Wu Zhiwen dbe9ee0924 ocl: simplify ocl::Timer ... Use clFinish to gurantee commands completed, instead of waiting for events. Signed-off-by: Wu Zhiwen <zhiwen.wu@intel.com>		2017-10-09 13:48:38 +08:00
..
runtime	core: fix OpenCL runtime compilation with HAVE_OPENCL_STATIC	2017-09-08 12:43:33 +03:00
arithm.cl	Removed incorrect using of rootn() and powr() in ocl_pow	2014-11-06 16:23:02 +03:00
convert.cl	It is unnecessary to use fma() if no scaling.	2015-07-23 10:18:11 +08:00
copymakeborder.cl
copyset.cl
cvtclr_dx.cl	finished with NV12 support for D3D11-interop. Now, if texture is in NV12 format then it will be converted to/from BGR UMat.	2015-07-29 19:52:05 +03:00
fft.cl	fixed compile errors on ARM, as well as failures in OCL_Dft* regression tests	2015-05-06 10:00:10 +03:00
flip.cl
gemm.cl	use LOCAL_SIZE+1	2014-10-28 15:18:31 +03:00
halfconvert.cl	add OpenCL version of convertFp16 and test	2017-05-23 20:00:21 +09:00
inrange.cl
intel_gemm.cl	Merge pull request #8104 from insoow:master	2017-04-19 12:57:54 +03:00
lut.cl
meanstddev.cl
minmaxloc.cl	ocl: fix unaligned memory access	2015-07-06 13:58:17 +03:00
mixchannels.cl
mulspectrums.cl
normalize.cl
reduce2.cl
reduce.cl
repeat.cl
set_identity.cl
split_merge.cl
transpose.cl