Mateusz Tabaka
270051ebce
[CPU] Add RDFT and IRDFT operators ( #12099 )
...
* [CPU] Add RDFT and IRDFT operators
Tickets: 79178 and 79192
Co-authored-by: Mateusz Bencer <mateusz.bencer@intel.com>
2022-07-25 19:23:27 +02:00
Irina Efode
862aebce71
Update summarize.py ( #12175 )
2022-07-25 15:34:28 +03:00
Vladimir Paramuzov
87b73b4508
[GPU] Get rid of direct layout::size field usages ( #12172 )
...
* [GPU] Get rid of direct layout::size field usages to simplify further replacement
* [GPU] Enabled -Wall and resolved compiler complaints
2022-07-25 16:31:01 +04:00
Ilya Lavrenov
36df7f51ae
Fixes for cases when TBB_DIR env var is set ( #12266 )
...
* Fixes for cases when TBB_DIR env var is set
* Don't use make in build_samples.sh script
2022-07-24 15:13:00 +04:00
Ilya Churaev
cb6ca7bb89
Disable loading of v7 reader for new IR versions ( #12252 )
...
* Disable loading of v7 reader for new IR versions
* Try to fix CI
* Fixed PDPD frontend
* Fixed error message creation
2022-07-22 23:34:04 +04:00
Ilya Lavrenov
926a87e7eb
Install user provided TBB as well ( #12260 )
2022-07-22 22:36:58 +04:00
Ilya Churaev
811a483acb
Fixed newAPI for case if core was removed ( #12207 )
...
* Fixed newAPI for case if core was removed
* Fixed code style
* Fixed typo
* Use new API by default
* Create core with template plugin
* Added doxygen comment
2022-07-22 16:46:08 +03:00
Roman Kazantsev
23e513d679
[MO] Fix Mul fusion with dynamic dimension ( #12253 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-22 14:01:42 +04:00
Xiping Yan
9519461453
Move GNU build flag to "cmake/developer_package/compile_flags/sdl.cmake" ( #12143 )
...
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
2022-07-22 10:13:13 +04:00
Ilya Lavrenov
564b25a71f
Fixed WIndows backslash paths ( #12250 )
2022-07-22 01:34:46 +03:00
Konstantin Beluchenko
ed65d199bb
[GPU] ROIAlign v9 support ( #11899 )
...
* ROIAlign v9 support
* Code changes after review1
* Code changes after review2
* fix of single layer test for Windows
* Since PR #12043 we don't need strong include order of primitive_base.hpp and
impls/implementation map.hpp anymore
* Code changes after review3
* Code changes after review4
2022-07-21 11:52:32 +02:00
Roman Kazantsev
598975fb63
[TF FE] Handle optional attributes for Convolutional operations ( #12230 )
...
* [TF FE] Handle optional attributes for Convolutional operations
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
* Apply code-style rules
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-21 09:30:13 +02:00
Marcin Kusmierski
3eafa653f3
[GNA] Fix accuracy degradation in compact mode ( #12150 )
2022-07-20 12:53:45 +02:00
Nadezhda Ageeva
fdae2eb8e3
[GNA] Fixed convolutions with shared transpose and un-fuse-able activations after Convolution filter (Renew PR11373) ( #12152 )
...
* Commits from PR11373:
Fixed handling of transpose after convolution
[GNA] Fixed calculation of dimensions for ConvolutionFilter and PWL primitives
[GNA] Fixed coverity error and failed tests
* Apply comments
* Update src/plugins/intel_gna/gna_graph_compiler.cpp
Co-authored-by: Marcin Kusmierski <marcin.kusmierski@intel.com>
* Update src/plugins/intel_gna/gna_graph_compiler.cpp
Co-authored-by: Marcin Kusmierski <marcin.kusmierski@intel.com>
* Rollback names
* Separate test data
* Move coverity issue to separate request
Co-authored-by: Elizaveta Lobanova <elizaveta.lobanova@intel.com>
Co-authored-by: Marcin Kusmierski <marcin.kusmierski@intel.com>
2022-07-20 14:50:07 +04:00
Egor Duplenskii
3cec746a64
[CPU] Explicitly enable DNNL_VERBOSE only in case of CPU_DEBUG_CAPS ( #12108 )
2022-07-20 14:08:24 +04:00
Chen Xu
ee9127e10e
[CPU] Fixed heap sort bug regarding heapifying ( #12221 )
2022-07-20 13:14:08 +04:00
Roman Kazantsev
c332a162ff
[MO] Fix TopK partial shape inference with dynamic K ( #12212 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-07-20 09:16:24 +02:00
River Li
9a3c969cb7
Restore FEM to be static instance ( #12219 )
...
