IntenseWebs/openvino
3
0 Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
12,576 Commits 38 Branches 54 Tags
999e9ef9ad2fa144910082b64b5d0a72b1586c62
Commit Graph
966 Commits
Author SHA1 Message Date
Pawel Raasz 7d1b7b6bec [core] Api 2.0/migrate operators without evaluate (#19988) 
* Migrate ops evaluate

* Remove using ngraph and std from ops

* Use OPENVINO_ASSERT instead of NGRAPH_CHECK

* Move `shape_util.hpp` to `dev_api/openvino/core/`

* Remove visit_attributes, same as base impl

* Fix build issues

* Fix build issues
 2023-09-25 14:22:59 +04:00
Yuan Hu ec45107723 [CPU] Fix memory leak in binconv (#19999) 2023-09-25 12:45:25 +04:00
Oleg Pipikin f82c668d28 Refactor GatherLayerTest, GatherElementsLayerTest (#20020) 
* Refactor GatherLayerTest

* Refactor GatherElementsLayerTest
 2023-09-25 11:29:57 +04:00
Sun Xiaoxia c983b464ba enable cpu pinning on Windows by setting property affinity CORE (#19418) 
* set enableCpuPinning=true by '-p YES'

* add test case of setting ov::Affinity::CORE

* add affinity=NUMA/HYBRID_AWARW

* fix build failure
 2023-09-25 12:51:09 +08:00
Sun Xiaoxia 678e919b13 CPU pinning on Windows (#19405) 
* add cpu pinning on windows

* remove pinning limitation on windows

* only support the machine with one numa node

* fix code style

* fix build error on macos

* set mask initial value

* fix test failure on window

* fix build failure on macos, add limitation on windows machine with two sockets

* fix test failure on windows

* fix test failure

* fix comments
 2023-09-23 11:28:15 +08:00
Oleg Pipikin ce378739f0 Refactor DetectionOutputLayerTest, DFTLayerTest, EltwiseLayerTest (#19922) 
* Refactor DetectionOutputLayerTest

* Refactor DFTLayerTest

* Refactor EltwiseLayerTest

* Fix

* Fix

* Disable tests
 2023-09-22 16:35:20 +04:00
Oleg Pipikin c1271d1217 Refactor EmbeddingBagOffsetsSumLayerTest, EmbeddingBagPackedSumLayerTest, EmbeddingSegmentsSumLayerTest (#19952) 
* Refactor EmbeddingBagOffsetsSumLayerTest

* Refactor EmbeddingBagPackedSumLayerTest

* Refactor EmbeddingSegmentsSumLayerTest
 2023-09-22 10:12:28 +00:00
Egor Duplenskii 3f3d89678e [CPU][ARM] Reorder FullyConnected weights in scope of compile_model (#19634) 2023-09-22 09:33:33 +04:00
Egor Duplenskii 6de8579b1d [CPU][ARM] Choose eltwise layout based on model type (#19234) 
Eltwise order of the supported primitive descriptors affects the
performance of the model.
Often only one of the port descriptors matches with the layout
of the parent descriptors, i.e. when two parent ports have mixed
layout "nchw nhwc".
So either nchw or nhwc layout will be used for the eltwise node
and reorder will be used for either of the ports.
The shape of the ports also can be different (when one of the inputs is
broadcasted). So reorders on different ports have different
performance impact.
The layout of the eltwise node child has an effect on the performance
as well, since it may or may not require reorder on input.
 2023-09-22 09:33:16 +04:00
Egor Duplenskii aec4c6c843 [CPU][ARM][FP16] Use Transpose executor for layout Reorder (#19227) 2023-09-22 09:32:12 +04:00
Oleg Pipikin b1bf16c7cf Refactor ConversionLayerTest, ConcatLayerTest, ConstantLayerTest, ConvertColorI420LayerTest, ConvertColorNV12LayerTest (#19777) 
* Refactor ConversionLayerTest

* Refactor ConcatLayerTest

* Refactor ConstantLayerTest

* Refactor ConvertColorI420LayerTest

* Refactor ConvertColorNV12LayerTest
 2023-09-21 22:56:14 +02:00
Vitaliy Urusovskij 318106d17d StridedSliceLayerTest and SqueezeUnsqueezeLayerTest to API2.0 (#19955) 
* `StridedSliceLayerTest` to API2.0

* `SqueezeUnsqueezeLayerTest` to API2.0

* Fix CppLint
 2023-09-21 15:08:51 +02:00
Vitaliy Urusovskij e5acf880ad Slice8, ShuffleChannels, ShapeOf layer tests to API2.0 (#19975) 
* `Slice8LayerTest` to API2.0

* `ShuffleChannelsLayerTest` to API2.0

* `ShapeOfLayerTest` to API2.0
 2023-09-21 14:36:26 +02:00
Vitaliy Urusovskij fc9dedfd6a Split, SpaceToDepth, SpaceToBatch layer tests to API2.0 (#19973) 
* `SplitLayerTest` to API2.0

