[GPU] Fuse type conversion only reorders to the prev nodes#17881
Merged
yeonbok merged 5 commits intoopenvinotoolkit:masterfrom Jun 9, 2023
Merged
[GPU] Fuse type conversion only reorders to the prev nodes#17881yeonbok merged 5 commits intoopenvinotoolkit:masterfrom
yeonbok merged 5 commits intoopenvinotoolkit:masterfrom
Conversation
ab0c74f to
9056f46
Compare
Signed-off-by: Andrew Park <andrew.park@intel.com>
Signed-off-by: Andrew Park <andrew.park@intel.com>
Signed-off-by: Andrew Park <andrew.park@intel.com>
Signed-off-by: Andrew Park <andrew.park@intel.com>
aedc279 to
341f83d
Compare
Contributor
Author
|
There is no performance and accuracy regression for static shape case |
yeonbok
reviewed
Jun 8, 2023
| // Because mvn and concatenation kernel can work cross-layout, if reorder only performs type conversion, | ||
| // fusing reorder to the previous node can be done even if it is a dynamic shape case | ||
| if ((prev.is_type<mvn>() || prev.is_type<concatenation>()) && | ||
| node.as<reorder>().get_primitive()->truncate && |
Contributor
There was a problem hiding this comment.
Even though the reorder is truncate, it might be also fused with other reorder or reshape.
How about add a new flag to reorder: is_type_conversion_only ?
When the reorder is created with truncate, => is_type_conversion_only is to be true.
And once the reorder is fused with other reshape => set is_type_conversion_only false.
Also we need to check such a behavior with a unittest.
Contributor
Author
There was a problem hiding this comment.
Before checking can_fuse_reorder_to_prev, in the corresponding logic of remove_redundant_reorders, if reorder has a fused primitive, it will be skipped. Therefore, it seems that there is no need to consider whether reorder is fused with other reorder or reshape in this part.
Contributor
There was a problem hiding this comment.
Hmm as I see there are still reorders being removed without adding it to fused_desc.
(For example in shirink_reorder...)
Could you check them?
Contributor
Author
There was a problem hiding this comment.
As discussed, I added common function to check whether reorder is only type conversion and reinforced condition of this part.
Signed-off-by: Andrew Park <andrew.park@intel.com>
alvoron
pushed a commit
to alvoron/openvino
that referenced
this pull request
Jun 21, 2023
…oolkit#17881) * Fuse convert reorder to prev MVN/Concat node Signed-off-by: Andrew Park <andrew.park@intel.com> * Add dynamic TCs for ov_gpu_unit_test Signed-off-by: Andrew Park <andrew.park@intel.com> * Add descriptions for changes Signed-off-by: Andrew Park <andrew.park@intel.com> * Fix kernel selection failure Signed-off-by: Andrew Park <andrew.park@intel.com> * Add is_type_conversion_only function for reorder_node Signed-off-by: Andrew Park <andrew.park@intel.com> --------- Signed-off-by: Andrew Park <andrew.park@intel.com>
mryzhov
pushed a commit
to mryzhov/openvino
that referenced
this pull request
Jun 29, 2023
…oolkit#17881) * Fuse convert reorder to prev MVN/Concat node Signed-off-by: Andrew Park <andrew.park@intel.com> * Add dynamic TCs for ov_gpu_unit_test Signed-off-by: Andrew Park <andrew.park@intel.com> * Add descriptions for changes Signed-off-by: Andrew Park <andrew.park@intel.com> * Fix kernel selection failure Signed-off-by: Andrew Park <andrew.park@intel.com> * Add is_type_conversion_only function for reorder_node Signed-off-by: Andrew Park <andrew.park@intel.com> --------- Signed-off-by: Andrew Park <andrew.park@intel.com>
mryzhov
added a commit
to mryzhov/openvino
that referenced
this pull request
Jul 18, 2023
commit 19125a7c95f36916ec895513e364f5cf25bde1f0
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Sun Jul 2 20:39:06 2023 +0200
is_concat_supported based on ngraph
commit e8f99ef52197600b791211c389b84943b31a79ee
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Fri Jun 30 11:47:51 2023 +0200
Enabled the rigth concat axis check
commit 158e1c36282213c853e4c744085f70e91f9a2a62
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:20:26 2023 +0200
clang fix
commit 515b78863a264826679779c3d26276180669bc65
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:01:28 2023 +0200
Fixed concat axis checks
commit bd04f4c6d64f766a10c6b6465346568394eeb2fc
Merge: 17ea24d214 deb6231329
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Sun Jul 2 20:42:07 2023 +0200
Merge branch 'master' into feature/2d_transpose_rebased
commit 17ea24d2141ec4f6bb018e1ad01371da458831b8
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Fri Jun 30 11:47:51 2023 +0200
Enabled the rigth concat axis check
commit f76833f17eeb56a5fa4b1d5372dce71df9bb539b
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 13:59:17 2023 +0200
fixed tests
commit 47f3ef4444d8e1de7be51ceced2ee26fccfafbaf
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 11:35:51 2023 +0200
corrected transpose checking
commit 2f5443bd75264fcb67b23a507a8330d56dc9aa42
Merge: a4a7344732 985f02974a
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 11:25:47 2023 +0200
Merge branch 'feature/2d_transpose' into feature/2d_transpose_rebased
commit 985f02974a77ec25537f73d20fce2558f7d66322
Merge: a4a7344732 583aed5d2d
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 11:16:08 2023 +0200
rebase on master
commit 583aed5d2d14d983ca1ac0902c9945beb7adfcd7
Merge: 1e2560e349 fd35bad32b
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 10:12:17 2023 +0200
Merge branch 'feature/2d_transpose' of https://github.com/mryzhov/openvino into feature/2d_transpose
commit 1e2560e3495402be591712b4b645b05c8282059c
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:28:08 2023 +0200
clang fixes
commit ef49c802650e8e5cc8f1bd18b22376b79fa7d257
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 19:15:20 2023 +0200
added tests
commit 066df5dffce8bcf23b8b2c2c8546803c8d3091ee
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 14:21:57 2023 +0200
rename transformation
commit d0a3a0eba7028185a16b1ee39b2770cae6992fb9
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon Jun 19 15:28:10 2023 +0200
additional check
commit 65f201891ffa6328682627a52cc5a5b0233685fc
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Tue Jun 13 15:09:51 2023 +0200
Fixed fused indexes
commit d3337bafa1c2d1b33911ea49941d40500edb571b
Author: Ivan Novoselov <ivan.novoselov@intel.com>
Date: Mon Jun 12 08:07:49 2023 +0100
[Snippets] Documentation update (#17678)
commit 24997fba7728c98c08ab6b25f26046ebf5695199
Author: Pawel Raasz <pawel.raasz@intel.com>
Date: Mon Jun 12 07:05:46 2023 +0200
Add static shape adapters to reduce dimension conversion in shape_infer for CPU (#17862)
* Add static shape adapter
- Adapters holds CPU dimension which can be reference to it or vector
- Add ov::optional for holding optional result from shape inference
- Add new `infer` function in `IStaticShapeInfer`
* Temporary support of StaticShape
* Fix build issues
* Correct shape adapter compare
- minor static shape adapter refactor
* Minor corrections in ShapeInferenceTA
* Fix subscript operator in StaticShapeRef
commit 7e2bffdf57b7082621e636c199938fe16538a2e7
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Mon Jun 12 08:39:42 2023 +0400
[GPU] Fix dynamic padding processing of static dimension (#17978)
commit 88cf0413388142e4d187f3d06ada013cb70cefc6
Author: Mateusz Tabaka <mateusz.tabaka@intel.com>
Date: Sun Jun 11 10:49:31 2023 +0200
Fix static analysis issues in pruning mask propagation (#17910)
Ticket: CVS-108960
commit f9b073902e41d8af6618e0d096c1557854d86a2f
Author: Mateusz Tabaka <mateusz.tabaka@intel.com>
Date: Sun Jun 11 09:49:21 2023 +0200
Don't constantfold weights in MatMulConstTransposesExtraction transformation (#17917)
get_constant_from_source for Transpose node calls evaluate method
twice which is unnecessary in this case.
Ticket: CVS-105967
commit dcba15d5561568d2944d9d2283cc934e516c589d
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Sat Jun 10 23:40:39 2023 +0400
ARM static build (#17970)
commit 9182f16e749776b77a277754b15cab8ab09fd761
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Sat Jun 10 19:25:54 2023 +0400
Deprecate main IE developer API classes (#17983)
* Deprecate main IE develiper API classes
* Remove legacy snippet
* Fixed warning for VariableState
commit da350f585f270eebfb6722e98b35162967b285e3
Author: Ivan Tikhonov <ivan.tikhonov@intel.com>
Date: Sat Jun 10 12:24:43 2023 +0400
Delete the deprecated LowLatency (version1) transformation (#17965)
* Delete the deprecated LowLatency (version1) transformation
* detele LowLatency refs from the docs
commit fae241f092a723537fa39815a4509467b54377bf
Author: Wilson Seok <wilson.seok@intel.com>
Date: Sat Jun 10 16:28:00 2023 +0900
[GPU] gather nd shape agnostic kernel implementation (#17940)
* gather nd shape agnostic kernel implementation
* add func test
* fix minor bugs
* minor bug fixes
* fix win build error
commit 614947ce2950d70616c9e9cb4a4670e59ffe0d04
Author: Andrew Kwangwoong Park <andrew.park@intel.com>
Date: Sat Jun 10 08:07:01 2023 +0900
[GPU] Fuse type conversion only reorders to the prev nodes (#17881)
* Fuse convert reorder to prev MVN/Concat node
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add dynamic TCs for ov_gpu_unit_test
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add descriptions for changes
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix kernel selection failure
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add is_type_conversion_only function for reorder_node
Signed-off-by: Andrew Park <andrew.park@intel.com>
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
commit c5bb3e038b9fed4cf4ba47faf16555acf870df5d
Author: Egor Duplenskii <egor.duplensky@gmail.com>
Date: Sat Jun 10 00:09:59 2023 +0200
[CPU][DEBUG_CAPS] Fix compilation warnings (#17977)
commit 8bad2620950c85039cd5c77e730c2ff517097cda
Author: Wang Kai <53281385+kai-waang@users.noreply.github.com>
Date: Sat Jun 10 05:13:31 2023 +0800
fixing some typos (#17980)
commit c5cc3959cf21c3d4d7683802659ed882eacd37bf
Author: Edward Shogulin <edward.shogulin@intel.com>
Date: Fri Jun 9 22:12:52 2023 +0100
[LPT] tests rename for nightly: part #2 (#17926)
commit b4abaf61b61b25f6189aea4f5cf42e0fc22b6576
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 21:55:14 2023 +0400
Deprecate plugins config keys (#17974)
commit 4c74924fb05bb73a35f7c6a9f392965a3c408965
Author: Mateusz Tabaka <mateusz.tabaka@intel.com>
Date: Fri Jun 9 18:31:20 2023 +0200
AlignEltwiseInputRanks - fix when output rank is less than constant rank (#17895)
Fixes an issue when AlignEltwiseInputRanks is applied on FakeQuantize with
scalar as a first input and input/output low/high being Shape{1} constants.
In such case FakeQuantize output is still a scalar, so the difference
between output rank and input/output low/high rank is negative.
