Commit Graph

12098 Commits

Author SHA1 Message Date
Vladislav Golubev
4733c32e75
[CPU] Fix initSupportedPrimitiveDescriptors for conv_dw_conv case (#19045) 2023-08-08 15:40:00 +00:00
Maxim Vafin
542842b0c0
[PT FE] Fix sporadic issue in round layer tests (#19051)
* [PT FE] Fix sporadic issue in round tests

* Better comment
2023-08-08 14:14:38 +00:00
Karol Blaszczak
859c03268b
[DOCS] installation guide restructuring (#19044) 2023-08-08 16:05:40 +02:00
Maciej Smyk
25b48dc105
[DOCS] Delete GNA pre-release content for master 2023-08-08 15:58:30 +02:00
Vitaliy Urusovskij
4e777b69c8
Advanced mmap test for IR FE (#18711)
* Advanced `mmap` test for IR FE

* Move memory functions to `CommonTestUtils`

* CppLint + ClangFormat

* Refactor IR FE `mmap` tests

1) Remove `compile_model` stage as not required, so also remove
"CPU" dependency
2) Run test in separate process to make RAM values more stable
3) Update RAM reference as "binsize / 2"

* Skip test on Apple platform

* Remove `getRssFileInKB()` as unused
2023-08-08 17:56:54 +04:00
Sergey Shlyapnikov
e7565eda3e
[GPU] Added paddings processing for dynamic convolutions primitives; enabled convolution osv16 optimized shape agnostic kernel (#19001) 2023-08-08 14:57:54 +02:00
Ilya Churaev
5ae9d80113
Remove core properties from set_property() call (#19008)
* Remove core properties from compiled_model call

* Add ENABLE_MMAP NO to python test

* Fixed set_property tests

---------

Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com>
2023-08-08 15:55:41 +04:00
Ilya Lavrenov
6f84f91655
Remove WA for Conan in TBB search (#19024) 2023-08-08 15:08:09 +04:00
Aleksandr Voron
a246003b79
[CPU][ARM] Reshape tensors for ACLConvertExecutor (#18578) 2023-08-08 14:56:49 +04:00
Roman Kazantsev
5a1dc93034
[TF FE][TF Hub] Support AdjustContrastv2 operation (#19029)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-08-08 13:49:52 +04:00
Ekaterina Aidova
c92f8ee86c
[PT FE]: support aten::masked_scatter (#19038) 2023-08-08 09:35:55 +00:00
Min, Byungil
70e88c6b23
[GPU] Add reorder to avoid perf drop by using mvn_ref kernel (#18871)
+ Added is_padded_spatial to program_node
+ Added reorder to remove padded input in spatial axis for mvn
+ case applied only for blocked formats of implemented mvn opt kernel

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2023-08-08 16:04:54 +09:00
Wanglei Shen
e733b0466c
[CPU] Update streams calculation for latency mode on MacOS (#18818) 2023-08-08 10:53:48 +04:00
Kelvin Choi
b83389a557
[GPU] Support non constant input of split length for variadic split (#18898) 2023-08-07 21:26:54 -07:00
Jade Cho
e5e944ccc2
[dGPU] Copy data from gpu_buffer to gpu_usm (#19010)
* [dGPU] Copy data from gpu_buffer to gpu_usm

* Add a unit test.
2023-08-08 11:47:22 +09:00
Andrew Kwangwoong Park
a2807f1edb
[GPU] Add debug config for disabled primitive fusing (#18938)
* Add debug config for disabled primitive fusing

* Apply comment

* Fix failed TCs on CI
2023-08-07 18:02:48 -07:00
Eddy Kim
d278ff5786
[GPU] updated to enqueue only fully_connected layers for async build (#18891)
* 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
2023-08-08 09:27:35 +09:00
Maxim Vafin
70c8cf2a5f
[PT FE] Support dynamic rank for aten::t (#19030)
* Support dynamic rank for aten::t

* Fix code style
2023-08-08 00:06:30 +04:00
Roman Kazantsev
710a46cb47
[TF FE][TF Hub] Support InvertPermutation and CheckNumerics operations (#19020) 2023-08-07 23:05:23 +04:00
Anton Voronov
eacdc24d54
[CPU] Transpose constant folding on cpu plug-in side for MatMul op (#18877) 2023-08-07 22:17:08 +04:00
Irina Efode
0232042061
[CONFORMANCE] Change URL to conformance IRs and add list of failed models (#19023) 2023-08-07 19:42:01 +04:00
Katarzyna Mitrus
c1c9c62816
[ShapeInference] GenerateProposals - shape infer review and tests (#18943)
* type_prop tests

* add set_attrs

* Update to use shape infer check
2023-08-07 14:42:48 +00:00
Roman Kazantsev
b1db7223fd
[TF FE][TF Hub] Support DivNoNan and EnsureShape operations (#19007)
Signed-off-by: Kazantsev, Roman <roman.kazantsev@intel.com>
2023-08-07 17:50:30 +04:00
Mateusz Mikolajczyk
a22c5f16b6
[PT FE] Add aten::linspace (#18998)
* Add linspace

* Add linspace tests

* Cleanup

* Format schema
2023-08-07 12:07:51 +02:00
Przemyslaw Wysocki
4ad072e55c
[PyOV] Add temporary workaround for wheel building issue (#19011)
* Add upper bound

* Minor changes
2023-08-07 13:06:02 +04:00
Zhang Yi
648351ba39
[CPU] Disable mlas with webassembly (#19005) 2023-08-07 09:19:42 +04:00
Ekaterina Aidova
d2947e2385
[PT FE]: support aten::view_as and aten::std (#18960)
* [PT FE]: support aten::view_as and aten::std

