ocl_calcOpticalFlowPyrLK optimizations

1. decrease branch number in CL code by replacing them into weights
2. decrease local mem pressure in reduce operation by using private variables
3. decrease image sampler pressure by caching data into local memory
4. remove unnecessary sync point on the HOST side.

modules/video/src/lkpyramid.cpp

@@ -989,7 +989,7 @@ namespace cv
             idxArg = kernel.set(idxArg, (int)winSize.height); // int c_winSize_y
             idxArg = kernel.set(idxArg, (int)iters); // int c_iters
             idxArg = kernel.set(idxArg, (char)calcErr); //char calcErr
-            return kernel.run(2, globalThreads, localThreads, true);
+            return kernel.run(2, globalThreads, localThreads, false);
         }
     private:
         inline static bool isDeviceCPU()