Commit Graph

8954 Commits

Author SHA1 Message Date
Karol Blaszczak
779aac9de8
Update OV_flow_optimization_hvr.svg (#14180) 2022-11-23 09:57:46 +01:00
Tatiana Savina
4fd16185a6
change importlib vers (#14123) 2022-11-23 12:56:33 +04:00
Mateusz Tabaka
e105b3ea37
[LPT] fix weights output channel index in ConvolutionBackpropDataTransformation (#14124)
ConvolutionBackpropData weights have following shape {input channels, output_channels, ...},
so unlike forward convolution, the output channels are on the second dimension.
2022-11-23 09:01:59 +01:00
Eddy Kim
ae0b2ce3c3
[GPU] GPU serialization fix (#14164)
* kernel_impl_params should be serialized before primitive_impl

* reduced the range of min max values ​​for this test case

* updated to use default get_mem when min max are not specified
2022-11-23 12:00:22 +04:00
Wang, Yang
7aac663f4a
[AUTO Plugin] Remove/Add some test cases for AUTO/MULTI (#14117)
* Update.

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

* 1. Remove part of AUTO/MULTI test case since they has been coverred in another PR[13738].
2. Move the rest part of AUTO/MULTI test cases into CPU function test suit.

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

* Update.

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

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
2022-11-23 14:56:03 +08:00
Ilya Lavrenov
86e71003e6
Put json library finding under ENABLE_SAMPLES (#14138) 2022-11-23 10:07:17 +04:00
Zhang Yi
0b361768ce
[CPU] Use common transform for logsoftmax (#14150) 2022-11-23 09:27:44 +04:00
hyunback kim
96e408899e
[GPU] Update oneDNN v2.7 (#14139)
include enable deconv binary dims, types issue

Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-11-23 12:37:22 +09:00
yanlan song
8e4bd92d12
change default value (#14142)
Signed-off-by: fishbell <bell.song@intel.com>

Signed-off-by: fishbell <bell.song@intel.com>
2022-11-23 10:05:32 +08:00
Wilson Seok
0c8a49034c
[GPU] add fs_b_yx_fsv32 in concat ref kernel and unit test for axis=3 (#14081)
* add fs_b_yx_fsv32 in concat ref kernel and unit test for axis=3

* add more blocked format for axis3 test case
2022-11-22 18:03:21 -08:00
Mingyu Kim
1d80f90316
[GPU] Layout propagation with preferred_layout (#14061)
* [GPU] Layout propagation with preferred_layout
2022-11-23 08:29:27 +09:00
Anastasiia Pnevskaia
74758c0ca5
copy() and deepcopy() methods for PartialShape. (#14136)
* Added copy and deepcopy methods for PartialShape.

* Clang format.
2022-11-23 01:09:30 +04:00
Anastasiia Pnevskaia
256b27c381
Fix for MO IR reader loading old meta data. (#14171)
* Fix for IR reader loading.

* Condition fix.
2022-11-22 22:06:32 +04:00
Anastasiia Pnevskaia
83e41d5d88
Fixed layout parsing. (#14157)
* Fixed layout parsing.

* Small fix.

* Test fixed.
2022-11-22 22:06:22 +04:00
Maxim Vafin
580c0c6b90
Fix squeeze shape infer to not change axis value (#13975)
* Fix squeeze shape infer to not change axis value

* Fix TensorIterator

* Revert Unsqueeze changes
2022-11-22 21:24:03 +04:00
Felix Dohyun Kim
2176e8f13c
[GPU][DG2] Add fuse_count_onednn in test parameter (#14106) 2022-11-23 00:32:35 +09:00
Ilya Churaev
55b672b3dd
Fixed link to developer documentation (#14149) 2022-11-22 18:02:02 +04:00
Asthestarsfalll
2edb9f7775
add paddle box coder (#12394)
Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-11-22 15:20:46 +03:00
Mikhail Ryzhov
7244f1227d
Removed unnecessary convertation nodes to output (#14125) 2022-11-22 11:25:07 +01:00
Ryszard Jezierski
e205538129
[GNA plugin] Fix issues from static code analysis (#13432)
* fix static code analysis

* reverted manual ostream flags reset
2022-11-22 11:24:09 +01:00
hyunback kim
c1bb0b59e7
[GPU] Fix kernel build failed issue (#14007)
* [GPU] Fix kernel build failed issue

redefinition of 'eltwise0_data0' FUSED_OPS_PRELOAD
Target model: cocosnet/onnx/INT8

Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-11-22 19:03:21 +09:00
Eddy Kim
0b1e36600b
[GPU] Graph serialization for GPU #2 (#13986)
* moved serialization include path

* quiet onednn-gpu patching

* save and load kernels in _impls

* changed to use OPENVINO_ASSERT

* fix errata

* updated to follow OpenVINO naming convention

* updated error messages

* binary buffer by vector<uint8_t>

* partial_shape serialization

* removed object_type

* added a new storage class for primitive_type_string and id

* updated to throw an exception when _node is null in build_deps().

