Commit Graph

10 Commits

Author SHA1 Message Date
Eddy Kim
f488e6cc49 [GPU] Graph serialization for GPU (#13801)
* 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
2022-11-13 16:39:45 -08:00
Eddy Kim
daec2605e4 [GPU] changing references to pointers for GPU graph serialization (#13559)
* 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
2022-10-29 04:39:51 +03:00
Eddy Kim
b9457b3a31 [GPU] Get rid program_node reference from all primitive_impl classes (#12211)
* 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
2022-08-11 14:14:21 +04:00
Vladimir Paramuzov
3b5cc98b1c [GPU] Replaced shared_ptr with const ref for impl_params (#12399) 2022-08-08 20:55:57 +03:00
Wilson Seok
32182bd3ce [GPU]get data type of conv weights from node.weights() when network is internal (#12232)
* get data type of convolution weights from node.weights() when network is internal

* use only instance.node.weights().get_output_layout().data_type

* fix typo

* add unit test for the case
2022-08-03 03:49:53 +03:00
Taylor Yeonbok Lee
361ca2078d [GPU] Fix get_default_params & choose_impl not to dependent on program_node (#12239)
* Getting rid of dependency from get_default_param for typed_program_node

* Fix bug

* Enable two pathes to call choose_impl / does_possible_impl_exists / does_an_impl_exists to be able to use given layout

* Replaced impl factory API to get kernel_impl_param's pointer

* Update for recently added primitives

* Add and apply optional_layout

* fix kernel_param_impl to be handled as unique_ptr

* Applied review comments

* Fix rebase conflict

* Fix CI error
2022-07-27 14:36:53 +04:00
Vladimir Paramuzov
050e2e518d [GPU] Replaced tensor dims usages with layout methods calls (#10984) 2022-04-05 21:49:34 +03:00
Vladimir Paramuzov
b2110b352c [GPU] Update data structures for conv/pool/deconv params (#9641) 2022-03-19 11:11:07 +03:00
Alexey Suhov
a79830cb55 Update year to 2022 in copyright notice (#9755) 2022-01-19 01:07:49 +03:00
Vladimir Paramuzov
f565e0f854 [GPU] Merge cldnn and plugin code (#8484) 2021-12-27 18:35:01 +03:00