* `SpaceToDepthLayerTest` to API2.0

* `SpaceToBatchLayerTest` to API2.0
 2023-09-21 12:29:30 +00:00
Vitaliy Urusovskij 2489356121 Skip failed TensorIteratorTest and CTCGreedy* CPU f16 tests on Mac (#19969) 
* Skip failed `TensorIteratorTest` CPU f16 tests

* Skip `CTCGreedyDecoder` on MacOS CPU ARM f16
 2023-09-21 15:44:37 +04:00
Nesterov Alexander 194b9f5c38 [ARM CPU] Migration Arm Compute Library to 23.08 version (#19523) 2023-09-21 14:30:38 +04:00
Luwei Zhou 9dcd66c695 [CPU] Unify oc block to optimize peak memory. (#19575) 2023-09-21 09:54:55 +04:00
Oleg Pipikin 69e9124eb7 Refactor ConvolutionBackpropDataLayerTest, ConvolutionLayerTest, DeformableConvolutionLayerTest (#19810) 
* Refactor ConvolutionBackpropDataLayerTest

* Refactor ConvolutionLayerTest

* Refactor DeformableConvolutionLayerTest

* Apply comments

* Apply comments

* Fix
 2023-09-21 00:50:52 +04:00
Evgenya Nugmanova c1a8380052 Symbolic shape inference and graph optimizations (#19392) 
* Symbolic shape inference and graph optimizations
- Prepares a place in CommonOptimizations pipeline for symbolic optimizations
- Introduces symbolic propagation and symbolic optimizations for ChainedMaximum, NopBroadcast and shape sub-graph optimization
- Introduces utility runtime info for TableOfEquivalence passing and disabling of value invalidation during shape inference

* Executes NgramFusion in a symbolic environment. Relaxes Ngram fusion pattern utilizing symbolic knowledge

* Remove debug model visualization

* rt_info copying to new Add operation

* Fix visualization and place validation in nicer place in symbolic transformation

* Fix Slice operation not to propagate labels if input and output dimension is fully dynamic

* Covering Vladislav comments

* Replace value invalidation followed by validation to revalidation since it does the same thing

* Adding back invalidation of cached values to Symbolic Propagation pass

* Fix StridedSlice label propagation. Code style

* Update src/common/transformations/tests/symbolic_transformations/nop_broadcast.cpp
 2023-09-20 18:00:07 +04:00
Aleksandr Voron 8558476047 [CPU] [ARM] Enable SoftMax SLT tests on ARM (#19823) 2023-09-20 17:57:34 +04:00
Fang Xu 228ea44743 [CPU] Use omp section instead of task in UpdateNodes logic (#19831) 2023-09-20 17:47:48 +04:00
Ilya Lavrenov e5a3500174 Fixed compilation on macOS 14 with new core development tools (#19946) 2023-09-19 17:14:28 +04:00
Oleg Pipikin 57df7a44b7 Refactor CTCGreedyDecoderSeqLenLayerTest, GreedyDecoderLayerTest, CTCLossLayerTest (#19842) 
* Refactor CTCGreedyDecoderSeqLenLayerTest

* Refactor usingGreedyDecoderLayerTest

* Refactor CTCLossLayerTest
 2023-09-19 15:03:06 +02:00
Vitaliy Urusovskij ca344aea54 TensorIteratorTest to API2.0 (#19869) 
* `TensorIteratorTest` to API2.0

* Port `TensorIteratorBody` to ov::test::utils
 2023-09-19 15:46:13 +04:00
Oleg Pipikin 068cd4473d Refactor AdaPool, BatchToSpace, and BatchNorm shared tests (#19597) 
* Refactor AdaPool, BatchToSpace, and BatchNorm shared tests
 2023-09-19 09:40:29 +02:00
Chenhu Wang e961ce307b [CPU] Eliminate dependency for emitters tails process (#19527) 2023-09-19 10:41:38 +04:00
Zhang Yi 9c4bc1cc2b [CPU] Fix OMP thread count for MLAS ThreadPool initialization (#19731) 2023-09-19 10:30:33 +04:00
Ilya Lavrenov 54609e7b72 Removed FixRtInfo pass (#16870) 
* Removed FixRtInfo pass

* Removed FixRtInfo pass

* Fixed macOS compilation
 2023-09-19 00:07:59 +04:00
Ilya Lavrenov 253ca8c746 Fixed GPU plugin static build with oneDNN (#19811) 
* Fixed GPU plugin static build with oneDNN

* Fixed issue with absolute paths inside installed OpenVINOConfig.cmake

* Fixed absolute paths in installed OpenVINOConfig.cmake

* Changed components for installation
 2023-09-18 13:58:20 +04:00
mei, yang e9aaf9aa1b [CPU] Fix Interpolate impl bug and add related test case (#19783) 2023-09-18 12:39:11 +04:00
Ilya Lavrenov db395155b3 Removed warnings suppressions for extra modukes (#16479) 2023-09-15 02:53:32 +00:00
Ilya Lavrenov ba67db66ae Properly enable CMAKE_COMPILE_WARNING_AS_ERROR (#19828) 
* Properly enable CMAKE_COMPILE_WARNING_AS_ERROR_DEFAULT