* removed redundant memory_pool clearing

* added a new net_id creator

* newline at eof

* updated CLDNN with GPU

* added cache blob descriptions

* updated output allocation logic  in serialization

* added ov::device::architecture in supported properties

* overrided save and load in data_inst and mutable_data_inst

* removed save and load functions in mutable_data

* baseline for serialization unit tests

* added serialization unit tests

* added serialization unit tests

* updated not to execute build_deps when deserialized

* make_data without namespace

* updated to use default layout c-tor

* updated get_unique_net_id()

* updated get_type_id() to a pure virtual method

* updated ov::caching_properties

* added [GPU] tags

* updated network c-tor

* updated unit tests
2022-11-22 12:43:50 +03:00
Vitaliy Urusovskij
97878dee34
Load plugin libraries safely (#14034)
For security purposes load plugin libraries only by absolute path to prevent
search from environment variables, working directory etc.
2022-11-22 12:44:56 +04:00
Xuejun Zhai
1910f42179
[C API DOC][DG] C API developer documentation (#13499)
* [C API DOC] add c api docs

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

* Update OpenVINO_Runtime_C_API_User_Guide.md

Add mapping relationship about C++ API 2.0 and C API

* [C API][DG] Add some roles for developping C API

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

* [C API DOC][DG] Implement the developer guide

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

* [C API DOC][DG] Fix comments

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

* [C API DOC][DG] Fix format issue

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

* [C API][DG] Fix review issues including add reference link, clear description

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

* [C API][DOC] Fix review comments

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

* [C API][DOC] remove the mapping relationship of interface & object

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

* [C API][DOC] Fix review comments

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

* [C API][DOC] add descriptions for unit test

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

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>
2022-11-22 10:38:17 +04:00
Fang Xu
8786fbe0c3
update tbb linux and mac binaries (#14080)
Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-11-22 14:33:52 +08:00
Mateusz Tabaka
47acda3476
Cleanup in Split mask propagation transformation (#14119)
* Cleanup in Split mask propagation transformation

* review comments
2022-11-22 10:25:58 +04:00
Ivan Tikhonov
81c579fd2a
fix inference of some with TensorIterator (#14108) 2022-11-22 10:17:58 +04:00
River Li
bf5b7a5fec
[DOC] Add developer guide for conditional compilation (#13852)
* Add developer guide for conditional compilation

Change-Id: If769ce1afc045e678b5816ed6ae903ba48a5a320

* Use reference to real code as example

Change-Id: I21f6aa47dfdf4ab7e92424a3ccc3d7524cc4b762

* Add table for macros

Change-Id: I9503d801ebe67ea5c6e525e02a21a7295ba56bc6

* Update for more clear description

Change-Id: I83b39f4a2462fb47ad1537e9747a2bb4a031dab9

* Use refer link replace code snippet

Change-Id: I5e63302718ab02eb4bd7a28ae994c8e5e26e0e02

* Add README.md for CC

Change-Id: I90abe73297deb5f55f219c15b093a02a30f9e8b5

* Update README.md

Change-Id: I8199252cb24fdacba16ea8b9fac63f6f47e4f1e3

* Add link list to doc

Change-Id: Id9a512cf8998cf18795cc0ac096fbbf89b28941c
2022-11-22 09:28:01 +04:00
Vladimir Paramuzov
dfb31f485b
[GPU] Insert reorder for eltwise const dependency (#14013)
* [GPU] Insert reorder for eltwise const dependency

* [GPU] Fixes for const reorder logic. Updated one codegnerator config
2022-11-22 09:10:00 +04:00
Oleg Pipikin
6b4b01aecf
Move transformation and lp transformations tests from IeFuncTests and IeUnitTests (#14096)
* Move transformation and lp transformations tests from IeFuncTests and IeUnitTests

* Enable tests in Azure CI

Co-authored-by: Ilya Churaev <ilya.churaev@intel.com>
2022-11-22 07:46:19 +04:00
Taylor Yeonbok Lee
dc3d5755cf
[GPU] Fix dynamic shape accuracy issue w.r.t crop (#14104)
* Fix wrong dependency issue to split/variadic split issue