* Restore FEM to be static instance
* Restore frontend manager in ie_read_network.cpp
2022-07-20 08:09:31 +03:00
Ilya Lavrenov
00fe7be00f
Use system pugixml where it's possible ( #12218 )
2022-07-20 08:53:17 +04:00
Chenhu Wang
43b3fff708
[DOC][CPU] Denormals optimization doc ( #12127 )
2022-07-20 04:35:45 +03:00
Jan Iwaszkiewicz
06019c442f
[PyOV][DOCS] Python API contribution and developer guide ( #12145 )
...
Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
2022-07-19 16:25:58 +02:00
Irina Efode
5ea8186888
[IE TESTS][CONFORMANCE] Fix OpImplCheck Precision ( #12148 )
2022-07-19 12:35:12 +04:00
Artur Kulikowski
6a795936b2
ONNX: Pass name to the InputEdge ( #12177 )
2022-07-19 08:52:54 +02:00
Xiping Yan
6966af3ced
Xp/benchmark app ocl ( #12112 )
...
* Add some tip description about enable OpenCL for benchmark_app.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Export doesn't work, we need to add -Dopencl_root_hints=[PATH]/OpenCL-CLHPP/include to cmake command.
Signed-off-by: xipingya <xiping.yan@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-07-19 14:43:59 +08:00
Ilya Lavrenov
3c0b17f108
Debian packages: base version ( #11387 )
2022-07-19 09:07:26 +03:00
Ilya Lavrenov
6307fdc77b
Fixes for system libraries pugixml, tbb ( #12206 )
...
* Fixes for system libraries pugixml, tbb
* Added more dependencies for core
2022-07-19 08:52:06 +04:00
Evgenya Stepyreva
1535be3c16
TI repetative shape inference ( #12178 )
2022-07-18 18:47:15 +03:00
Jade Cho
7b03520395
Check memory allocation size of network graph ( #11911 )
...
+ Add exception handling for out of resource
2022-07-18 20:39:21 +09:00
Sungeun Kim
3bd475ad26
[GPU] integrate persistent caching for onednn ( #12094 )
...
* integrate persistant caching for onednn
* add api to save/load binary file.
2022-07-18 20:13:46 +09:00
Katarzyna Mitrus
4e379d63eb
Update opset.md with opset9 ( #12169 )
2022-07-18 11:01:45 +02:00
Tomasz Dołbniak
cc3ec0c50a
Update of naming of the last operators in the graph ( #12139 )
2022-07-18 07:34:14 +02:00
Taylor Yeonbok Lee
fae113f7f5
[GPU] optimize permute_ref ( #12159 )
...
* change memory access pattern of fsv layout for permute
* Fix permute_ref to process F first only when (bf...) => (b...f)
* Refactor
Co-authored-by: si-eun-kim <sieun.kim@intel.com>
2022-07-18 10:41:45 +09:00
Ilya Lavrenov
6514c213c3
Ubuntu 22.04 support ( #11472 )
...
* Ubuntu 22.04 support
* Try to fix setuptools
* Try to fix arm
* Try to add more packages
* Test 2
* test 3
* Turn dependnecies download off
* Fix
* Fix
* Fix
* Fix
* Fix
* test
* Fix
* restore eveything
* Try to restore
* Restore install_openvino_dependencies.sh
* clean-up raspbian
* New if conditions
* Removed excess dependencies
* COsmetic chnages
* Removed autools
* Removed libgkt-2
* Added HDLDL libs
* Test
* Removed some dependnecies
* Better fixes
* Removed some dependencies
* Fixed compilation
* Removed all extra
2022-07-17 11:10:02 +04:00
Yuan Xu
09f2b5062b
Update pypi.org pages ( #12170 )
...
