e56310999c
[Snippets] TPP FP32 MHA support ( #22210 )
...
### Details:
- *Enable FP32 MHA lowering using TPP backend*
- *This PR is a productization of the [TPP integration
POC](https://github.com/openvinotoolkit/openvino/pull/20956 )*
### Prerequisites:
- https://github.com/openvinotoolkit/openvino/pull/21303
- https://github.com/openvinotoolkit/openvino/pull/21672
Branch to Branch PR in to review the changes before the Prerequisites
are merged: https://github.com/IvanNovoselov/openvino/pull/18
---------
Co-authored-by: egeorgan <evangelos.georganas@intel.com>
2024-04-22 14:52:42 +00:00
5801756fb9
[IE TESTS] Extend behavior tests by shared input for infer request ( #23803 )
...
### Details:
- *Add a test case about shared input*
### Tickets:
- *https://github.com/openvinotoolkit/openvino/issues/23376 *
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-04-03 08:21:08 +00:00
a3b08c86c7
[IE TESTS] Skip Import/Export/QueryModel tests for SW plugin from API Conformance ( #23793 )
...
### Details:
- *Skip some tests based on Import/Export/QueryModel in API conformance*
### Tickets:
- *[136558](https://jira.devtools.intel.com/browse/CVS-136558 )*
2024-04-02 13:20:54 +00:00
db36552920
[CPU] Remove redundant tensor compatibility check from init_tensor ( #23564 )
...
### Details:
- Remove redundant tensor compatibility check from init_tensor
- Add test case for parameter->result tensor sharing.
### Tickets:
- *CVS-135890*
---------
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
Co-authored-by: River.Li <river.li@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-03-29 05:48:53 +00:00
aebf81419b
[ IE TESTS ] Update tensor comparation function according plugin requirments ( #23226 )
...
### Details:
- *Comparation function was changed to compare tensors based on element
comparation*
- *`std::abs(ref_value - plugin_value) <= abs_threshold + rel_threshold
* ref_value`*
- *`abs_threshold ` =
std::max(std::numeric_limits::eps<plugin_element_type>(),
std::numeric_limits::eps<ref_element_type>())*
- *`ref_threshold = eps_by_expected_type()`, which is based on half `bit
length of mantissa`*
### Tickets:
- [CVS-133173](https://jira.devtools.intel.com/browse/CVS-133173 )
- [CVS-135540](https://jira.devtools.intel.com/browse/CVS-135540 )
---------
Co-authored-by: sbalandi <sofya.balandina@intel.com>
2024-03-23 18:08:25 +00:00
791feb469f
[API CONFORMANCE] Modify API conformance suite for SW plugins ( #23557 )
...
### Details:
- *Move some properties from mandatory to optional for sw plugins*
- *...*
### Tickets:
- *[133459](https://jira.devtools.intel.com/browse/CVS-133459 )*
2024-03-22 09:52:25 +00:00
93765bc121
[CPU][ARM] Make f16 precision as default for CNN ( #22839 )
2024-03-19 13:04:39 +00:00
22bd6ff049
[GPU] Refactor ( #23472 )
...
### Details:
- *experimental_detectron_prior_grid_generator*
### Tickets:
- *CSV-131562*
2024-03-15 11:46:26 +00:00
3a4d1ff4dd
enable CMAKE_COMPILE_WARNING_AS_ERROR on windows ( #23267 )
...
### Details:
- *enable CMAKE_COMPILE_WARNING_AS_ERROR on windows*
### Tickets:
- *CVS-120604*
2024-03-15 05:34:54 +00:00
239466ca5d
copyright year update ( #23370 )
...
New PR due to merge
conflicts(https://github.com/openvinotoolkit/openvino/pull/22917 )
Updated the copyright year from 2018-2023 to 2018-2024 in all openvino
files
Ref. to script: CVS-101144
Command used:
```bash
git grep -lz '2018-2023 Intel Corporation' | xargs -0 sed -i '' -e 's/2018-2023 Intel Corporation/2018-2024 Intel Corporation/g'
```
2024-03-14 09:37:02 +00:00
5b7d7c87a8
Get rid of `ov_models` ( #23084 )
2024-03-10 20:25:20 +00:00
b068ea2a33
[Snippets] SoftmaxDecomposition is moved to data flow pipeline ( #21672 )
...
### Details:
- *Control flow pass `SoftmaxDecomposition` removed*
- *Introduced data flow `SoftmaxDecomposition` pass which decomposes
`Softmax` operation to a sequence of `Eltwise` ops + `Reduce` ops*
- *Introduced control flow `ReduceDecomposition` pass which decomposes
Reduce operation to a range of low-level operations on linear IR.
