Merge pull request #2882 from akarsakov:ocl_pyrDown_opt

modules/imgproc/src/pyramids.cpp

@@ -405,10 +405,10 @@ typedef void (*PyrFunc)(const Mat&, Mat&, int);
 
 static bool ocl_pyrDown( InputArray _src, OutputArray _dst, const Size& _dsz, int borderType)
 {
-    int type = _src.type(), depth = CV_MAT_DEPTH(type), channels = CV_MAT_CN(type);
+    int type = _src.type(), depth = CV_MAT_DEPTH(type), cn = CV_MAT_CN(type);
 
     bool doubleSupport = ocl::Device::getDefault().doubleFPConfig() > 0;
-    if (channels > 4 || (depth == CV_64F && !doubleSupport))
+    if (cn > 4 || (depth == CV_64F && !doubleSupport))
         return false;
 
     Size ssize = _src.size();
@@ -423,17 +423,20 @@ static bool ocl_pyrDown( InputArray _src, OutputArray _dst, const Size& _dsz, in
 
     int float_depth = depth == CV_64F ? CV_64F : CV_32F;
     const int local_size = 256;
+    int kercn = 1;
+    if (depth == CV_8U && float_depth == CV_32F && cn == 1 && ocl::Device::getDefault().isIntel())
+        kercn = 4;
     const char * const borderMap[] = { "BORDER_CONSTANT", "BORDER_REPLICATE", "BORDER_REFLECT", "BORDER_WRAP",
                                        "BORDER_REFLECT_101" };
     char cvt[2][50];
     String buildOptions = format(
             "-D T=%s -D FT=%s -D convertToT=%s -D convertToFT=%s%s "
-            "-D T1=%s -D cn=%d -D %s -D LOCAL_SIZE=%d",
-            ocl::typeToStr(type), ocl::typeToStr(CV_MAKETYPE(float_depth, channels)),
-            ocl::convertTypeStr(float_depth, depth, channels, cvt[0]),
-            ocl::convertTypeStr(depth, float_depth, channels, cvt[1]),
-            doubleSupport ? " -D DOUBLE_SUPPORT" : "",
-            ocl::typeToStr(depth), channels, borderMap[borderType], local_size
+            "-D T1=%s -D cn=%d -D kercn=%d -D fdepth=%d -D %s -D LOCAL_SIZE=%d",
+            ocl::typeToStr(type), ocl::typeToStr(CV_MAKETYPE(float_depth, cn)),
+            ocl::convertTypeStr(float_depth, depth, cn, cvt[0]),
+            ocl::convertTypeStr(depth, float_depth, cn, cvt[1]),
+            doubleSupport ? " -D DOUBLE_SUPPORT" : "", ocl::typeToStr(depth),
+            cn, kercn, float_depth, borderMap[borderType], local_size
     );
     ocl::Kernel k("pyrDown", ocl::imgproc::pyr_down_oclsrc, buildOptions);
     if (k.empty())
@@ -441,8 +444,8 @@ static bool ocl_pyrDown( InputArray _src, OutputArray _dst, const Size& _dsz, in
 
     k.args(ocl::KernelArg::ReadOnly(src), ocl::KernelArg::WriteOnly(dst));
 
-    size_t localThreads[2]  = { local_size, 1 };
-    size_t globalThreads[2] = { src.cols, dst.rows };
+    size_t localThreads[2]  = { local_size/kercn, 1 };
+    size_t globalThreads[2] = { (src.cols + (kercn-1))/kercn, dst.rows };
     return k.run(2, globalThreads, localThreads, false);
 }