IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
10,641 Commits 38 Branches 54 Tags
9b9c31d46ba9932d708ee18ceea862d914f48b83
Commit Graph
10641 Commits
This Branch
This Branch
All Branches
Author SHA1 Message Date
Eddy Kim 9b9c31d46b [GPU] Updated to allocate memory in order of size while deserializing (#16867) 
* updated to allocate memory in order of size while deserializing

* fix windows build error

* updated to check dependencies between not connected nodes
 2023-04-16 22:33:57 -07:00
Egor Duplenskii 175db3523a [CPU] Add few tests to smoke scope (#16963) 2023-04-17 09:04:57 +04:00
Taylor Yeonbok Lee c96a5c4b70 Fix prepare padding which was not handling group size properly (#16977) 2023-04-16 21:42:03 -07:00
Ilya Lavrenov 31398bb3eb Fixed deprecated API warnings (#16949) 2023-04-17 07:19:53 +04:00
Roman Kazantsev 18da874c57 [MO] Remove use of mapping file and its generation (#16944) 
* [MO] Remove use of mapping file and its generation

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Fix pylinter findings

* Remove usage of mapping file in the layer tests

* Fixing layer tests for legacy frontend

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-04-15 10:38:33 +00:00
Andrew Kwangwoong Park 507b3251ef [GPU] Fix to skip reorder optimization during post_optimize_graph phase (#16908) 
* [GPU] Fix to skip reorder optimization during post_optimize_graph phase

Signed-off-by: Andrew Park <andrew.park@intel.com>

* Apply comment

Signed-off-by: Andrew Park <andrew.park@intel.com>

* update condition to check empty padding

Signed-off-by: Andrew Park <andrew.park@intel.com>

* add condition to check batch size

Signed-off-by: Andrew Park <andrew.park@intel.com>

---------

Signed-off-by: Andrew Park <andrew.park@intel.com>
 2023-04-15 02:24:06 +00:00
Taylor Yeonbok Lee 824a5aa7fb [GPU] Fix nonzero issue in constant propagate (#16933) 
* Fix gather_nonzero not to be marked as constant.
Even though count nonzero is to be turned into a constant, gather nonzero still cannot infer shape at the moment of propagate constant.

* Apply the fix only for gather_non_zero
 2023-04-14 23:16:34 +00:00
Sofya Balandina 9f3bc22e7a [apiConformance] Refactoor core_integration.cpp (#16416) 2023-04-14 23:15:41 +00:00
Roman Kazantsev 4ba0ac5476 [MO][TF FE] Support delayed batch setting (#16937) 
* [TF FE] Support delayed batch setting

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

* Cover BOM list

* Add unit-tests for batch setting with layout

* Apply code-review: check batch size

* Apply code-review: default index for any dimension

---------

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
 2023-04-14 22:35:43 +00:00
Edward Shogulin 8bdc5bc85f [LPT] Support ONNX quantized models coming from ORT PTQ (#14811) 
* [LPT] FakeQuantize fuse

* GPU & CPU tests alignment

* refactoring & comments

* doc quick fix

* quick fix
 2023-04-14 21:22:55 +00:00
Ilya Lavrenov de2e9faa58 Corrected pattern for Linux ARm64 tests disablement 2023-04-14 22:28:58 +04:00
Gorokhov Dmitriy cc6fd80d0a [CPU] Fixed Softmax and TopK nodes initilization for ARM devices (#16950) 2023-04-14 22:13:42 +04:00
Oleg Pipikin 7ce40996e5 Fix copy constructor and assignment for ov::Any (#16757) 
* Fix copy constructor and assignment for ov::Any

* Fix1

* Apply comments

* Add test

* Fix code style

* Fix2

* Fix3
 2023-04-14 22:12:18 +04:00
Aleksandr Voron dc941f69ae fix (#16969) 2023-04-14 22:09:50 +04:00
Aleksandr Voron fe98b8ee13 reduce 6d+ fix (#16931) 2023-04-14 22:09:22 +04:00
Ilya Lavrenov df5ada8b19 Skipped failed tests on Linux ARM64 (#16970) 2023-04-14 21:56:28 +04:00
Liubov Talamanova 0c0aa5c997 [POT] Fix POT CI (#16955) 2023-04-14 17:21:01 +00:00
Tomasz JankowskiandIvan Tikhonov 129670ab1e [Transformations] Fix Parameter name override while removing Select node (#16934) 
Details:
Applies valid node replacement method which avoids Parameter name override

