Min, Byungil
0e486c1b9b
[GPU] Reduce overhead in device_query ( #13200 )
...
+ Reduced overhead of is_local_block_io_supported in ocl_device
+ Updated hash_value in kernels_cache
Signed-off-by: Min, Byungil <byungil.min@intel.com >
2022-11-09 11:59:52 +09:00
cecilia peng
3bdb9cae54
[CPU] add support for internal ops augrucell and augrusequence ( #12647 )
...
* [cpu] enable augru.
* initiate opset_private_tbl.hpp for private ops.
* fix ngraph_functions target_linker.
* temporaliy disable a failure test.
2022-11-09 05:58:04 +03:00
Tetiana Gubanova
4d1de75b24
[GPU] Add blocked layouts support to normalize operation ( #12459 )
...
* Add blocked layouts support to normalize operation
* Add normalize logic for blocked and plain layouts to one kernel
2022-11-08 17:50:44 -08:00
Paul Youngsoo Ahn
5c17c7e0a0
[GPU] Fix multistream issue for dynamic shape ( #13433 ) ( #13433 )
...
- Separate kernels_cache::add_kernel from factory (choose_impl)
- Reset kenrels_cache._kernels after kernels_cache.compile
- Create cldnn unit test case to check multi-stream processing
2022-11-08 17:34:40 -08:00
Roman Kazantsev
9943edfa34
[Core] Fix StridedSlice shape infer in case dynamic end and input of dynamic shape ( #13909 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
2022-11-08 22:52:13 +03:00
Katarzyna Mitrus
03d048240c
Broadcast-3 shape_infer review ( #13849 )
...
* v3::Broadcast tests
* Shape infer improvements
* Use Dimension broadcast_merge in Bidirectional mode
* More tests
* Style apply
* Fix Unqueeze with Broadcast tests
* Align Squeeze/Unsqueeze tests
* Fix warning
* Updates test shapes names
* loops refactor
* Remove redundant set/get labels from expected shapes
* Padding refactor
* Tests refactor
* Revert auto for i in loop
2022-11-08 21:51:04 +03:00
Sun Xiaoxia and Shen, Wanglei <wanglei.shen@intel.com>
73a8718b47
Xiaoxia/Default setting with hyper thread enabled on Hybrid-aware P/E-core ( #13773 )
...
* add HybridAware stream setting and core binding
* fix clang format issue
* unified code style, add parameter check
* correct input affinity skip NUMA, modify function name
* remove unnecessary floor
* fix ci compile issue on Mac/windows platform
* modify smoke_SetConfigAffinity test
* modify ov_core_set_and_get_property_enum test, affinity HYBRID_AWARE is changed to NUMA
* remove affinity correcting on this pr
* revert ov_core_test.cpp
* merge function by comments
* fix code style issue
* add custom nstreams setting, remove mutable qualifier
* fix code style issue
* fix some issues according to comments
* modify UpdateHybridCustomThreads
* fix code style issue
* modify comments
* use logic core in phase 2
* modify steams threads setting method
* move properties used in P/E-core to ie_internal_plugin_config.hpp
* fix streams is wrong on P/E-core which has 6 big cores
* modify code according to comments
* add threads_per_stream_small=3
* add the judgment of logical core
* fix code style issue
Co-authored-by: Shen, Wanglei <wanglei.shen@intel.com >
2022-11-08 21:18:23 +03:00
Roman Kazantsev and Maxim Vafin
124106f81b
[TF FE] Refactor SpaceToBatchND and BatchToSpaceND operations ( #13884 )
...
* [TF FE] Refactor SpaceToBatch and BatchToSpace operations
Make them to support inputs of dynamic rank and shapes
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
* Add layer tests in the pre-commit
* Fix for normalizing padding and crops
* Correct the type of paddings and crops
* Fix incorrect changes for paddings and crops
* Update src/frontends/tensorflow/src/op/space_to_batch_nd.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com >
* Update src/frontends/tensorflow/src/op/space_to_batch_nd.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com >
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com >
2022-11-08 20:38:55 +03:00
Jan Iwaszkiewicz
5ae221e107
[PyOV] Fix mypy after bump, general refactor ( #13913 )
...