* fix references
* update links
* update the wording to be more clear
* add the error message about Visual studio back
* update links to static html links of 2022.2
2022-07-15 16:27:52 +00:00
Kelvin Choi
68bda59c20
[GPU] Add reorder from i32 to f32 for max-pooling/conv/fc which doesn't support i32 ( #12137 )
2022-07-15 23:24:37 +09:00
Przemyslaw Wysocki
603b56ec7f
[MO] Fix output shape bug in GatherNDDecomposition ( #12110 )
2022-07-15 15:37:57 +02:00
Mateusz Bencer
e8310f7e0b
Fix IRDFT for case when axes are in reversed order ( #12155 )
2022-07-15 13:22:52 +03:00
Eddy Kim
dc7efafd7c
Revert "[GPU] Pass activation unit tests on DG2 ( #11969 )" ( #12167 )
...
This reverts commit 3334e8933c
2022-07-15 12:58:09 +03:00
Bonhun Koo
a230eebcc1
[POT] optimizer - update usage of IndexSampler ( #12146 )
2022-07-15 09:31:29 +09:00
Tetiana Gubanova
35a31a329d
[GPU] Implement NMS-9 operation ( #11890 )
...
* Fix GPU NonMaxSuppression implementation
* Introduce Nms9 single layer tests
* Adapt internal NMS and GPU implementation for NMS9 implementation
* Adapt CPU implementation in GPU for NMS9
* Add blocked layouts support to NMS
* Add unit tests for blocked formats for NMS
* Fix boxes groups size for the small shapes
* Use ocl implementation for blocked layout input
* Fix templates typedefs to pass win build
* Fix second output to set data in correct format
2022-07-14 22:56:15 +09:00
sheng.gui@intel.com
b67aeb881c
[ONNX] Add operator com.microsoft.Fusedgemm support into frontend/onnx ( #11878 )
2022-07-14 14:35:49 +02:00
zihan wu
2f1ad1a54f
polish onednn cc readme ( #12114 )
2022-07-14 14:25:16 +04:00
Luo Cheng
23b1b76457
[CPU] revert pr 11990 and enable brgconv avx512 on SPR by default ( #12105 )
2022-07-14 14:11:21 +04:00
RICKIE777
64c0af3568
[PYTHON][BENCHMARK_APP] Add BGR covert to Gray function ( #12118 )
...
* Fix the JIRA 80700 issue. Add BGR covert to Gray function
* Support NCHW and NHWC
Co-authored-by: Shen, Wanglei <wanglei.shen@intel.com>
2022-07-14 11:10:02 +02:00
Andrew Kwangwoong Park
dc374ca1bf
Enable tensor offset to GemmKernelRef for input padding support ( #12133 )
...
Signed-off-by: Andrew Park <andrew.park@intel.com>
2022-07-14 06:22:36 +03:00
Min, Byungil
99dbb35835
[GPU] modify fusing condition for reduce ( #12119 )
...
Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-07-14 11:04:14 +09:00
Felix Dohyun Kim
3c1ed2ce1f
[GPU] Pass eltwise unit tests on DG2 ( #12113 )
...
* check fusion in onednn too
2022-07-14 10:15:57 +09:00
Krzysztof Bruniecki
9d0e623af6
[GNA] Add support for future devices with relaxed capabilities ( #12000 )
2022-07-13 14:18:34 +02:00
Vladimir Paramuzov
a185299ba4
[GPU] Simplify namespaces in the plugin part ( #12121 )
2022-07-13 15:47:40 +04:00
Szymon Irzabek
ed812bdf68
[GNA] Reduce impact of sf propagation fix ( #12115 )
2022-07-13 11:59:44 +02:00