* fix tests
2023-08-06 15:14:54 +04:00
Ilya Lavrenov
b616cb1212
Try to detect linux-arm64 samples build failure (#18984) 2023-08-04 23:13:14 +04:00
Pawel Raasz
2385c2769e
[PT FE] Improved MaxPool convert by PyTorch FE (#18965)
* Improved MaxPool convert by PyTorch FE

* Mark xfail corner cases for AvgPool

* Update src/frontends/pytorch/src/op/max_poolnd.cpp

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Update src/frontends/pytorch/src/op/max_poolnd.cpp

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>

* Fix build issues

---------

Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
2023-08-04 15:07:33 +00:00
Andrei Gorbachev
36309938d9
[Coverity] fix coverity (#18784)
* fix CVS-112758

* fix CVS-114053

* fix CVS-116203

* fix CVS-112785 part 0

* fix CVS-112785 part 1

* fix CVS-112785 part 2

* fix CVS-112785 part 2+

* Update src/plugins/intel_gpu/src/plugin/ops/gather.cpp

Co-authored-by: Roman Lyamin <Roman.Lyamin@intel.com>

* fix CVS-112785 OPENVINO_ASSERT

* add suggestion

* fix CVS-112785

---------

Co-authored-by: Roman Lyamin <Roman.Lyamin@intel.com>
2023-08-04 14:38:06 +00:00
Edward Shogulin
b76fc24824
[LPT] Unexpected quantisation level fix (#18888)
* [LPT] Unexpected quantisation level support

* [LPT] Unexpected quantisation level support - extension for weights

* [LPT] Unexpected quantisation level support - extension for weights + tests

* refactoring: compilation fix
2023-08-04 15:02:12 +01:00
Oleg Pipikin
74c778e7ee
Refactor engines utils. Delete the target (#18916)
* Refactor engines utils. Delete the target

* Apply comments
2023-08-04 13:25:47 +00:00
Andrew Kwangwoong Park
a3bb0a8cc7
Restore disable_memory_reuse initialization (#18987) 2023-08-04 12:53:09 +00:00
Maciej Smyk
70e33469a8
Update model_optimization_guide.md (#18952) 2023-08-04 14:49:56 +02:00
Maxim Vafin
4470546d2f
Remove converts to target type before Range for aten::arange op (#18985) 2023-08-04 14:33:43 +02:00
Tatiana Savina
803843dad9
[DOCS] Change sample structure (#18942) 2023-08-04 13:21:15 +02:00
Irina Efode
9b801bcff8
[CONFORMANCE] Add ReadMe file for new SubgraphsDumper tool (#18802)
* [CONFORMANCE] Add ReadMe file for new SubgraphsDumper tool

* Review comments apply

* move readme

* Update README.md

* Update README.md
2023-08-04 10:30:48 +00:00
Karol Blaszczak
b7331016db
[DOCS] fix ext directive (#18990) 2023-08-04 12:22:48 +02:00
Ivan Tikhonov
5f6aba5ec5
Update ResolveNameCollisions to handle all friendly names, not only auto-generated (#18948)
* Update ResolveNameCollisions transformation to handle all friendly names, not only autogenerated

* codestyle
2023-08-04 13:38:59 +04:00
Pavel Esir
aeffdec5b2
Fix Division with eps marking (#18932)
* improve Division with eps marking

* delete obsolete empty files
2023-08-04 13:23:15 +04:00
Ilya Churaev
28ce25421a
Removed some deprecated API from inference component (#18981) 2023-08-04 12:34:33 +04:00
Dmitriy Valetov
245e0c8f7e
fix at docs/dev/build_webassembly.md (#18979) 2023-08-04 12:34:13 +04:00
Ekaterina Aidova
3c4beb1f16
[PT FE]: support aten::outer op (#18903) 2023-08-04 10:26:40 +02:00
Maxim Vafin
da36633c08
[PT FE] Raise graceful exception when model has incorrect type (#18976)
* [PT FE] Raise graceful exception when model has incorrect type

* Improve message
2023-08-04 09:36:09 +02:00
Gorokhov Dmitriy
80a807e26c
[CPU] FullyConnected op acceleration with 8bit weights decompression (#18915) 2023-08-04 09:34:48 +04:00
yanlan song
2c3e17ef2a
Respect secondary property of performance hint (#18728)
* enable feature

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

* do not overwrite secondary property

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

* enable new tests

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

* revert changes

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

* update tests

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

* resolve merge conflict

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

* azure failure dbug

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

* debug azure failure

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

* fix missing dependency

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

* fix case fail by merge

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

cpplint

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

* fix build error on windows

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

* rewrite case to remove dependent on public API

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

* resolve master conflict

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

---------

Signed-off-by: fishbell <bell.song@intel.com>
2023-08-04 12:37:04 +08:00
Taylor Yeonbok Lee
08ab7f4ab5
Removing blocking enqueuememcpy (#18977) 2023-08-04 02:46:41 +00:00
Roman Kazantsev
625d50c8c8
[TF FE] Handle intermediate outputs in SavedModel (#18970) 2023-08-03 23:36:00 +04:00
Kelvin Choi
561f71d86c
[GPU Enable dynamism for grid_sample (#18953) 2023-08-03 11:09:07 -07:00
Wilson Seok
bdab260131
[GPU] Fix priorbox constant propagation (#18842)
* removed priorbox in mark_if_constant

* fix priorbox operation for dynamic shape

* restore share test classes and disabled the test cases

* add exception throw for PriorBoxClustered
2023-08-03 10:39:56 -07:00