* Properly enable CMAKE_COMPILE_WARNING_AS_ERROR
 2023-09-15 01:20:00 +04:00
Egor Duplenskii 73d8843da8 [CPU] Correct ConvertFqRnnToQuantizeRnn transformation (#19850) 
by ensuring convert is placed after u8/i8 output
 2023-09-14 18:04:58 +00:00
Ilya Lavrenov 35a0706dff Replaced several cmake utilities with new ov_ prefix (#19819) 
* Replaced several cmake utilities with new ov_ prefix

* Replaced several cmake utilities with new ov_ prefix
 2023-09-14 16:22:50 +04:00
Edward ShogulinandKarol Blaszczak 16adb01810 [LPT] SpaceToBatch & BatchToSpace implementation (#19660) 
* [LPT] SpaceToBatch & BatchToSpace implementation

* Update docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step3_main.md

* comments: fixes & refactoring

* rebase fix

* Update docs/IE_PLUGIN_DG/plugin_transformation_pipeline/low_precision_transformations/pipeline/step3_main.md

* rebase fix

---------

Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com>
 2023-09-14 08:16:04 +01:00
Ilya ChuraevandIlya Lavrenov 4df4ea9b31 Move ngraph function to new api (#19728) 
* Moved ngraphFunctions to new API

* Fixed code style

* Fixed build function

* Fixed cpu unit tests

* Fixed code style

* Fixed transformation tests

* Fixed code style

* Fixed build

* Fixed LP tests

* Fixed build all for macOS

* Fixed more issues

* Fixed some func tests

* Try to fix CPU tests

* Revert incorrect change

* Try to fix tests

* Fixed merge conflicts

* Remove redundant headers

* Update src/tests/ngraph_helpers/ngraph_functions/src/non_max_suppression.cpp

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
 2023-09-14 10:57:23 +04:00
Oleg Pipikin f744869551 Refactor BroadcastLayerTest and GRUSequenceTest (#19486) 
* Refactor GRUSequenceTest

* Refactor BroadcastLayerTest

* Temporary disable GRUSequenceTest
 2023-09-13 19:18:56 +02:00
Ivan Tikhonov d0213301a5 Transformations: API 2.0 transition part 3 for LPT transformations (#19610) 
* lpt transformations: transition to api 2.0, ngraph -> openvino

* use ov namespace for lpt transformations

* fix low_precision usings

* includes refactoring

* delete RecurrentGraphRewrite and RecurrentMatcher as unused classes

* use ov header for itt; delete the disabled test

* delete the unused function

* suppress doxygen warning

* fix link in the documentation
 2023-09-13 12:30:31 +00:00
Vitaliy Urusovskij 972bb73298 TileLayerTest to API2.0 (#19770) 
* `TileLayerTest` to API2.0

* Remove `ngraph::` use

* Fix cpplint
 2023-09-13 12:10:02 +00:00
Pawel Raasz f3d4665f7b Api 2.0/migrate shape inference test to new api (#19665) 
* Migrate static shape inference test to new API

* Use new API in CPU custom shape inference tests

* Rename range shape inference test file
 2023-09-12 15:15:04 +04:00
Oleg Pipikin 0675d9fd8b Refactor ComparisonLayerTest, ClampLayerTest (#19681) 
* Refactor ClampLayerTest

* Refactor ComparisonLayerTest
 2023-09-12 11:46:30 +02:00
Ilya Lavrenov 58546b2ecb Use ov_mark_target_as_cc in CPU oneDNN (#19766) 2023-09-12 12:20:49 +04:00
Vitaliy Urusovskij 7bb22b43b3 TopKLayerTest to API2.0 (#19738) 2023-09-12 12:02:01 +04:00
Ilya Lavrenov 6a1d680f90 Partially fixed github issue 18274 (#19758) 2023-09-12 07:34:45 +04:00
Nikolay Shchegolev 497f42bd82 Post commit fix for #19521. (#19741) 2023-09-12 01:31:57 +04:00
Ilya Lavrenov a1cc5e6692 Resolve ARM CPU plugin illegal instruction on older Linux systems (like Ubuntu 18.04) (#19717) 2023-09-11 17:15:42 +04:00
Vitaliy Urusovskij 847eb3f4f1 TransposeLayerTest to API2.0 (#19671) 2023-09-11 16:15:53 +04:00
Vitaliy Urusovskij fb59d0eb36 VariadicSplitLayerTest refactoring to API2.0 (#19648) 2023-09-11 14:55:36 +04:00
Nikolay Shchegolev f0421d94a6 [CPU] Scalar is passed as a tensor with shape [1] in custom op evaluate. (#19521) 
[CPU] Scalar is passed as a tensor with shape [1] in custom op evaluate.
 2023-09-08 19:40:44 +04:00
Ivan Novoselov 8124f5c435 Snippets shape inference infrastructure (#18887) 2023-09-08 12:58:21 +04:00