Tickets: 101209

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-04-14 18:36:25 +02:00
Sun Xiaoxia 25058da48f Hot Fix: threading is disable with "threading=omp" (#16923) 
* fix omp threading disable

* the divisor and dividend are reversed
 2023-04-14 20:24:28 +04:00
Ilya Lavrenov f5c2db73d5 Moved heavy OVInferConsistencyTest tests to nightly (#16967) 2023-04-14 20:02:06 +04:00
Anastasiia Pnevskaia 24c9d95779 Support of unnamed input for MO Python API. (#16373) 
* Support of unnamed input for MO Python API.

* Code correction, tests fix.

* Small fix.

* Added tests for unnamed input, code fixes.

* Small code correction.

* Removed code comment.

* Added tests, fixed bugs.

* Minor corrections, added comments.

* Code refactoring.

* Added defaults for InputCutInfo.

* Fixed error.

* Small fixes.

* Removed wrong change.

* Fixed error.

* Corrected input description.
 2023-04-14 19:37:46 +04:00
Irina Efode ae34720818 [CONFORMANCE] Add check devices in parallelization over devices (#16964) 
* [CONFORMANCE] Add check devices in parallelization over devices

* Remove extra
 2023-04-14 15:50:35 +01:00
Vladimir Paramuzov 231569db16 [GPU] Fix group axis value for blocking desc (#16936) 2023-04-14 14:42:21 +00:00
Tatiana Savina cf12f92fae DOCS shift to rst - IR articles (#16437) 
* add IR documentation
 2023-04-14 14:11:00 +00:00
Tatiana Savina 9e5be9ad24 DOCS shift to rst Advanced topics (#16454) 2023-04-14 16:06:59 +02:00
Ilya Lavrenov 9b38e5168f Updated oneDNN to fix crash on aarch64 Linux (#16961) 2023-04-14 17:49:21 +04:00
Irina Efode d07fa6f80e [CONFORMANCE] Fix Opset filters (#16928) 
* [CONFORMANCE] Fix filters related to opsets

* fix

* Fix op_summary

* Update op_summary.cpp

* fix

* fix
 2023-04-14 17:42:42 +04:00
Irina Efode fd824cf036 [CONFORMANCE] Correct passrate when added skipped tests (#16844) 
* init

* Refactor

* Static and dynamic approach

* next

* fix

* small fixes

* fix
 2023-04-14 17:00:19 +04:00
Ilya Lavrenov b9f82e37b9 Removed WAs from packaging scripts related to old ARM plugin (#16952) 2023-04-14 16:17:12 +04:00
Vitaliy Urusovskij 04a4971481 Small docs fixes (#16945) 2023-04-14 15:14:48 +04:00
Aleksandr Voron 2c7cbdb293 [TEMPLATE] Skip TopK tests for ARM (#16946) 
* skip topk tests for arm

* changed macros

* added include
 2023-04-14 14:50:10 +04:00
Marcin Kusmierski d6f7e5e84d [GNA] Fix UT for adding extra segments to PWL-s after convolution (#16732) 2023-04-14 11:25:10 +02:00
Maciej Kwapulinski 435a79a2a3 Fix stride height setting in input_conv test (#16813) 2023-04-14 08:53:24 +02:00
Marcin Kusmierski 67aa807892 Fix smoke_LSTMCellBasicCommon for GNA 3.5 (#16924) 2023-04-14 08:43:30 +02:00
Egor Duplenskii e98bd0dae4 [CPU] Correct crop in FQ optimized formula (#16887) 2023-04-14 10:43:05 +04:00
Michael Frank Hansen a7228534af DOCS Adding results for RPL-S (#16862) 
* Adding results for RPL-S
* Create OVMS-benchmark-data.csv
 2023-04-14 08:01:59 +02:00
Aleksandr Voron 55fa8da5e4 [CPU] MVN 1D fix in ACL Executor (#16930) 2023-04-14 10:00:20 +04:00
Xuejun Zhai 802742e59f split evaluate_map.cpp to small files (#16216) 
* Split evaluate_map.cpp