* Fix mypy errors after bump PEP482, reformat code in general
* Enable checks
* Fix smaller issues
* Revert typo with comments
* Fix indents
2022-11-08 19:26:39 +04:00
Mateusz Bencer and Michal Lukaszewski
116f294a9a
Introduce PullThroughReduce and ReduceReshapeFusion transformations ( #13047 )
...
* Initial version of PullThroughReduce and ReduceReshapeFusion transformation
* remove std namespace
* headers + namespaces clean-up
* resolved problem with ambiguous namespace
* clang format applied
* tests refactor. part 1
* tests refactor. part.2
* changed includes
* review remarks
* tests refactor. part.3
* review remarks
* fix build problem
* remarks
* fix reserving memory
* review remarks
* styles applied
* handle axes in the middle in try_get_unsqueeze_axes_from_reshape
* handle case of scalar input shape
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com >
2022-11-08 17:33:04 +03:00
Nikolay Shchegolev
b6ec6d4ec0
[CPU] GridSample operation implementation. ( #12910 )
2022-11-08 14:53:33 +03:00
d2871fd52c
[PyOV] Enable Python 3.10 on Azure CI ( #12578 )
...
* Fix mypy for numpy==1.21.6
* Apply CR changes
* Allow Python 3.6 for open source
* Attempt to silence mypy
* Revert to 3.6 in setup.pys
* Fix merge conflict
* Add newline
* Fix Python version assert
* Test Python 3.10 CI
* Try bumping up pybind to 2.10
* Link default python to python 3.10
* Add sudo to changing default python
* Bump python version in setupvars
* Fix exception in test
* Do the same for compatibility
* Apply same CI changes to other pipelines
* Attempt to fix arm and windows CIs
* Fix win py lib version and links?
* Try to fix CI
* Fix win python path
* Update win path
* Test disable PDPD
* Disable TF for testing CI
* Add sudo to rm
* Test linux
* Update requirements
* RM sudo
* Add debug step to CI on ARM
* build py from source on linux
* Remove debug step from ARM
* Fix err
* Fill num_proc
* Fic py installation
* Bump pdpd to 2.3.1
* Bump np vers
* Try to upgrade onnx to 1.12.0
* Revert onnx upgrade, enable frontends
* Build py shared
* Export library
* activate py env
* Bump scipy for py3.10
* Another scipy bump
* Fix Windows path, add nfs helper for mount
* Attempt to fix win_cc
* Batch of changes
* Try to fix ngraph-onnx-lin
* Install lsb-release for docker on ngraph-onnx-lin
* Link lsb_release
* Try bumping Ubuntu to 22.04
* Revert ubuntu change in dockerfile
* Refactor tests for onnx1.12
* Fix ONNX compatibility and numpy warnings
* Refactor tests for onnx1.12
* Fix ONNX compatibility and numpy warnings
* Upgrade ONNX to 1.12 in cpp
* Skip unsupported ops
* Revert "Fix ONNX compatibility and numpy warnings"
This reverts commit cd8a0e6b8emateusz.mikolajczyk@intel.com >
Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com >
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com >
2022-11-08 11:38:39 +04:00
Szymon Irzabek and Marcin Kacprzak
3ea77b9966
GNA MTL mixed precision ( #13166 )
...
* [GNA] Enable int8 weights for convolutions
* [GNA] Implement convolution low precision tests for MTL
Co-authored-by: Marcin Kacprzak <marcin.kacprzak@intel.com >
2022-11-08 07:34:01 +01:00
Ilya Churaev
0fa1573bbb
Enable disabled check ( #13908 )
2022-11-08 10:27:23 +04:00
Ilya Churaev
0bb72a4949
Add ctest for some test targets ( #13727 )
...
* Add ctest for some test targets
* Fixed test coverage
* Replaced unit tests cmake script
* Fixed code style
* Use ov_add_test_target for FEs
* Fixed code style
2022-11-08 10:25:16 +04:00
Tatiana Savina
07a0ff58f2
DOCS: Developer documentation Inference component update ( #13895 )
...
* dev docs fixes
* fix space
* fix paragraphs
2022-11-08 07:42:10 +04:00
Andrew Kwangwoong Park
e1f014ac15
[GPU] Fix performance degradation of bfyx conv with FP16 compared to FP32 ( #13847 )
...
