Namgoo Lee
2c1ce8c0e9
cuda_meanStdDev : bug fix
7 years ago
Tomoaki Teshima
f4e5d777e8
follow histogram
7 years ago
Tomoaki Teshima
6c25351049
make the asynchronous call to NPP safe
...
* Stop calling nppSetStream
7 years ago
Vladislav Vinogradov
671b59aa9d
fix windows build with CUDA
...
rename cv::cuda::internal namespace
to cv::cuda::device to prevent conflicts
with cv::internal
10 years ago
Vladislav Vinogradov
a932d8aba1
use full qualified name for all internal namespaces to prevent ambiguous symbol errors
10 years ago
Vladislav Vinogradov
cd0e95de16
refactor cudaarithm reductions:
...
* remove overloads with explicit buffer, now BufferPool is used
* added async versions for all reduce functions
10 years ago
Vladislav Vinogradov
8ed47c01b7
used new device layer for cv::cuda::norm
12 years ago
Vladislav Vinogradov
7839dbd2c4
used new device layer for cv::gpu::integral
12 years ago
Vladislav Vinogradov
1ef211b889
used new device layer for cv::gpu::reduce
12 years ago
Vladislav Vinogradov
31a7814395
used new device layer for cv::gpu::countNonZero
12 years ago
Vladislav Vinogradov
020624c481
used new device layer for cv::gpu::minMaxLoc
12 years ago
Vladislav Vinogradov
045a856c24
used new device layer for cv::gpu::minMax
12 years ago
Vladislav Vinogradov
b705e0d886
used new device layer for cv::gpu::sum
12 years ago
Vladislav Vinogradov
dcd600cc47
renamed gpuarithm -> cudaarithm
12 years ago
Vladislav Vinogradov
6d216d78d9
renamed gpulegacy -> cudalegacy
12 years ago
Vladislav Vinogradov
8282f6ebc1
renamed gpu::cudev namespace -> cuda::device
...
cudev is used for new device layer
12 years ago
Vladislav Vinogradov
e895b7455e
renamed gpu namespace -> cuda
12 years ago
Vladislav Vinogradov
8fcef225fb
switched to Input/Output Array in reductions operations
12 years ago
Vladislav Vinogradov
3eeaa9189c
Revert "Revert "Merge pull request #836 from jet47:gpu-modules""
12 years ago
Vladislav Vinogradov
58e472754a
fixed norm diff function (it uses pre-allocated buffer now)
12 years ago
Andrey Kamaev
416fb50594
Revert "Merge pull request #836 from jet47:gpu-modules"
...
This reverts commit fba72cb60d
, reversing
changes made to 02131ffb62
.
12 years ago
Vladislav Vinogradov
b4f3d08725
gpuarithm module fixes
12 years ago
Vladislav Vinogradov
71eeaa7276
gpuarithm module fixes
12 years ago
Vladislav Vinogradov
d08ebfe4d3
moved rectStdDev to gpuarithm
12 years ago
Vladislav Vinogradov
c2402053b9
removed columnSum function (it is a duplicate for reduce)
12 years ago
Vladislav Vinogradov
31c8b527c6
gpuarithm module for arithmetics operations on matrices
12 years ago
Vladislav Vinogradov
54e7c76d99
fixed compilation errors
12 years ago
Vladislav Vinogradov
b50090f850
restore cudaSafeCall
12 years ago
Vladislav Vinogradov
204a19b431
moved common gpu utility functionality to gpu_private.hpp
12 years ago
marina.kolpakova
84f45e1e03
fixed build with CUDA after latest merge
12 years ago
Vladislav Vinogradov
f0b19d4659
updated license header in whole gpu module
12 years ago
Vladislav Vinogradov
61b54149b1
added mask support to gpu norm and sum
12 years ago
Vadim Pisarevsky
efd00238e2
fixed warnings; restored fixed_size parameter in AutoBuffer
12 years ago
Vladislav Vinogradov
281d036fcf
optimizations:
...
- new reduce implementation (with kepler optimizations)
- saturate_cast via asm command
- video SIMD instructions in element operations
- float arithmetics instead of double
- new deviceSupports function
12 years ago
Vadim Pisarevsky
c197a46e7e
removed rarely used fixed_size parameter from AutoBuffer type, added optional AutoBuffer* but to cvarrToMat in order to speedup CvSeq->Mat conversion; finished conversion of convex hull and related functions to C++
12 years ago
Vladislav Vinogradov
dd8e442bda
replaced DeviceInfo().supports with deviceSupports
12 years ago
Vladislav Vinogradov
e8f9762ef3
matrix reduction
13 years ago
OpenCV Buildbot
81f826db2b
Normalize line endings and whitespace
13 years ago
OpenCV Buildbot
04384a71e4
Normalize line endings and whitespace
13 years ago
Anatoly Baksheev
55b1d7c097
added CUDA_DISABLER preprocessor commands
13 years ago
Anatoly Baksheev
70204a8e68
Removed PtrElemStep, Marked DevMem1D as deprecated, now should use PtrStepSz now
13 years ago
Anatoly Baksheev
4ce8de5174
Merged revision(s) 8455 from trunk/opencv/modules/gpu/src:
...
compilation with CUDA5.0 (#1982 , thanks to Rodrigo)
........
13 years ago
Anatoly Baksheev
543825f2f5
compilation with CUDA5.0 ( #1982 , thanks to Rodrigo)
13 years ago
Vladislav Vinogradov
eaea6782d5
added more assertion on device features to gpu functions and tests
...
moved TargerArchs and DeviceInfo to core
fixed bug in GpuMat::copy with mask (incorrect index in function tab)
13 years ago
Vladislav Vinogradov
26691e00d4
fixed gpu core tests (added additional check for device's feature support)
...
added assertion on double types for old devices
13 years ago
Vladislav Vinogradov
2d30480982
created wrappers for new NPP functions
...
removed void integral(const GpuMat& src, GpuMat& sum, GpuMat& sqsum, Stream& stream) - it fails with NPP_NOT_IMPLEMENTED error
updated docs, accuracy and performance tests
13 years ago
Vladislav Vinogradov
f8aba8608d
fixed build under CUDA 4.1
13 years ago
Vladislav Vinogradov
0f53f2993e
removed BEGIN_OPENCV_DEVICE_NAMESPACE macros
14 years ago
Vladislav Vinogradov
fcfa72081e
moved GpuMat and DevMem2D to core module, some code refactoring
14 years ago
Anatoly Baksheev
7076dfd7d6
gpu module: refactored devmem2d.hpp (atomic bomb)
14 years ago