Commit Graph

7655 Commits

Author SHA1 Message Date
Bonhun Koo
d5e8d1d968
Nm/outputs quantization scheme (#12035)
* [POT] outputs quantization scheme

* [POT] remove needless blank line

* add a range_estimator config for outputs

* Add fq_config_priority
2022-07-07 16:08:55 +09:00
Luwei Zhou
0224e6a067
Fix the deconv depwise post ops issue on AVX2 and AVX512 and enable deconv test (#11870)
* Fix the deconv fused issue on AVX2 and AVX512 and enable deconv test

* Keep GroupDeconv BF16 test cases still disabled.

* Update to also excluding nightly

* Update onednn submodule.

* Update onednn submodule

* Update onednn submodule.

* Update the ONDENN submodule

* Update the ONEDNN commit.

* Update with merged onednn commit.
2022-07-07 13:26:44 +08:00
RICKIE777
70d967ffb6
[C API] Enable hello_nv12_input_classification samples for C APIs of OV API 2.0 (#12031)
* Define new ppp API for nv12

* Add new ppp API function

* Add new ppp API unit test

* Add hello nv12 input classification ov

* Define new ppp API for nv12

* Add new ppp API function

* Add new ppp API unit test

* Add hello nv12 input classification ov

* Fix the clang -formate issue

* Modify the function called is_supported_image_size

* Update code as suggested

* Add hello_nv12_input_classification e2e test

* clang-format openvinotoolkit

* Fix the doc error in CI

Co-authored-by: River Li <river.li@intel.com>
2022-07-07 11:36:55 +08:00
Xiping Yan
e8bd70f273
Add build flag for GCC. (#12017)
Some compiler flags restrict the compiler from making arbitrary decisions while handling undefined C/C++ behaviors.

Therefore they can be used to fix some issues caused by undefined behavior.

Signed-off-by: Yan, Xiping <xiping.yan@intel.com>

Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-07-07 10:02:04 +08:00
River Li
b80f724414
Fix rnn cache missing issue (#12053) 2022-07-06 11:20:27 +00:00
Kelvin Choi
63ab516c85
[GPU] Delete previous inputs by numbered new name for batching (#12045) 2022-07-06 16:32:14 +09:00
Bonhun Koo
1901087677
[POT] GNA - prevent an overflow in eltwise layer (#12048) 2022-07-06 16:15:13 +09:00
yanlan song
e718e51a85
Bell/fix lifecycle coredump (#11934)
* enable binder schedule

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

* add cases

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

* refine

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

* fix build failure

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

* fix coredump

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

* do not return hw requests directly, potential issues

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

* fix bug

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

typo

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

* optimize memory

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

* hold the hw plugin

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

* Revert "hold the hw plugin"

This reverts commit 5b537f5b6f.

* apply the fix

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

apply the fix

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

* hold the plugin library for destructing tensor

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

* solve the virtuual plugin Getblob life cycle issue

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

* remove log

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

* refine interface

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

* fix build failure

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

* fix for hetero plugin

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

* replace with vector

* enable life time tests for virtual plugins

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

rework cases due to vpux build issue

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

disable context test for now

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

Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-07-06 05:21:17 +00:00
opoluektov-lohika
7a50ce2491
Coverity: fix issue with uninitialized members (#11996) 2022-07-05 23:55:53 +00:00
Mateusz Bencer
43c0c964b8
Added FoldSubgraphEmptyInputs transformation (#11957) 2022-07-05 19:38:46 +02:00
Maciej Smyk
d91a06ac08
Apache MXNet rename (#11871)
* MXNet

MXNet renaming into Apache MXNet

* Update docs/MO_DG/prepare_model/Model_Optimizer_FAQ.md

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>

* MXNet 2

* MXNet 3

* Revert "MXNet 3"

This reverts commit 046c25239d.

Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com>
2022-07-05 15:04:03 +02:00
Karol Blaszczak
f635621aab
DOCS-return ONNX and MO_techniques articles (#11805)
* DOCS-return ONNX and MO_techniques articles

ONNX support article revised and changed to local tabs

* Update docs/MO_DG/prepare_model/Model_Optimization_Techniques.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>

* Update docs/OV_Runtime_UG/ONNX_Support.md

* Update docs/OV_Runtime_UG/ONNX_Support.md

* Update docs/OV_Runtime_UG/ONNX_Support.md

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-07-05 15:03:26 +02:00
Pawel Raasz
e1bcfeca9d
Add SoftSign to CPU plugin (#12034) 2022-07-05 13:34:42 +02:00
River Li
177d977449
oneTBB support terminate tbb thread (#11972)
Change-Id: Iea618b72db193bd48bfbf0dba3586dcdb139c43f

Co-authored-by: Shen, Wanglei <wanglei.shen@intel.com>
2022-07-05 14:11:10 +03:00
Bartek Szmelczynski
82f691c38b
[ONNX FE] Extend ONNX FE NMS-9 (#11790)
* update ONNX FE NMS to v9

* remove reshaping dynamic shapes

* fix style

* xfail two MSFT models
2022-07-05 12:10:29 +02:00
Sungeun Kim
654105d567
Set reorder format in reorder_inputs pass (#11992)
* Set reorder format in reorder_inputs pass
* set zyx_fsv16 formats if input is zyx_fsv4 formats
2022-07-05 18:20:01 +09:00
Tingqian Li
3e97d12fe2
[Transformation] transform ConvertLike into Convert when applicable (#7543)
* [Transformation] transform ConvertLike into Convert when applicable

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Remove xfail markup for onnx castlike cpu tests

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* remove un-used xfail

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* Enable ConvertLike cpu functional test

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* remove unnecessary headers

* move to common transformation

Signed-off-by: Li, Tingqian <tingqian.li@intel.com>

* remove test

* fix pytest CI issue

* minor fix after rebase

* fix clang format check

* fix failed tests
2022-07-05 15:50:35 +08:00
Chenhu Wang
8c152405ad
[CPU] General denormals optimization (#11883)
* FTZ_and_DAZ_set_for_cpu

* remove DAZ

* fix

* extract to utils

* ie core part changes to add do as property and benchmark_app enable do

* enable brgcov from Luocheng patch

* add debug info

* enable_brgemm_on_avx512

* add python binding

* dlb test

* FTZ_and_DAZ_set_for_cpu

* remove DAZ

* fix

* extract to utils

* ie core part changes to add do as property and benchmark_app enable do

* enable brgcov from Luocheng patch

* add debug info

* enable_brgemm_on_avx512

* add python binding

* dlb test

* revert test code

* revert test code
2022-07-05 15:50:16 +08:00
Kelvin Choi
186189ee09
[GPU][DOC] Change fixed input string name to get_friendly_name at yuv infer request (#12003) 2022-07-05 15:36:02 +09:00
Tingqian Li
3f9c6b2f3f
[BUG fix] Reshape node: WA in-place failure case by mem-copy (#10828)
* Handle in-place failure cases in reshape node

* Disable inplace when non-const reshape connected to constant

* Add comment to reshape_inplace test

* move copy WA into execute() to cover more general in-place failure cases
2022-07-05 04:46:27 +00:00
Mang Guo
a571539107
Optimize FullyConnected FakeQuantize post-ops (#11819)
* Optimize FullyConnected FakeQuantize post-ops

* matmul bias fuse

* Add simplifyToScale for FakeQuantize and use it in FC and Conv.

* Add fakequantize documentation

* Update doc and fix accuracy issue

* Update doc

* Fix accuracy regression

* Generalize the judgment Criteria about fake quantization with scale

* Update document

Co-authored-by: Zhang Yi3 <yi3.zhang@intel.com>
Co-authored-by: xuchen-intel <chen.xu@intel.com>
2022-07-05 09:39:42 +08:00
Luo Cheng
35ee842446
[CPU] [WA] Use config to enable brgconv f32 kernel (#11990)
* enable brgconv f32

* use config to enable brgconv f32

* when brg disabled not init bin-postops

* change prop name for extensive

* use more general field

* fix review comments.
2022-07-05 07:14:40 +08:00
River Li
30c7f561e3
Add FORCE_TBB_TERMINATE to legacy API (#12022)
* Add FORCE_TBB_TERMINATE to legacy API