Ticket: CVS-112454
commit bd93876f5ec76ef6a61eeb4894b28ff1cbe084e7
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 18:08:53 2023 +0400
Port some changes from proxy branch (#17961)
* Port some changes from proxy branch
* Port test changes
* Rewrite approach for compile model and tensor
* Fixed review
commit 6742f6ec10ddd88fcf3eeb5ad165fe319ae44246
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 15:48:04 2023 +0400
Update OMZ to support OpenCV without GAPI (#17972)
commit 4e81d814f267905ea40a0cb1eec8476a29f78f39
Author: Alexey Kazakov <alexey.kazakov@intel.com>
Date: Fri Jun 9 12:15:02 2023 +0100
Move dependencies to the new share (#17825)
commit a93c312d663d6f997a2b2de8e936317948912e14
Author: Maciej Smyk <maciejx.smyk@intel.com>
Date: Fri Jun 9 13:04:00 2023 +0200
Update build_linux.md (#17966)
commit 3174067c48b8aab01e72322accb3b55e2beab3b9
Author: Wonju Lee <wonju.lee@intel.com>
Date: Fri Jun 9 18:56:30 2023 +0900
[DOCS] Adding Datumaro document into OV Ecosystems (#17944)
* add Datumaro document
* add datumaro into toctree
commit 0187b1230a34297892268103cbcf8b7c07e26af8
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 13:09:17 2023 +0400
Update OMZ submodule (#17963)
commit 3a23dd7bca44859d261cc3c42b43022720535514
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Fri Jun 9 09:08:14 2023 +0200
[DOCS] Fixing broken code blocks (#17959)
* code-blocks-fixes
commit 1188dc581031a93c799f50577696495903424fa7
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Fri Jun 9 08:03:10 2023 +0400
Android debug build (#17955)
commit 11da2f7755002e638922ee46996a153a893ec183
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 21:22:33 2023 +0400
Try to use system flatbuffers on Android (#17954)
commit cf64e6ca38fc67f28926e8c8ab8dadcf5cfd0fc4
Author: Gorokhov Dmitriy <dmitry.gorokhov@intel.com>
Date: Thu Jun 8 21:09:37 2023 +0400
[CPU] Fixed KEY_LP_TRANSFORMS_MODE internal propery behavior (#17945)
commit 1cfd25e89e08058a43beff090af4808b1cb2f0de
Author: Zlobin Vladimir <vladimir.zlobin@intel.com>
Date: Thu Jun 8 19:30:29 2023 +0400
cpp/samples: update build (#17900)
* cpp/samples: update build
Ticket 111295
* Fix sample_type extraction
* Fix inputLog type
* include <limits>
* Add missing const
* Revert cpp/speech_sample error message
* update azure CI
commit eb1d14b264a61ff732a333b3d7f7ac352384c65a
Author: Mircea-Aurelian Dan <mircea-aurelian.dan@intel.com>
Date: Thu Jun 8 17:55:53 2023 +0300
Set default duration to 60 for device `VPU` (#17952)
commit f1ceb912cff722be558cf481689c383b64a6eab7
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 18:31:55 2023 +0400
Fixes for deployment manager (#17899)
commit de4108579ba8991baff686a4af2732134d95c8c9
Author: Sun Xiaoxia <xiaoxia.sun@intel.com>
Date: Thu Jun 8 14:28:35 2023 +0000
Xiaoxia/update cpu mapping (#17451)
* generate cpu mapping table pre tbb
* change function name
* fix proc_type_table is wrong in RPL
* add getCpuMapFromCores test, fix comments
* modify test case
* fix comments
* fix code style
* add throw an exception
* fix numa_nodes=0 on ARM
* modify numa_nodes
* fix ExportOptimalNumStreams failed on ARM
* fix comments
* add discription of get_cpu_mapping_from_cores
* update for numactl support
* fix cores is wrong
---------
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
commit c95a8225a5f4c16257ab6ecb0da4e9ff54fdd2f5
Author: Daria Mityagina <daria.mityagina@intel.com>
Date: Thu Jun 8 16:47:40 2023 +0300
Update comments and help text (#17707)
commit 9b98ac0fb2f86ddf873440c4e95bc19fa14b3136
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Thu Jun 8 16:22:48 2023 +0400
[Snippets] Fixed copy runtime info which contains PortDescriptors (#17774)
commit f16c961a73cad3886d47f5d34730473afcc50b5f
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 15:35:27 2023 +0400
Enable python API in deb / rpm packages (#17923)
* Enable python API in debian package
* Enable python API in debian package
commit a20e43238a8f65dd679c11df10c7037d55a8d8bb
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 15:00:25 2023 +0400
Align tabs in install archives Linux (#17947)
commit cac43ca565afd508d4b6abf70e8b416c3f651b82
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Thu Jun 8 13:46:21 2023 +0400
[GPU] Add shape_of subgraphs markup and initial cpu implementations (#17762)
* [GPU] Add shape of subgraphs markup and initial cpu implementations for some of primitives
* Apply review comments
* Exclude eltwise with boolean mode types from shape of subgraphs and fix leftovers
commit 36bed862a767fa9f65eb5d61e4c13feaaeab64a2
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Thu Jun 8 12:05:14 2023 +0400
[Snippets] Add support of MHA Tokenization for different precisions (#15647)
commit 728763bde1b8c09d48f0c01ec6af65cae2f6f698
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 11:08:58 2023 +0400
Support different names for ITTAPI (#17889)
commit 1d0f52e62f4ea2fc14493a69f477f64f667c110d
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Thu Jun 8 08:32:08 2023 +0200
update-deployment-manager (#17903)
commit 3a5575837460e97c4cb1da0095970f7a6326cf26
Author: Taylor Yeonbok Lee <taylor.lee@intel.com>
Date: Wed Jun 7 19:39:26 2023 -0700
[GPU] Fix issue in runtime buffer fusing (#17909)
* There were two issues in runtime buffer fusing
1) Missing condition in matcher for dyanmic tensor
2) If the node is marked as can_be_optimized = true at build time and then turned out to false at runtime, the kernel compilation has been skipped becuaes it was checking node->can_be_optimized
=> To resolve this issue, added can_be_optimzied to impl_param and let the impl create check can_be_optimized in impl_param instead of that in node.
* Fixed primtiive::can_be_optimize to be set through function
commit 6ac4ae06aea35c6dbb6eee9667fb5f0f7dc1eaea
Author: Mingyu Kim <mingyu.kim@intel.com>
Date: Thu Jun 8 10:27:26 2023 +0900
[docs] typo fix (#17915)
commit 1c79f1ab1d188698a4ce5a5228e5d12bdd9dc102
Author: Tatiana Savina <tatiana.savina@intel.com>
Date: Wed Jun 7 18:57:42 2023 +0200
[DOCS] Port release doc fixes (#17939)
* [DOCS] Model optimization paragraph fix (#17907)
* fix mo guide paragraph
* fix format
* fix paragraph
* remove extra line
* fix archive link (#17918)
* [DOCS] Add sudo to uninstall (#17929)
* add sudo to uninstall
* Update uninstalling-openvino.md
commit 18862a770b480a5e9cc1989554c0da244a4513f5
Author: Zlobin Vladimir <vladimir.zlobin@intel.com>
Date: Wed Jun 7 19:20:42 2023 +0400
Update open_model_zoo submodule (#17927)
Catch up https://github.com/openvinotoolkit/open_model_zoo/pull/3782
commit 993db4300ce3d19d879e4d0f973470882b4cabcf
Author: Edward Shogulin <edward.shogulin@intel.com>
Date: Wed Jun 7 15:31:06 2023 +0100
[CPU] Quantized MHA extension for SmoothQuant (#17906)
commit 5f58bef711677a0f21d794000169dfca85dbfca7
Author: Anton Voronov <anton.voronov@intel.com>
Date: Wed Jun 7 17:15:01 2023 +0400
[CPU] gemm convolution: fixed bias offset (#17357)
commit f3e680ed2fa799f3be07cbb3453b53641d073997
Author: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
Date: Wed Jun 7 14:17:20 2023 +0400
[TF FE] Workaround for Broadcast/Concat issue with empty tensors (#17864)
* Added transformation for Concat
* Added test
* CI fix
* Fixed behavior of the "empty tensor list" test
commit 68a5aedd6832f56103ffb96110dc4f60e59ce5aa
Author: Tomasz Otoka <tomasz.otoka@intel.com>
Date: Wed Jun 7 12:16:28 2023 +0200
Adds configuration file for cspell (#17355)
the file for future use with cspell
commit cc27122018c95fc501970dbf8fc6f356a52002cd
Author: Tomasz Otoka <tomasz.otoka@intel.com>
Date: Wed Jun 7 12:13:15 2023 +0200
Adds Python wheel requirements info to docs (#17922)
commit 1d1ac3ab73cabff9a5eddb331fd6f2b4a223d712
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Wed Jun 7 14:12:54 2023 +0400
Added cmake_policy call to allow IN_LIST in if() (#17916)
commit 5464f71cd83baf1b3438748505540f6e53792475
Author: Pawel Raasz <pawel.raasz@intel.com>
Date: Wed Jun 7 11:28:45 2023 +0200
Add interpolate from all opsets to cpu shape infer (#17875)
commit 4977437359310b53cc724e0dff72475d17fa1ca4
Author: hyunback kim <hyunback.kim@intel.com>
Date: Wed Jun 7 16:20:59 2023 +0900
Optimize permute gemm onednn (#17621)
* [GPU] Optimized out permute in permute-gemm(onednn) pattern.
Permute can be optimized out when permute's in and out are compatible and onednn gemm.
Signed-off-by: hyunback <hyunback.kim@intel.com>
commit c2eba2d2d1a440ac59ac7b041c3e657ca84e6e2b
Author: Chen Xu <chen.xu@intel.com>
Date: Wed Jun 7 13:11:18 2023 +0800
[CPU] Reduce node improve parallelism (#17615)
commit 31eb04818de2ba1c4009b6468085c858ac14c931
Author: Wang Wangwang <wangwang.wang@intel.com>
Date: Wed Jun 7 10:31:27 2023 +0800
[AUTO] Support setting log_level from config (#17569)
* [AUTO] Support setting log_level from config
* Add test cases
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
commit 24b55e3b9e18fe846c8dfae86297687f92cbdbff
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Tue Jun 6 22:14:40 2023 +0800
update scheduling core type value (#17771)
* update scheduling core type value
* update for comments
* update for comments
* fix code style issue
commit eb0ac0c0ae3db967b9d30c45d3165ca4e8fd185b
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Tue Jun 6 16:55:01 2023 +0400
[Snippets] Added support of 3D MHA (#17817)
commit ac1e0d56dc0beea7c79f8b18cfbd07cbe8675eb5
Author: Nikita Malinin <nikita.malinin@intel.com>
Date: Tue Jun 6 14:19:53 2023 +0200
ENABLE_MMAP property pos (#17896)
commit c43ea371f5c4959ef4fed6667e9f4e6bc833dec1
Author: Tatiana Savina <tatiana.savina@intel.com>
Date: Tue Jun 6 12:48:18 2023 +0200
[DOCS] Port release doc fixes to master (#17901)
* [DOCS] Change downloads directory link (#17846)
* installation link
* fix path
* change notebooks links (#17857)
* fix apt and yum links (#17877)
* [DOCS] Fix list and links to POT (#17887)
* change link to POT
* change header label
* fix typo
commit f7a54452cd8b7c0f8e72bc3bf4c51c2faa9c914b
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Tue Jun 6 09:12:16 2023 +0400
Use tbb from vcpkg (#17891)
commit d2e6163f5b64622063cc8d95fd027f0c88695340
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Tue Jun 6 00:23:07 2023 +0400
Fixed compilation with clang (#17890)
commit cf3878fc125afa5b05167a0f05b99a7f1c33cc69
Author: Zlobin Vladimir <vladimir.zlobin@intel.com>
Date: Mon Jun 5 20:31:05 2023 +0400
Work around deprecation error (#17888)
For some reason my MSVC gives the following error:
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\utility(176,5): error C4996: 'ngraph::SlicePlan::SlicePlan': T
he nGraph API is deprecated and will be removed in the 2024.0 release. For instructions on transitioning to the new API, please refer to https://docs.openv
ino.ai/latest/openvino_2_0_transition_guide.html [C:\Users\vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj
]
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\xmemory(680,47): message : see reference to function 'std::pai
r<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan>::pair(std::pair<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan> &&)' [C:\Users\
vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj]
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\utility(175,5): error C4996: 'ngraph::SlicePlan::SlicePlan': T
he nGraph API is deprecated and will be removed in the 2024.0 release. For instructions on transitioning to the new API, please refer to https://docs.openv
ino.ai/latest/openvino_2_0_transition_guide.html [C:\Users\vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj
]
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\xmemory(680,47): message : see reference to function 'std::pai
r<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan>::pair(const std::pair<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan> &)' [C:\U
sers\vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj]
commit 596a642d9f4b2d682ceaec84e05b3190622f64d3
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Mon Jun 5 20:12:17 2023 +0400
Install all python build artifacts to a single folder (#17883)
commit 4332c2604e1b50d38eaf5bf2204eb9f76da093f6
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Mon Jun 5 16:39:19 2023 +0200
DOCS post-release adjustments (#17874)
commit 4b7fdd842a3a30fa355ff3cbd0ebdc8c9dadda71
Author: Chen Xu <chen.xu@intel.com>
Date: Mon Jun 5 18:52:18 2023 +0800
[CPU] Improve performance in 5D scenario of Reduce node (#17828)
commit 81623446f154ccdb3df471f5414703d416f0ce10
Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com>
Date: Mon Jun 5 12:17:54 2023 +0200
[CPU] Align jit and ref offsets handling in DeformableConvolution implementation (#10686)
commit 071a6f92fe9bdd6b79d59e9d58fdc877922d9ba2
Author: Roman Zubarev <roman.zubarev@intel.com>
Date: Mon Jun 5 11:14:48 2023 +0100
remove quantization config for vpu (#17507)
* remove quantization config for vpu
* remove VPU config testcases from test unify scales
---------
Co-authored-by: shokinal <alexander.shokin@intel.com>
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
commit 6e8d0b5597899751678429c1612beb3aa81e104c
Author: Piotr Krzemiński <piotr.krzeminski@intel.com>
Date: Mon Jun 5 10:59:12 2023 +0200
[PT FE] Add aten::_shape_as_tensor (#17804)
* [PT FE] Add aten::_shape_as_tensor impl
* Update shape_as_tensor.cpp
* [PT FE] Fix headers, add explicit type, comment out shape detection
* [PT FE] Reverse example comments
commit efd0d27e1ecca490abe8a222b844c041565ebb2c
Author: Aleksandr Voron <aleksandr.voron@intel.com>
Date: Mon Jun 5 10:58:12 2023 +0200
[CPU] Enable SLT Eltwise tests on ARM (#17713)
commit 969afc617fe1c00ae691f7c70b96dd94a4693ec5
Author: Piotr Krzemiński <piotr.krzeminski@intel.com>
Date: Mon Jun 5 10:55:03 2023 +0200
[PT FE] Add aten::_native_multi_head_attention (#17550)
* [PT FE] Add implementation of MHA
* [PT FE] Add tests, add scaled dot product attention
* [PT FE] Fix missing transpose for Q,K,V & output Attention
* [PT FE] Formatting errors
* [PT FE] Fix testing class with nn.Linear
* [PT FE] Fix incorrect key franspose in dot product attention computation
* [PT FE] Fix incorrect matmul due to lack of transpose
* [PT FE] Enable support for all boolean masks
* [PT FE] Fix returned weights
* [PT FE] Remove debugging artifacts
* [PT FE] Remove unused nodes, optimize transpose nodes' usage, add comments to floating masks
* [PT FE] Further reduce node usage, return None instead of 0 for return_weights=false
* [PT FE] Allow for dynamic num_num_head, embed_dim
* [PT FE] Improve error comment, remove unnecessary Unsqueeze
* [PT FE] Clang format
* Update tests/layer_tests/pytorch_tests/test_native_multi_head_attention.py
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* [PT FE] Add masks comments, improve mask broadcasting
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
commit 1acaeedb26767f9a5bdbc7e345f2c86baa9be00f
Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com>
Date: Mon Jun 5 10:52:58 2023 +0200
[CPU][Commit slider] Rmtree fixed (#17858)
commit e9a2efcb387d288800bf98dc844bfb0b27b64488
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Mon Jun 5 12:00:04 2023 +0400
[GPU] Fix GPU remote context name initialization (#17850)
commit 4e15aef22f45e989f27e9ac70542deafba8f4937
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Mon Jun 5 11:21:26 2023 +0400
[GPU] Change priority of CPU implementations (#17829)
commit 7a1e940ac00d6e968001c8e1f07313a0b491a099
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Mon Jun 5 08:16:29 2023 +0200
update-diagram (#17871)
commit fd138b6f78f1fdaeae1cd12ca968ed8aaf6f12da
Author: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Date: Mon Jun 5 09:30:22 2023 +0400
[GPU] Better device input memory reuse (#17853)
commit ca4c6422ea02ffe637b6ba43ca458c461f3d15cc
Author: Asthestarsfalll <72954905+Asthestarsfalll@users.noreply.github.com>
Date: Mon Jun 5 11:06:05 2023 +0800
【PaddlePaddle Hackathon 4】add paddle set_value op (#15888)
* add set_value op
* Support for tensor input
* fix shape error
* refactor for dynamic shape
* update process of target_value_shape and add comments
* support arbitrary steps
* fix
* fix ends_node
* fix and add test cases
* fix error when slice operation return maximum number in int32
* remove redundant function call
* update for minus step
* add constraints for minus inputs
---------
Co-authored-by: mei, yang <yang.mei@intel.com>
commit c1ffeebafc3b1a1913c5d19811d338906640e93d
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Sat Jun 3 17:07:02 2023 +0800
enable CPU map and multiple streams for ARM Linux (#17450)
* enable CPU map for ARM Linux based on freqency information
* fix code style issue
* fix code style issue
* remove 'streams = 1' WA for ARM linux
* update for typo and comments
* update for comments
* keep WA
* keep WA of streams = 1 for ARM Linux
* update num_streams WA for ARM Linux in test case
* update for comments
* update for comments
* update for comments
* update for comments
* update for merge conflict
* update and add test case for MTL
commit d12bd8ee077a97a5fb648f6bed10560a428f9d0f
Author: Kelvin Choi <kelvin.choi@intel.com>
Date: Sat Jun 3 09:29:02 2023 +0900
[GPU] Apply m_pythondiv for fusing of eltwise div (#17590)
commit 0464d0f7e42741e2f9e346301b984bc806470d43
Author: Alina Kladieva <alina.kladieva@intel.com>
Date: Sat Jun 3 00:50:57 2023 +0200
Revert "Stale PRs/Issues action limit extention (#17491)" (#17868)
This reverts commit c351335661b5fd4bbfe229fe548a439db237814a.
