9811a739b0
Change gaussianBlur5x5 perf test epsilon
...
Set it 1 instead of 0.001, as is already done in gaussianBlur3x3. That
will allow integer destination matrices that are not exactly the same,
but very close to the expected result, to pass the test.
10 years ago
9c6da03504
SymmRowSmallVec_32f 1x5 asymm
...
NEON speedup: 2.31x
Auto-vect speedup: 2.26x
Test kernel: [-0.9432, -1.1528, 0, 1.1528, 0.9432]
10 years ago
13c0855114
SymmRowSmallVec_32f 1x5
...
NEON speedup: 2.36x
Auto-vect speedup: 2.36x
Test kernel: [0.1, 0.2408, 0.3184, 0.2408, 0.1]
10 years ago
ed0ce48179
SymmColumnVec_32f16s asymm
...
NEON speedup: 9.46x
Auto-vect speedup: 1x
Test kernel: [-0.9432, -1.1528, 0, 1.1528, 0.9432]
10 years ago
a2a131799f
SymmColumnVec_32f16s
...
NEON speedup: 8.64x
Auto-vect speedup: 1x
Test kernel: [0.1, 0.2408, 0.3184, 0.2408, 0.1]
10 years ago
37e018454d
SymmColumnSmallVec_32s16s 3x1 asymm
...
NEON speedup: 2.12x
Auto-vect speedup: 1.01x
Test kernel: [-2, 0, 2]
10 years ago
4443d6b0a1
SymmColumnSmallVec_32s16s [-1, 0, 1]
...
NEON speedup: 3.27x
Auto-vect speedup: 1.01x
10 years ago
99e782e62c
SymmColumnSmallVec_32s16s 3x1
...
NEON speedup: 1.75x
Auto-vect speedup: 1x
10 years ago
33dfeb85be
SymmColumnSmallVec_32s16s [3, 10, 3] Scharr
...
NEON speedup: 2.04x
Auto-vect speedup: 1x
10 years ago
61a7f48bf4
SymmColumnSmallVec_32s16s [1, -2, 1]
...
NEON speedup: 2.75x
Auto-vect speedup: 1.01x
10 years ago
4f906372e2
SymmColumnSmallVec_32s16s [1, 2, 1]
...
NEON speedup: 2.66x
Auto-vect speedup: 1x
10 years ago
80a0364465
SymmColumnVec_32s8u asymm
...
NEON speedup: 2.95x
Auto-vect speedup: 1x
Test kernel: [-0.9432, -1.1528, 0, 1.1528, 0.9432]
10 years ago
4f5916f12d
SymmColumnVec_32s8u
...
NEON speedup: 1.96x
Auto-vect speedup: 1x
Test kernel: [0.0708, 0.2445, 0.3694, 0.2445, 0.0708]
10 years ago
1fb966dc61
SymmRowSmallVec_8u32s 1x5 asymm
...
NEON speedup: 3.14x
Auto-vect speedup: 1.6x
Test kernel: [-5, -2, 0, 2, 5]
10 years ago
2e7b9a2c0f
SymmRowSmallVec_8u32s 1x3 asymmetric
...
NEON speedup: 1.95x
Auto-vect speedup: 1.17x
Test kernel: [-2, 0, 2]
10 years ago
969a218057
SymmRowSmallVec_8u32s [-1, 0, 1]
...
NEON speedup: 1.84x
Auto-vect speedup: 1.2x
10 years ago
c0019a42e4
SymmRowSmallVec_8u32s 1x5 general
...
NEON speedup: 3.86x
Auto-vect speedup: 1.67x
Test kernel: [0.0708, 0.2445, 0.3694, 0.2445, 0.0708]
10 years ago
cb48d7798d
SymmRowSmallVec_8u32s 1x3 general
...
NEON speedup: 2.56x
Auto-vect speedup: 1.26x
Test kernel: [1, 3, 1]
10 years ago
0ba3b06efd
SymmRowSmallVec_8u32s [1, 2, 1]
...