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix compiler error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI build error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI build error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI build error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI format issues

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI format issues

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI format issues

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Fix CI format issues

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* Add op v7::Gelu

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
 2023-04-14 06:57:19 +04:00
Pavel EsirandKarol Blaszczak 68f46ff9a1 [MO] compress_to_fp16=False by default (#16854) 
* compress_to_fp16=False by default

* Apply suggestions from code review

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>

* note abound RAM consumption for FP16 compressed models

* detailed notion about RAM usage

* update 'get_compression_message()'

* corrected get_compression_message: remove infor about RAM

* fix pytorch convert layer tests

---------

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
 2023-04-14 01:16:41 +00:00
Ilya Lavrenov de8f34c8f0 Fixed plugin name in tests for ARM CPU (#16932) 2023-04-13 22:35:21 +04:00
Ilya Lavrenov 85f9d1392c Used cmake interface in ARM compute (#16929) 2023-04-13 22:35:03 +04:00
Luwei ZhouandVladislav Golubev 6aeb054e48 [CPU] Use ONEDNN3.x weight/dest scale API to optimize perf (#16805) 
* [LPT][CPU] Added callback for AddTransformation

* [WIP] Convolution scales fusion

* Force to use weight sclae to test performance.

* Update on interface.

* Use weight scale to adapt to ONEDNN 3.x API changes.

* Update the code.

* Update ONEDNN fix for gemm_x8s8s32x_conv kernel

* Fix the bug in ONEDNN and deconvFusingScale.

* Fuse FC Bias when having DQscale.

* WR to perf regression on

* Update onednn version.

* Fix bug and clean code.

* FC fusing dq scale bug fix.

* Add more comments and debug information.

* Fix CI issues.

* Merge ONEDNN changes.

* Fix CI issues and bugs.

* Apply review comments.

* Update comments.

* Apply reveiw comments.

* Avoid using LPT BiasAttribute RTInfo.

* Applied review comments.

---------

Co-authored-by: Vladislav Golubev <vladislav.golubev@intel.com>
 2023-04-13 19:02:48 +02:00
Maxim Vafin 25015f9790 [PT FE] Support prim::DictConstruct on the output (#16894) 
* Support dict on the output

* Preserve output order
 2023-04-13 16:42:17 +00:00
Aleksandr Voron 0426c645eb Fix for ambiguous overloaded function call (#16927) 
* fix

* change type to unsigned long long
 2023-04-13 19:28:30 +04:00
Shen, Wanglei 3461064507 update benchmark_app to remove setting UNDEFINED with -hint none (#16695) 
* Remove setting ov::hint::PerformanceMode::UNDEFINED from benchmark_app

* update benchmark_app

* update python code and description

* update python code

* fix code style issue

* update python code

* update c++ app
 2023-04-13 14:29:13 +00:00
Maxim Vafin c592ecd44e [MO] Fix legacy If (#16613) 
* Fix legacy If

* Add test for If op

* Small fix
 2023-04-13 18:10:40 +04:00
bstankix 5795a50a22 [docs] Update switchers 5 (#16925) 2023-04-13 16:07:53 +02:00
Egor Duplenskii a016e4e6bb [IE_TESTS] Avoid any extra work for the skipped tests (#16915) 
i.e. do not clone the function if it is unnecessary
 2023-04-13 13:23:38 +00:00
Vladimir ParamuzovandSergey Shlyapnikov 5299f26168 [GPU] Handle unsupported eltwise fusion for onednn gemm in dynamic cases (#16875) 
* [GPU] Handle unsupported eltwise fusion for onednn gemm in dynamic cases

* Update src/plugins/intel_gpu/tests/fusions/gemm_fusion_test.cpp

Co-authored-by: Sergey Shlyapnikov <Sergeishlyapnikov@gmail.com>

---------

Co-authored-by: Sergey Shlyapnikov <Sergeishlyapnikov@gmail.com>
 2023-04-13 15:55:44 +04:00
Roman Lyamin 656428bc4f [GPU] Skip kernel logic for Concat fix (#16885) 2023-04-13 15:55:05 +04:00