Commit Graph

8954 Commits

Author SHA1 Message Date
Vladislav Golubev
b11adcdde4
[LPT] FQ Decomposition improvement (#14203)
* [LPT] FQ Decomposition modified to create FQ without constants with several consumers

* [LPT] Added subgraph test

* CPUTestsBase: Added the ability to check only fusing results

* [CPU] Added subgraph test

* LPT review comments applied

* CPUTestsUtils: added special string 'anytype' for selectedType check ignore
2022-11-30 01:04:10 +00:00
Pavel Esir
2a1a2532b2
more safe get_output_types in callback in convert_compression_only_to_legacy.cpp;more readable unit-tests for out of bound Intervals (#14300) 2022-11-29 22:05:16 +00:00
Trawinski, Dariusz
a2b46ed2eb
update NEO drivers to support DG2 and fix package name for rhel8 (#14016)
* update code deps for rhel

* new neo driver version

* new neo driver version fix

* fix

* fix

* drop not needed gpu packages

* removed not necessry NEO packages, updated ov deps

* add gflag for rhel8 os

* update python on ubuntu18 and add core rhel8 rpm URLs

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-11-30 00:41:24 +04:00
Eddy Kim
cb15d281f1
[GPU] Serialize GPU memory reuse flag (#14269)
* serialize gpu memory reuse flag

* added c-tor of reduce_impl

* renamed memory_reuse_by_user as can_reuse_memory, and modified memory allocation logic to be simpler
2022-11-29 22:13:00 +03:00
Ilya Lavrenov
115a9071e4
Revert "[Common] Implement SelectWithOneValueCondition common transformation (#14242)" (#14317)
This reverts commit 5a59b2b8f2.
2022-11-29 21:08:48 +04:00
Vladimir Paramuzov
a1e30996a4
[GPU] Disable unused oneDNN features to reduce binary size (#12987)
* [GPU] Disable unused oneDNN features to reduce binary size

* [GPU] Fixed list args

* [GPU] unit test skip

* [GPU] Disable more onednn primitives
2022-11-29 18:55:14 +04:00
Georgy Krivoruchko
c4e15e0883
Added support of float16 in decoder proto, test (#13891) 2022-11-29 17:17:04 +04:00
Ekaterina Aidova
090261c852
[OMZ]: align dependencies (#14298) 2022-11-29 13:58:40 +01:00
Irina Efode
48dd92de47
[CONFORMANCE][IE TESTS] Reduce SLT execution time (#14165)
* init

* Reduce time

* remove extra

* try

* dd

* one more try

* Fix mistakes

* skip some cpu tests

* comment

* one more skip
2022-11-29 15:49:03 +04:00
Roman Kazantsev
5a59b2b8f2
[Common] Implement SelectWithOneValueCondition common transformation (#14242)
* [Common] Implement SelectWithOneValueCondition common transformation

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

* Add transformation tests for select_with_one_value_condition

* Move call of SelectWithOneValueCondition transformation to MOC

* Apply code-review feedback

* Remove corner case with dynamic output shape for Select

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-29 15:40:04 +04:00
Oleg Pipikin
de33d6d38b
Fix inference tests build and tests in case of buind with disabled targets (#14286) 2022-11-29 13:50:53 +03:00
Maxim Vafin
0377acfdfe
Fix issue with mxnet rnn model (#14225)
* Fix issue with mxnet rnn model

* Fix code style

* Add test
2022-11-29 14:17:54 +04:00
Artur Kulikowski
a0dd07f7e1
Add default visibility to class LegacyOpExtension (#14220)
* Add default visibility to class LegacyOpExtension

* Implement destructor in class LegacyOpExtension
2022-11-29 13:09:49 +03:00
Pavel Esir
e648001b12
[IE] keep constants in shape subgraphs in f32 (#14204)
* keep constants in shape subgraphs in f32

* added unit-test without callback; added comment in convert_compression_only_to_legacy.cpp
2022-11-29 13:55:06 +04:00
Adrian Varlan
97dd3e6a21
Adapt myriad plugin for new firmware (#14246)
Co-authored-by: Maksim Doronin <maksim.doronin@intel.com>
2022-11-29 01:46:45 -08:00
Wilson Seok
dd0e76b384
add input0(cond) broadcast in select (#14267) 2022-11-29 17:42:23 +09:00
Egor Duplenskii
03583d93cb
[CPU] Add option to disable XBYAK_NO_EXCEPTION and fix itt win lib load (#14252)
Two oneDNN changes in scope of single PR
2022-11-29 10:36:29 +04:00
Vladimir Paramuzov
52b02c190b
[GPU] Fixed bias fusion tests (#14285) 2022-11-29 01:26:13 +00:00
Wang, Yang
a0814953a4
sync benchmark python version with benchmark c++ version (#14212)
* sync benchmark Python version with benchmark C++ version.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

* Update tools/benchmark_tool/openvino/tools/benchmark/main.py

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

* Update tools/benchmark_tool/openvino/tools/benchmark/utils/utils.py

Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Zlobin Vladimir <vladimir.zlobin@intel.com>
2022-11-29 04:08:20 +03:00
Ekaterina Aidova
dc27a5d723
[OMZ]: update submodule (#14255) 2022-11-28 20:34:10 +01:00
Ilya Lavrenov
121cc920b7
Removed global defitniions for plugins (#14273) 2022-11-28 21:52:19 +03:00
Mateusz Bencer
09637ca5f2
[ONNX FE] Improve error handling during op registration (#14201) 2022-11-28 17:30:44 +01:00
Anastasiia Pnevskaia
af49e51b54
--input format update in MO docs (#14272)
* Updated input param in docs.