commit 4231b25511da61e1b92b29674d77dd933cb26a53
Author: Yaroslav Torziuk <yaroslav.torzuk2@altran.com>
Date: Fri Jun 2 21:59:55 2023 +0200
Add subgroup block reading in softmax_gpu_items_class_optimized.cl (#16223)
commit 81fb4a46a16c614cc18e847449b42097189b7f27
Author: Taylor Yeonbok Lee <taylor.lee@intel.com>
Date: Fri Jun 2 12:39:28 2023 -0700
[GPU] Enable runtime buffer fusing for dynamic shape (#17668)
* Initial impl for runtime buffer fusing
Passing unittest with static kernel
* pass unittest with dynamic impl
* Refactor allocate_output
* Separate header of buffer fusing
* Refactored buffer fusing :: matcher/optimize
* More cleanup
* Fix crash in dolly
* Reset can_be_optimized of primitive_inst when it is not
* Fix empty tensor : Primitive with empty data should be skipped
* Fix issue in dynamic padding : Static kernel should not contain dynamic padding dims
Fix missing reset of update_shape_done_by_other flag
* Not to add cache with emtpy kernel for optimized out inst
* Fix corner case error in buffer fusing
- Shapes of some preds may not be changed, but still needed to do update_impl because 1) paddings are changed 2) output memory should be updated
- optimizable impl should not be added to the cache
* Allowing reorder & permute_ref to be optimized concat predecessor
* Some more fixes :
runtime buffer fusing is available only when all preds/concat are dynamic
runtime buffer fusing is to be executed only if the node is dynamic
* Fix allocate_output parameter called by get_estimated_device_mem_usage according to the new change
* Fixed error in cascaded concatt
* Need to reinterprete even though the size is same
commit a95298fceb0f559b3952d9ba76593bc12205e6ab
Author: Marcus van Houdt <mjvh80@gmail.com>
Date: Fri Jun 2 20:05:57 2023 +0200
Add missing != operator, fixing compilation issue with Visual Studio 17.6 together with /std:c++latest (#17860)
commit 2fd7e99526e683f9a9ecb4eed8e86eb0b6a3bf25
Author: Sofya Balandina <sofya.balandina@intel.com>
Date: Fri Jun 2 18:44:54 2023 +0100
[conformance] Add rel pass rate to highlight table (#17783)
commit 6d6809c42525ae3258566076688d7cab0a8797a2
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Fri Jun 2 16:17:05 2023 +0400
[GPU] Remove clFinish call from USM memory lock function (#17830)
commit c770095abe6ce2d90ecd0dfb26998be744af68b6
Author: Edward Shogulin <edward.shogulin@intel.com>
Date: Fri Jun 2 08:47:36 2023 +0100
[LPT] StridedSlice dequantization improvement (#17563)
* [LPT] StridedSlice dequantization improvement
* review comments: refactoring & simplification
commit b9c98765b568f5c5b34188c257fca32563a2a1c5
Author: Chen Peter <peter.chen@intel.com>
Date: Fri Jun 2 15:04:33 2023 +0800
Requirements for the HW plugin to integrate with AUTO (#17053)
* Requirements for the HW plugin to integrate with AUTO
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Update property requirements and wording
1. Added purpose for each reqired property
2. Removed autobatching properties
3. Updated wording
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Add one BA test and update purpose for model_name
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Add request to ov::compilation_num_threads
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Add link to intgration with AUTO
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Wording with API 2.0
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Try to fix the link
* Remove ":doc:"
* Add postfix "__" for external link
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* bash command and multiple devices description update
Signed-off-by: Peter Chen <peter.chen@intel.com>
---------
Signed-off-by: Peter Chen <peter.chen@intel.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
commit d31f14be10916be64a445fb18ecbd6dbc0890f62
Author: bstankix <bartoszx.stankiewicz@intel.com>
Date: Thu Jun 1 15:28:37 2023 +0200
Add default platform type selection to ov graphs (#17844)
commit e848609551ec02ffb06193972b278e9ef9aa2933
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Thu Jun 1 15:16:10 2023 +0200
DOCS homepage update (#17842)
commit 7f88a49cda2f934f6f8be622ece18275a64b8f56
Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Date: Thu Jun 1 14:11:05 2023 +0200
Update networkx requirement from <=2.8.8 to <3.1.0 in /tools/mo (#15293)
commit 713c566441aff64d0db5882932f468d0a91b24d3
Author: Piotr Krzemiński <piotr.krzeminski@intel.com>
Date: Thu Jun 1 14:04:27 2023 +0200
[PT FE] Add aten::LogSoftmax (#17629)
* [PT FE] Add aten::LogSoftmax implementation & tests
* Update log_softmax.cpp
* Update src/frontends/pytorch/src/op/log_softmax.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* [PT FE] Add recommended comment, replace get_input_tensor with new implementation
* [PT FE] Align to f32 if no dtype provided
* [PT FE] Revert type align
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
commit 08089e3a3a9b4c7491eec427bc169094349ca070
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 15:23:08 2023 +0400
Use 2023.0.0 debian packages on CI (#17840)
commit e27290c8295e70ef2ba23d98bf99a9e69c3be58e
Author: Maciej Kwapulinski <maciej.kwapulinski@intel.com>
Date: Thu Jun 1 13:21:54 2023 +0200
[GNA] convertFunctionToICNNNetwork operation performance improovement (#17685)
* make CNNLayerCreator be persistent accross single convertFunctionToICNNNetwork operation
* [GNA] RR comments applied
* [GNA] RR comments applied
commit 732240f038a88a330b834df7a58b5f13c9922d96
Author: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Date: Thu Jun 1 13:21:43 2023 +0200
[Pad-12] Introduce PadBase and Pad-12 operation (#17796)
* Introduce PadBase
* Update ov scope name
* Introduce Pad-12
* Common type_prop Pad tests
* Init Pad-12 ref tests
* Add Pad reference tests
* attr and op check tests
* Move eval and clone inputs from PadBase
* Init opset12
* Headers clean up
* Update shape_inference map for CPU
* Update Pad evaluates to use ov::TensorVetor
* Update shape infer map with Pads
* Fix namespace
* Update op check test
* Add common Pad shape_inference tests
* Reuse PadBase shape_infer
commit e9cb787f798da7cddd0545cf0edc6f9562d36fb9
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 15:04:32 2023 +0400
Use OpenCL from CCI (#17839)
commit 15320b22ae6479cd2de17936555263a85dab26a5
Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com>
Date: Thu Jun 1 12:20:30 2023 +0200
[CPU][Tools] wa for tmp directory handling in linux (#17824)
commit de134c6c714a67fbefee0273c4612c7297b0f865
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Thu Jun 1 13:51:55 2023 +0400
[Snippets] Refactored work with Loop ID (#17680)
commit d13bcbe0e907a660c6e0090f9dc18949bee43fae
Author: Xuejun Zhai <xuejun.zhai@intel.com>
Date: Thu Jun 1 16:52:47 2023 +0800
Fix C API registers unit test failed (#17800)
* Fix C API registers unit test failed
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* Fix compile error in macos
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* Fix CI format issue
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* using the getExecutableDirectory() func from openvino::utils
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
---------
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
commit 71b2d6f994b461dd4a6591da89da2e8c3b0f7f12
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Thu Jun 1 12:50:56 2023 +0400
Deprecate ExecutableNetwork and InferRequest API (#17801)
* Deprecate ExecutableNetwork and InferRequest API
* Fixed some warnings
* Fixed some warnings
* Try to fix documentation
* Try to skip documentation warnings
commit 5d013d8ae57e7985c4f0c7b7e044d8517bf5e594
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Thu Jun 1 12:47:55 2023 +0400
Deprecate legacy precisions and layouts (#17803)
* Deprecate legacy precisions and layouts
* Suppress some warnings
* Fixed some warnings
commit 369f51cf50d5954c1b0e4c42fcae945d7a030ab2
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Thu Jun 1 12:44:28 2023 +0400
Mark as deprecated nGraph API (#17647)
* Mark as deprecated nGraph API
* Fixed code style
* Added IN_OV_LIBRARY define
* Suppress warnings for log
* Suppress warning
* Updated nGraph headers
* Fixed build for macOS
* Fixed lpt and snippets
* Fixed build all on macOS
* Suppress some warnings
* Fixed some new warnings
* Fixed new warnings
* Try to fix some warnings
* More warnings
* Soome change
* Suppress more warnings
* Suppress warnings for transformations
* Suppress warnings for LPT
* One more fix
* Suppress more warnings
* Try to fix opset error
* Remove opset constructor
* Cannot fix opset warning
* Suppress warnings for offline transfromations
* Fixed some warnings for Windows
* Fixed code style
* Suppress some warnings for onnx FE
* Revert "Suppress some warnings for onnx FE"
This reverts commit 75d23b64fc7333afddd68a8c96ded694167b2425.
* Revert "Fixed code style"
This reverts commit c6eba6311663a29c6338ade435e10bf55dd51482.
* Revert "Fixed some warnings for Windows"
This reverts commit 23d7ed88b694f47edfa331a6267d6795edd98438.
* Revert "Suppress warnings for offline transfromations"
This reverts commit 0b9f6317bff0d489cee6b30e064bad7d04367ae9.
* Revert "Cannot fix opset warning"
This reverts commit 19ea658639d64bb2020cfb8424ea43ffa9a2dbf7.
* Revert "Remove opset constructor"
This reverts commit 06afb1bc2037156bfb65b6b58a2b732e19a74ce5.
