IntenseWebs/openvino
3
0
Fork 0
Code Issues Pull Requests Packages Projects Releases Wiki Activity
11,748 Commits 38 Branches 54 Tags
44cae128cce476ff5381dcc183062d2404a0b53e
Commit Graph

814 Commits

Author SHA1 Message Date
Fang Xu
e478964695 merge loadnetwork and importnetwork for cpu plugin (#18024) 
* merget loadnetwork and importnetwork for cpu plugin

* fix testcase

* remove multithreading config saving

* modify test case

* separate function

* modify function name

* save model_prefer_threads to cache

* remove function encapsulation for config
 2023-07-21 14:02:11 +08:00
Sun Xiaoxia
2dfb537bcb Xiaoxia/add get_socket_id interface based on threading2.0 (#18264) 
* add streams_info_table init in the constructor of config

* add refresh _proc_type_table

* add get_org_proc_type_table

* add numa_node per stream in reserve_available_cpus()

* fix warning

* remove log

* fix code style

* fix gpu test build failed issue, modify debug info

* fix code style

* fix build failed on macos

* fix code style

* select socket in reserve cpu on 2 sockets platform

* fix build failed on macos

* modify numa node selecting in reserve_cpu_by_streams_info

* add test case

* fix code style

* modify test case

* fix core dump

* fix core dumped on pin=NUMA

* fix test failed on macos

* fix reserve cpu is wrong when streams_info_table=[1 1 36] proc_type_table=[36 18 0 18]

* add test case in LinuxCpuReserve

* modify test case

* add test case in cpu_reserve_test

* add cpu_stream_info_test

* modify enum

* fix test failed

* change int to size_t

* remove invalid code, fix running failed on macos

* modify LinuxCpuStreamType test case, move ie_cpu_streams_info.hpp to openvino/runtime/threading/

* fix code sytle

* modify enum name

* add comments in test case

* fix build issue

* change IE_ASSERT to OPENVINO_ASSERT

* fix test failed on macos and windows

* updated test cases due to the cpu mapping is changed

* enable numa_node_id and socket_id in streams_info_table

* fix code style issue

* fix document issue

* add get socket id interface

* fix segment fault on machine enabled socket_id=1 with numactl command

* fix numactl failed on four numa nodes machine

* remove compile warning

* fix numa_node_id=-1

* fix test case failed on macos

* fix test failed on macos

* fix numa_node_id=0 on macos

* Solve conflicts with master branch

* separate test cases for Linux and Mac/Windows

* update code style for windows compiler

* fix comments

* fix code style

* fix code style

* remove _plugin_mutex, fix comments

* fix code style

* fix code style

* add get_num_sockets

* fix cpu reserve issue in latency mode,ANY core on RPL machine

* add cpu reserve test case

---------

Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
 2023-07-20 23:34:21 +08:00
Chenhu Wang
b5b11f3b29 [CPU]Shape agnostic jit kernel for MVN (#17988) 2023-07-20 13:40:37 +00:00
Mateusz Tabaka
fe8b8a96ff Handle sequence ops with non constant W, R, B inputs (#18138) 
* Handle sequence ops with non constant W, R, B inputs

Ticket: CVS-49207

* fix tests

* tests

* fix gna tests

* add include

* change type for seqLenIdx

* rename is_constfoldable to is_on_constant_path

---------

Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com>
 2023-07-20 14:48:41 +04:00
Oleg Pipikin
60a8c2bc7a Extend data_utils to work with ov::Tensor (#18142) 
* Extend data_utils to work with ov::Tensor. Update SplitConcatMemory tests

* Fix1

* Apply comments

* Apply comments 2

* Apply comments 3

* Apply comments 4
 2023-07-20 08:29:47 +00:00
Anton Voronov
60e40843c0 [CPU] f16 constant folding on cpu plug-in side for MatMul only (#18079) 2023-07-20 08:58:46 +04:00
Xuejun Zhai
ba76b45194 [AUTO BATCH PLUGIN] enable api 2.0 for auto batch plugin (#18172) 
* [AUTO BATCH PLUGIN] enable API 2.0 for auto batch plugin

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] disenable auto batch plugin unite test for tmp

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] remove test with ov::auto_batch_timeout(-1), cause the variable is unsigned int

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix compiler error caused by std::atomic_uint32_t

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [Remote Context] fix revew comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix compiler warnings

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix compiler warnings

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix test error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix CI test error in cpu func test case, caused by batched model lost rt info

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix CI build error, caused by unused variable