Signed-off-by: Andrew Park <andrew.park@intel.com >
Signed-off-by: Andrew Park <andrew.park@intel.com >
2022-11-07 16:55:47 -08:00
Ilya Lavrenov
1f561033fa
temporary commented failed test ( #13904 )
2022-11-08 01:24:59 +04:00
Taylor Yeonbok Lee
cd94a1f17b
[GPU] Enable Conv/GroupConv shape infer for explicit/valid padding ( #13731 )
...
* Enabled Conv dynamic shape & Added conv dynamic functional test
* Fix layout optimizor
* Revert layout optimizer change
* Set expected layout of convolution for dynamic shape to be fsv16
* Fixed groupConv for dynamic shape
Added 1D dw/group convolution tests for both static & dynamic
Currently, 1D group convolution is only works for dw..
* Minor fix
* Updated for 3D conv dynamic case + corresponding test
* Fix lint error
* Fix INSTANTIATE_TEST_CASE to INSTANTIATE_TEST_SUITE
* Fix clang format & skip 1D group conv test
2022-11-07 11:38:52 -08:00
venki-thiyag and venki
835236fae6
#13888 [Bug] Unable to load OpenVINO in Electron app node addon ( #13890 )
...
Co-authored-by: venki <venkatesan.t@ringcentral.com >
2022-11-07 19:27:17 +04:00
Pawel Raasz
c37e06f947
Review opset1 split for shape inference aspects ( #13844 )
...
* Review split operator for shape inference:
- check label and dimension propagation
- check evaluation lowe, upper and labels
* Review split static shape inference by tests
* Use shape_infer in split evaluate
* Fix compilation issues
* Fix usage of broadcast in bound tests
2022-11-07 17:04:25 +04:00
Roman Lyamin
34b76584f7
[GPU] AvgPool/MaxPool dynamic support ( #13754 )
2022-11-07 15:46:17 +04:00
Anastasia Kuporosova
713eb9683f
[Pyskip failed tests ( #13892 )
2022-11-07 14:46:51 +04:00
Roman Kazantsev
995bcdbe47
[TF FE] Refactor Where translator and test it ( #13880 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
2022-11-07 12:32:16 +04:00
Roman Kazantsev
2e9a8cd332
[TF FE] Refactor SpaceToDepth and test it in the precommit ( #13882 )
...
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
2022-11-07 12:23:54 +04:00
Min, Byungil
e676ae7016
[GPU] Resolve reduce test failure ( #13607 )
...
+ Added logic to select planar format for b-f axes reduction
+ Bugfix of reorder_unreduced_axis_no_fusion
+ Bugfix to resolve an issue of cgan_mnist
Signed-off-by: Min, Byungil <byungil.min@intel.com >
2022-11-07 16:57:53 +09:00
Vladimir Paramuzov
ad403cf55e
[GPU] Remove f16<->f32 conversion duplicates ( #13735 )
2022-11-07 11:01:20 +04:00
Wang, Yang
560dba22cb
Fix the logic issue of handling the ov::device::properties in the ie core. ( #13482 )
...
* Update the logic to handle the ov:device::properties in the ie core.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* Update test cases.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* 1. Remove the config filter within AUTO plugin when passing the configs to target hardwre device through AUTO plugin.
2. add test cases to check if the secondary properties have been passed into the target device through virtaul device.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* Add mock tests to check if device properties works throgh the AUTO or MULTI plugin.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* Add mock head file for loadnetwork with device properties testing.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* Update.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
* Update gtest commit to fix the warning issue appeared in the macro MATCHER_P.
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
2022-11-07 10:36:25 +08:00
Wang, Yang
8f9fc34ed3
Enable AUTO to accept the ov::device::properties with device name contained the index. ( #13665 )
...
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
Signed-off-by: Wang, Yang <yang4.wang@intel.com >
2022-11-07 10:23:35 +08:00
yanlan song
394b6fe9ee
Bell/execution device ( #13737 )
...
