* faster large data loading by double buffering
* added get_allocating_order() that is cached for faster loading
* added offset usm memory copy tests
* removed negative_same_names_within_different_networks_cache
* replaced get_processing_order() with processing_order
* cldnn::program serialization
* fixed to set a stream in a outputbuffer
* removed unnecessary comments
* replaced emplace_back with push_back
* updated bool vector serializer
* fixed several bugs
* removed m_model from compiled_model
* fixed streams_test for model caching
* updated mutable_data handling logic
* added a new API SetUpdateDispatchDataFunc
* updated to serialize weights_reorder_param
* added functional tests for dynamic model caching
* renamed to GetUpdateDispatchDataFunc
* added dynamic model caching tests
* updated to enqueue only fc for async build
* updated use_async_compilation(), make_task_executor_config() and disabled gemm_onednn.impl_replacement_with_cldnn
* added _num_async_build_threads
* added gemm to the async compliation targets
* enable memory reuse for dynamic models
* updated to return dependant events for the shape_of primitive
* fixed memory_pool.release_memory()
* fixed a lint error
* fixed missing default value
* updated to use reset flag for dynamic models
* changed to use is_dynamic_output_layout instead of is_dynamic
* updated to use get_internal_params instread of buffer_ptr
* added a memory reuse test for dynamic models
* primitive serialization
* updated primitive::desc() to use impl_param instead of program_node
* added hash caching unit tests
* added missed calls to save and load of parent
* updated copyright year
* deserialization of dynamic batch
* updated multi stream tests
* added unit tests
* updated cache dir name
* resolved type conversion warning
* removed teardown()
* added const
* updated to allocate memory in order of size while deserializing
* fix windows build error
* updated to check dependencies between not connected nodes
* IR serialization for dynamic models
* added ShapeOf1To3 transformation pass
* fixed input output type mismatch
* removed unnecessary codes
* moved ConvertShapeOf1To3 from common to GPU plugin
* updated copyright year
* fixed build errors
* use kernel caching for dynamic models
* replaced cl_cache with blob
* updated to serialize dims info of input and output
* updated to skip unicode tests in Windows
* gpu model caching unit tests
* added serialization unit tests
* added save and load for quantize primitive_inst
* reduced the range of inputs for Gemm tests
* updated the copyright year
* serialization of proposal
* serialization of anchors in proposal
* added unit tests for gpu proposal
* updated the proposal primitive to be partially serialized
* serialization of primitive class
* removed unnecessary codes
* removed white spaces
* serialization of loop primitive
* serialization of nms
* fixed implicit concat logic in serialization
* added RUN_ALL_MODEL_CACHING_TESTS directive
* fixed an error related with specialization of boolean vector
* serialization of read_value and assign primitives
* lines should be <= 160 characters long
* added unit tests for read_value and assign
* updated to store is_output_evnet in primitive_inst
* removing _is_output_event in typed_primitive_impl_ocl
* added comments for mem_allocated and is_output_null
* [GPU] The draft for integration oneDNN3.0
Initial PR.
1. Support oneDNN3.0 API
2. Use binary_mul post_opt instead of oscale channel-wise mask(2)
3. Disable some post-opt fusing because of no eltwise scale API
eltw(non_linear)+eltw(linear), eltw+sum+eltw(linear)
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Fix hardwish issue in 3.0
hard coded hardswish parameter(2.7) is changed alpha and beta from user's required input.
Signed-off-by: hyunback <hyunback.kim@intel.com>
* clean up code
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Apply code review comment and fix ci issue
Signed-off-by: hyunback <hyunback.kim@intel.com>
* Remove setting dst scale
- ACC issue
- No perf gain compared binary_mul
Signed-off-by: hyunback <hyunback.kim@intel.com>
* gpu serialization for onednn 3.0
* missed changes
* add onednn engine creator when loading model from cache
* fixed to use mem_dep index
* updated to save zero_point_mask for serialization
* fixed onednn fc serialization logic
* updated the logic to check if onednn is enabled
---------
Signed-off-by: hyunback <hyunback.kim@intel.com>
Co-authored-by: hyunback <hyunback.kim@intel.com>
* added missed layout to string conversion
* added an unit test for layout_from_string
* added missing spaces around =
* replaced 95 with SCALAR
* moved layout_to_string into a new file
* changed to parametrized test
* 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
* serialize gpu memory reuse flag
* added c-tor of reduce_impl
* renamed memory_reuse_by_user as can_reuse_memory, and modified memory allocation logic to be simpler
* added gpu driver version and gpu architecture properties
* deleted unnecessary header inclusion
* reverted to use gfx_ver for architecture string
* device_id is added to caching_properties
* kernel_impl_params should be serialized before primitive_impl
* reduced the range of min max values for this test case
* updated to use default get_mem when min max are not specified
* moved serialization include path
* quiet onednn-gpu patching
* save and load kernels in _impls
* changed to use OPENVINO_ASSERT
* fix errata
* updated to follow OpenVINO naming convention
* updated error messages
* binary buffer by vector<uint8_t>
* partial_shape serialization
* removed object_type
* added a new storage class for primitive_type_string and id
* updated to throw an exception when _node is null in build_deps().
* removed redundant memory_pool clearing
* added a new net_id creator
* newline at eof
* updated CLDNN with GPU
* added cache blob descriptions
* updated output allocation logic in serialization
* added ov::device::architecture in supported properties
* overrided save and load in data_inst and mutable_data_inst
* removed save and load functions in mutable_data
* baseline for serialization unit tests
* added serialization unit tests
* added serialization unit tests
* updated not to execute build_deps when deserialized
* make_data without namespace
* updated to use default layout c-tor
* updated get_unique_net_id()
* updated get_type_id() to a pure virtual method
* updated ov::caching_properties
* added [GPU] tags
* updated network c-tor
* updated unit tests
* 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
* usage of program and program_node are changed to use kernerl_impl_params
* pointer to network is replaced with reference
* moved primitive specific parameters out of kernel_impl_params
* use impl_params instead of program_node in onednn_impl
* relocate params from impl_params to primitive_inst
* added conditional directives around fused_desc_onednn
* removal of unnecessary changes
* node_output is separated from impl_param->output
* cldnn serialization
* read layout from _impl_param instead of node
* changed ref in kernel_impl_param to pointer
* removed serialization utils
* removed serialzation related changes
* restored references in function arguments
* remove trailing spaces
* revert change in bs_x_bsv16
* fix to rebase
* removed references to program_node
* removed member variables in primitive_impl
* removed redundant variables
* removed whithspace at the end of line
* added ctor for updated primitive_impls
* changed init_kernels to require kernels_cache
* removed program_node ref from custom_primitive
* added set_node_params to update the lastest status of program_node
* removed const from get_kernel
Eddy Kim