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] using ov::threading

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] clear code in batched req share buffer with non-batched req

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] clean code & fix format issue

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] clean code & fix format issue

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] add api implementation about get_default_context() & create_context() and remove the test config with AUTO_BATCH_TIMEOUT(-1)

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix gpu test with auto btch failed

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix warning

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix get_default_context() issue

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix using namespace redundancy

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] modify variable naming style

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix CI test error, cause by tensor reference in virtual plugin

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] implement get_profiling()

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] remove get_context() from auto batch compiled model using the interface from parent class

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] implement create_context() & get_default_context for auto batch plugin

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix format issue

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] implement auto batch remote context

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix error after merge with master

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix compiler error caused by update master

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] refact remote context in auto batch plugin

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] add unite test cases for auto batch plugin

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix CI warning caused by unused variable & add unite of remote context

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] add virtual property for get_context() in icompiled_model & implement it in auto batch plugin

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] add ov::loaded_from_cache support

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix error caused by updating with master

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix unite test error

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix conflict

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix error caused by update master

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

* [AUTO BATCH PLUGIN] fix review comments

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>

---------

Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
Signed-off-by: xuejun <xuejun.zhai@intel.com>
 2023-07-20 07:02:45 +04:00
Edward Shogulin
38dec7b8cf [CPU] Fixed zero-point fusion transformation (#18435) 
Proper hanlding for subgraphs where ZP parent node has more than one output port
 2023-07-19 11:30:21 +04:00
Nesterov Alexander
510f578aab [ARM CPU] ACL TBB scheduler (#17445) 2023-07-19 10:01:31 +04:00
Oleg Pipikin
cdef86c366 Move unit and func test utils (#18423) 
* Move unit and func test utils. Rename targets

* Fix1
 2023-07-18 16:23:58 +02:00
Chen Xu
9334ad0790 [CPU] Reduce node supports fp16 precision (#18227) 2023-07-18 12:49:25 +00:00
Pawel Raasz
ff5b56ee07 Improve node validation failure message for shape infer (#18520) 
* Add NODE_SHAPE_INFER_CHECK macro
throws NodeValidationFailure for shape inference

* Use NODE_SHAPE_INFER_CHECK in topk shape inference

* Move description to header file

* export NodeValidationFailure::create function
 2023-07-18 11:41:19 +04:00
Vladislav Golubev
42d2c130c2 [Snippets] ExtractReshapesFromMHA transformation (#18477) 2023-07-17 20:42:18 +02:00
Oleg Pipikin
b211767280 Consolidate common test utils targets (#18385) 
* Consolidate test util targets

* Fix code style

* Fix 1

* Fix code style
 2023-07-17 11:59:13 +00:00
Nesterov Alexander
238c7fa47e [CPU][ARM] Add ACL executor for Transpose (#17322) 
* separate executors + add acl executor fot transpose

* correct axisCast

* update transpose executors list

* update new changes

* enable tests

* fix fortting

* fixed test shapes and transpose generalization

* fixed different signedness error

* size_t usage in loop counters

* undo unwanted changes

* fixed comments

* added i8 and fp32 to blocked x86 tests

* fixed comments

* fixed comments

* extracted general reference executor from PermuteKernel

* fix mayiuse in JitTransposeExecutorBuilder::isSupported

* getDescWithType name refactoring

* refactoring

* removed 2nd executor creation in transpose node

* Moved RefOptimizedTranspose to the top

* fixed comments

---------

Co-authored-by: Aleksandr Voron <aleksandr.voron@intel.com>
 2023-07-14 15:16:09 +02:00
Alexandra Sidorova
67c88f4434 [Snippets] Added SplitDimensionM optimization (#18160) 2023-07-14 07:31:24 +02:00
Vitaliy Urusovskij
43ff356f1a Hetero 2.0 (#18429) 
* Hetero 2.0: Implement `hetero::Plugin`

* Fix CMakeLists.txt

* Remove duplicated "itt.hpp"

* Remove extra API method

* Delete `HeteroPlugin::Engine`

* Intregrate `ov::hetero::Plugin` into `HeteroExeNet`

* Use `is_new_api()`

* Add `override` modificator

* Rename `GetDevicePlugins` to `get_device_properties`

* Small fixes

* Fix precommit

* Fix Import/Export

* Fix `import_model()`

* Remove extra lines

* TEMPORARY disable one test

* ClangFormat+Refactoring

* Build fix

* Update `hetero::Configuration` logic

* Update `hetero::Plugin::get_property()`

* Fix

* Changes after code review

* Remove extra comments

* Revert "TEMPORARY disable one test"

This reverts commit 13fa48d8102ec5146e79987835e6f7444e469f7a.