* Put this config into proper place

* fix issue in property test

Co-authored-by: Shen, Wanglei <wanglei.shen@intel.com>
2022-07-04 18:49:23 +03:00
Jan Iwaszkiewicz
e5a719480b
[PyOV] Fix bugbear's B023 (#12040) 2022-07-04 15:57:36 +02:00
Felix Dohyun Kim
3334e8933c
[GPU] Pass activation unit tests on DG2 (#11969)
* supprot bfwzyx format
* Add test: bfwzyx activation
* Make opt kernel support bfwzyx
2022-07-04 19:54:17 +09:00
Jade Cho
195f5df2e8
set zero-point as immediate value (#12002) 2022-07-04 19:53:50 +09:00
avoskoboinyk-lohika
88784c2b6f
[CPU] Optimize NonZero operation (#11549)
* [CPU] Optimize NonZero operation

# Conflicts:
#	src/plugins/intel_cpu/src/nodes/non_zero.cpp

* [CPU] Rewrite NonZero implementation, so it will use generic ie_parallel API

* [CPU] NonZero operation: apply an additional optimization

* NonZero operation: add fallback code for inRank >= 6

* NonZero operation: apply review modifications

# Conflicts:
#	src/plugins/intel_cpu/src/nodes/non_zero.cpp

* NonZero operation: inShape.getDims().size() -> inRank

* NonZero operation: eliminate input array index calculation by slight modification of ie_parallel API

* Adjust ie_parallel.hpp style for clang-format

* Try to unbreak the build

* Move to parallel_nt and add a cache for nd loops to optimize more

* Add minimal size threshold for threading and reduce warning count

* Try to workaround linter errors

* One more try to unbreak cpplint build

Co-authored-by: Michal Lukaszewski <michal.lukaszewski@intel.com>
2022-07-04 10:52:18 +08:00
Mang Guo
d22c429d0e
[CPU] Remove vmaxps in store_vector. (#12005)
* Remove vmaxps in store_vector.
This instruction is not needed for dst_prc int8.
And it may lead to wrong result with denormals optimization is on.

* Add vpmaxsd if dst_prc is u8 or u16.
2022-07-02 13:22:05 +00:00
Oleksandr Kramskyi
dde3300cac
[GPU] Add SoftSign_9 operation (#11795) 2022-07-01 15:22:17 +09:00
Mykhailo Hnap
e23a568b7a
Added axes node validation to DFTs operations (#11814)
* Fix DFTs axes node validation.

* Add DFTs type prop tests for invalid nodes.

* Adjusted DFTs axes node validation.
2022-07-01 15:19:04 +09:00
Wang, Yang
8138e240a0
Remove the config key MULTI_WORK_MODE_AS_AUTO from the AUTO/MULTI plugin. (#12016)
Signed-off-by: Wang, Yang <yang4.wang@intel.com>

Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-07-01 05:05:39 +00:00
Wang, Yang
378b3a2dca
Enable default performance hint as tput in AUTO (#11848)
* Enable hint to tput if no property is specified for both AUTO device and target device.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* 1. Update logic.
2. Add test cases.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>

* Update. Set hints to default for target device if no hints setting for AUTO plugin and no specific properties setting for target device.

Signed-off-by: Wang, Yang <yang4.wang@intel.com>
2022-07-01 02:49:20 +00:00
Taylor Yeonbok Lee
1872e05375
Fix wrong output type propagation for gather elements (#12013) 2022-06-30 17:22:38 +00:00
Tomasz Dołbniak
5a5c404f13
Hello reshape SSD sample fix (#12004) 2022-06-30 13:35:14 +03:00
Bo Liu
7834dba545
fix CPU Plugin deformable conv Node output incorrect issues with uneven dilations (#11940) 2022-06-29 18:14:30 +08:00
Min, Byungil
730c3f8f25
[GPU] Update Debug config for GPU plugin (#11983)
+ Added OV_GPU_DumpLayersResult
+ Applied minor update