* Updated input param in docs.
2022-11-28 20:20:13 +04:00
Vladimir Paramuzov
9d954c7920
[GPU] Added several shape agnostic ref kernels (#13987)
* [GPU] Broadcast shape agnostic ref kernel

* [GPU] enable input_layout & data impls for dyn shapes

* [GPU] cum sum shape agnostic kernel

* [GPU] Eltwise shape agnostic kernel

* [GPU] Shape agnostic gather kernel

* [GPU] Shape agnostic mvn

* [GPU] Shape of and reshape dynamic kernels

* [GPU] Dynamic reshape

* [GPU] dynamic softmax

* [GPU] Dyn reshape fixes

* [GPU] Build fix

* [GPU] Prohibit reshape opt for padded case

* [GPU] Dynamic FC

* [GPU] Dynamic gemm

* [GPU] Dynamic reorder

* [GPU] int32 clamp WA

* [GPU] Review fixes

* [GPU] Fixed impls map for dyn cases

* [GPU] Broadcast fixes

* [GPU] Unit test fixes

* [GPU] Fixed gemm

* [GPU] Revert unexpected reorder kernel changes

* [GPU] Fix WA for clamp

* [GPU] Prohibit dynamic impl selection for non-planar output formats

* [GPU] Fix FC reshape to 2d

* [GPU] WA for fc with rank > 3
2022-11-28 18:08:48 +04:00
Roman Kazantsev
b9fe83b6aa
[TF FE] Remove fallback from TF FE and accelerate conversion for .pb (#14179)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>

Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2022-11-28 14:06:58 +00:00
Vladimir Paramuzov
63b80a4fee
[GPU] Async static kernels compile for dynamic flow (#14205)
* [GPU] Async static kernels compile

* [GPU] Added interface for async compilation worker

* [GPU] refactoring
2022-11-28 17:18:17 +04:00
Wang, Yang
a37723e8cf
[AUTO] Enable Benchmark APP to parse the ov::device::properties through dump_config()/load_config() (#14057)
* [AUTO] update property setting logic.

* Update core::set_property() logic to only support primary property for AUTO and MULTI.
* Separate AUTO and MULTI supported properties.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Add test case.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* 1. revert the changes for ie core.
2. Enable AUTO/MULTI only accepting its own properties.
3. Enable AUTO/MULTI accepting device properties passed from loadnetwork().

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Revert "[AUTO]Update the incorrect config test for Myriad (#13271)"

This reverts commit 0552d98802.

* MULTI only accepts its own properties that is same as AUTO currently.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Add test cases for AUTO/MULTI property test.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update to enable MULTI supporting hw primary property setting throw the compile_model().

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Remove the added test case for setting secondary property through set_property().

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* 1. For AUTO/MULTI, property setting will be passed via core::compile_model() instead of core::set_property().
2. update the logic to infer precision setting that will transform into secondary property setting to each hw device.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* set default value for nstreams when -d AUTO/MULTI and no nstreams setting from command line.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update code format.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Enable BA to support if -d AUTO:MULTI,xxx/MULTI:AUTO,xxx. while AUTO Plugin need to update the logic of generating supported config list to virtual device.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* move device configuration handling outside form function main.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Revert "move device configuration handling outside form function main."

This reverts commit ef77bfc602.

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Setting property performance hint to 'THROUGHPUT' and passing to executable network if no setting for of AUTO/MULTI.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

* 1. Fix the issue that the dumped configuration file retrieves empty config list when using OpenCV to dump configuration.
2. Enable load_config() to load secondary property.
3.  ov:device:properties from command line will replace the ov::device::properties loaded from configuration file.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update the performance statistics showing format.

* Update format.

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update samples/cpp/benchmark_app/main.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update samples/cpp/benchmark_app/main.cpp

Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update README to add some simple configuration files loaded into benchmark app.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* 1. Enable dump/load function for AUTO to support hw device property setting thorugh configuration JSON.
2. Update README.md to example a simple JSON file containing the hw device properties setting for AUTO/MULTI.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

* Update.

* Update.

* Drop the changes within dump/load of OpenCV config parsing.

* Update.