* Revert "Suppress warnings for LPT"
This reverts commit 58b1c0f5a041e099cd715ebac28f8f96fead936a.
* Revert "Suppress warnings for transformations"
This reverts commit f8bb9814a1d160c5c770f399489936f228f24c75.
* Revert "Suppress more warnings"
This reverts commit f9f0da9acb566200465a9540ca91bc9ff33cc825.
* Revert "Soome change"
This reverts commit e545d4984ef6eac60d8c2ce6b1d6ee805072bd28.
* Remove deprecation for ngraph::OpSet and FactoryRegistry
commit fa6b667423374eaaab3c3d2ff6bd59f9ded533d6
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 12:28:47 2023 +0400
Update archive names for 2023.0 release (#17835)
commit 070a7094ee1790177d4714c906b08978188db628
Author: Anton Voronov <anton.voronov@intel.com>
Date: Thu Jun 1 12:26:06 2023 +0400
[DOC] cpu documentation fixes (#17815)
commit 26d43ebcbda10e3aae72cbf324a91bd2f6efb9f7
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 12:24:02 2023 +0400
Updated badges to reflect new release 2023.0 (#17834)
commit 3d7b8d7e22c9ee831edf5e36caa020f2563ed1d6
Author: Andrei Gorbachev <andrei.gorbachev@intel.com>
Date: Thu Jun 1 07:51:48 2023 +0100
[GPU] fix incorrect deformable_group_idx calculation (#17759)
commit e7c9450acb8e8cf6a687ca87e5fa8e562eb60434
Author: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Date: Thu Jun 1 08:49:02 2023 +0200
GroupNormalization core op (#17781)
commit 55aa932130a53a837a2fc70b29652f1641c685c5
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 10:31:10 2023 +0400
Added vcpkg build to CI (#17808)
commit d11597f2648ee8942d09a5fbe02b3480e116e8c5
Author: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Date: Thu Jun 1 09:45:30 2023 +0400
[GPU] Functional fixes for nvidia (#17735)
commit a2e7e3f574bb5fca7a7b0f56a5be7a2596c5cf63
Author: Haiqi Pan <haiqi.pan@intel.com>
Date: Thu Jun 1 10:22:08 2023 +0800
[C API] some contents missed in doxygen (#17671)
* remove @param and separate line
* separate line of ov_remote_context_free
* fix code style
* Update src/bindings/c/include/openvino/c/ov_remote_context.h
Co-authored-by: Chen Peter <peter.chen@intel.com>
* add ...
* add ...
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
commit 18792b8531de1ad83774daec9148e3f521c33c25
Author: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
Date: Wed May 31 22:26:39 2023 +0200
[PT FE] Fix aten::squeeze translation + add tests for aten::slice (#17584)
* Fix squeeze compatibility
* Fix issue in remainder causing model to fail
* Add tests for slice
* Modify remainder to support int + add type tests
* Apply requested changes
* Add comment
commit 0a52640f51b1e8293d918e249c491f0f76c17362
Author: Nikolay Shchegolev <nikolay.shchegolev@intel.com>
Date: Wed May 31 21:05:59 2023 +0400
[CPU] GridSample tests threshold. (#17782)
commit 6b11eaadb1a9839d38e70476bc5e887d7c7abc9d
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Wed May 31 17:53:22 2023 +0200
[DOCS] `convert_model()` as a default conversion path (#17454)
commit a8d3a0f1a5e3b187f8ef9c41d3c7372687db928a
Author: Pawel Raasz <pawel.raasz@intel.com>
Date: Wed May 31 17:33:48 2023 +0200
Relax sizes and scales check for (#17811)
commit 00a2ce0ca82646ae4472823c52070430863e0174
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 16:25:59 2023 +0200
[CPU] Skip some DefConv test cases (#17810)
commit ea6ee349296223a3ccdacbc24bfd62b0b0f5963c
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Wed May 31 15:47:24 2023 +0200
[DOCS] Updating Tutorials (#17769)
commit b8347c709d4880465740fdce80b511fa5acc1f6c
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 15:39:17 2023 +0200
[CPU] Graph::DropNode fix (#17702)
commit 36fd514a2ac798673b3c2d1dd664ae08ef33bb96
Author: OK <fedorx.kutsepin@intel.com>
Date: Wed May 31 16:38:57 2023 +0300
Validation: Test AUTO plugin timetests (#17508)
* Validation: Test AUTO plugin
* config
* Add debug logs against AUTO
* Iteration
* iteration
* iteration
* iteration
* iter
* iteration
* iteration
* iteration
* iteration
---------
Co-authored-by: Daria Ilina <daria.ilina@intel.com>
commit 0b21873a2356bce517116582e3e189c7c04e6604
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 14:13:44 2023 +0200
[CPU] RNN: Shape checks are relaxed (#17724)
commit 1d69898669540b7b4f7d57fd5cf6a672ee863293
Author: Nadezhda Ageeva <nadezhda.ageeva@intel.com>
Date: Wed May 31 15:13:01 2023 +0400
[HETERO]: Avoid duplicated results (#17725)
* [HETERO]: Avoid duplicated results
* Code style
commit fb807183b28e328f7b0ac61016d677f0e8b85c0c
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Wed May 31 12:39:10 2023 +0200
Updated install docs for 2023.0 (#17764) (#17807)
port: #17764
authored by @ilya-lavrenov
commit e52d848b2ca11428fbe5b652df4a1379d26aaa11
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 12:25:17 2023 +0200
[CPU] Deconv dummy shape calculation: validate upper bound only if it is defined (#17690)
commit 51a97077fd3fdf5aca76a99e8418065a0883c0de
Author: Ekaterina Aidova <ekaterina.aidova@intel.com>
Date: Wed May 31 14:07:24 2023 +0400
[PT FE]: support flip operation (#17705)
* [PT FE]: support flip operation
* more tests
commit 688fcbb2642fb4b272fe7f1db047d2b2a848828b
Author: Ekaterina Aidova <ekaterina.aidova@intel.com>
Date: Wed May 31 14:07:12 2023 +0400
[PT FE]: support aten::cdist and aten::pairwise_distance (#17718)
* [PT FE]: support aten::cdist and aten::pairwise_distance
* p and eps non-const
commit c4ee67b68a96ec4f6ac61eac9c1cc2ada39ed861
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Wed May 31 12:01:55 2023 +0200
DOCS operation support articles update (#17449)
conformance table added
ARM merged with CPU
precision support and layout tables removed from the overview device article (info available in device articles)
commit 133ec1942fddfd68a1d617d73156133fbd41b464
Author: Mingyu Kim <mingyu.kim@intel.com>
Date: Wed May 31 18:39:19 2023 +0900
Typo fix (#17723)
commit a112140cf07160bf79b7b87575990c6fa01188b5
Author: Maciej Smyk <maciejx.smyk@intel.com>
Date: Wed May 31 11:27:20 2023 +0200
[DOCS] Link adjustment for dev docs + fix to build.md CPU link for master (#17744)
* link-update-1
* link update
* Update build.md
* dl workbench
* Update README.md
commit c4f0ac91b41ed9cbf9bf9369060120c7274a50e7
Author: Ivan Vikhrev <vikhrev.iv@gmail.com>
Date: Wed May 31 12:04:12 2023 +0300
Align sync mode fps measurement in py benchmark_app with cpp benchmark_app (#17773)
commit 8b6be7269d21374fc546ff056ddce3fed91684f6
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Wed May 31 10:51:43 2023 +0200
[DOCS] benchmark 23.0 update (#17789)
commit c5589b844e2b8ce6ae66095680ceff758ec830c5
Author: Xiping Yan <xiping.yan@intel.com>
Date: Wed May 31 15:58:29 2023 +0800
[CPU]Remove warning suppression '-Wno-sign-compare' and fix warnings (#16476)
* fix some warning sign-compare
1: get_length() sometime return dimension, sometime return static_dimension(template param), all convert to int64_t for comparing;
src/core/include/openvino/core/dimension.hpp:28 value_type=int64_t;
src/plugins/intel_cpu/src/utils/shape_inference/static_dimension.hpp:24 value_type = size_t;
2: auto default = int; for loop and const declaration;
3: sign and no-sign compare, compiler will convert them to no-sign to compare automatically;
So recommend to static_cast<size_t>;
Signed-off-by: xipingya <xiping.yan@intel.com>
* - size_t brg0BaseIdx = -1;
+ int64_t brg0BaseIdx = -1;
And some test case sign no-sign comparison.
* Fix new warnings after rebase.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Update based on maxnick review.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Process latest comments.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Change embIndex from int to size_t
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* 1: Revert lastNumSegments_, segmentIds_ to int
2: Initialize size_t brg1BaseIdx = std::numeric_limits<size_t>::max();
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Simplify this comparing.
- indexes.push_back(std::max<size_t>(idx - 1, 0u));
+ indexes.push_back(0u == idx ? 0 : idx - 1);
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Fix arm build warning.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Fix ARM plugin build fail issue.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Fix new warning
Signed-off-by: xipingya <xiping.yan@intel.com>
* outConf.inPlace() maybe is -1
Signed-off-by: xipingya <xiping.yan@intel.com>
---------
Signed-off-by: xipingya <xiping.yan@intel.com>
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
commit ef767d00ce89379a648ea7e4fd510e96ca19395e
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Wed May 31 15:31:56 2023 +0800
[DOC] Add multi threading for 2023.0 release in CPU plugin document (#17638)
commit 8d4e953c81e42ea2883c820bd8f4f7c5036fcba8
Author: Anton Voronov <anton.voronov@intel.com>
Date: Wed May 31 10:37:32 2023 +0400
[DOC][CPU] Documentation update (#17784)
commit 39ac6debf0e800a2969f31fa58bc1e28ef5b1d63
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Wed May 31 09:44:19 2023 +0800
support numactl on Linux in multi-threading 2.0 (#17209)
* support numactl on Linux in multi-threading 2.0
* update cache file reader
* fix warning
* keep change for numactl support only
* keep change for numactl support only
* keep change for numactl support only
* keep change for numactl support only
* keep change for numactl support only
* fix typo
* update for comments
* fix code style issue
* update is_cpu_map_available()
* update for comments
* update for comments
* update for comments
commit 95b26e3c1b5d6123c6dde7797756391a5c64e0d8
Author: bstankix <bartoszx.stankiewicz@intel.com>
Date: Tue May 30 16:11:14 2023 +0200
[DOCS] Add ability to build notebooks from local files (#17797)
* Add build notebooks from local files
* Add local notebook files v0.1.0-latest/20230529220816
commit fd8acc1627d557058c5592fe85ab135e0b0f8242
Author: Egor Duplenskii <egor.duplensky@gmail.com>
Date: Tue May 30 16:00:43 2023 +0200
[CPU] Fix assert in oneDNN dw conv (#17634)
commit 2947693d7e6aa961e2ae573f4f2c74d295a8a66f
Author: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
Date: Tue May 30 13:47:40 2023 +0200
[PyOV] Add objects representations (#17519)
commit 03ea5559cd6e9f0b29f76927b20275db098dd711
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:32:10 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit e4c2bede8af81aff09cd79e406071d604e5135e9
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:51 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.hpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 1ac37f619d4ca52db509b2341a1a449e7885b7cd
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:41 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 70672ac7188bc8eacbde89d642e57cc5f6ea0138
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 15:12:35 2023 +0200
clang fixes
commit d9843a562be729aff5255ad6342d9abac8cc5301
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 13:58:21 2023 +0200
transpose 2d
# Conflicts:
# src/plugins/intel_gna/src/gna_transformations_pipeline.cpp
commit fd35bad32b291832430c6b3c1ece67a18e79c6e2
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:28:08 2023 +0200
clang fixes
commit f96a77778b302d87fb54739e4269b35de846caa0
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 19:15:20 2023 +0200
added tests
commit 1783f642de6a950882d44d643b0d2e8aee8ec1a5
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 14:21:57 2023 +0200
rename transformation
commit 8eed68e2f0e7b70531ed544d7b7ca844d10f92ea
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon Jun 19 15:28:10 2023 +0200
additional check
commit 061ff18bd9f11004b0dc6063c9298988f4cdee0d
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Tue Jun 13 15:09:51 2023 +0200
Fixed fused indexes
commit b7a3ed0ff37ede98961874c13051bdfefb8e4725
Merge: 742435a232 a106eb0d75
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon Jun 12 09:51:53 2023 +0200
Merge branch 'master' into feature/2d_transpose
commit 742435a2328313a59de5d38ab681b5e0c522991d
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:32:10 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 8fbdbeaab1087db4dcf7e0292c437c9e97e737ab
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:51 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.hpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 7d88b1444f7742fb5a339ae43acd200472ec9a26
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:41 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 51c3fd3468836326a62cb572f7b54c7e357efd43
Merge: 1461423933 77bd72081f
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon May 22 12:34:03 2023 +0200
Merge branch 'master' into feature/2d_transpose
commit 1461423933bb4443abab9ac2476c2ac8e31d07fa
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 15:12:35 2023 +0200
clang fixes
commit 001f34788c9a95e4cebaf5b75a0670a79a69e935
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 13:58:21 2023 +0200
transpose 2d
# Conflicts:
# src/plugins/intel_gna/src/gna_transformations_pipeline.cpp
mryzhov