* Small fix

* Refactoring + Fixes

* Add `hetero::Plugin::device_supports_model_caching`

* Replace `device_supports_model_caching` with ICore impl

* Code review changes

* Rework `Configuration`

* Implement `hetero::CompiledModel`

* Fix caching_test

* ClangFormat

* Fix inputs/outputs mapping
After some fix in ICompiledModel, m_inputs != model->inputs,
so mapping was updated to be independent from m_inputs
(same for m_outputs)

* Fix types

* Update `get_runtime_model()`

* Remove `ngraph` and `IE_THROW`

* Implement Hetero Sync/Async Infer Requests

* A lot of changes

* Add `submodels_output_to_input` to import/export

* Implement `get_tensors()`/`set_tensors()`

* Fix `Configuration` ctor

* Skip `SetPreProcessTo` legacy tests for hetero

* Change `Output->Input` logic to `Input->PrevOutput`
because for one output may be several inputs
(map key collision)

* Update `CompiledModel` to use shared_ptr vs *

* Update `CompiledModel`  public/private members

* Names refactoring

* Optimize imports

* Fix properties for `query_model()` call

* Use static objects in `Configuration` methods

* `Configuration` refactoring

* Get `ov::supported_properties` from subdevices

* InferRequest +1 import and fwd declaration

* Update `InferRequest` prof_info, remove extra methods

* Remove `InferRequestDesc`

* Remove `InferRequest::cancel()`

* Update CMakeLists.txt

* Remove extra `catch` in `CompiledModel`

* Replace `InferenceEngine::details::contains()`

* ClangFormat

* Use `const auto&`

* Try to fix types

* Remove `friendly_name` for subgraphs connection

* Remove TODO comment

* Remove `CompiledModel::m_model` as unused

* Polish .hpp files

* Fix size_t serialization in `CompiledModel::export_model()`

* Minor changes

* Move `intersect*` IE utils to anonym namespace

* Use `const auto&`

* Update Hetero `get_profiling_info()`

* Minor changes

* Rename `deviceName` to `device_name`

* Add `hetero::VariableState` in order to hold HW so

* Port internal properties to `ov::internal`

* Add `CompiledModel::set_inputs_and_outputs()`

* Add `OPENVINO_SUPPRESS_DEPRECATED_*`

* Fix CompiledModel `ov::device::properties` issue

* Use `get_device_name()` instead of hardcoded name

* Make `get_profiling_info()` names bwd compatible

* Remove `include` folder

* Remove try/catch from CompiledModel

* Update error message

* `CompiledModel::set_property` throw not implemented
 2023-07-13 23:26:04 +04:00
Nesterov Alexander
6822eb612e [CPU][ARM] Add ACL executor for Convert (#17323) 
* seaprate executors + add acl executor for convert

* update convert

* enabled tests and lot of changes in acl executor

* fixed different signedness comparison

* added expectedPrimitiveType method

* fixed comments

* fp16 WAs

* enable fp16 convert tests

* Revert "enable fp16 convert tests"

This reverts commit 037af672ce.

* Revert "fp16 WAs"

This reverts commit 3db3d4294e.

* fixed comments

* updated expected privitive to ref

* fixed comments

* getDescWithType name refactoring

* GetPtr to getData refactoring

* GetPtr to getData refactoring

---------

Co-authored-by: Aleksandr Voron <aleksandr.voron@intel.com>
 2023-07-13 12:36:49 +02:00
Xiping Yan
a396f07421 [CPU][NGraph]Enable node scatter_nd_update support negative indices. (#17219) 2023-07-12 17:04:44 +04:00
Nikolay Shchegolev
98e88bee52 [CPU] Support Pad-12. (#18407) 2023-07-12 16:59:07 +04:00
Nadezhda Ageeva
3330cd69a7 [GPU] Introduce ov::config_device_id internal property to the new API (#17820) 
* [GPU] Introduce ov::config_device_id internal property to the new API. Fix setting property for specific device

* Introduce ov::internal::supported_properties

* Fix caching tests

* Fix win tests

* Fix Proxy tests

* Replace CONFIG_KEY_INTERNAL(CONFIG_DEVICE_ID) by ov::internal::config_device_id in PROXY plugin

