Commit Graph

699 Commits

Author SHA1 Message Date
Alexandra Sidorova
b01cc9297f [CPU][Tests] Removed Swish ref primitive (#17597) 2023-05-18 13:04:47 +00:00
Egor Duplenskii
20cddb3a6e [CPU][TESTS] Separate custom single layer tests per architecture (#17520) 2023-05-18 11:02:39 +04:00
Egor Duplenskii
1e878b6a01 [CPU] Reorganize development documentation (#16708) 2023-05-17 17:29:47 +04:00
Nikolay Shchegolev
a6b043b1ca [Core] Conv reference optimization. (#17303) 2023-05-17 15:54:33 +04:00
Nesterov Alexander
96a80ffc3d [ARM CPU] Enable swish (#17542) 2023-05-17 10:20:42 +04:00
Egor Duplenskii
84b9262aea [CPU] Get rid of shouldTryBrgconv flag (#17539)
No code logic changed overall
2023-05-17 10:17:36 +04:00
Ilya Lavrenov
04171416f4 Put mingw on gcc code path (#16101)
* Supported mingw-w64

* Supported mingw-w64

* Supported mingw-w64
2023-05-17 00:47:55 +04:00
Pawel Raasz
78bb0c4837 [ShapeInfer] Review experimental detectron prior grid generator class for shape inference aspects (#17474)
* Review detectron prior grid generator for:
- Check interval shapes and label propagation.
- Check template implementation of shape infer.
- Add update or correct unit test for static and dynamic shapes.

* Remove ngraph namespace in reviewed op

* Use detectron validation util to check inputs
in all related detectrons operators

* Relax first dim of feat map and im data check

* Fix test after dimension validation update

* Fix typo in detectron util file name
2023-05-16 14:58:00 +04:00
Pawel Raasz
5ff0081489 [ShapeInfer] Review detectron ROI feature extractor shape inference aspects (#17532)
* Review detectron ROI feature extractor shape infer
- Check Interval dimension and label propagation.
- Check template implementation of shape_infer.
- Add/Update unit test for static and dynamic shapes.
- Remove `ngraph` namespace from reviewed operator.

* Fix compilation issues
2023-05-16 14:57:29 +04:00
Egor Duplenskii
ab119faa0b [CPU] Use switch case to ensure to_string methods are complete (#17522)
And add missing cases
Compiler can warn about missed enum entry in switch case
2023-05-15 15:57:13 +00:00
Edward Shogulin
3525cae612 [LPT] tests rename for nightly (#17425) 2023-05-15 18:41:54 +04:00
Egor Duplenskii
fe95ed27b1 [CPU][ARM] Enable oneDNN acl fullyconnected (inner_product) (#17331) 2023-05-15 17:50:28 +04:00
Gorokhov Dmitriy
dab190b988 [CPU] Restore OneDNN InnerProduct primitive os_block computation behavior (#17495) 2023-05-12 15:50:04 +04:00
Mateusz Mikolajczyk
fe1d081e44 [CPU] Add missing check for special zero (#17490) 2023-05-12 09:49:32 +04:00
Pawel Raasz
c13423e2ca Introduce data accessor function for infer in IStaticShapeInfer (#15574)
* Tensor accessor for shape inference
- as functor for getting data from tensor vector or map.
- as lambda in GPU plugin on tile op

* Make tensor data adapter pure virtual
- function accessor to data returns pointer to interface

* Refactor tensor data accessor and adapter

* Extract memory adapter make it GPU graph internal
- can't be part of GPU runtime memory core dev API not visible there

* Expand IStaticShapeInfer by port map
- update factory map for new infer interface with port map information
- add bit util to generate bit mask use it in PortMask

* Pass tensor accessor as reference not fun object
- Add cldnn data adapter and accessor
- Reduce dynamic allocations in data accessors

* Fix compilation issues

* Use ov::Tensor for data accessor
- remove data adapters are they not required

* Update comments

* Fix build issues

* Fix tile shape infer test

* Add empty null tensor accessor as specialization

* Apply style formatting

* Move data accessor from dev API to shape inference

* Fix linking issues
2023-05-11 13:30:30 +04:00
Pawel Raasz
0a26372a4f Review experimental detectron detection output for shape inference aspects (#17407)
* Review detectron detection output for:
- Interval shapes and label propagation.
- Check template implementation of shape_infer.
- Add/update unit test for static and dynamic shapes.