* Correct property name. Update ov::num_stream to ov::inference_precision.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
Co-authored-by: Nadezhda Ageeva <nkogteva@gmail.com>
2022-11-28 17:09:51 +04:00
Krzysztof Bruniecki
fe52337840
[GNA] Fix log level settings to control exporting of GNA text model description and allocations (#14251) 2022-11-28 12:24:49 +00:00
Georgy Krivoruchko
5c638df1c3
TensorFlow AddN layer test implementation (#13533) 2022-11-28 15:46:59 +04:00
Katarzyna Mitrus
13a76a8b72
[Unique-10] ConvertPrecision transformation and new attribute for output type (#14229)
* Add attribute for last output element type

* Add convert precision transformation and tests

* Update Unique python API with new attribute

* Update Unique-10 op specification

* Update docstrings

* Update visitor tests

* Add type prop tests for the new attribute

* Check axis constant before shape, compare with partial shape
2022-11-28 11:56:49 +01:00
Vladislav Golubev
f06c44115f
[LPT] Check on isQuantized fixed (#14151) 2022-11-28 13:58:42 +04:00
Maciej Kwapulinski
4b51cf5ba0
GNA library update to ver 03.00.00.1910 (#14215) 2022-11-28 09:36:29 +00:00
Taylor Yeonbok Lee
aa88f0f756
[GPU] Enable bias fusing for dynamic shape (#14146)
* Fuse bias for dynamic fc

* Passing bias fusing unit tests
2022-11-28 12:24:52 +04:00
Ilya Lavrenov
79c6968024
Added older pugixml version support (#14260)
* Added pugixml finding w/o cmake, pkg-config

* Fixed findings

* Pugixml

* Removed sudo from install_build_dependencies.sh

* Fixed compilation with old pugixml

* Fixed Azure pipelines

* Updated clang-format step

* Add new approach for pugixml find to OpenVINO Developer package

* Fixed compilation with older pugixml

* Added openssl-devel for cmake build

* Fixed finding pugixml in developer package
2022-11-28 11:54:54 +04:00
Sungeun Kim
6bcdaa782a
fusing reorder after quantize (#14235) 2022-11-28 16:04:54 +09:00
cecilia peng
b955e7e514
95436: sporadic failure (#14183)
* 95436: sporadic failure

* Update input_model.cpp
2022-11-28 14:03:51 +08:00
Zhang Yi
ead91d7c2f
[CPU] Fixed Concat node performance (#14216) 2022-11-28 10:00:03 +04:00
Roman Lyamin
eb9946bd25
[GPU] Added support dynamic sizes/scales inputs for Interpolate (#14074) 2022-11-28 09:10:12 +04:00
Vladimir Paramuzov
7933cc7e0b
[GPU] Adjust dynamic eltw fusion to keep correct shape infer (#14198)
* [GPU] Adjust dynamic eltw fusion to keep correct shape infer

* [GPU] Fixed eltwise shape infer
2022-11-28 09:08:19 +04:00
Vladimir Paramuzov
03b677b10b
[GPU] Retain engine ptr in RemoteBlob impl (#14244) 2022-11-28 09:07:31 +04:00
Oleg Pipikin
f1795ad78a
Move new transformation tests from ieFuncTests to ov_transformations_tests (#14241) 2022-11-28 08:23:17 +04:00
Oleg Pipikin
0b754189d1
Remove duplicated ir_serialization tests (#14256)
* Remove duplicated ir_serialization tests

* Fix code style

* Fix1
2022-11-28 08:22:41 +04:00
Irina Efode
c63f20fa7d
[CONFORMANCE] Fix canExport model test + fix some instantiations (#14153)
* [CONFROMANCE] Fix OV Path in new conformance runner

* filelist

* dd

* try

* one

* Update run_conformance.py

* sss

* revert extra

* f

* exec_net

* init_1

* fix_instantiations

* remove extra

* Update summarize.py
2022-11-28 07:41:24 +04:00
Min, Byungil
1849a0be0b
[GPU] Modify can_fuse_reorder for permute (#14234)
+ Remove reorder fusing condition for oneDNN execution of permute

Signed-off-by: byungilm <byungil.min@intel.com>
2022-11-28 12:30:40 +09:00
Jade Cho
6bc7cd73cd
[GPU] Remove WA to fallback to cldnn (#14147) 2022-11-28 12:23:32 +09:00
Kelvin Choi
003e25b6fe
[GPU] Update Reduce Op to use dynamic input (#13998) 2022-11-27 17:13:58 -08:00
Pavel Esir
e0c026cdfc
fix Interval multiplication when result exceeds int64_max (#14230)
* fix Interval multiplication when result exceeds int64_max

* added unit-test with corner cases
2022-11-27 22:40:44 +04:00
Andrei Kochin
0246eb7917
[Req] upgrade mxnet to 1.9.1 (#14120)
* [Req] upgrade mxnet to 1.9.1

Signed-off-by: andrei.kochin <andrei.kochin@intel.com>

* [Req] upgrade relax mxnet dependancy

Signed-off-by: andrei.kochin <andrei.kochin@intel.com>

* specify upper bound

Signed-off-by: andrei.kochin <andrei.kochin@intel.com>

Signed-off-by: andrei.kochin <andrei.kochin@intel.com>
2022-11-27 22:26:09 +04:00
Maxim Vafin
a1cef7ab3a
Fix value infer for ScatterUpdate in case of dynamic value in updates (#14222) 2022-11-27 22:23:39 +04:00
Ilya Lavrenov
9db70d774f
Properly added dependencies between RPM packages (#14258) 2022-11-26 11:11:19 +04:00