added a commit
to mryzhov/openvino
that referenced
this pull request
Jul 20, 2023
commit 19125a7c95f36916ec895513e364f5cf25bde1f0
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Sun Jul 2 20:39:06 2023 +0200
is_concat_supported based on ngraph
commit e8f99ef52197600b791211c389b84943b31a79ee
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Fri Jun 30 11:47:51 2023 +0200
Enabled the rigth concat axis check
commit 158e1c36282213c853e4c744085f70e91f9a2a62
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:20:26 2023 +0200
clang fix
commit 515b78863a264826679779c3d26276180669bc65
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:01:28 2023 +0200
Fixed concat axis checks
commit bd04f4c6d64f766a10c6b6465346568394eeb2fc
Merge: 17ea24d214 deb6231329
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Sun Jul 2 20:42:07 2023 +0200
Merge branch 'master' into feature/2d_transpose_rebased
commit 17ea24d2141ec4f6bb018e1ad01371da458831b8
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Fri Jun 30 11:47:51 2023 +0200
Enabled the rigth concat axis check
commit f76833f17eeb56a5fa4b1d5372dce71df9bb539b
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 13:59:17 2023 +0200
fixed tests
commit 47f3ef4444d8e1de7be51ceced2ee26fccfafbaf
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 11:35:51 2023 +0200
corrected transpose checking
commit 2f5443bd75264fcb67b23a507a8330d56dc9aa42
Merge: a4a7344732 985f02974a
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 11:25:47 2023 +0200
Merge branch 'feature/2d_transpose' into feature/2d_transpose_rebased
commit 985f02974a77ec25537f73d20fce2558f7d66322
Merge: a4a7344732 583aed5d2d
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 11:16:08 2023 +0200
rebase on master
commit 583aed5d2d14d983ca1ac0902c9945beb7adfcd7
Merge: 1e2560e349 fd35bad32b
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Thu Jun 29 10:12:17 2023 +0200
Merge branch 'feature/2d_transpose' of https://github.com/mryzhov/openvino into feature/2d_transpose
commit 1e2560e3495402be591712b4b645b05c8282059c
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:28:08 2023 +0200
clang fixes
commit ef49c802650e8e5cc8f1bd18b22376b79fa7d257
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 19:15:20 2023 +0200
added tests
commit 066df5dffce8bcf23b8b2c2c8546803c8d3091ee
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 14:21:57 2023 +0200
rename transformation
commit d0a3a0eba7028185a16b1ee39b2770cae6992fb9
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon Jun 19 15:28:10 2023 +0200
additional check
commit 65f201891ffa6328682627a52cc5a5b0233685fc
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Tue Jun 13 15:09:51 2023 +0200
Fixed fused indexes
commit d3337bafa1c2d1b33911ea49941d40500edb571b
Author: Ivan Novoselov <ivan.novoselov@intel.com>
Date: Mon Jun 12 08:07:49 2023 +0100
[Snippets] Documentation update (#17678)
commit 24997fba7728c98c08ab6b25f26046ebf5695199
Author: Pawel Raasz <pawel.raasz@intel.com>
Date: Mon Jun 12 07:05:46 2023 +0200
Add static shape adapters to reduce dimension conversion in shape_infer for CPU (#17862)
* Add static shape adapter
- Adapters holds CPU dimension which can be reference to it or vector
- Add ov::optional for holding optional result from shape inference
- Add new `infer` function in `IStaticShapeInfer`
* Temporary support of StaticShape
* Fix build issues
* Correct shape adapter compare
- minor static shape adapter refactor
* Minor corrections in ShapeInferenceTA
* Fix subscript operator in StaticShapeRef
commit 7e2bffdf57b7082621e636c199938fe16538a2e7
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Mon Jun 12 08:39:42 2023 +0400
[GPU] Fix dynamic padding processing of static dimension (#17978)
commit 88cf0413388142e4d187f3d06ada013cb70cefc6
Author: Mateusz Tabaka <mateusz.tabaka@intel.com>
Date: Sun Jun 11 10:49:31 2023 +0200
Fix static analysis issues in pruning mask propagation (#17910)
Ticket: CVS-108960
commit f9b073902e41d8af6618e0d096c1557854d86a2f
Author: Mateusz Tabaka <mateusz.tabaka@intel.com>
Date: Sun Jun 11 09:49:21 2023 +0200
Don't constantfold weights in MatMulConstTransposesExtraction transformation (#17917)
get_constant_from_source for Transpose node calls evaluate method
twice which is unnecessary in this case.
Ticket: CVS-105967
commit dcba15d5561568d2944d9d2283cc934e516c589d
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Sat Jun 10 23:40:39 2023 +0400
ARM static build (#17970)
commit 9182f16e749776b77a277754b15cab8ab09fd761
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Sat Jun 10 19:25:54 2023 +0400
Deprecate main IE developer API classes (#17983)
* Deprecate main IE develiper API classes
* Remove legacy snippet
* Fixed warning for VariableState
commit da350f585f270eebfb6722e98b35162967b285e3
Author: Ivan Tikhonov <ivan.tikhonov@intel.com>
Date: Sat Jun 10 12:24:43 2023 +0400
Delete the deprecated LowLatency (version1) transformation (#17965)
* Delete the deprecated LowLatency (version1) transformation
* detele LowLatency refs from the docs
commit fae241f092a723537fa39815a4509467b54377bf
Author: Wilson Seok <wilson.seok@intel.com>
Date: Sat Jun 10 16:28:00 2023 +0900
[GPU] gather nd shape agnostic kernel implementation (#17940)
* gather nd shape agnostic kernel implementation
* add func test
* fix minor bugs
* minor bug fixes
* fix win build error
commit 614947ce2950d70616c9e9cb4a4670e59ffe0d04
Author: Andrew Kwangwoong Park <andrew.park@intel.com>
Date: Sat Jun 10 08:07:01 2023 +0900
[GPU] Fuse type conversion only reorders to the prev nodes (#17881)
* Fuse convert reorder to prev MVN/Concat node
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add dynamic TCs for ov_gpu_unit_test
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add descriptions for changes
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Fix kernel selection failure
Signed-off-by: Andrew Park <andrew.park@intel.com>
* Add is_type_conversion_only function for reorder_node
Signed-off-by: Andrew Park <andrew.park@intel.com>
---------
Signed-off-by: Andrew Park <andrew.park@intel.com>
commit c5bb3e038b9fed4cf4ba47faf16555acf870df5d
Author: Egor Duplenskii <egor.duplensky@gmail.com>
Date: Sat Jun 10 00:09:59 2023 +0200
[CPU][DEBUG_CAPS] Fix compilation warnings (#17977)
commit 8bad2620950c85039cd5c77e730c2ff517097cda
Author: Wang Kai <53281385+kai-waang@users.noreply.github.com>
Date: Sat Jun 10 05:13:31 2023 +0800
fixing some typos (#17980)
commit c5cc3959cf21c3d4d7683802659ed882eacd37bf
Author: Edward Shogulin <edward.shogulin@intel.com>
Date: Fri Jun 9 22:12:52 2023 +0100
[LPT] tests rename for nightly: part #2 (#17926)
commit b4abaf61b61b25f6189aea4f5cf42e0fc22b6576
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 21:55:14 2023 +0400
Deprecate plugins config keys (#17974)
commit 4c74924fb05bb73a35f7c6a9f392965a3c408965
Author: Mateusz Tabaka <mateusz.tabaka@intel.com>
Date: Fri Jun 9 18:31:20 2023 +0200
AlignEltwiseInputRanks - fix when output rank is less than constant rank (#17895)
Fixes an issue when AlignEltwiseInputRanks is applied on FakeQuantize with
scalar as a first input and input/output low/high being Shape{1} constants.
In such case FakeQuantize output is still a scalar, so the difference
between output rank and input/output low/high rank is negative.
Ticket: CVS-112454
commit bd93876f5ec76ef6a61eeb4894b28ff1cbe084e7
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 18:08:53 2023 +0400
Port some changes from proxy branch (#17961)
* Port some changes from proxy branch
* Port test changes
* Rewrite approach for compile model and tensor
* Fixed review
commit 6742f6ec10ddd88fcf3eeb5ad165fe319ae44246
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 15:48:04 2023 +0400
Update OMZ to support OpenCV without GAPI (#17972)
commit 4e81d814f267905ea40a0cb1eec8476a29f78f39
Author: Alexey Kazakov <alexey.kazakov@intel.com>
Date: Fri Jun 9 12:15:02 2023 +0100
Move dependencies to the new share (#17825)
commit a93c312d663d6f997a2b2de8e936317948912e14
Author: Maciej Smyk <maciejx.smyk@intel.com>
Date: Fri Jun 9 13:04:00 2023 +0200
Update build_linux.md (#17966)
commit 3174067c48b8aab01e72322accb3b55e2beab3b9
Author: Wonju Lee <wonju.lee@intel.com>
Date: Fri Jun 9 18:56:30 2023 +0900
[DOCS] Adding Datumaro document into OV Ecosystems (#17944)
* add Datumaro document
* add datumaro into toctree
commit 0187b1230a34297892268103cbcf8b7c07e26af8
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Fri Jun 9 13:09:17 2023 +0400
Update OMZ submodule (#17963)
commit 3a23dd7bca44859d261cc3c42b43022720535514
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Fri Jun 9 09:08:14 2023 +0200
[DOCS] Fixing broken code blocks (#17959)
* code-blocks-fixes
commit 1188dc581031a93c799f50577696495903424fa7
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Fri Jun 9 08:03:10 2023 +0400
Android debug build (#17955)
commit 11da2f7755002e638922ee46996a153a893ec183
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 21:22:33 2023 +0400
Try to use system flatbuffers on Android (#17954)
commit cf64e6ca38fc67f28926e8c8ab8dadcf5cfd0fc4
Author: Gorokhov Dmitriy <dmitry.gorokhov@intel.com>
Date: Thu Jun 8 21:09:37 2023 +0400
[CPU] Fixed KEY_LP_TRANSFORMS_MODE internal propery behavior (#17945)
commit 1cfd25e89e08058a43beff090af4808b1cb2f0de
Author: Zlobin Vladimir <vladimir.zlobin@intel.com>
Date: Thu Jun 8 19:30:29 2023 +0400
cpp/samples: update build (#17900)
* cpp/samples: update build
Ticket 111295
* Fix sample_type extraction
* Fix inputLog type
* include <limits>
* Add missing const
* Revert cpp/speech_sample error message
* update azure CI
commit eb1d14b264a61ff732a333b3d7f7ac352384c65a
Author: Mircea-Aurelian Dan <mircea-aurelian.dan@intel.com>
Date: Thu Jun 8 17:55:53 2023 +0300
Set default duration to 60 for device `VPU` (#17952)
commit f1ceb912cff722be558cf481689c383b64a6eab7
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 18:31:55 2023 +0400
Fixes for deployment manager (#17899)
commit de4108579ba8991baff686a4af2732134d95c8c9
Author: Sun Xiaoxia <xiaoxia.sun@intel.com>
Date: Thu Jun 8 14:28:35 2023 +0000
Xiaoxia/update cpu mapping (#17451)
* generate cpu mapping table pre tbb
* change function name
* fix proc_type_table is wrong in RPL
* add getCpuMapFromCores test, fix comments
* modify test case
* fix comments
* fix code style
* add throw an exception
* fix numa_nodes=0 on ARM
* modify numa_nodes
* fix ExportOptimalNumStreams failed on ARM
* fix comments
* add discription of get_cpu_mapping_from_cores
* update for numactl support
* fix cores is wrong
---------
Co-authored-by: Wanglei Shen <wanglei.shen@intel.com>
commit c95a8225a5f4c16257ab6ecb0da4e9ff54fdd2f5
Author: Daria Mityagina <daria.mityagina@intel.com>
Date: Thu Jun 8 16:47:40 2023 +0300
Update comments and help text (#17707)
commit 9b98ac0fb2f86ddf873440c4e95bc19fa14b3136
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Thu Jun 8 16:22:48 2023 +0400
[Snippets] Fixed copy runtime info which contains PortDescriptors (#17774)
commit f16c961a73cad3886d47f5d34730473afcc50b5f
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 15:35:27 2023 +0400
Enable python API in deb / rpm packages (#17923)
* Enable python API in debian package
* Enable python API in debian package
commit a20e43238a8f65dd679c11df10c7037d55a8d8bb
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 15:00:25 2023 +0400
Align tabs in install archives Linux (#17947)
commit cac43ca565afd508d4b6abf70e8b416c3f651b82
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Thu Jun 8 13:46:21 2023 +0400
[GPU] Add shape_of subgraphs markup and initial cpu implementations (#17762)
* [GPU] Add shape of subgraphs markup and initial cpu implementations for some of primitives
* Apply review comments
* Exclude eltwise with boolean mode types from shape of subgraphs and fix leftovers
commit 36bed862a767fa9f65eb5d61e4c13feaaeab64a2
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Thu Jun 8 12:05:14 2023 +0400
[Snippets] Add support of MHA Tokenization for different precisions (#15647)
commit 728763bde1b8c09d48f0c01ec6af65cae2f6f698
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 8 11:08:58 2023 +0400
Support different names for ITTAPI (#17889)
commit 1d0f52e62f4ea2fc14493a69f477f64f667c110d
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Thu Jun 8 08:32:08 2023 +0200
update-deployment-manager (#17903)
commit 3a5575837460e97c4cb1da0095970f7a6326cf26
Author: Taylor Yeonbok Lee <taylor.lee@intel.com>
Date: Wed Jun 7 19:39:26 2023 -0700
[GPU] Fix issue in runtime buffer fusing (#17909)
* There were two issues in runtime buffer fusing
1) Missing condition in matcher for dyanmic tensor
2) If the node is marked as can_be_optimized = true at build time and then turned out to false at runtime, the kernel compilation has been skipped becuaes it was checking node->can_be_optimized
=> To resolve this issue, added can_be_optimzied to impl_param and let the impl create check can_be_optimized in impl_param instead of that in node.