* Remove ngraph namespace from experimental
detectron detection output
2023-05-09 14:08:23 +03:00
Pawel Raasz
94a7342548 Review roi align class for shape inference aspects (#17154)
* Review ROIAlign for shape inference aspects:
- Check interval shape and label propagation
- Check template implementation of shape_infer
- Add unit test for static and dynamic shapes

* Update ROIAlign::evaluate to use ov::Tensor
- remove ngraph namespace from op where possible
2023-05-08 10:42:55 +04:00
Pawel Raasz
f3fa1a5f96 Review prior box and clustered class for shape inference aspects (#17382)
* Review PriorBox op for shape inference aspects:
- check interval shape and label propagation
- check preserve interval values and labels on inputs
- add template shape_infer function
- add/update test for dynamic and static shape inference

* Update PriorBox evaluate to use ov::Tensor
- remove ngraph namespace form PriorBox where possible

* Review PriorBoxClustered for shape infer aspects
- check interval dimension and label propagation
- check preserve partial values and labels on inputs
- add template implementation of shape_infer
- add/update test for static and dynamic shapes

* Use correct shape for PriorBox transformation test

* PriorBoxClustered evaluate use ov::Tensor
Remove ngraph namespace from op where possible

* Fix compilation issues
2023-05-08 10:40:07 +04:00
Pawel Raasz
8d81223a28 Review experimental detectron topk rois for shape inference aspects (#17018)
* Review experimental detectron topk rois for:
- interval shape and label propagation
- template implementation of shape_infer
- expand unit test fot partial and static shapes

* Fix build issues
2023-05-08 10:34:56 +04:00
Pawel Raasz
f93c8dda78 Review detectron generate proposal for: (#17103)
- interval shape propagation
- label propagation
- template implementation of shape_infer
- add more unit tests for dynamic and static shapes
2023-05-08 10:34:37 +04:00
Edward Shogulin
9c3186b243 [LPT] Concat: different branch precisions support (#17330)
* [LPT] Concat: different branch precisions support
2023-05-07 11:38:32 +01:00
Chen Xu
4fd42cdd62 [CPU] Fix kernel precision mismatch in Reduce node (#17371)
* [CPU] Fix kernel precision mismatch in Reduce node

* Apply review comments
2023-05-05 14:39:02 +02:00
Nikolay Shchegolev
2f9fe67691 [CPU] Fix for SpaceToBatch dead loop. (#17352) 2023-05-04 18:24:47 +02:00
Yuan Hu
88c154953e [CPU] fix coverity issue in multiclass and a bug in matrix_nms (#17180)
* fix coverity issue in multiclass_nms

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix issue in matrix_nms.cpp

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

---------

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
2023-05-04 10:34:56 +02:00
Sofya Balandina
bda41b7321 [ie tests] Move CheckOperationInProfilingInfo to common part (#17282) 2023-05-03 14:42:03 +04:00
Sofya Balandina
96c5cd16d5 [conformance] Rebalance props tests (#17124) 2023-05-03 14:22:43 +04:00
Egor Duplenskii
f22aaaf239 [CPU] Clean up primitive desc creation in prepareParams (#16739) 2023-05-03 09:51:03 +02:00
Yuan Hu
82ec92dd98 [CPU][coverity] fix coverity issue in concat and graph_optimizer (#17191)
* fix coverity issue in concat

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix coverity issue in graph_optimizer.cpp

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix review issue

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

* fix the mistaken that there are two throw

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>

---------

Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
2023-05-02 12:27:05 +02:00
Ilya Lavrenov
0374a65fad Fixed cpplint for arm (#17296) 2023-04-29 01:31:42 +04:00
Nesterov Alexander
f4d78ff9d8 [ARM CPU] Fix AVGPool tests (#17272)
* fix interpolate bug

* fix ceil part in avgpool

* Update acl_interpolate.cpp

* Update acl_interpolate.cpp

* Update acl_pooling.cpp

* Update acl_pooling.cpp
2023-04-28 23:44:57 +04:00
Egor Duplenskii
058c07008c [CPU][ARM][DEBUG_CAPS] Fix cross-compilation issue (#17285) 2023-04-28 16:02:23 +00:00
Egor Duplenskii
25ed941691 [CPU] Add CPU plugin specific properties to supported_properties list (#16720)
* [CPU] Add CPU plugin specific properties to supported_properties list