NEON speedup: 4.1
Auto-vect speedup: 2.25
10 years ago
79f770455b
Merge pull request #3517 from wangyan42164:ocl_denoising_2
10 years ago
fd2d800c06
Remove unnecessary local variable "size".
...
It should also be better for optimizing when compiling kernel.
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
10 years ago
009aec5164
Merge pull request #3491 from mshabunin:ios-extra-world
10 years ago
3c74c23bad
Merge pull request #3473 from TobyWanKenobi:master
10 years ago
d54b069ae1
Merge pull request #3448 from Ashod:highgui_trackbar_improvements
10 years ago
fed1b3fd59
Merge pull request #3495 from taka-no-me:fix_android_arm64
10 years ago
25378587e2
Merge pull request #3479 from mshabunin:doxygen-tutorials
10 years ago
10dc5a3759
Merge pull request #3492 from Dmitry-Me:reduceVariablesScope1
10 years ago
9582c33eab
Fix build for Android arm64-v8a
10 years ago
0f7721e915
Merge pull request #3486 from Chuanbo-Weng:repeat-perf
10 years ago
f269828160
Reduce variables scope, move declaration to first use point
10 years ago
b35f5d115f
Removed "FORMAT_XML" to generalize format
...
Removed the "FileStorage::FORMAT_XML" to generalize format of the String
model.
10 years ago
006384edaf
highgui: Support to change trackbar count in setTrackbarPos and replaced deprecated CreateToolbarEx in Windows.
10 years ago
0a4c616d43
Merge pull request #3487 from taka-no-me:ctrl_s_gtk
10 years ago
ef347f4b62
Merge pull request #3472 from Dmitry-Me:preventDivByZero
10 years ago
e0ab007b2b
Merge pull request #3475 from fhsm:master
10 years ago
ef534537b4
Merge pull request #3478 from akarsakov:rect_fix_typo
10 years ago
bada364eb3
Merge pull request #3481 from mshabunin:python-test
10 years ago
c28fea32c7
Build separate world-like iOS framework for contrib
10 years ago
893deb4040
Merge pull request #3483 from wangyan42164:ocl_orb_improve
10 years ago
1252e870f9
Merge pull request #3482 from wangyan42164:ocl_brute_match_improve
10 years ago
ecfd056111
Fixed whitespace warnings in new tutorials
10 years ago
05bc48e8f4
Make Ctrl+S open save dialog on Gtk backend
10 years ago
fac99de7ec
It turns opengl gheck is not needed for win ctrl+s
10 years ago
2df606f098
Use sincos instead of sin and cos.
...
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
10 years ago
1c9f956b88
Remove unnecesary operations and calculations in loop body.
...
Signed-off-by: Yan Wang <yan.wang@linux.intel.com>
10 years ago
2d8c89c40b
Remove unnecessary kercn limitation of 4.
...
When accessing global memory by DWORD4, memory bandwidth
can be fully utilized on Intel platform. This patch will
make more image format(e.g. 8UC4) be processed in DWORD4
by work-item. After applying this patch, 3 subcase of
./opencv_perf_core --gtest_filter=OCL_RepeatFixture_Repeat.Repeat/*
can be speedup on HD4000 graphics card with Beignet:
OCL_RepeatFixture_Repeat.Repeat/2, 64% improvement.
OCL_RepeatFixture_Repeat.Repeat/6, 50% improvement.
OCL_RepeatFixture_Repeat.Repeat/8, 56% improvement.
Signed-off-by: Chuanbo Weng <chuanbo.weng@intel.com>
10 years ago
f54b80d2c8
Re-edition of documentation
...
Re-edited the documentation again.
10 years ago
84379140ba
Python test: added options to provide local data path
10 years ago
b3bba3476d
Re-editing Documentation
...
Attempting to re-editing the documentation, to satisfy buildbot error
status.
10 years ago
270af2ca79
Changing tabs to spaces.
...
Edited previous code to change tabs into spaces.
10 years ago
orestis
Vadim Pisarevsky
Yan Wang
Andrey Kamaev
Alexander Alekhin
Dmitry-Me
TobyWanKenobi
Ashod Nakashian
Maksim Shabunin
Chuanbo Weng