Ilya Lavrenov
fc0869735d
used popcnt
10 years ago
Ilya Lavrenov
bc394e7516
detection of other CPU features
10 years ago
Ilya Lavrenov
63fc6ef316
convertTo from 64f
10 years ago
Ilya Lavrenov
8870ef4159
convertTo from 16u, 16s, 32s, 32f
10 years ago
Ilya Lavrenov
116fb275a8
convertTo from 8s
10 years ago
Ilya Lavrenov
19e77e4787
convertTo from 8u
10 years ago
Ilya Lavrenov
b758dbd384
convertTo AVX2
10 years ago
Ilya Lavrenov
3a78a22733
convertScaleAbs for s8, f64
10 years ago
Ilya Lavrenov
5578088983
countNonZero
10 years ago
Ilya Lavrenov
972ff1d0c4
polarToCart
10 years ago
Ilya Lavrenov
0a5c9cf145
magnitude 64f
10 years ago
Ilya Lavrenov
6ab928fb39
phase 64f
10 years ago
Ilya Lavrenov
a2a8ba17fc
compare
10 years ago
Ilya Lavrenov
8d48632ebe
avx2
10 years ago
Joe Howse
379de5708f
Fix shadowed variable warning
10 years ago
Ilya Lavrenov
68962adc54
SSE mul
10 years ago
Ilya Lavrenov
60f2f7898a
SSE4.1 addWeighted fo 16u
10 years ago
Vladislav Vinogradov
b4e7ee46c6
fix compilation without CUDA
11 years ago
Vladislav Vinogradov
00e7816c1b
add auxiliary functions to work with Input/Output arrays:
...
they allow to perform asynchronous upload/download into temporary buffer
to get valid GpuMat object
11 years ago
Ilya Lavrenov
f57136fd79
SSE2 cv::Mat::dot
11 years ago
Ilya Lavrenov
f6b3bc01e5
addWeighted
11 years ago
Ilya Lavrenov
1af7d397d4
optimization of UMat::setTo
11 years ago
Vladislav Vinogradov
f36546dbd2
improve error reporting in _InputArray methods
11 years ago
Vladislav Vinogradov
f054d6316a
add cuda::HostMem::getAllocator method
...
it allows to use cudaHostAlloc methods for cv::Mat objects
11 years ago
Vladislav Vinogradov
53862687d5
rename CudaMem -> HostMem to better reflect its purpose
11 years ago
Vladislav Vinogradov
9210d8e542
move allocMatFromBuf function to farneback.cpp:
...
* it is the only place, where it is used
* no need to make this function public
11 years ago
Vladislav Vinogradov
68e08bbecd
fix null stream initialization for multi-gpu systems
11 years ago
Vladislav Vinogradov
05d40946f3
move StackAllocator to cpp file
...
it is internal class, no need to export it
11 years ago
Vladislav Vinogradov
7ed38b97c3
fix cuda::BufferPool deinitialization
...
The deinitialization of BufferPool internal objects is controled by global
object, but it depends on other global objects, which leads to errors
caused by undefined deinitialization order of global objects.
I merge global objects initialization into single class, which performs
initialization and deinitialization in correct order.
11 years ago
Chuanbo Weng
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>
11 years ago
Dmitry-Me
4ff8a3ad92
Fix incorrect size computation
11 years ago
Alexander Karsakov
462c3c25a9
Removed incorrect using of rootn() and powr() in ocl_pow
11 years ago
Alexander Alekhin
4eb16122c0
ocl: change processing of OpenCL failures
...
disable "unwanted" messages
11 years ago
Alexander Alekhin
1c9f590f0d
IPPICV: disable NormDiff_L1_16s_C1R for IPP/ICV 8.2/8.2.1
11 years ago
Ilya Lavrenov
5ca25ab8f0
cv::pow (integer power)
11 years ago
Ilya Lavrenov
ccdc71286c
cv::polarToCart
11 years ago
Ilya Lavrenov
d5f006eee5
cv::magnitude; cv::corner**
11 years ago
Ilya Lavrenov
fb97273b3c
cv::phase; cv::cartToPolar
11 years ago
ElenaGvozdeva
d88fdd0378
use LOCAL_SIZE+1
11 years ago
ElenaGvozdeva
65b8a1cb37
Some small fixes
11 years ago
Elena Gvozdeva
c5a2879ce0
use vectors
11 years ago
Elena Gvozdeva
2d89df1804
use local memory
11 years ago
Elena Gvozdeva
d78bc3c321
naive implementation
11 years ago
vbystricky
8466911ad0
Move _dst.create() to the begining of scaleAdd function
11 years ago
Alexander Karsakov
237cb93143
Added extra checks to ocl::Image2D
11 years ago
Alexander Alekhin
579a7fff6d
ocl: restore clFinish() in unmap() for AMD devices
...
This reverts commit 7d91b8efcd
.
11 years ago
Alexander Karsakov
3a263c6326
Added tests for Image2D
11 years ago
vbystricky
a8aa6381d9
Optimize OpenCL version of conversScaleAbs function
11 years ago
ElenaGvozdeva
070e5ec042
Changed predictOptimalVectorWidth function, now it is possible to choose vector size.
11 years ago
Vadim Pisarevsky
d2b9dc5530
quickly corrected the previous refactoring of features2d: moved from set(SOME_PROP, val) to setSomeProp(val)
11 years ago