* Add tests and move cpu specific tests from shared_tests_instances

---------

Co-authored-by: Anton Voronov <anton.voronov@intel.com>
2023-04-28 19:09:38 +04:00
Vladislav Golubev
4ffde4c786 [CPU] Deconv dummy shape generation fix (#17210)
* [CPU] Deconv dummy shape generation fix

* Added test cases

* genaral padding generation solution

* Review comments applied
2023-04-28 17:02:34 +02:00
Sofya Balandina
9248ecadee [apiConformance] Rebalance ImportExport and LifeTime tests (#17129) 2023-04-28 16:19:20 +04:00
Chenhu Wang
43842e2486 [CPU] proofreading correction (#17246) 2023-04-28 12:13:30 +02:00
Nikolay Shchegolev
22bb3af7df [CPU] Disable test case with sporadic failure. (#17256) 2023-04-27 14:06:33 +04:00
Yuan Hu
cecd0e75a6 coverity Uninitialized scalar variable (#17182)
Signed-off-by: Hu Yuan2 <yuan2.hu@intel.com>
2023-04-26 23:49:21 +04:00
Nesterov Alexander
dbaa1f0c0d [ARM CPU] Fix interpolate tests (#17171)
* fix interpolate bug

* fix interpolate bug - some tests

* fix interpolate bug - change init

* fix interpolate bug - shape fix

* fix interpolate bug - shape fix 2

* fix interpolate bug - add assert
2023-04-26 23:28:02 +04:00
Egor Duplenskii
f1bc402b38 [CPU] Pick fix for oneDNN v3.1 release (#17144) 2023-04-26 17:44:36 +04:00
Nikolay Shchegolev
c8ac7c9b82 [CPU] Infer_request crashes for SpaceToBatch operation. (#16974)
* [CPU] Infer_request crashes for SpaceToBatch operation.

* Fixes as per comments.

* Fixes as per comments 2.
2023-04-26 17:39:54 +04:00
Edward Shogulin
14a14ecd76 [LPT] Precision restriction customization extending: tests (#17196)
* [LPT] Precision restriction customization extending

* comments fix: refactoring

* [LPT] Precision restriction customization extending: tests
2023-04-26 16:53:04 +04:00
Ilya Lavrenov
cfbfa18f34 Fixed WASM build in update docker container / new dependencies (#17224) 2023-04-26 16:32:36 +04:00
Edward Shogulin
e593cf8545 [LPT] Precision restriction customization extending (#17147)
* [LPT] Precision restriction customization extending

* comments fix: refactoring
2023-04-26 13:29:09 +01:00
Alexandra Sidorova
a032d67cc7 [CPU] Fixed enforcebf16 condition for transformation pipeline (#17157)
* [CPU] Fixed enforcebf16 condition for transformation pipeline

* [Snippets][CPU][Tests] Added test with bf16
2023-04-26 16:13:01 +04:00
Ilya Lavrenov
da91b33763 ARM32 ACL kernels in oneDNN (#17142)
* ARM32 ACL kernels in oneDNN

* Fixed review comments

* Fixed ERF

* Disabled several eltwise tests on arm32
2023-04-26 13:50:10 +04:00
Luwei Zhou
6cb6c5958a Fix the SDL issues. (#17107)
* Fix the SDL issues.

* Applied review comments.

* Update Slice test case to test none-const axis input.
2023-04-26 13:35:36 +04:00
Chenhu Wang
737864bdc7 [CPU] layout alignment to improve perf for interpolate pillow modes (#17079)
* infer planar layout with [1,2] axis as nhwc layout pass and kernel

* leftover comments apply

* comment apply
2023-04-26 11:33:17 +02:00
Mateusz Tabaka
da4316845f ConvMulFusion - handle ConvolutionBackpropData with 3 inputs (#17145)
* ConvMulFusion - handle ConvolutionBackpropData with 3 inputs

Ticket: 98769

* add using

* use compare functions
2023-04-26 11:37:31 +04:00
Egor Duplenskii
dabd5ee412 [CPU][TESTS] Fix cmake test dependencies (#17202)
Co-authored-by: Maksim Doronin <maksim.doronin@intel.com>
2023-04-26 01:17:12 +04:00
Ilya Lavrenov
57d4ca27e6 Revert "Proper ACL version detection (#17152)" (#17206)
This reverts commit 1aec450fc6.
2023-04-25 17:36:18 +04:00