* debug only
Signed-off-by: fishbell <bell.song@intel.com >
* add execution_device property for auto
Signed-off-by: fishbell <bell.song@intel.com >
* Revert "debug only"
This reverts commit 5ef6140b63bell.song@intel.com >
* polish tests to cover multiple gpu platform
Signed-off-by: fishbell <bell.song@intel.com >
clean up
Signed-off-by: fishbell <bell.song@intel.com >
* clang format
Signed-off-by: fishbell <bell.song@intel.com >
* only cpu in cpuFunctest
Signed-off-by: fishbell <bell.song@intel.com >
* thread-safe implementation
Signed-off-by: fishbell <bell.song@intel.com >
* remove not needed locl
Signed-off-by: fishbell <bell.song@intel.com >
* apply review comments
Signed-off-by: fishbell <bell.song@intel.com >
* remove blank line
Signed-off-by: fishbell <bell.song@intel.com >
Signed-off-by: fishbell <bell.song@intel.com >
2022-11-07 10:12:28 +08:00
Roman Kazantsev
57eddaa239
[TF FE][Common] Use opset Unique in TF FE and move Unique decomposition to common ( #13818 )
...
* [TF FE][Common] Move TF FE to opset Unique and add Unique decomposing to common
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
* Add Unique decomposition transformation into the common part
* Add transformation tests for UniqueDecomposition
* Fix unique_decomposition_test
* Simplify condition of transformation applicability
* Clarify the comment when the transformation is applicable
* Fix transformation test
* Fix transformation test
* Add support of opset10 in IR Reader
* Mark the single element case as xfail
* Fix tensor names in the transformation
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com >
2022-11-07 01:24:23 +03:00
Przemyslaw Wysocki and jiwaszki
520b9ff68c
[PyOV] Disallow Python 3.6 usage ( #13240 )
...
* Remove py3.6 constraints
* Cleanup out of date python versions
* Bump pybind11 to v2.10.1 release tag
* [PyOV] Fix wheel requirements for new package versions
Co-authored-by: jiwaszki <jan.iwaszkiewicz@intel.com >
2022-11-06 10:45:42 +04:00
Jan Iwaszkiewicz
664c196a13
[PyOV] Fix wheel requirements for new package versions ( #13871 )
...
* Bump pybind11 to v2.10.1 release tag
* [PyOV] Fix wheel requirements for new package versions
2022-11-05 16:01:45 +04:00
Katarzyna Mitrus
c953186ff0
GRU/AUGRUCell shape inference function ( #13708 )
...
* Add shape_infer function for GRUCell op
* Add shape_infer function for AUGRUCell
* Consts refactor
* Add batch_size check
* Enable GRUCell shape_infer for CPU
* Style apply
* Use OV_EXPECT_THROW in tests
* Use helper for input shapes
* Use .back() instead of index
* Change rnn_seq namespace to rnn
* Fix win warnings
* Enable AUGRUCell/Sequence shape_infer on CPU
* Fix warn
* Fix warn
2022-11-04 23:31:58 +03:00
Alexandra Sidorova
cbf037b9a8
[Snippets] Fixed SnippetsMarkSkipped for dynamic branches ( #13751 )
2022-11-04 16:15:19 +04:00
Sungeun Kim
f1cf1948d5
[GPU] add errata for onednn layout selection ( #13758 )
2022-11-04 15:44:36 +04:00
Pawel Raasz
0646d49d35
Review opset1 squeeze for shape inference aspects ( #13716 )
...
* Review squeeze operator for
- label preserve and propagation
- partial values preserve and propagation
- interval shapes propagation
* Review static shape inference tests
* Add template shape inference for squeeze
* Update include for OV_EXPECT_THROW
* Correct has_static_axes initialization
* remove test_squeeze from xfail 44968
* Fix inference parameter op with no data
- add additional test to check if axes are parameter without data
- revert xfail marks for squeeze tests
* Fix inference parameter op with no data
- add additional test to check if axes are parameter without data
- revert xfail marks for squeeze tests
* Refactor axes acquire logic
2022-11-04 13:42:05 +03:00
Zlobin Vladimir
28a118be39
Apply improvements I found during https://github.com/openvinotoolkit/openvino/pull/13388 ( #13743 )
2022-11-04 14:41:15 +04:00
Artur Kulikowski
a48d1558e3
ONNX: Throw exception if attribute reduction is used in ScatterND or ScatterElements ( #13778 )
...
* ONNX: Throw exception if `reduction` attribute has unsupported value
Operators:
- ScatterND
- ScatterElements
2022-11-04 10:40:14 +01:00
Tomasz Adamowicz and Krzysztof Bruniecki <krzysztof.bruniecki@intel.com> 🥇
5f0b063455
[GNA] Support GNA 3.5 (MTL) target in OV ( #13478 )
...
