op_mat_mask(__global T * src1, int src1_step, int src1_offset,
+                              __global T * src2, int src2_step, int src2_offset,
+                              __global uchar * mask, int mask_step, int mask_offset,
+                              __global T * dst, int dst_step, int dst_offset,
+                              int cols, int rows)
+{
+    int x = get_global_id(0);
+    int y = get_global_id(1);
+
+    if (x < cols && y < rows)
+    {
+        int mask_index = mad24(y, mask_step, x + mask_offset);
+        if (mask[mask_index])
+        {
+            int src1_index = mad24(y, src1_step, x + src1_offset);
+            int src2_index = mad24(y, src2_step, x + src2_offset);
+            int dst_index  = mad24(y, dst_step, dst_offset + x);
+
+            dst[dst_index] = convertToT(convertToWT(src1[src1_index]) Operation convertToWT(src2[src2_index]));
+        }
+    }
+}