### Details:
- *Added brgemm blocking support for bf16 and int8 precisions: in this
case blocking loops are shared between BrgemmCopyB and BrgemmCPU nodes*
- *Reduced allocation shapes of input brgemm buffers in case of low
precision*
### Tickets:
- *CVS-115165*
### Details:
- *Now `PortDescriptor` contains `tensor_shape` as `shared_ptr`. It's
needed for the further optimization of `InsertSpecificIterations` (when
each copy of loop iterations has the same shape) and the separate
`LinearIR` for shape inference. It will help to have shape match between
the both `LinearIRs'` instances*
### Tickets:
- *138888*
### Details:
GNU compiler doesn't support
`-fsanitize-blacklist=${OpenVINO_SOURCE_DIR}/tests/asan/ignore.txt` and
doesn't require `-shared-libasan` flags. In this PR configurations for
the ASAN build for Clang and GCC are split.
### Details:
- *add test for thread_local*
- *thread_local may cause memory leak during AppVerifier check*
### Tickets:
- *CVS-129729*
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
### Details:
- *Add ScatterNDUpdate-15 to PyAPI*
- *Parametrize to test both ScatterND versions + add test for reduce
attribute*
### Tickets:
- *111092*
---------
Co-authored-by: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
### Details:
- Register BACKEND_COMPILATION_PARAMS in properties
### Tickets:
- *[EISW-112824](https://jira.devtools.intel.com/browse/EISW-112824)*
The option was added to compiler as part of this ticket. But we also
need this option registered to properties in order to start using it
with single image test
### Details:
- I've aligned the ReduceL2 operation with opset 11, 13, and 18. I have
some doubts about how to implement support for the tensor bfloat16 for
opset 13 and also some doubts about opset 18. I've registered the
function inside the ops_bridge.cpp, created test models, and added them
inside onnx_import.in.cpp.
### Tickets:
- Closes#20560
---------
Co-authored-by: Przemyslaw Wysocki <przemyslaw.wysocki@intel.com>
Co-authored-by: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
### Details:
- Added ROIAlignRotated definition to core
- Refactored tests of ROIAlign shape inference info - to use the same
tests for ROIAlignRotated
### Tickets:
- *CVS-115297*
---------
Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
### Details:
- Generalize `UnsqueezeBroadcastReshapeMatmulFusion` pass for non-const
broadcast's input support
- Update test case for `UnsqueezeBroadcastReshapeMatmulFusion` pass
### Tickets:
- 136386
Dynamic convolution with padding run cldnn NOT onednn. cldnn test run
with onednn and it caused can't find kernel selection issue.
### Details:
- *item1*
- *...*
### Tickets:
- *ticket-id*
Signed-off-by: hyunback <hyunback.kim@intel.com>
### Details:
- *Add links to driver installation guides*
- *Add short context about compiler in driver*
- *Update the list of supported properties*
- *Remove invalid limitations*
### Tickets:
- *E-119403*
### Details:
- *Extended the calls to as_node and as_nodes with the name parameter in
all the opsets.*
- *Added tests for the involved operations.*
### Tickets:
- #24030
- part of
[CVS-133139](https://jira.devtools.intel.com/browse/CVS-133139)
**Details:** Fix model input and output names in case absence of serving
signature. mil-nce model from TF Hub does not have default signature
("serving") so use user names from other signatures to resolve internal
tensor names.
Also, it adds validation for `read_model` scenario.
**Tickets:** 139245, 124401
---------
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
### Details:
- `set_data` only accepts TypedArrays.
- Each entry is a value in one of the supported formats, from 8-bit
integers to 64-bit floating-point numbers.
- Before copying data to Tensor, there is a check if buffers have the
same length and if the element types are the same
- Add helper function `const std::unordered_map<napi_typedarray_type,
ov::element::Type>& get_ov_type()` equivalent to Python APIs `const
std::map<std::string, ov::element::Type>& dtype_to_ov_type();`
### Tickets:
- *128274*
_Dynamic convolutions with explicit padding run planar bfyx format in
clDNN.
But this limitation is only for clDNN NOT oneDNN. Because unexpected
format selection in dynamic convolution, SD1.5 in platform used dpas
always run clDNN and it caused bad performance._
### Tickets:
- *138632*
---------
Signed-off-by: hyunback <hyunback.kim@intel.com>
### Details:
- Send Telemetry info during importing of openvino, required for correct
user count statistic.
Following line will trigger event sending:
import openvino
For Linux event send time:
~0.08016 ms
For Win event send time:
~0.31248 ms
### Tickets:
- 133670
Depends on: https://github.com/huggingface/optimum-intel/pull/648
---------
Co-authored-by: Ekaterina Aidova <ekaterina.aidova@intel.com>
### Details:
Numpy started preparation to release 2.0 version.
It brings many breaking changes listed below.
Align with these changes it's a plan for further development
(CVS-138766), for today we want to secure users against unintentional
installation of 2.x version of numpy with OV.
This PR has to be ported for 2024/1 branch
- Preparing to restrict OV to not use release of Numpy 2.0 which may
introduce many breaking changes including:
- required bump of `pybind` to 2.12+
- API and namespaces clean-ups and deprecations
- behavior changes of keywords such as `copy`
- changes to existing and introduction of new dtypes (such as
`StringDType` and possibility of adding custom ones)
- more can be found here:
https://numpy.org/devdocs/release/2.0.0-notes.html
- and here:
https://numpy.org/devdocs/numpy_2_0_migration_guide.html#numpy-2-migration-guide
### Tickets:
- CVS-138838
---------
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
Oleg Pipikin