Limitation: only reduction by last dimension is supported*
### Tickets:
- *CVS-112847*
### Prerequisites:
- #21303
PR between branches for review (all the review discussions are there):
[Softmax decomposition moved to data flow
pipeline](https://github.com/v-Golubev/openvino/pull/24#top )
2024-03-08 09:51:06 +00:00
093a2823ae
Fix and enable some tests ( #23087 )
...
### Details:
- Fix and enable some tests
### Tickets:
- [CVS-121228](https://jira.devtools.intel.com/browse/CVS-121228 )
- [CVS-122177](https://jira.devtools.intel.com/browse/CVS-122177 )
- [CVS-122094](https://jira.devtools.intel.com/browse/CVS-122094 )
- [CVS-121709](https://jira.devtools.intel.com/browse/CVS-121709 )
- [CVS-121710](https://jira.devtools.intel.com/browse/CVS-121710 )
- [CVS-121715](https://jira.devtools.intel.com/browse/CVS-121715 )
- [CVS-120329](https://jira.devtools.intel.com/browse/CVS-120329 )
2024-02-28 07:10:13 +00:00
976298c417
[UNICODE] solve windows unicode inconsistent issue ( #23100 )
...
### Details:
- solve windows unicode inconsistent issue
- add more test case
### Tickets:
- Closes https://github.com/openvinotoolkit/openvino/issues/23072
- CVS-128116
2024-02-27 12:32:16 +00:00
b711ed0841
[CONFORMANCE] Fix core_threading test on Template + reusing core in a… ( #22595 )
...
### Details:
- *item1*
- *...*
### Tickets:
- *ticket-id*
---------
Co-authored-by: sbalandi <sofya.balandina@intel.com>
2024-02-27 10:18:10 +00:00
c0908b3f14
Delete `layer_test_utils.hpp` ( #22750 )
...
Co-authored-by: Pavel Durandin <pavel.durandin@intel.com>
2024-02-22 20:50:12 +00:00
1c6e2f5f78
Remove legacy ngraph builders ( #22709 )
...
### Details:
- Remove legacy ngraph builders
- Remove ngraph test utils
### Tickets:
- [CVS-131962](https://jira.devtools.intel.com/browse/CVS-131962 )
2024-02-20 00:23:51 +00:00
11e78848c2
Add func to infer model via template into test utils ( #22760 )
...
### Details:
- Add func to infer model via template into test utils
### Tickets:
- [CVS-131962](https://jira.devtools.intel.com/browse/CVS-131962 )
2024-02-16 11:57:11 +00:00
5150118e0c
[Ref][Core][CPU][Opset14] Inverse Operation ( #22649 )
...
Review of any part is more than welcome!
### Details:
- Add Core for Inverse Operation
- Register Inverse Operation in Python API
- Add Reference implementation for Inverse - LU decomposition with
partial pivoting
- Add CPU implementation for Inverse - Parallel LU decomposition with
partial pivoting
- Add tests - Reference, Visitor, Type prop, Shape Inference, Python,
Conformance, CPU, Template
### Tickets:
- 131143
- 131144
- 131145
- 131147
- 131148
2024-02-14 11:58:38 +00:00
94accfbf0f
[Op][String][Ref] Extend Concat op reference to support string type ( #22686 )
...
### Details:
- [Op][String][Ref] Extend Concat op evaluate and reference to support
string type
- Enablement of CPU fallback to the Concat reference implementation
### Tickets:
- 131838
2024-02-09 14:25:50 +00:00
c96c6e316c
Inference Engine API 1.0 leftovers ( #22667 )
...
### Details:
- Includes https://github.com/openvinotoolkit/openvino/pull/22653
---------
Co-authored-by: Oleg Pipikin <oleg.pipikin@intel.com>
2024-02-08 09:04:49 +00:00
cf76d233a8
Remove ie api ( #22666 )
...
### Details:
- Remove ie api
### Tickets:
- [CVS-131687](https://jira.devtools.intel.com/browse/CVS-131687 )
2024-02-07 17:22:47 +00:00
8f232278e3
Cleaning and refactoring test utils ( #22653 )
...
### Details:
- Cleaning and refactoring test utils
### Tickets:
- [CVS-111359](https://jira.devtools.intel.com/browse/CVS-111359 )
2024-02-07 03:53:46 +00:00
56719acac5
[GPU] Resolved function test issue. ( #22648 )
...
### Tickets:
- *129728*
---------
Signed-off-by: hyunback <hyunback.kim@intel.com>
2024-02-07 03:36:00 +00:00
a2818110cc
[Op][Ref][CPU] Extend Gather op with String support ( #22465 )
...