* Fixed primtiive::can_be_optimize to be set through function
commit 6ac4ae06aea35c6dbb6eee9667fb5f0f7dc1eaea
Author: Mingyu Kim <mingyu.kim@intel.com>
Date: Thu Jun 8 10:27:26 2023 +0900
[docs] typo fix (#17915)
commit 1c79f1ab1d188698a4ce5a5228e5d12bdd9dc102
Author: Tatiana Savina <tatiana.savina@intel.com>
Date: Wed Jun 7 18:57:42 2023 +0200
[DOCS] Port release doc fixes (#17939)
* [DOCS] Model optimization paragraph fix (#17907)
* fix mo guide paragraph
* fix format
* fix paragraph
* remove extra line
* fix archive link (#17918)
* [DOCS] Add sudo to uninstall (#17929)
* add sudo to uninstall
* Update uninstalling-openvino.md
commit 18862a770b480a5e9cc1989554c0da244a4513f5
Author: Zlobin Vladimir <vladimir.zlobin@intel.com>
Date: Wed Jun 7 19:20:42 2023 +0400
Update open_model_zoo submodule (#17927)
Catch up https://github.com/openvinotoolkit/open_model_zoo/pull/3782
commit 993db4300ce3d19d879e4d0f973470882b4cabcf
Author: Edward Shogulin <edward.shogulin@intel.com>
Date: Wed Jun 7 15:31:06 2023 +0100
[CPU] Quantized MHA extension for SmoothQuant (#17906)
commit 5f58bef711677a0f21d794000169dfca85dbfca7
Author: Anton Voronov <anton.voronov@intel.com>
Date: Wed Jun 7 17:15:01 2023 +0400
[CPU] gemm convolution: fixed bias offset (#17357)
commit f3e680ed2fa799f3be07cbb3453b53641d073997
Author: Georgy Krivoruchko <georgy.krivoruchko@intel.com>
Date: Wed Jun 7 14:17:20 2023 +0400
[TF FE] Workaround for Broadcast/Concat issue with empty tensors (#17864)
* Added transformation for Concat
* Added test
* CI fix
* Fixed behavior of the "empty tensor list" test
commit 68a5aedd6832f56103ffb96110dc4f60e59ce5aa
Author: Tomasz Otoka <tomasz.otoka@intel.com>
Date: Wed Jun 7 12:16:28 2023 +0200
Adds configuration file for cspell (#17355)
the file for future use with cspell
commit cc27122018c95fc501970dbf8fc6f356a52002cd
Author: Tomasz Otoka <tomasz.otoka@intel.com>
Date: Wed Jun 7 12:13:15 2023 +0200
Adds Python wheel requirements info to docs (#17922)
commit 1d1ac3ab73cabff9a5eddb331fd6f2b4a223d712
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Wed Jun 7 14:12:54 2023 +0400
Added cmake_policy call to allow IN_LIST in if() (#17916)
commit 5464f71cd83baf1b3438748505540f6e53792475
Author: Pawel Raasz <pawel.raasz@intel.com>
Date: Wed Jun 7 11:28:45 2023 +0200
Add interpolate from all opsets to cpu shape infer (#17875)
commit 4977437359310b53cc724e0dff72475d17fa1ca4
Author: hyunback kim <hyunback.kim@intel.com>
Date: Wed Jun 7 16:20:59 2023 +0900
Optimize permute gemm onednn (#17621)
* [GPU] Optimized out permute in permute-gemm(onednn) pattern.
Permute can be optimized out when permute's in and out are compatible and onednn gemm.
Signed-off-by: hyunback <hyunback.kim@intel.com>
commit c2eba2d2d1a440ac59ac7b041c3e657ca84e6e2b
Author: Chen Xu <chen.xu@intel.com>
Date: Wed Jun 7 13:11:18 2023 +0800
[CPU] Reduce node improve parallelism (#17615)
commit 31eb04818de2ba1c4009b6468085c858ac14c931
Author: Wang Wangwang <wangwang.wang@intel.com>
Date: Wed Jun 7 10:31:27 2023 +0800
[AUTO] Support setting log_level from config (#17569)
* [AUTO] Support setting log_level from config
* Add test cases
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
commit 24b55e3b9e18fe846c8dfae86297687f92cbdbff
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Tue Jun 6 22:14:40 2023 +0800
update scheduling core type value (#17771)
* update scheduling core type value
* update for comments
* update for comments
* fix code style issue
commit eb0ac0c0ae3db967b9d30c45d3165ca4e8fd185b
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Tue Jun 6 16:55:01 2023 +0400
[Snippets] Added support of 3D MHA (#17817)
commit ac1e0d56dc0beea7c79f8b18cfbd07cbe8675eb5
Author: Nikita Malinin <nikita.malinin@intel.com>
Date: Tue Jun 6 14:19:53 2023 +0200
ENABLE_MMAP property pos (#17896)
commit c43ea371f5c4959ef4fed6667e9f4e6bc833dec1
Author: Tatiana Savina <tatiana.savina@intel.com>
Date: Tue Jun 6 12:48:18 2023 +0200
[DOCS] Port release doc fixes to master (#17901)
* [DOCS] Change downloads directory link (#17846)
* installation link
* fix path
* change notebooks links (#17857)
* fix apt and yum links (#17877)
* [DOCS] Fix list and links to POT (#17887)
* change link to POT
* change header label
* fix typo
commit f7a54452cd8b7c0f8e72bc3bf4c51c2faa9c914b
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Tue Jun 6 09:12:16 2023 +0400
Use tbb from vcpkg (#17891)
commit d2e6163f5b64622063cc8d95fd027f0c88695340
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Tue Jun 6 00:23:07 2023 +0400
Fixed compilation with clang (#17890)
commit cf3878fc125afa5b05167a0f05b99a7f1c33cc69
Author: Zlobin Vladimir <vladimir.zlobin@intel.com>
Date: Mon Jun 5 20:31:05 2023 +0400
Work around deprecation error (#17888)
For some reason my MSVC gives the following error:
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\utility(176,5): error C4996: 'ngraph::SlicePlan::SlicePlan': T
he nGraph API is deprecated and will be removed in the 2024.0 release. For instructions on transitioning to the new API, please refer to https://docs.openv
ino.ai/latest/openvino_2_0_transition_guide.html [C:\Users\vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj
]
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\xmemory(680,47): message : see reference to function 'std::pai
r<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan>::pair(std::pair<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan> &&)' [C:\Users\
vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj]
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\utility(175,5): error C4996: 'ngraph::SlicePlan::SlicePlan': T
he nGraph API is deprecated and will be removed in the 2024.0 release. For instructions on transitioning to the new API, please refer to https://docs.openv
ino.ai/latest/openvino_2_0_transition_guide.html [C:\Users\vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj
]
C:\Program Files\Microsoft Visual Studio\2022\Professional\VC\Tools\MSVC\14.35.32215\include\xmemory(680,47): message : see reference to function 'std::pai
r<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan>::pair(const std::pair<std::shared_ptr<ov::op::v1::StridedSlice>,ngraph::SlicePlan> &)' [C:\U
sers\vzlobin\r\openvino\build\src\common\transformations\inference_engine_transformations_obj.vcxproj]
commit 596a642d9f4b2d682ceaec84e05b3190622f64d3
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Mon Jun 5 20:12:17 2023 +0400
Install all python build artifacts to a single folder (#17883)
commit 4332c2604e1b50d38eaf5bf2204eb9f76da093f6
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Mon Jun 5 16:39:19 2023 +0200
DOCS post-release adjustments (#17874)
commit 4b7fdd842a3a30fa355ff3cbd0ebdc8c9dadda71
Author: Chen Xu <chen.xu@intel.com>
Date: Mon Jun 5 18:52:18 2023 +0800
[CPU] Improve performance in 5D scenario of Reduce node (#17828)
commit 81623446f154ccdb3df471f5414703d416f0ce10
Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com>
Date: Mon Jun 5 12:17:54 2023 +0200
[CPU] Align jit and ref offsets handling in DeformableConvolution implementation (#10686)
commit 071a6f92fe9bdd6b79d59e9d58fdc877922d9ba2
Author: Roman Zubarev <roman.zubarev@intel.com>
Date: Mon Jun 5 11:14:48 2023 +0100
remove quantization config for vpu (#17507)
* remove quantization config for vpu
* remove VPU config testcases from test unify scales
---------
Co-authored-by: shokinal <alexander.shokin@intel.com>
Co-authored-by: Alexander Kozlov <alexander.kozlov@intel.com>
commit 6e8d0b5597899751678429c1612beb3aa81e104c
Author: Piotr Krzemiński <piotr.krzeminski@intel.com>
Date: Mon Jun 5 10:59:12 2023 +0200
[PT FE] Add aten::_shape_as_tensor (#17804)
* [PT FE] Add aten::_shape_as_tensor impl
* Update shape_as_tensor.cpp
* [PT FE] Fix headers, add explicit type, comment out shape detection
* [PT FE] Reverse example comments
commit efd0d27e1ecca490abe8a222b844c041565ebb2c
Author: Aleksandr Voron <aleksandr.voron@intel.com>
Date: Mon Jun 5 10:58:12 2023 +0200
[CPU] Enable SLT Eltwise tests on ARM (#17713)
commit 969afc617fe1c00ae691f7c70b96dd94a4693ec5
Author: Piotr Krzemiński <piotr.krzeminski@intel.com>
Date: Mon Jun 5 10:55:03 2023 +0200
[PT FE] Add aten::_native_multi_head_attention (#17550)
* [PT FE] Add implementation of MHA
* [PT FE] Add tests, add scaled dot product attention
* [PT FE] Fix missing transpose for Q,K,V & output Attention
* [PT FE] Formatting errors
* [PT FE] Fix testing class with nn.Linear
* [PT FE] Fix incorrect key franspose in dot product attention computation
* [PT FE] Fix incorrect matmul due to lack of transpose
* [PT FE] Enable support for all boolean masks
* [PT FE] Fix returned weights
* [PT FE] Remove debugging artifacts
* [PT FE] Remove unused nodes, optimize transpose nodes' usage, add comments to floating masks
* [PT FE] Further reduce node usage, return None instead of 0 for return_weights=false
* [PT FE] Allow for dynamic num_num_head, embed_dim
* [PT FE] Improve error comment, remove unnecessary Unsqueeze
* [PT FE] Clang format
* Update tests/layer_tests/pytorch_tests/test_native_multi_head_attention.py
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* [PT FE] Add masks comments, improve mask broadcasting
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
commit 1acaeedb26767f9a5bdbc7e345f2c86baa9be00f
Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com>
Date: Mon Jun 5 10:52:58 2023 +0200
[CPU][Commit slider] Rmtree fixed (#17858)
commit e9a2efcb387d288800bf98dc844bfb0b27b64488
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Mon Jun 5 12:00:04 2023 +0400
[GPU] Fix GPU remote context name initialization (#17850)
commit 4e15aef22f45e989f27e9ac70542deafba8f4937
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Mon Jun 5 11:21:26 2023 +0400
[GPU] Change priority of CPU implementations (#17829)
commit 7a1e940ac00d6e968001c8e1f07313a0b491a099
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Mon Jun 5 08:16:29 2023 +0200
update-diagram (#17871)
commit fd138b6f78f1fdaeae1cd12ca968ed8aaf6f12da
Author: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Date: Mon Jun 5 09:30:22 2023 +0400
[GPU] Better device input memory reuse (#17853)
commit ca4c6422ea02ffe637b6ba43ca458c461f3d15cc
Author: Asthestarsfalll <72954905+Asthestarsfalll@users.noreply.github.com>
Date: Mon Jun 5 11:06:05 2023 +0800
【PaddlePaddle Hackathon 4】add paddle set_value op (#15888)
* add set_value op
* Support for tensor input
* fix shape error
* refactor for dynamic shape
* update process of target_value_shape and add comments
* support arbitrary steps
* fix
* fix ends_node
* fix and add test cases
* fix error when slice operation return maximum number in int32
* remove redundant function call
* update for minus step
* add constraints for minus inputs
---------
Co-authored-by: mei, yang <yang.mei@intel.com>
commit c1ffeebafc3b1a1913c5d19811d338906640e93d
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Sat Jun 3 17:07:02 2023 +0800
enable CPU map and multiple streams for ARM Linux (#17450)
* enable CPU map for ARM Linux based on freqency information
* fix code style issue
* fix code style issue
* remove 'streams = 1' WA for ARM linux
* update for typo and comments
* update for comments
* keep WA
* keep WA of streams = 1 for ARM Linux
* update num_streams WA for ARM Linux in test case
* update for comments
* update for comments
* update for comments
* update for comments
* update for merge conflict
* update and add test case for MTL
commit d12bd8ee077a97a5fb648f6bed10560a428f9d0f
Author: Kelvin Choi <kelvin.choi@intel.com>
Date: Sat Jun 3 09:29:02 2023 +0900
[GPU] Apply m_pythondiv for fusing of eltwise div (#17590)
commit 0464d0f7e42741e2f9e346301b984bc806470d43
Author: Alina Kladieva <alina.kladieva@intel.com>
Date: Sat Jun 3 00:50:57 2023 +0200
Revert "Stale PRs/Issues action limit extention (#17491)" (#17868)
This reverts commit c351335661b5fd4bbfe229fe548a439db237814a.
