ocl kernel performance optimization for box filter
authorLi Peng <peng.li@intel.com>
Fri, 14 Oct 2016 07:13:10 +0000 (15:13 +0800)
committerLi Peng <peng.li@intel.com>
Wed, 26 Oct 2016 03:56:11 +0000 (11:56 +0800)
commit3607da9f6b769d1e8c26c9b118747410461526de
treef803085c03792672834dc25350964e4691601854
parent18327aed30a6959607d8732462f54f080b0a5c39
ocl kernel performance optimization for box filter

The optimization is for CV_8UC1 format and 3x3 box filter,
it is 15%~87% faster than current ocl kernel with below perf test

./modules/ts/misc/run.py -t imgproc --gtest_filter=OCL_BlurFixture*

Also add test cases for this ocl kernel.

Signed-off-by: Li Peng <peng.li@intel.com>
modules/imgproc/src/opencl/boxFilter3x3.cl [new file with mode: 0644]
modules/imgproc/src/smooth.cpp
modules/imgproc/test/ocl/test_boxfilter.cpp