### Details:
- Extend Gather op with String support for data input
(agreed to do it within the same op version, existing reference
implementation is common for GatherBase and ready to handle strings, ref
changes are not needed, just evaluate supported types updated)
- Enable fallback to the reference implementation from CPU plugin
- Extend Template and CPU plugin operator tests with string validation
(most of the changes are tests related)
### Tickets:
- 130688
2024-02-06 06:00:39 +00:00
abc2899df8
Add test instantiations for template plugin ( #22627 )
...
### Details:
- Add test instantiations for template plugin
### Tickets:
- [CVS-130342](https://jira.devtools.intel.com/browse/CVS-130342 )
2024-02-05 08:31:34 +00:00
2d9467d247
Delete `single_layer/` folder ( #21990 )
2024-02-02 18:39:10 +00:00
cdb975c665
[CPU] Run with FP32 when compress fp16 is disabled in Ngraph. ( #21440 )
...
* [CPU] Run with FP32 on the accuracy aware node.
* Applied review comments.
* Apply review comments.
* Update.
* Add debuglogs to print lowering precision RTinfo list for easier debuggging.
* Update RoPE RT info.
* Applied review comments.
* Update.
* Update.
* Applied review comment.
* Applied review comments.
2024-02-02 05:49:52 +00:00
9bdd36be9c
[Core] Remove ngraph env_util.hpp graph_util.hpp util.hpp ( #22540 )
...
* Delete env_util
* Remove ngraph graph_util (initial)
TODO: remove ngraph/graph_util.hpp and remains from graph_util.cpp
* Remove ngraph util (initial)
TODO: remove ngraph/util.hpp and remains from util.cpp
* Remove ngraph util (onnx fe not finished)
TODO: remove ngraph/util.hpp and util.cpp.
* Use OV in test helpers
* Remove ngraph graph_util
* [ONNX FE] Rename onnx_import::Node class
to ONNX_Node temporarily (to hide conflicts with missing Node from ::ngraph::)
* Remove ngraph graph_util from onnx fe
* [ONNX FE] Rename onnx_import::ONNX_Node class back to Node
* Delete ngraph util
* Update copyright notes
* Update copyright notes
* Fix style
* Fix gpu plugin
* Remove useless macros
---------
Co-authored-by: Pavel Durandin <pavel.durandin@intel.com>
2024-02-02 02:53:20 +00:00
42ea6068f2
Clean `LayerTestsUtils::LayerTestsCommon` ( #22309 )
...
* Delete `LayerTestsCommon::CalculateRefs()` impl
* Delete `ConvertRefsParams()`
* Delete `LayerTestsCommon::Validate()` impl
* Delete `LayerTestsUtils::getRuntimePrecision*()`
* Delete `LayerTestsCommon::Serialize()`
* Delete `LayerTestsCommon::QueryNetwork()`
2024-02-01 13:45:00 +00:00
3b2db3b9a0
add topk_v11 ( #22575 )
2024-02-01 08:17:19 +00:00
2e6d061583
[CPU] [LPT] CPU limitation ( #22522 )
...
* [CPU] [LPT] CPU limitation
* tests
* comments fixes
* tests fix
* tests refactoring
2024-01-31 22:27:54 +00:00
4e302aafca
Move ImportModelWithNullContext test to core tests ( #22511 )
...
* Move ImportModelWithNullContext test to core tests
* Apply comments
2024-01-31 18:14:06 +00:00
e40e5b809c
[api conformance] Fix extra crash in report ( #22468 )
...
Co-authored-by: Irina Efode <irina.efode@intel.com>
2024-01-31 10:23:58 +00:00
92b1e9f1a3
Remove ngraph::AxisSet and ngraph::AxisVector ( #22350 )
2024-01-31 04:02:36 +00:00
b0e507c6c3
Removed runtime::Tensor alias ( #22429 )
...
* Removed AllocatorImpl, runtime::Tensor alias
* Update OMZ
* Updated submodule
2024-01-30 11:34:21 +00:00
97ea693030
[core] Migrate `FactoryRegistry` to API 2.0 ( #22371 )
...
* Migrate `FactoryRegistry` to API 2.0
- remove add custom factory
- remove FactoryAttributeAdapter
* Fix opset name in ONNX FE
* Corrections in include files
* Fix build issues
* Use OpSet in visitor tests instead FactoryRegister
* Integrate `FactoryRegistry` into `OpSet`
* Remove ngraph/factory_adapter.hpp
* Fix auto batch test warning for windows build
2024-01-27 21:51:11 +00:00
a3bcb655de
Delete `behavior/` tests + `codegen.*pp` snippets test ( #22314 )
...