commit 4231b25511da61e1b92b29674d77dd933cb26a53
Author: Yaroslav Torziuk <yaroslav.torzuk2@altran.com>
Date: Fri Jun 2 21:59:55 2023 +0200
Add subgroup block reading in softmax_gpu_items_class_optimized.cl (#16223)
commit 81fb4a46a16c614cc18e847449b42097189b7f27
Author: Taylor Yeonbok Lee <taylor.lee@intel.com>
Date: Fri Jun 2 12:39:28 2023 -0700
[GPU] Enable runtime buffer fusing for dynamic shape (#17668)
* Initial impl for runtime buffer fusing
Passing unittest with static kernel
* pass unittest with dynamic impl
* Refactor allocate_output
* Separate header of buffer fusing
* Refactored buffer fusing :: matcher/optimize
* More cleanup
* Fix crash in dolly
* Reset can_be_optimized of primitive_inst when it is not
* Fix empty tensor : Primitive with empty data should be skipped
* Fix issue in dynamic padding : Static kernel should not contain dynamic padding dims
Fix missing reset of update_shape_done_by_other flag
* Not to add cache with emtpy kernel for optimized out inst
* Fix corner case error in buffer fusing
- Shapes of some preds may not be changed, but still needed to do update_impl because 1) paddings are changed 2) output memory should be updated
- optimizable impl should not be added to the cache
* Allowing reorder & permute_ref to be optimized concat predecessor
* Some more fixes :
runtime buffer fusing is available only when all preds/concat are dynamic
runtime buffer fusing is to be executed only if the node is dynamic
* Fix allocate_output parameter called by get_estimated_device_mem_usage according to the new change
* Fixed error in cascaded concatt
* Need to reinterprete even though the size is same
commit a95298fceb0f559b3952d9ba76593bc12205e6ab
Author: Marcus van Houdt <mjvh80@gmail.com>
Date: Fri Jun 2 20:05:57 2023 +0200
Add missing != operator, fixing compilation issue with Visual Studio 17.6 together with /std:c++latest (#17860)
commit 2fd7e99526e683f9a9ecb4eed8e86eb0b6a3bf25
Author: Sofya Balandina <sofya.balandina@intel.com>
Date: Fri Jun 2 18:44:54 2023 +0100
[conformance] Add rel pass rate to highlight table (#17783)
commit 6d6809c42525ae3258566076688d7cab0a8797a2
Author: Sergey Shlyapnikov <sergey.shlyapnikov@intel.com>
Date: Fri Jun 2 16:17:05 2023 +0400
[GPU] Remove clFinish call from USM memory lock function (#17830)
commit c770095abe6ce2d90ecd0dfb26998be744af68b6
Author: Edward Shogulin <edward.shogulin@intel.com>
Date: Fri Jun 2 08:47:36 2023 +0100
[LPT] StridedSlice dequantization improvement (#17563)
* [LPT] StridedSlice dequantization improvement
* review comments: refactoring & simplification
commit b9c98765b568f5c5b34188c257fca32563a2a1c5
Author: Chen Peter <peter.chen@intel.com>
Date: Fri Jun 2 15:04:33 2023 +0800
Requirements for the HW plugin to integrate with AUTO (#17053)
* Requirements for the HW plugin to integrate with AUTO
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Update property requirements and wording
1. Added purpose for each reqired property
2. Removed autobatching properties
3. Updated wording
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Add one BA test and update purpose for model_name
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Add request to ov::compilation_num_threads
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Add link to intgration with AUTO
Signed-off-by: Peter Chen <peter.chen@intel.com>
* Wording with API 2.0
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
* Try to fix the link
* Remove ":doc:"
* Add postfix "__" for external link
* Apply suggestions from code review
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
* bash command and multiple devices description update
Signed-off-by: Peter Chen <peter.chen@intel.com>
---------
Signed-off-by: Peter Chen <peter.chen@intel.com>
Co-authored-by: Ilya Churaev <ilyachur@gmail.com>
Co-authored-by: Tatiana Savina <tatiana.savina@intel.com>
commit d31f14be10916be64a445fb18ecbd6dbc0890f62
Author: bstankix <bartoszx.stankiewicz@intel.com>
Date: Thu Jun 1 15:28:37 2023 +0200
Add default platform type selection to ov graphs (#17844)
commit e848609551ec02ffb06193972b278e9ef9aa2933
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Thu Jun 1 15:16:10 2023 +0200
DOCS homepage update (#17842)
commit 7f88a49cda2f934f6f8be622ece18275a64b8f56
Author: dependabot[bot] <49699333+dependabot[bot]@users.noreply.github.com>
Date: Thu Jun 1 14:11:05 2023 +0200
Update networkx requirement from <=2.8.8 to <3.1.0 in /tools/mo (#15293)
commit 713c566441aff64d0db5882932f468d0a91b24d3
Author: Piotr Krzemiński <piotr.krzeminski@intel.com>
Date: Thu Jun 1 14:04:27 2023 +0200
[PT FE] Add aten::LogSoftmax (#17629)
* [PT FE] Add aten::LogSoftmax implementation & tests
* Update log_softmax.cpp
* Update src/frontends/pytorch/src/op/log_softmax.cpp
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
* [PT FE] Add recommended comment, replace get_input_tensor with new implementation
* [PT FE] Align to f32 if no dtype provided
* [PT FE] Revert type align
---------
Co-authored-by: Maxim Vafin <maxim.vafin@intel.com>
commit 08089e3a3a9b4c7491eec427bc169094349ca070
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 15:23:08 2023 +0400
Use 2023.0.0 debian packages on CI (#17840)
commit e27290c8295e70ef2ba23d98bf99a9e69c3be58e
Author: Maciej Kwapulinski <maciej.kwapulinski@intel.com>
Date: Thu Jun 1 13:21:54 2023 +0200
[GNA] convertFunctionToICNNNetwork operation performance improovement (#17685)
* make CNNLayerCreator be persistent accross single convertFunctionToICNNNetwork operation
* [GNA] RR comments applied
* [GNA] RR comments applied
commit 732240f038a88a330b834df7a58b5f13c9922d96
Author: Katarzyna Mitrus <katarzyna.mitrus@intel.com>
Date: Thu Jun 1 13:21:43 2023 +0200
[Pad-12] Introduce PadBase and Pad-12 operation (#17796)
* Introduce PadBase
* Update ov scope name
* Introduce Pad-12
* Common type_prop Pad tests
* Init Pad-12 ref tests
* Add Pad reference tests
* attr and op check tests
* Move eval and clone inputs from PadBase
* Init opset12
* Headers clean up
* Update shape_inference map for CPU
* Update Pad evaluates to use ov::TensorVetor
* Update shape infer map with Pads
* Fix namespace
* Update op check test
* Add common Pad shape_inference tests
* Reuse PadBase shape_infer
commit e9cb787f798da7cddd0545cf0edc6f9562d36fb9
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 15:04:32 2023 +0400
Use OpenCL from CCI (#17839)
commit 15320b22ae6479cd2de17936555263a85dab26a5
Author: Yury Gaydaychuk <yury.gaydaychuk@intel.com>
Date: Thu Jun 1 12:20:30 2023 +0200
[CPU][Tools] wa for tmp directory handling in linux (#17824)
commit de134c6c714a67fbefee0273c4612c7297b0f865
Author: Alexandra Sidorova <alexandra.sidorova@intel.com>
Date: Thu Jun 1 13:51:55 2023 +0400
[Snippets] Refactored work with Loop ID (#17680)
commit d13bcbe0e907a660c6e0090f9dc18949bee43fae
Author: Xuejun Zhai <xuejun.zhai@intel.com>
Date: Thu Jun 1 16:52:47 2023 +0800
Fix C API registers unit test failed (#17800)
* Fix C API registers unit test failed
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* Fix compile error in macos
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* Fix CI format issue
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
* using the getExecutableDirectory() func from openvino::utils
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
---------
Signed-off-by: Zhai, Xuejun <xuejun.zhai@intel.com>
commit 71b2d6f994b461dd4a6591da89da2e8c3b0f7f12
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Thu Jun 1 12:50:56 2023 +0400
Deprecate ExecutableNetwork and InferRequest API (#17801)
* Deprecate ExecutableNetwork and InferRequest API
* Fixed some warnings
* Fixed some warnings
* Try to fix documentation
* Try to skip documentation warnings
commit 5d013d8ae57e7985c4f0c7b7e044d8517bf5e594
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Thu Jun 1 12:47:55 2023 +0400
Deprecate legacy precisions and layouts (#17803)
* Deprecate legacy precisions and layouts
* Suppress some warnings
* Fixed some warnings
commit 369f51cf50d5954c1b0e4c42fcae945d7a030ab2
Author: Ilya Churaev <ilya.churaev@intel.com>
Date: Thu Jun 1 12:44:28 2023 +0400
Mark as deprecated nGraph API (#17647)
* Mark as deprecated nGraph API
* Fixed code style
* Added IN_OV_LIBRARY define
* Suppress warnings for log
* Suppress warning
* Updated nGraph headers
* Fixed build for macOS
* Fixed lpt and snippets
* Fixed build all on macOS
* Suppress some warnings
* Fixed some new warnings
* Fixed new warnings
* Try to fix some warnings
* More warnings
* Soome change
* Suppress more warnings
* Suppress warnings for transformations
* Suppress warnings for LPT
* One more fix
* Suppress more warnings
* Try to fix opset error
* Remove opset constructor
* Cannot fix opset warning
* Suppress warnings for offline transfromations
* Fixed some warnings for Windows
* Fixed code style
* Suppress some warnings for onnx FE
* Revert "Suppress some warnings for onnx FE"
This reverts commit 75d23b64fc7333afddd68a8c96ded694167b2425.
* Revert "Fixed code style"
This reverts commit c6eba6311663a29c6338ade435e10bf55dd51482.
* Revert "Fixed some warnings for Windows"
This reverts commit 23d7ed88b694f47edfa331a6267d6795edd98438.
* Revert "Suppress warnings for offline transfromations"
This reverts commit 0b9f6317bff0d489cee6b30e064bad7d04367ae9.
* Revert "Cannot fix opset warning"
This reverts commit 19ea658639d64bb2020cfb8424ea43ffa9a2dbf7.
* Revert "Remove opset constructor"
This reverts commit 06afb1bc2037156bfb65b6b58a2b732e19a74ce5.
* Revert "Suppress warnings for LPT"
This reverts commit 58b1c0f5a041e099cd715ebac28f8f96fead936a.
* Revert "Suppress warnings for transformations"
This reverts commit f8bb9814a1d160c5c770f399489936f228f24c75.
* Revert "Suppress more warnings"
This reverts commit f9f0da9acb566200465a9540ca91bc9ff33cc825.
* Revert "Soome change"
This reverts commit e545d4984ef6eac60d8c2ce6b1d6ee805072bd28.
* Remove deprecation for ngraph::OpSet and FactoryRegistry
commit fa6b667423374eaaab3c3d2ff6bd59f9ded533d6
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 12:28:47 2023 +0400
Update archive names for 2023.0 release (#17835)
commit 070a7094ee1790177d4714c906b08978188db628
Author: Anton Voronov <anton.voronov@intel.com>
Date: Thu Jun 1 12:26:06 2023 +0400
[DOC] cpu documentation fixes (#17815)
commit 26d43ebcbda10e3aae72cbf324a91bd2f6efb9f7
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 12:24:02 2023 +0400
Updated badges to reflect new release 2023.0 (#17834)
commit 3d7b8d7e22c9ee831edf5e36caa020f2563ed1d6
Author: Andrei Gorbachev <andrei.gorbachev@intel.com>
Date: Thu Jun 1 07:51:48 2023 +0100
[GPU] fix incorrect deformable_group_idx calculation (#17759)
commit e7c9450acb8e8cf6a687ca87e5fa8e562eb60434
Author: Tomasz Dołbniak <tomasz.dolbniak@intel.com>
Date: Thu Jun 1 08:49:02 2023 +0200
GroupNormalization core op (#17781)
commit 55aa932130a53a837a2fc70b29652f1641c685c5
Author: Ilya Lavrenov <ilya.lavrenov@intel.com>
Date: Thu Jun 1 10:31:10 2023 +0400
Added vcpkg build to CI (#17808)
commit d11597f2648ee8942d09a5fbe02b3480e116e8c5
Author: Vladimir Paramuzov <vladimir.paramuzov@intel.com>
Date: Thu Jun 1 09:45:30 2023 +0400
[GPU] Functional fixes for nvidia (#17735)
commit a2e7e3f574bb5fca7a7b0f56a5be7a2596c5cf63
Author: Haiqi Pan <haiqi.pan@intel.com>
Date: Thu Jun 1 10:22:08 2023 +0800
[C API] some contents missed in doxygen (#17671)
* remove @param and separate line
* separate line of ov_remote_context_free
* fix code style
* Update src/bindings/c/include/openvino/c/ov_remote_context.h
Co-authored-by: Chen Peter <peter.chen@intel.com>
* add ...