* Enable TLV
* [GNA] Add smoke test for Conv with padding on MTL
* [GNA] Allow skipping tests based on gna lib version
Co-authored-by: Krzysztof Bruniecki <krzysztof.bruniecki@intel.com > 🥇
2022-11-04 10:26:22 +01:00
Vladimir Paramuzov
8b93e3f2ec
[GPU] Ability to compile OV with OCL 1.2 ( #13706 )
2022-11-04 12:31:01 +04:00
Tingqian Li
f34f35bfc7
[CPU] Enable scratchpad user mode for oneDNN based nodes ( #12038 )
2022-11-04 11:10:26 +03:00
avoskoboinyk-lohika
6fc23b4768
[CPU] Optimize DFT operation ( #11946 )
2022-11-04 09:46:46 +03:00
Taylor Yeonbok Lee
e9e3044d99
Fix error in calling is_dynamic ( #13769 )
2022-11-04 09:31:41 +03:00
Mikhail Ryzhov
7a6960b2f4
[GNA] Added support of the all log levels ( #13359 )
...
* Added GNA logger
* Added GNA logger class
* Replaced old looger by the new one
* Added support of the all log levels in the tests
* Renaming
* fixed cpplint issue
* Reduced error level
* fixed cpplint issues
* Fixed linking error
* Fixed linux build
* Rebase fix
* Removed unused code
* Fixed compile issue after rebase
* Aligned code usage and style
* Fixed default constructor
* Fixed test
* One more rebase
* Added exveption test
* Fixed the old logging tests
* restored static constants
* Removed dublicated log messages
* Removed incorrect log::level comparation
* Fixed generic api test
* Rebased
2022-11-04 04:58:01 +03:00
yanlan song
b04624766e
Bell/conditionally enable threadingtests for getavailabledevices ( #13772 )
...
* passthrough cache_dir for auto/multi
Signed-off-by: fishbell <bell.song@intel.com >
* enable tests for certain glibc version
Signed-off-by: fishbell <bell.song@intel.com >
* Revert "passthrough cache_dir for auto/multi"
This reverts commit 58591a1bcebell.song@intel.com >
* apply the review comment
Signed-off-by: fishbell <bell.song@intel.com >
Signed-off-by: fishbell <bell.song@intel.com >
2022-11-04 02:45:23 +03:00
Jan Iwaszkiewicz and Ilya Lavrenov
9f2489941f
Bump pybind11 to v2.10.1 release tag ( #13793 )
...
Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com >
2022-11-04 02:12:47 +04:00
Przemyslaw Wysocki
1cc499429a
[PyOV] Upgrade ONNX to 1.12.0 ( #12847 )
...
* Refactor tests for onnx1.12
* Fix ONNX compatibility and numpy warnings
* Upgrade ONNX to 1.12 in cpp
* Skip unsupported ops
* Revert "Fix ONNX compatibility and numpy warnings"
This reverts commit cd8a0e6b8e
2022-11-03 22:56:57 +04:00
Roman Lyamin
6c7f1f8792
[GPU] Fix performance drop on new API ( #13767 )
2022-11-03 18:34:14 +04:00
Vladimir Paramuzov
ced0eebd13
[GPU] Silence ocl include pragma message ( #13789 )
2022-11-03 18:02:23 +04:00
Min, Byungil
cecilia peng
Tetiana Gubanova
Paul Youngsoo Ahn
Roman Kazantsev
Katarzyna Mitrus
Sun XiaoxiaandShen, Wanglei <wanglei.shen@intel.com>
Jan Iwaszkiewicz
Mateusz BencerandMichal Lukaszewski
Nikolay Shchegolev
Szymon IrzabekandMarcin Kacprzak
Ilya Churaev
Tatiana Savina
Andrew Kwangwoong Park
Taylor Yeonbok Lee
venki-thiyagandvenki
Pawel Raasz
Roman Lyamin
Anastasia Kuporosova
Vladimir Paramuzov
Wang, Yang
yanlan song
Alexandra Sidorova
Sungeun Kim
Zlobin Vladimir
Artur Kulikowski
Tomasz AdamowiczandKrzysztof Bruniecki <krzysztof.bruniecki@intel.com> 🥇
Tingqian Li
avoskoboinyk-lohika
Mikhail Ryzhov