* Delete behavior/
* Delete template `behavior/`
* Remove obsolete `codegen_bert.*pp`
* Port auto_batch behavior tests
2024-01-26 16:34:09 +00:00
e1fcafc165
Remove ngraph/type API ( #22297 )
2024-01-26 11:56:14 +00:00
db24bab90a
Remove ngraph node_input and node_output ( #22392 )
...
* Remove ngraph node_input and node_output
* Fix
* Fix
2024-01-25 22:10:22 +00:00
d45d9f24c1
Get rid of builders.hpp and subgraph_builders.hpp includes ( #21926 )
...
* Get rid of legacy builder headers
* Fix
* Fix
2024-01-25 11:01:37 +04:00
5a4f419f14
Subgraph tests leftovers ( #22241 )
...
* Delete subgraph `basic_lstm.*pp`
* Delete `multiple_connect_split_concat.hpp`
* Delete `parameter_shapeof_result.hpp`
* Delete `reshape_permute_reshape.hpp`
* Delete `transpose_add.hpp`
* Remove `tensor_names.*pp`
2024-01-24 22:30:31 +04:00
9a0538b482
LP Transformation tests move from ngraph to ov namespace ( #22324 )
...
* fix ngraph -> ov
* fix build ngraph -> ov
2024-01-24 19:09:44 +04:00
e5ca6a30ca
[conformanceAPI] Remove outdated test ( #18323 )
...
* [ov_api_conformance] Remove outdated test
* move import export
2024-01-24 13:02:51 +01:00
ac99cc882b
[Remove API] remove ov::clone_model() replace by ov::model:;clone() ( #22283 )
...
* [Remove API] remove ov::clone_model() replace by ov::model:;clone()
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* clean code
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
---------
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
2024-01-23 14:04:49 +01:00
0ccfb6cd0e
Replace ngraph to ov namespace ( #22276 )
...
* Replace ngraph to ov namespace
* Removed headers
2024-01-23 01:36:16 +04:00
c538d0319d
[Core] rearrange pugixml and performance heuristics ( #22234 )
...
* Move performance_heuristics.hpp to openvino folder
* Refactor pugixml::utils
1. move pugixml::util from src/inference to openvino/util
2. move duplicated pugixml::utils implement to opeenvino/util
* Fix build error and rename namespace
1. fix build error caused by library dependency
2. rename openvino::util::pugixml
3. NamingConventionCheck issue
4. Clang format issue
5. smoke_createMockEngineConfigThrows failure due to pugixml exception type
* Use friendly namespace
* Update
* update cmake
* update
2024-01-22 14:47:54 +01:00
d0619edd21
Removed IE and ngraph headers / cmake interfaces from package ( #22203 )
...
* Revert "Revert IE cmake config back"
* Update src/cmake/openvino.cmake
* Fixed for NVIDIA plugin
* Fixed tests compilation
* Use ilya's contrib repo
* Fixes for ONNX Runtime tests
* Use custom nVIDIA repo
* Disable ONNX Runtime
2024-01-19 16:48:27 +04:00
f4fbbb954d
[API 2.0] Add memory_states test cases ( #21627 )
...
* add memory_states test case
* add memory_states.cpp
* fix m_cached_output_names.count(tensor_name) failed
* add inferreq_smoke_VariableState_SetState
* add inferreq_smoke_VariableState_Reset
* add inferreq_smoke_VariableState_2infers_set
* add inferreq_smoke_VariableState_2infers
* fix name style
* Update src/tests/functional/plugin/shared/src/behavior/ov_infer_request/memory_states.cpp
Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
* move SKIP_IF_CURRENT_TEST_IS_DISABLED before std::tie
* Update src/plugins/intel_cpu/tests/functional/shared_tests_instances/behavior/ov_infer_request/memory_states.cpp
Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>
* Update src/tests/functional/plugin/shared/include/behavior/ov_infer_request/memory_states.hpp
Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>
* Update src/tests/functional/plugin/shared/src/behavior/ov_infer_request/memory_states.cpp
Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>
* fix comment
* use vector to replace array
* Update src/tests/functional/plugin/shared/src/behavior/ov_infer_request/memory_states.cpp
Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
* avoid temporary vector creation
* fix element
* fix element
* remove test in arm
---------
Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
Co-authored-by: Vitaliy Urusovskij <vitaliy.urusovskij@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-01-19 15:18:52 +04:00
f05e89ac8a
fix race condition in layout attribute visiting ( #21852 )
...
* fix rc
Signed-off-by: fishbell <bell.song@intel.com>
* enable tests
Signed-off-by: fishbell <bell.song@intel.com>
---------
Signed-off-by: fishbell <bell.song@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
2024-01-19 10:16:00 +04:00
Ivan Novoselov