* add ...
---------
Co-authored-by: Chen Peter <peter.chen@intel.com>
commit 18792b8531de1ad83774daec9148e3f521c33c25
Author: Mateusz Mikolajczyk <mateusz.mikolajczyk@intel.com>
Date: Wed May 31 22:26:39 2023 +0200
[PT FE] Fix aten::squeeze translation + add tests for aten::slice (#17584)
* Fix squeeze compatibility
* Fix issue in remainder causing model to fail
* Add tests for slice
* Modify remainder to support int + add type tests
* Apply requested changes
* Add comment
commit 0a52640f51b1e8293d918e249c491f0f76c17362
Author: Nikolay Shchegolev <nikolay.shchegolev@intel.com>
Date: Wed May 31 21:05:59 2023 +0400
[CPU] GridSample tests threshold. (#17782)
commit 6b11eaadb1a9839d38e70476bc5e887d7c7abc9d
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Wed May 31 17:53:22 2023 +0200
[DOCS] `convert_model()` as a default conversion path (#17454)
commit a8d3a0f1a5e3b187f8ef9c41d3c7372687db928a
Author: Pawel Raasz <pawel.raasz@intel.com>
Date: Wed May 31 17:33:48 2023 +0200
Relax sizes and scales check for (#17811)
commit 00a2ce0ca82646ae4472823c52070430863e0174
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 16:25:59 2023 +0200
[CPU] Skip some DefConv test cases (#17810)
commit ea6ee349296223a3ccdacbc24bfd62b0b0f5963c
Author: Sebastian Golebiewski <sebastianx.golebiewski@intel.com>
Date: Wed May 31 15:47:24 2023 +0200
[DOCS] Updating Tutorials (#17769)
commit b8347c709d4880465740fdce80b511fa5acc1f6c
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 15:39:17 2023 +0200
[CPU] Graph::DropNode fix (#17702)
commit 36fd514a2ac798673b3c2d1dd664ae08ef33bb96
Author: OK <fedorx.kutsepin@intel.com>
Date: Wed May 31 16:38:57 2023 +0300
Validation: Test AUTO plugin timetests (#17508)
* Validation: Test AUTO plugin
* config
* Add debug logs against AUTO
* Iteration
* iteration
* iteration
* iteration
* iter
* iteration
* iteration
* iteration
* iteration
---------
Co-authored-by: Daria Ilina <daria.ilina@intel.com>
commit 0b21873a2356bce517116582e3e189c7c04e6604
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 14:13:44 2023 +0200
[CPU] RNN: Shape checks are relaxed (#17724)
commit 1d69898669540b7b4f7d57fd5cf6a672ee863293
Author: Nadezhda Ageeva <nadezhda.ageeva@intel.com>
Date: Wed May 31 15:13:01 2023 +0400
[HETERO]: Avoid duplicated results (#17725)
* [HETERO]: Avoid duplicated results
* Code style
commit fb807183b28e328f7b0ac61016d677f0e8b85c0c
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Wed May 31 12:39:10 2023 +0200
Updated install docs for 2023.0 (#17764) (#17807)
port: #17764
authored by @ilya-lavrenov
commit e52d848b2ca11428fbe5b652df4a1379d26aaa11
Author: Vladislav Golubev <vladislav.golubev@intel.com>
Date: Wed May 31 12:25:17 2023 +0200
[CPU] Deconv dummy shape calculation: validate upper bound only if it is defined (#17690)
commit 51a97077fd3fdf5aca76a99e8418065a0883c0de
Author: Ekaterina Aidova <ekaterina.aidova@intel.com>
Date: Wed May 31 14:07:24 2023 +0400
[PT FE]: support flip operation (#17705)
* [PT FE]: support flip operation
* more tests
commit 688fcbb2642fb4b272fe7f1db047d2b2a848828b
Author: Ekaterina Aidova <ekaterina.aidova@intel.com>
Date: Wed May 31 14:07:12 2023 +0400
[PT FE]: support aten::cdist and aten::pairwise_distance (#17718)
* [PT FE]: support aten::cdist and aten::pairwise_distance
* p and eps non-const
commit c4ee67b68a96ec4f6ac61eac9c1cc2ada39ed861
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Wed May 31 12:01:55 2023 +0200
DOCS operation support articles update (#17449)
conformance table added
ARM merged with CPU
precision support and layout tables removed from the overview device article (info available in device articles)
commit 133ec1942fddfd68a1d617d73156133fbd41b464
Author: Mingyu Kim <mingyu.kim@intel.com>
Date: Wed May 31 18:39:19 2023 +0900
Typo fix (#17723)
commit a112140cf07160bf79b7b87575990c6fa01188b5
Author: Maciej Smyk <maciejx.smyk@intel.com>
Date: Wed May 31 11:27:20 2023 +0200
[DOCS] Link adjustment for dev docs + fix to build.md CPU link for master (#17744)
* link-update-1
* link update
* Update build.md
* dl workbench
* Update README.md
commit c4f0ac91b41ed9cbf9bf9369060120c7274a50e7
Author: Ivan Vikhrev <vikhrev.iv@gmail.com>
Date: Wed May 31 12:04:12 2023 +0300
Align sync mode fps measurement in py benchmark_app with cpp benchmark_app (#17773)
commit 8b6be7269d21374fc546ff056ddce3fed91684f6
Author: Karol Blaszczak <karol.blaszczak@intel.com>
Date: Wed May 31 10:51:43 2023 +0200
[DOCS] benchmark 23.0 update (#17789)
commit c5589b844e2b8ce6ae66095680ceff758ec830c5
Author: Xiping Yan <xiping.yan@intel.com>
Date: Wed May 31 15:58:29 2023 +0800
[CPU]Remove warning suppression '-Wno-sign-compare' and fix warnings (#16476)
* fix some warning sign-compare
1: get_length() sometime return dimension, sometime return static_dimension(template param), all convert to int64_t for comparing;
src/core/include/openvino/core/dimension.hpp:28 value_type=int64_t;
src/plugins/intel_cpu/src/utils/shape_inference/static_dimension.hpp:24 value_type = size_t;
2: auto default = int; for loop and const declaration;
3: sign and no-sign compare, compiler will convert them to no-sign to compare automatically;
So recommend to static_cast<size_t>;
Signed-off-by: xipingya <xiping.yan@intel.com>
* - size_t brg0BaseIdx = -1;
+ int64_t brg0BaseIdx = -1;
And some test case sign no-sign comparison.
* Fix new warnings after rebase.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Update based on maxnick review.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Process latest comments.
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Change embIndex from int to size_t
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* 1: Revert lastNumSegments_, segmentIds_ to int
2: Initialize size_t brg1BaseIdx = std::numeric_limits<size_t>::max();
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Simplify this comparing.
- indexes.push_back(std::max<size_t>(idx - 1, 0u));
+ indexes.push_back(0u == idx ? 0 : idx - 1);
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
* Fix arm build warning.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Fix ARM plugin build fail issue.
Signed-off-by: xipingya <xiping.yan@intel.com>
* Fix new warning
Signed-off-by: xipingya <xiping.yan@intel.com>
* outConf.inPlace() maybe is -1
Signed-off-by: xipingya <xiping.yan@intel.com>
---------
Signed-off-by: xipingya <xiping.yan@intel.com>
Signed-off-by: Yan, Xiping <xiping.yan@intel.com>
commit ef767d00ce89379a648ea7e4fd510e96ca19395e
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Wed May 31 15:31:56 2023 +0800
[DOC] Add multi threading for 2023.0 release in CPU plugin document (#17638)
commit 8d4e953c81e42ea2883c820bd8f4f7c5036fcba8
Author: Anton Voronov <anton.voronov@intel.com>
Date: Wed May 31 10:37:32 2023 +0400
[DOC][CPU] Documentation update (#17784)
commit 39ac6debf0e800a2969f31fa58bc1e28ef5b1d63
Author: Wanglei Shen <wanglei.shen@intel.com>
Date: Wed May 31 09:44:19 2023 +0800
support numactl on Linux in multi-threading 2.0 (#17209)
* support numactl on Linux in multi-threading 2.0
* update cache file reader
* fix warning
* keep change for numactl support only
* keep change for numactl support only
* keep change for numactl support only
* keep change for numactl support only
* keep change for numactl support only
* fix typo
* update for comments
* fix code style issue
* update is_cpu_map_available()
* update for comments
* update for comments
* update for comments
commit 95b26e3c1b5d6123c6dde7797756391a5c64e0d8
Author: bstankix <bartoszx.stankiewicz@intel.com>
Date: Tue May 30 16:11:14 2023 +0200
[DOCS] Add ability to build notebooks from local files (#17797)
* Add build notebooks from local files
* Add local notebook files v0.1.0-latest/20230529220816
commit fd8acc1627d557058c5592fe85ab135e0b0f8242
Author: Egor Duplenskii <egor.duplensky@gmail.com>
Date: Tue May 30 16:00:43 2023 +0200
[CPU] Fix assert in oneDNN dw conv (#17634)
commit 2947693d7e6aa961e2ae573f4f2c74d295a8a66f
Author: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
Date: Tue May 30 13:47:40 2023 +0200
[PyOV] Add objects representations (#17519)
commit 03ea5559cd6e9f0b29f76927b20275db098dd711
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:32:10 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit e4c2bede8af81aff09cd79e406071d604e5135e9
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:51 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.hpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 1ac37f619d4ca52db509b2341a1a449e7885b7cd
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:41 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 70672ac7188bc8eacbde89d642e57cc5f6ea0138
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 15:12:35 2023 +0200
clang fixes
commit d9843a562be729aff5255ad6342d9abac8cc5301
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 13:58:21 2023 +0200
transpose 2d
# Conflicts:
# src/plugins/intel_gna/src/gna_transformations_pipeline.cpp
commit fd35bad32b291832430c6b3c1ece67a18e79c6e2
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 22:28:08 2023 +0200
clang fixes
commit f96a77778b302d87fb54739e4269b35de846caa0
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 19:15:20 2023 +0200
added tests
commit 1783f642de6a950882d44d643b0d2e8aee8ec1a5
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 28 14:21:57 2023 +0200
rename transformation
commit 8eed68e2f0e7b70531ed544d7b7ca844d10f92ea
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon Jun 19 15:28:10 2023 +0200
additional check
commit 061ff18bd9f11004b0dc6063c9298988f4cdee0d
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Tue Jun 13 15:09:51 2023 +0200
Fixed fused indexes
commit b7a3ed0ff37ede98961874c13051bdfefb8e4725
Merge: 742435a232 a106eb0d75
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon Jun 12 09:51:53 2023 +0200
Merge branch 'master' into feature/2d_transpose
commit 742435a2328313a59de5d38ab681b5e0c522991d
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:32:10 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 8fbdbeaab1087db4dcf7e0292c437c9e97e737ab
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:51 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.hpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 7d88b1444f7742fb5a339ae43acd200472ec9a26
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed Jun 7 17:31:41 2023 +0200
Update src/plugins/intel_gna/src/transformations/transpose_2d.cpp
Co-authored-by: Szymon Irzabek <szymon.jakub.irzabek@intel.com>
commit 51c3fd3468836326a62cb572f7b54c7e357efd43
Merge: 1461423933 77bd72081f
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Mon May 22 12:34:03 2023 +0200
Merge branch 'master' into feature/2d_transpose
commit 1461423933bb4443abab9ac2476c2ac8e31d07fa
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 15:12:35 2023 +0200
clang fixes
commit 001f34788c9a95e4cebaf5b75a0670a79a69e935
Author: Mikhail Ryzhov <mikhail.ryzhov@intel.com>
Date: Wed May 17 13:58:21 2023 +0200
transpose 2d
# Conflicts:
# src/plugins/intel_gna/src/gna_transformations_pipeline.cpp
This file contains hidden or bidirectional Unicode text that may be interpreted or compiled differently than what appears below. To review, open the file in an editor that reveals hidden Unicode characters.
Learn more about bidirectional Unicode characters
Sign up for free
to join this conversation on GitHub.
Already have an account?
Sign in to comment
3 participants
Add this suggestion to a batch that can be applied as a single commit.This suggestion is invalid because no changes were made to the code.Suggestions cannot be applied while the pull request is closed.Suggestions cannot be applied while viewing a subset of changes.Only one suggestion per line can be applied in a batch.Add this suggestion to a batch that can be applied as a single commit.Applying suggestions on deleted lines is not supported.You must change the existing code in this line in order to create a valid suggestion.Outdated suggestions cannot be applied.This suggestion has been applied or marked resolved.Suggestions cannot be applied from pending reviews.Suggestions cannot be applied on multi-line comments.Suggestions cannot be applied while the pull request is queued to merge.Suggestion cannot be applied right now. Please check back later.
Details:
mvnandconcatenationTickets: