* gpu graph serialization
* fix to rebase
* onednn_gpu.patch for serialization
* git apply --verbode to --quiet
* functional tests
* removed referece of mas_unpooling.hpp
* git apply --verbose
* add no args ctor for proposal_impl
* changed kernel_cache save/load error messages
* gpu model cacning control env. variable
* fixed nonnull warning
* impl_params are added to save and load
* changed a way to use kernel_impl_params in save and load
* get_arguments_by_idx is added
* setenv is disabled in windows
* added missed part for onednn
* code refactoring based on code review
* fixed to use get_node_output_layout()
* OV_GPU_MODEL_CACHING is changed to OV_GPU_CACHE_MODEL
* reference to node and primitive are removed
* fixed hash of enum class
* restored CanShareContextWith
* serialization of intermediate memory
* fix to rebase
* multiclass_nms serialization
* caching_properties added
* add HybridAware stream setting and core binding
* fix clang format issue
* unified code style, add parameter check
* correct input affinity skip NUMA, modify function name
* remove unnecessary floor
* fix ci compile issue on Mac/windows platform
* modify smoke_SetConfigAffinity test
* modify ov_core_set_and_get_property_enum test, affinity HYBRID_AWARE is changed to NUMA
* remove affinity correcting on this pr
* revert ov_core_test.cpp
* merge function by comments
* fix code style issue
* add custom nstreams setting, remove mutable qualifier
* fix code style issue
* fix some issues according to comments
* modify UpdateHybridCustomThreads
* fix code style issue
* modify comments
* use logic core in phase 2
* modify steams threads setting method
* add custom setting nstreams nthreads
* modify comments
* fix code style issue
* fix threads_per_stream_big is wrong in the some ADL machine which has 6 pcore
* add one condition that custom set nthreads but not set nstreams
* remove the limit to nstreams
* remove the feature in branch p_e_core_phase2_logic
* add comments
* rename num_small_cores to num_small_cores_phys
* fix code style issue
* fix thread number is wrong in corner case on 6Pcore and 10Pcore condition
* fix some condition which nstreams<2
* add check for config._threads_per_stream_big
Co-authored-by: Shen, Wanglei <wanglei.shen@intel.com>
* Blocked layouts support for ExperimentalDetectronGenerateProposalsSingleImage
* fix RHEL 8.2 build
* reduce number of tests
* Added bs_fs_yx_bsv16_fsv32 format
* [PYTHON] CV2 module required only when loading images
* [PYTHON] Update tools/benchmark_tool/openvino/tools/benchmark/utils/inputs_filling.py
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* [PYTHON] Make CV import not global
* [PYTHON] Update format of inputs_filling.py
* [PYTHON] Fix missing newline
* Update tools/benchmark_tool/openvino/tools/benchmark/utils/inputs_filling.py
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
* [BENCHMARK_APP/PYTHON] Introduce exception when module is installed but fails to import
* [SAMPLES/PYTHON] Sporadic access violation fix through checking whether module was cached
Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
* Move GeluFusion into ov namespace
It required to move utils as well.
* Move AddFakeQuantizeFusion into ov namespace
* Move AlignEltwiseInputRanks into ov namespace
* Move BatchToSpaceFusion into ov namespace
* Move BinarizeWeights into ov namespace
* Move BroadcastElementwiseFusion into ov namespace
* Move ClampFusion into ov namespace
* Move Concats and Eliminations into ov namespace
* Move many passes and such into ov namespace
* Move many passes and such into ov namespace
ngraph_ops
op_conversions
* Move control_flow into ov namespace
* Apply style
* Move smart_reshape into ov namespace
* Move opset_conversions into ov namespace
* Move low_precision into ov namespace
* Apply style
* Move fused_names into ov namespace
* Add missing aliases
* Move few passes into ov namespace
ConvertPrecision
FixRtInfo
InitNodeInfo
* Move CommonOptimizations into ov namespace
* Fix convert_precision conflicting namespaces
* Apply code style
* ov-nize Type Relaxed definitions
* Remove useless aliases
bulkly added by script
* Revert opsets
* Address review comments
* Remove NGRAPH_RTTI
* Clean up remains of yet another implicit inclusion
Co-authored-by: Andrei Kochin <andrei.kochin@intel.com>
Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
* Single-layer test:
- support both v8 and v9 in shared test;
- add test for GPU.
* Transformation:
- convert both v8 and v9 to internal operation;
- add transformation to GPU pipeline.
* GPU primitive and CreateOp() for MulticlassNMS operation
* kernel stuff
* add unittests
* Added bs_fs_yx_bsv16_fsv32 format
* add int64 support
Co-authored-by: Mykhailo Hnap <mhnap@lohika.com>
* Set db_api_handler for pushing to new database in timetests
* Change function of pushing to db.
Co-authored-by: Daria Ilina <daria.krupnova@intel.com>
* Handle DT_UNKNOWN as DT_REG during file list-up
Some filesystem does not return dt_type properly. (such as sshfs)
Without this fix, openvino fails to search frontend when mounted on
sshfs.
* style fix
* style fix
* [GPU] Added unit tests for roi polling operations.
* [GPU] Added blocked layouts support for roi_pooling operations
* [GPU] Added single layer tests for roi polling operations.
* [GPU] Fix attach roi pooling impl, remov const from formats and types
* [GPU] Fix roi polling kernel, bilinear pooling operation
* Fix, whenever output_width and output_hight are equal to 1, which cause a dividing to 0.
* Fix, for proper calculation y and x.
Co-authored-by: Mykhailo Hnap <mhnap@lohika.com>
* Add reference implementation for Is ops
* FIx test
* Fix typo
* Remove deprecated
* Fix issues with API switch
* Force cast to float for float16/bfloat16 in ref
* Fix style
* Remove BWDCMP_RTTI
* Remove TensorVector helper check
* Remove evaluate functions
* Disable faling tests due to missing eval