* Review comments
 2023-07-12 10:03:35 +00:00
Chen Xu
7c1949421f [CPU] Fix performance issue for some cases of Reduce node (#11456) 2023-07-12 08:48:38 +00:00
Pawel Raasz
56f51135d4 Grey preprocessing yuv nv12 i420 (#18239) 
* Add two plane YOV to Grey conversion

* Add i420 to grey conversion

* Add yuv to grey conversion for GPU

* Fix cmakes

* Remove static from local function

* Remove opencv dependency from tests

* Put grey_from_yuv_single_plane into namespace
 2023-07-11 12:41:24 +02:00
Nikolay Shchegolev
88703905f4 [CPU] Leftovers for Extension convert I64/U64 to I32. (#16941) 
* [CPU] Leftovers for Extension convert I64/U64 to I32.

* Fix as per comments

* Fixes as per commits 2

* Fixes as per commits 3

* Revert "Fixes as per commits 3"

This reverts commit 84022be66f64faccd96a32da5611db0e5137d049.

* Some fixes

* Test fix
 2023-07-11 11:42:53 +02:00
Maksim Kutakov
900163c484 [CPU] In place memory for dynamic shapes (#17741) 
* InPlace memory direction resolution pass

* Partitioned mem mngr

* Concat reshape pattern has been enabled

* Enhanced in place conflicts detection

* Refactor Concat

* Fix Reshape isExecutable call

* Split node refactoring

* Gather node inPlace special case

* Temporal WA to enable zero copy on Split input

* Process inPlace edges in order

* Fixes

* Remove implicit initialization from Edge::getMemory

* Allow NotAllocated edges call allocate

* extract IMemory interface and implements Memory class.

* IMemory fixes after merge

* Prevent input memory modification

* Minor build fixes

* Fix unittest build

* Fix for variadic concat

* Edge reference fix

* Lock based mem manager

* Return value fix

* Naming refactoring

* Use make_unique

* Split output dims check

* Special processing for empty parts

* Concat null memory fix

* Fix downstream inplace resolution

* Concat allocated edge search fix

* Variadic split clean up tests

* Variadic Split tests update

* Fix make_unique conflict

* Split inPlace tests are back

* Concat inPlace dyn shapes tests

* Add safety checks to isInputTensorAtPortEmpty

* Fix partitioned mem mngr zero size reset

* Introduce Static Memory

* Gather InPlace Tests

* InPlace conflict check in merge Reorder Transpose

* Apply review comments

* fix after rebase

---------

Co-authored-by: jialipen <cecilia.peng@intel.com>
 2023-07-11 10:39:29 +02:00
Katarzyna Mitrus
827fb0234b [Shape Infer] RNN/GRU/LSTM Cell & Sequence - common shape infer and review (#18009) 
* rrn seq base common shape infer init

* Update and add shape infer to all seq rnn based ops

* Use shape_infer in lstm seq core op

* Use shape_infer in rnn seq core op

* Unified shape infer for rnn cell base

* Update and add missing cells shape_infer functions

* Use shpe_infer in rnn_cell

* Update shape_infer map

* shape_infer tests

* Move new shape_infer to TA map

* More tests and shape improvements

* Introduce common base tests

* Fix merge conflict

* Missing setters and default ctor tests

* Use RNNCellBase class instead of template type op

* Update v0 LSTMSequence to use RNNCellBase as parent class

* Style

* V0::LSTMSequence update

* Specify opset in shape infer registry

* Move rank check

* Output vec generation refactor

* Update num_dir_validation

* Tests warining fix

* Test types adjustment

* Commented code cleanup

* Move test helpers to test fixture

* Common default ctor tests for Cell

* Update GRU shape infer tests

* Update LSTM shape infer tests

* Update RNN shape infer tests

* File names update

* Functions renaming

* Cast hidden size in test

* Move v0::LSTMSequence conformance test

---------

Co-authored-by: Pawel Raasz <pawel.raasz@intel.com>
 2023-07-11 12:38:31 +04:00
Oleg Pipikin
d6c0289008 Move common test utils (#18339) 
* Move common test utils

* Apply comments

* Comments 2
 2023-07-10 12:48:24 +00:00
River Li
3286a405be Don't eliminate Transpose when 0 size of order_value (#18130) 
* Don't eliminate Transpose when 0 size of order_value

* Remove invalid test for transpose
 2023-07-10 14:58:02 +04:00
Vladislav Golubev
205de6106b [Snippets] BrgemmEmitter: blocking by K & N dimensions (#18302) 
* KN blocking draft

