- new reduce implementation (with kepler optimizations)
- saturate_cast via asm command
- video SIMD instructions in element operations
- float arithmetics instead of double
- new deviceSupports function

GPU: updated upsample, downsample functions, added pyrDown, pyrUp, added support of 16S filtering; put spherical warper on GPU (from opencv_stitching)

added assertion after all kernels calls

module reorganization: added folder with pure device functions, cuda_shared.hpp renamed to internal_shared.hpp

added support of BORDER_REFLECT into gpu::cornerHarris and etc, added support of border extr. int linear filters