- 19 Dec, 2014 13 commits
-
-
orestis authored
NEON speedup: 3.27x Auto-vect speedup: 1.01x
-
orestis authored
NEON speedup: 1.75x Auto-vect speedup: 1x
-
orestis authored
NEON speedup: 2.04x Auto-vect speedup: 1x
-
orestis authored
NEON speedup: 2.75x Auto-vect speedup: 1.01x
-
orestis authored
NEON speedup: 2.66x Auto-vect speedup: 1x
-
orestis authored
NEON speedup: 2.95x Auto-vect speedup: 1x Test kernel: [-0.9432, -1.1528, 0, 1.1528, 0.9432]
-
orestis authored
NEON speedup: 1.96x Auto-vect speedup: 1x Test kernel: [0.0708, 0.2445, 0.3694, 0.2445, 0.0708]
-
orestis authored
NEON speedup: 3.14x Auto-vect speedup: 1.6x Test kernel: [-5, -2, 0, 2, 5]
-
orestis authored
NEON speedup: 1.95x Auto-vect speedup: 1.17x Test kernel: [-2, 0, 2]
-
orestis authored
NEON speedup: 1.84x Auto-vect speedup: 1.2x
-
orestis authored
NEON speedup: 3.86x Auto-vect speedup: 1.67x Test kernel: [0.0708, 0.2445, 0.3694, 0.2445, 0.0708]
-
orestis authored
NEON speedup: 2.56x Auto-vect speedup: 1.26x Test kernel: [1, 3, 1]
-
orestis authored
NEON speedup: 4.1 Auto-vect speedup: 2.25
-
- 18 Dec, 2014 1 commit
-
-
Vadim Pisarevsky authored
-
- 16 Dec, 2014 1 commit
-
-
Yan Wang authored
It should also be better for optimizing when compiling kernel. Signed-off-by:
Yan Wang <yan.wang@linux.intel.com>
-
- 15 Dec, 2014 3 commits
-
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
- 09 Dec, 2014 4 commits
-
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
Andrey Kamaev authored
-
- 08 Dec, 2014 3 commits
-
-
Alexander Alekhin authored
-
Dmitry-Me authored
-
TobyWanKenobi authored
Removed the "FileStorage::FORMAT_XML" to generalize format of the String model.
-
- 06 Dec, 2014 6 commits
-
-
Ashod Nakashian authored
highgui: Support to change trackbar count in setTrackbarPos and replaced deprecated CreateToolbarEx in Windows.
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
Vadim Pisarevsky authored
-
- 05 Dec, 2014 6 commits
-
-
Maksim Shabunin authored
-
Alexander Alekhin authored
-
Alexander Alekhin authored
-
Maksim Shabunin authored
-
Andrey Kamaev authored
-
Andrey Kamaev authored
-
- 04 Dec, 2014 3 commits
-
-
Yan Wang authored
Signed-off-by:
Yan Wang <yan.wang@linux.intel.com>
-
Yan Wang authored
Signed-off-by:
Yan Wang <yan.wang@linux.intel.com>
-
Chuanbo Weng authored
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>
-