* some fixes

* IdentifyBuffers temporary hack

* Emitter cleanup

* IdentifyBuffers cleanup

* BrgemmCopyB validation: N_blk is taken from the child BrgemmCPU

* Added blocking parameters to BrgemCPU

* accuracy fixes

* Buffers insertion removed from BrgemmToBrgemmCPU

* Added blocking parameters to BrgemmCopyB

* blocking parameters

* Blocking params configuration removed from brgemm_to_brgemm_cpu transformation

* Introduced a transformation for blocking parameters configuration

* MHA tokenization alligned with blocking matmul requirements

* Alexandra's comments applied

* Alexandra's comments applied: 2nd round

* Ivan's comments applied

* MHA tokenization: removed kernel_buffer_size related heuristics
 2023-07-07 17:44:14 +02:00
Yury Gaydaychuk
33b457b097 [CPU] Fix of coverity issues (#17823) 
* mvn missing else handled

* negative binarization covered

* coverity 1502464

* coverity 1504685, 1504781, 1504786

* rollback regpool diff

* code review
 2023-07-07 15:24:15 +02:00
Luwei Zhou
a3bd0cb4d7 [CPU] oneDNN v3.2 migration (#18094) 
* [WA] Comment the onnx test.

Seems this test error would be a little bigger than expected error.

* Remove the softmax CPU function test filter because onednn merge all
ISAs into one primitive.

* Fix zero point issue.

* Remove wino conv test cases because ONEDNN3.2 does not supported.

* Fix cpu debug log verbose

* Update onednn to squash commit version.

* Applied tolerance threashold for onnx_model_bias_gelu test.

* Restore to fix ICX perf regression.

* Clean  winograd related code.

* Update ONEDNN to support ARM.

* Applied review comments.
 2023-07-07 11:12:02 +02:00
Aleksandr Voron
2b795afc09 fix multi-axis reduce transformation (#18414) 2023-07-07 10:56:09 +04:00
Wanglei Shen
d571ab3a12 enable numa_node_id and socket_id in streams_info_table (#18164) 
* enable numa_node_id and socket_id in streams_info_table

* fix code style issue

* fix document issue

* update for comments

* update for comments

* update for comments
 2023-07-07 12:33:23 +08:00
Aleksandr Voron
c40d6acfc8 [CPU] [ARM] Enable MVN SLT tests on ARM (#17973) 
* enabled MVN SLT tests on ARM

* moved nhwc to common section

* exclude normalizeVariance=true from x64

* fixed comments

* add NCHW+acrossChannels = false test case

* Add comment about unsupported case

* fixed 5d layout in Mvn5D_noAcrossChannels

* MvnLayerCPUTest::isSupportedTestCase() added
 2023-07-06 15:09:50 +02:00
Aleksandr Voron
fc9e0ce315 [CPU] [ARM] Enable Reduce SLT tests on ARM (#18006) 
* init

* moved NHWC to common section

* experiment to support dynamic shapes in reduce transformation

* support dynamic shapes

* axes sorting fix in reduce transformations
 2023-07-06 10:42:46 +02:00
Nikolay Shchegolev
886fd0debb [CPU] ONNX Unique tests failing on CPU (#18100) 
* [CPU] ONNX Unique tests failing on CPU

* Fixes as per comments.
 2023-07-05 18:16:21 +02:00
Luwei Zhou
0b3a004825 [CPU] Combine DQ scales and multiply into DQ scales. (#17276) 
* Fix the multible multiply case.

* Add test case.

* Fix CI issues.

* Fix the dynamic shape FC kernel creating issue.

* Expose FC weight with original linear layout to CPU graph.

* Apply review comments.

* Apply review comments.

* Applied review comments.
 2023-07-04 13:38:25 +02:00
Alexandra Sidorova
211c56acf9 [CPU] Fixed naming in SwapConvertTranspose pass (#18208) 
* [CPU] Fixed naming in SwapConvertTranspose pass

* Applied Vladislav comments
 2023-07-04 13:34:07 +04:00
Yury Gaydaychuk
a2b7d561e4 [CPU] Checking of nonbias port in FQ-ScaleShift fusing (#17555) 
* In FQ-MM fusing added checking of nonbias port during calculating channel dim

* comment added

* test added
 2023-06-30 16:01:32 +02:00
Vladislav Golubev
18e737493c [Snippets] MatMul: blocking by M dimension at the LIR stage (#18169) 
* [Snippets] MatMul: blocking by M dim at LIR level