* Added variadic split test

* minor changes
2022-11-22 06:21:26 +03:00
Sungeun Kim
9bcc730bec
check prev is next's dep(0). (#14107) 2022-11-22 12:05:28 +09:00
Jade Cho
4c0b8e6ebd
[GPU] Prevent that tanh is fused (#13976) 2022-11-22 10:33:48 +09:00
Mateusz Bencer
a693f4efac
[ONX FE][Quantize/DeQuantize] Ignore the axis attribute for scalar scale/zero_point (#14049) 2022-11-22 03:34:30 +03:00
Katarzyna Mitrus
adea538ba7
Fix Unique op python tests (#14118) 2022-11-22 02:50:08 +03:00
Katarzyna Mitrus
052a32be57
Add default to switch (#14110) 2022-11-21 23:59:23 +04:00
Oleg Pipikin
8134eba818
Fix typo in test executable (#14116) 2022-11-21 23:59:09 +04:00
Ilya Lavrenov
bbd6c03817
Fixed manylinux2014 with system TBB (#14126) 2022-11-21 20:43:22 +04:00
Egor Duplenskii
2d01ad3f18
[CPU] Fix seg fault in oneDNN 'parallel' with ITT built (#14048) 2022-11-21 20:11:03 +04:00
Irina Efode
68b6b273c5
[CONFORMANCE] Fix API Conformance run according changed functions (#14112)
* [CONFORMANCE] Fix API Conformance run according changed functions

* def para
2022-11-21 18:49:44 +03:00
Jan Iwaszkiewicz
abdcaef36d
[PyOV] Add README.md and align structure-showing style (#14093)
* [PyOV] Add README.md and align structure-showing style

* First batch of review changes

* Remove README from compatibility files

* Add note about coding style rules

* Add note about coding style rules pt2

* Update Components

* Apply fixes
2022-11-21 16:42:36 +01:00
Min, Byungil
0cf319f855
[GPU] Apply cached_blob to make engine (#13781)
+ Updated oneDNN to use cache_blob
+ Updated oneDNN to fix group conv failure
+ Add g_os_iyx_osv8 format and relevant reorder to support oneDNN update
+ Used cached_blob to make engine if cache_dir config is used

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-11-21 22:52:18 +09:00
Evgeny Kotov
0846bdb67e
Transpose sinking on passes for Concat, Split and binary eltwise operations (#13718)
* initial

* clang cleanup fixes

* remove TrasposeAxis function; cleanup namespaces

* fix TransposeInputsInfo spell

* one_input_transpose spell

* cleanup speel

* spell

* decompose forward sinking

* decompose backward sink

* use NodeVector

* clang cleanup

* decomposite transformations into different files

* decompose unit tests

* clang cleanup

* azure build fixes

* code review fixes

* clang cleanup fixes
2022-11-21 16:24:26 +04:00
Mateusz Tabaka
738d7bb09f
Remove ov::JsonConfigExtension (#14087)
Ticket: 96278

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2022-11-21 15:06:08 +04:00
Luo Cheng
cf7b174bf9
[CPU] Use brgconv1x1 instead of inner product in some cases (#13715) 2022-11-21 15:00:49 +04:00
Tomasz Adamowicz
47e80200dd
[GNA] Add 1DConv validator for GNA 3.5 (#13866)
* [GNA] Add 1DConv validator for GNA 3.5

* Improve gna lib version parser

* [GNA] Enable exec target=GNA_TARGET_3_5 testing
2022-11-21 09:01:07 +00:00
Alina Kladieva
0b97ab48a3
Revert "Fixed manylinux2014 with system TBB (#14076)" (#14113)
This reverts commit cfb21de775.
2022-11-21 09:56:24 +01:00
Ilya Lavrenov
cfb21de775
Fixed manylinux2014 with system TBB (#14076)
Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-11-21 09:54:57 +01:00
Luo Cheng
40089bdef7
[CPU] MergeTransposeAndReorder incorrectly removed const (#14067) 2022-11-21 11:18:57 +03:00
Xuejun Zhai
05ed3e218b
[C Sample][Readme] correct C sample read me (#14052)
* [C Sample][Readme] correct C sample read me

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

* [C API][Sample] modify readme about api list

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

Signed-off-by: xuejun <Xuejun.Zhai@intel.com>
2022-11-21 08:03:53 +04:00