Signed-off-by: Min, Byungil <byungil.min@intel.com>
2022-06-29 11:41:13 +03:00
Karol Blaszczak
563d4f16e6
DOCS-nncf_rephrasing (#11997) 2022-06-29 08:54:05 +02:00
Wonju Lee
62d5f9a006
[POT] Rename ranger to range_supervision (#11998)
* fix: rename ranger by range_supervision

* ci: dummy commit
2022-06-29 15:27:57 +09:00
stephenli2000
4125d71ce8
setupvars.sh: Removing extra semicolon, which breaks glibc build (#11849)
This extra semicolon creates an output as example below. The extra
'::' is equivalent to add '.' as part of the LD_LIBRARY_PATH. This
breaks glibc build, and very often creates weird issue when launch
commands from different path.

...inference_engine/external/tbb/lib::/opt/intel/openvino_2021/...

We also noticed that :${parameter:+:$parameter} is widely used in
this file. Please review the code and fix as needed.
2022-06-29 08:11:24 +02:00
Vladyslav Tsilytskyi
72505b1d82
Use 2020-resolver feature only for pip3 < 20.3.0 (#11926)
Co-authored-by: Jan Iwaszkiewicz <jan.iwaszkiewicz@intel.com>
2022-06-28 12:05:13 +02:00
Katarzyna Mitrus
674ca1ccc2
[ONNX] Enable Concat with empty tensor/scalar (#11979) 2022-06-28 08:34:10 +02:00
Chenhu Wang
1288706589
large_batch_opt (#11951) 2022-06-28 10:33:16 +08:00
Karol Blaszczak
a4e6cda7e8
DOCS-restore_gsearch_comma (#11980) 2022-06-27 23:27:12 +02:00
Mateusz Mikolajczyk
a70bbad988
[PyOV] Fix loading data to Tensor from array-like objects (#11974) 2022-06-27 16:26:45 +02:00
opoluektov-lohika
8a21e4e062
[GPU] Implement ExperimentalDetectronDetectionOutput operation (#11772)
* ExperimentalDetectronDetectionOutput: refine sorting criteria for NMS stage

This is to ensure the operation produces stable predictable results across
the possible sorting algorithm implementaions.
This property is useful for the operation testing.

* [GPU] Implement ExperimentalDetectronDetectionOutput operation

* [GPU] ExperimentalDetectronDetectionOutput: use vector types and operations in kernel

* Reformat changed files to make clang format checker happy

* [GPU] ExperimentalDetectronDetectionOutput: add another test case to the unit test

* [GPU] ExperimentalDetectronDetectionOutput: Add f16 test

* ExperimentalDetectronDetectionOutput: single-layer test: use all three outputs

* [GPU] ExperimentalDetectronDetectionOutput: increase single layer test coverage

More attribute permutations were added.
2022-06-27 23:11:03 +09:00
Chenhu Wang
95a297ed68
onednn_update (#11930) 2022-06-27 11:22:50 +00:00
Inhyuk Jo
4d741703d1
[POT] Fix dynamic shapes and batchfying data (#11923)
* fix: batchfy data by sampler or data loader

* feat: add batched sampler

* docs: update doc
2022-06-27 15:18:36 +09:00
Luwei Zhou
4be0c59505
Fix the Non_Zero childedge check. (#11963) 2022-06-27 10:43:38 +08:00
guozhong wang
44da3f06c4
add tag for log (#11887)
* add tag for log

* cumulative log tag output AUTOPLUGIN

* add use comment for log_xxx_tag and use AUTO OR MULTI for log tag
2022-06-26 15:10:45 +08:00
guozhong wang
c0a2c98a45
add testcase for plugin properties should not be revised by compile_m… (#11842)
* add testcase for plugin properties should not be revised by compile_model

* rename smoke_cpuCompileModelBehaviorTests to smoke_gpuCompileModelBehaviorTests

* remove property EXCLUSIVE_ASYNC_REQUESTS in ov2.0 test

* add testcase for plugin properties should not be revised by loadNetwork
2022-06-25 16:37:43 +08:00