* Alexandra's comments applied

* Ivan's comments applied

* Fix warning
 2023-06-28 19:31:44 +02:00
Irina Efode
31b07c40d9 Add global config for test infra (#17547) 
* [IE TESTS] Add Global test config for Subgraph base test

* Replace using option by function redefinition

* fix build

* remove extra changes for gna/template

* code style

* add nvidia to devices

* Fix debian

* remove nvidia
 2023-06-24 01:07:36 +04:00
Alexandra Sidorova
db4e3bf83d [Snippets] Added tailing processing support for splitted Loops (#17878) 2023-06-23 12:58:53 +04:00
Oleg Pipikin
48b47e754f Rename ngraph with ov in common_test_utils (#17905) 
* Rename ngraph with ov in common_test_utils

* Fix comments

* Delete opset includes from commonTestUtils

* Fix CI and code style

* Apply comments

* Fix CI and apply comments
 2023-06-23 09:51:47 +02:00
Ilya Lavrenov
15e69c280a Used pip wheel to build OpenVINO wheel (#18029) 
* Used pip wheel to build OpenVINO wheel

* Improvements

* Added python api properly into deb / rpm packages

* Use cmake -E variant from cmake 3.13

* Improvements to fix CI

* Some refactoring

* Don't use developer package for scripts projects

* Final fixes
 2023-06-23 09:17:02 +04:00
Tingqian Li
54bb74be38 [CPU] Enable f16 inference precision (#16500) 2023-06-22 11:03:38 +04:00
Nesterov Alexander
ed087d9bf1 [ARM CPU] Add parallel reference power operation (#18093) 2023-06-22 10:33:10 +04:00
Luwei Zhou
731ef78608 [CPU] Move the FC fusing bias into CPU graph optimizer (#17082) 2023-06-21 10:20:21 +04:00
yanlan song
05e8bd375e Bell/auto api 2.0 (#17805) 
* 2.0 innitial

Signed-off-by: fishbell <bell.song@intel.com>

* enable all tests

Signed-off-by: fishbell <bell.song@intel.com>

* remove unecessary files

Signed-off-by: fishbell <bell.song@intel.com>

* move container header to auto foler, remove uncessary macro define

Signed-off-by: fishbell <bell.song@intel.com>

* enable caching

Signed-off-by: fishbell <bell.song@intel.com>

* enable query_model

Signed-off-by: fishbell <bell.song@intel.com>

* support loaded_from_cache property

Signed-off-by: fishbell <bell.song@intel.com>

* fix some build warning

Signed-off-by: fishbell <bell.song@intel.com>

fake inputs/outputs if needed

Signed-off-by: fishbell <bell.song@intel.com>

* resolve conflict

Signed-off-by: fishbell <bell.song@intel.com>

* skip unsupported test

Signed-off-by: fishbell <bell.song@intel.com>

* use mock icore from common foler

Signed-off-by: fishbell <bell.song@intel.com>

* fix failure for remote tensors

Signed-off-by: fishbell <bell.song@intel.com>

* apply ppp related fix in auto

Signed-off-by: fishbell <bell.song@intel.com>

* fix build warning on windows

Signed-off-by: fishbell <bell.song@intel.com>

* fix ppp output layout issue

Signed-off-by: fishbell <bell.song@intel.com>

* fix ppp output layout issue

Signed-off-by: fishbell <bell.song@intel.com>

* clean up headers

Signed-off-by: fishbell <bell.song@intel.com>

* log formatting

Signed-off-by: fishbell <bell.song@intel.com>

* enable fps logging for binder mode

Signed-off-by: fishbell <bell.song@intel.com>

* apply review comments

apply review comments

Signed-off-by: fishbell <bell.song@intel.com>

* remove all legacy namings, exenetwork/network/metric/IE etc

Signed-off-by: fishbell <bell.song@intel.com>

* update readme

Signed-off-by: fishbell <bell.song@intel.com>

* fix build lto issue

Signed-off-by: fishbell <bell.song@intel.com>

* minor wording

Signed-off-by: fishbell <bell.song@intel.com>

* case fix

Signed-off-by: fishbell <bell.song@intel.com>

---------

Signed-off-by: fishbell <bell.song@intel.com>
Co-authored-by: Chen Peter <peter.chen@intel.com>
 2023-06-21 00:10:59 +08:00
Egor Duplenskii
b7cc327cb8 [IE_TESTS] Correct random data generation for real numbers (#17734) 2023-06-20 10:01:33 +04:00
Chen Xu
b4e608cf47 [Snippets] Implement shuffling based horizontal reduction emitter (#18099) 2023-06-20 09:15:18 +04:00