* [GNA] Move definition of GNAInferRequest class to source file
* [GNA] Fix handling exception for infer() and wait() gna_infer_request
* fixed handling of exceptions for wait and infer gna_infer_request
* fixed closing ongoing subrequest of divided model in case of exception on
on enqueueing request or waiting for end of request.
* [GNA] Apply review comments, Removed exceptions from enqueue and wait for Worker
* changed API of request worker to return:
* erorr in case wait failed instead of
throw,
* return true/false for enqueue instead of exception for failure case
* [GNA] Fix review commentd related to gna_infer_request and worker_impl
* [GNA] Add tests for GANInferRequest
* added tests for exception handling of Infer, Wait, StartAsync methods of
GNAInferRequest class.
* [GNA] Added final fixes for review comments.
* [GNA] Small Improvement in PWLApproximation and update of unit test for it.
* added template method for floating pointcomparision
* added new tests for PWLApproximation
* [GNA] Refactor numerical_utils and usage of its method in plugin
* refactor numerical utils use template methods for conversion and comparision
* Review tile for shape inference:
- propagate labels and dimension
- template implementation of shape inference
- if repeats is not-positive output dim is always 0
* Refactor Tile shape inference
* Review preserve partial values and labels
* Add support to evaluate bounds from repeats input
* Remove not used code
* Fixed shape infer dep for blocked format
* Set preferred format for shape_of to be made from input rank
- ShapeOf should get the original output layout of the previous node, which is not reorderd.
* Review dims and labels propagation for logical not
* Review dims and labels propagation
for logical and, or, xor
* Remove duplicated tests
* Expand logical ops tests by numpy broadcast
and inputs order
* Review template shape infer of logical ops
- add static shape inference test
- add default ctor test
* Default ctor test for LogicalNot op
* updated to get ockable memory for device inputs
* gpuFuncTest to set f64 scalar tensor
* aligned type names
* updated to get lockable memory for some specific precisions
* add a function to get a supported precision
* Review labels and dimension propagation
- check dimensions propagation with partial dimension
- extend testing for labels an dimensions propagation
* Shape inference support bounds evaluation
on begin, end inputs
* Review static shape inference
* Move sequence generator to dev API
to avoid create unnecessary library dependency
* Fix windows build issue
* Use strided slice in scatter update test
of partial value propagation
* Remove unused constant from test
* Fix strided dim calculation
* Fix clip lb,ub for strided dim calculation
* Use op strides if absent in input_shapes
* Move back SeqGen to shape inference
Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
* Review einsum shape and label propagation
- extend type_prop test by check labels and einsum properties
* Review template implementation of shape inference
- rename StaticShape inference test file
- use common fixture and rename test cases
- add default ctor test
- add equation string setter
* Fix einsum label propagation check
due to improvement of dimensions and labels merge
* Remove BWDCMP_RTTI_DEFINITION from einsum op
Co-authored-by: Evgenya Stepyreva <evgenya.stepyreva@intel.com>
