krodyush
65d64af2a8
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.
2014-03-19 19:31:14 +04:00
Andrey Pavlenko
a2dec6c34e
Merge pull request #2493 from ilya-lavrenov:tapi_fnlm
2014-03-19 12:56:11 +04:00
Roman Donchenko
b70332d806
Merge pull request #1986 from GregoryMorse:patch-3
2014-03-18 16:18:33 +04:00
Andrey Pavlenko
6e44f05e6f
Merge pull request #2464 from KonstantinMatskevich:ocl_stereobm_experiment
2014-03-18 15:53:09 +04:00
Ilya Lavrenov
6fe71bd27c
added 4 channels support to fnlm
2014-03-18 14:29:02 +04:00
Roman Donchenko
ae2b0b0098
Merge pull request #2486 from SpecLad:merge-2.4
2014-03-18 13:55:57 +04:00
Roman Donchenko
40a740ff88
Merge remote-tracking branch 'origin/2.4' into merge-2.4
...
Conflicts:
modules/imgproc/src/opencl/precornerdetect.cl
modules/nonfree/perf/perf_main.cpp
modules/nonfree/perf/perf_surf.ocl.cpp
modules/ocl/src/arithm.cpp
modules/ocl/src/gftt.cpp
modules/ocl/src/opencl/arithm_bitwise.cl
modules/ocl/src/opencl/arithm_bitwise_binary_scalar_mask.cl
modules/ocl/src/opencl/arithm_minMax.cl
modules/ocl/src/opencl/arithm_nonzero.cl
modules/ocl/src/opencl/arithm_sum.cl
modules/ocl/test/test_arithm.cpp
modules/viz/src/precomp.hpp
modules/viz/src/vizcore.cpp
modules/viz/src/vtk/vtkCloudMatSink.h
modules/viz/src/vtk/vtkXYZReader.cpp
modules/viz/src/vtk/vtkXYZReader.h
modules/viz/test/test_precomp.hpp
2014-03-17 14:14:07 +04:00
Andrey Pavlenko
dc28451b8a
Merge pull request #2479 from alalek:ocl_compare_scalar
2014-03-17 14:04:22 +04:00
Andrey Pavlenko
2a1d5c6d43
Merge pull request #2428 from alalek:ocl_copyMakeBorder_3channels
2014-03-17 13:10:34 +04:00
Alexander Alekhin
af062b7c42
ocl: compare: remove useless perf tests
2014-03-17 12:33:12 +04:00
Roman Donchenko
882971151d
Merge pull request #2485 from Nerei:viz_correct_viewer_pose
2014-03-17 11:59:14 +04:00
Roman Donchenko
136e5eb804
Merge pull request #2484 from berak:mat_doc_24
2014-03-17 11:57:10 +04:00
Konstantin Matskevich
1a43ed9893
finalizing
2014-03-17 10:42:19 +04:00
Anatoly Baksheev
24d8cbf940
Viz::setViewerPose() - changed up-vector to down (common for Computer Vision & Odometry)
2014-03-16 20:07:05 +04:00
berak
80708008a4
missing () on Mat::type()
2014-03-16 14:04:05 +01:00
Alexander Alekhin
7ce2ca2e0c
ocl: workaround for Pow accuracy test failure
2014-03-14 19:51:19 +04:00
Alexander Alekhin
9cafd50160
ocl: fixes
2014-03-14 19:51:19 +04:00
Alexander Alekhin
755ca4b7cf
ocl: compare with scalar
2014-03-14 19:51:19 +04:00
Andrey Pavlenko
dd6cf15a39
Merge pull request #2481 from akarsakov:fix_hog_intel
2014-03-14 19:17:03 +04:00
Andrey Pavlenko
bcb938efbb
Merge pull request #2483 from ilya-lavrenov:tapi_3_vs_4
2014-03-14 19:14:35 +04:00
Andrey Pavlenko
c72a0a1295
Merge pull request #2482 from ilya-lavrenov:tapi_fix
2014-03-14 19:08:07 +04:00
Andrey Pavlenko
6b434befc9
Merge pull request #2480 from vpisarev:ocl_orb
2014-03-14 19:04:19 +04:00
Konstantin Matskevich
af1084eb58
speedUp
2014-03-14 18:00:13 +04:00
Konstantin Matskevich
91e4334227
temp
2014-03-14 18:00:12 +04:00
Konstantin Matskevich
18a59b48ba
fixes
2014-03-14 18:00:12 +04:00
Konstantin Matskevich
ddc235172e
new approach
2014-03-14 18:00:11 +04:00
Konstantin Matskevich
a5d989f346
new attempt
2014-03-14 18:00:11 +04:00
Konstantin Matskevich
799d7e7a50
bad experiment =(
2014-03-14 18:00:10 +04:00
Konstantin Matskevich
0904f10ab5
optimizations
2014-03-14 18:00:10 +04:00
Konstantin Matskevich
bfc843a5f5
added optimization
2014-03-14 18:00:09 +04:00
Konstantin Matskevich
b5f717b6b3
stereoBM
2014-03-14 18:00:09 +04:00
Ilya Lavrenov
6f12f1b3b5
added 3 vs 4 channels performance tests
2014-03-14 17:30:14 +04:00
Ilya Lavrenov
6be7869ae8
fix for unsupported doubles
2014-03-14 16:54:52 +04:00
Roman Donchenko
4a4151ec97
Merge pull request #2474 from akarsakov:fix_getpolicy
2014-03-14 15:17:45 +04:00
Alexander Karsakov
4698d62125
Removed workaround for Intel platform.
2014-03-14 14:18:52 +04:00
Alexander Karsakov
8910508b83
Fixed getPolicy() method to make it thread-safe.
2014-03-14 13:50:33 +04:00
Vadim Pisarevsky
4fafab3786
fixed extra whitespace
2014-03-13 23:18:41 +04:00
Vadim Pisarevsky
42e604abea
fixed bug in FAST
2014-03-13 23:17:28 +04:00
Vadim Pisarevsky
3e854fa6e5
finished OpenCL port of ORB
2014-03-13 22:56:53 +04:00
Ilya Lavrenov
61c347fb76
typos
2014-03-13 22:56:46 +04:00
Ilya Lavrenov
357a856cf6
nonfree perf tests
2014-03-13 22:35:08 +04:00
Ilya Lavrenov
6f76e7b42d
improved performance of bitwise ops
2014-03-13 19:42:13 +04:00
Andrey Pavlenko
0ce8f1d5dd
Merge pull request #2477 from alalek:ocl_cleanup_workarounds
2014-03-13 18:55:28 +04:00
Andrey Pavlenko
c5bf1c108c
Merge pull request #2470 from ilya-lavrenov:tapi_reduction
2014-03-13 18:42:01 +04:00
Andrey Pavlenko
4233539617
Merge pull request #2469 from alalek:ocl_pyrUp_pyrDown_3channels
2014-03-13 18:37:05 +04:00
Ilya Lavrenov
adc15c2bba
improved performance of cv::ocl::sum
2014-03-13 17:33:18 +04:00
Andrey Pavlenko
a6c40abfb2
Merge pull request #2466 from ilya-lavrenov:tapi_transpose_3cn
2014-03-13 16:56:01 +04:00
Andrey Pavlenko
0764a23eb2
Merge pull request #2459 from ilya-lavrenov:tapi_experiments
2014-03-13 16:49:57 +04:00
Andrey Pavlenko
6b6cfa893d
Merge pull request #2382 from ilya-lavrenov:tapi_nlmeans
2014-03-13 16:48:38 +04:00
Alexander Alekhin
48196ad10b
ocl: cleanup workarounds
2014-03-13 15:46:38 +04:00
