Commit Graph

7508 Commits

Author SHA1 Message Date
Krzysztof Czugala
15d64d25af
removal of compatibility tests executing models with dynamic shapes (#11751) 2022-06-14 07:55:24 +02:00
Taylor Yeonbok Lee
c73201c9e6
Optimize memory depdendency analysis (Constant memory does not use pool : No need to add constant nodes to deps) (#11861) 2022-06-14 13:46:24 +09:00
Luo Cheng
cae0c924b6
[CPU] [Test] Eye testcase does not populate all parameters (#11869) 2022-06-14 09:32:56 +08:00
Luo Cheng
151d77062f
[CPU] remove unused primitive (#11811)
* remove unused primitive

* update onednn commit
2022-06-14 06:19:05 +08:00
Zhang Yi
209331d9df
Pr/8669 (#11840)
* Added tests

* Apply comments

* Update

* Apply comments

* Fixed remaining comments

* Use ov::test::SubgraphBaseTest

Co-authored-by: Egor Shulman <egor.shulman@intel.com>
2022-06-13 20:25:59 +08:00
Tomasz Dołbniak
8603acecba
Dont use moved-from object (#11859) 2022-06-13 10:13:47 +00:00
Katarzyna Mitrus
421520bda0
Handle error from propagate_rt_info (#11773) 2022-06-13 11:11:30 +02:00
Luo Cheng
922e32e2f1
disable avx512 brgconv (#11866) 2022-06-13 17:10:42 +08:00
cecilia peng
d91b8bd17c
disable random unit tests for multiclass nms and matrix nsm. (#11839)
They sporadically impact CI... possible reason is the order of paddle and openvino is not guaranteed when more than
one bboxes have equal scores.
Actually there is no need for these random tests as the remainding cases have covered them.
2022-06-13 16:43:57 +08:00
Bartek Szmelczynski
93839f8379
[PYTHON API] Check new config (#11402)
Improve code-style in Python API and reduce number of ignored hints.

Co-authored-by: Anastasia Kuporosova <anastasia.kuporosova@intel.com>
2022-06-13 10:21:04 +02:00
Luo Cheng
9fe27be1cb
[CPU] Fix smoke_Conv_3D_FP32_fusingScaleShiftAndFakeQuantizePerChannel sporadic failure (#11813)
* fix smoke_Conv_3D_FP32_fusingScaleShiftAndFakeQuantizePerChannel sporadic failure

* rebase onednn
2022-06-13 15:29:20 +08:00
Luo Cheng
91216fef5a
[CPU] Revert enable ReduceSum -> AvgPool transformation due to perf issues (#11865)
* disable ConvertReduceMeanToPooling

* recover testcase
2022-06-13 14:11:53 +08:00
River Li
c4fdcafa70
Enable unit test for OV 2.0 C API (#11828) 2022-06-13 13:37:59 +08:00
River Li
0571124fd3
Fix CC issues for transformation and snippets (#11798)
* Fix CC issues for transformation and snippets

Matcher should be enabled if it was hit during analyze stage.

* Fixed 3 naming issue
2022-06-13 13:36:35 +08:00
Luo Cheng
c848e138f8
[CPU] cherry-pick: Fix possible data race when accessing global reorder list (#11829)
* [CPU] cherry-pick: Fix possible data race when accessing global reorder list

* rebase onednn
2022-06-13 13:11:53 +08:00
Eddy Kim
3961a241cd
Revert "Disable fc_int8_inputs_fused_fp32_sum (#11709)" (#11863) 2022-06-13 13:25:59 +09:00
Sieun Kim
6e3dd4adce
Update scatter nd update kernel to support blocked_formats (#11533)
* draft pr for planar and fsv16

* draft pr for general test

* update fusion test (failing)

* update fusing test (pass)

* update fusing test (include exception)

* clean gpu unit test

* review comment applied

* unit test cases added & cpplint applied

* cpplint error fixed

* change gpu test cases for fp16

* fusing test fix generate_unique_indices

* fix typo

* revise cl kernel for occasions when updates shape is altered
2022-06-13 13:25:24 +09:00
Paul Youngsoo Ahn
ca7ddae9ba
[GPU][Coverity] Fix coverity defects (#86191) (#11852)
- CID 1486993 Big parameter passed by value (PASS_BY_VALUE)
- CID 1489431 Uninitialized scalar variable
- CID 1489432 Uninitialized scalar variable
2022-06-13 02:51:45 +00:00
Sungeun Kim
9bda2bd580
lws quantize/eltwise (#11851) 2022-06-13 11:18:49 +09:00
Felix Dohyun Kim
d831047f30
[GPU] Optimize DepthToSpace (#11761)
* lws optimize
2022-06-13 11:17:22 +09:00
Luwei Zhou
0066ddbd22
Update onednn submodule hash to fix 3D deconv post-ops issue. (#11836) 2022-06-13 09:21:29 +08:00
Luwei Zhou
c73f6576e0
Luwei/extend reorder test (#10003)
* Extend the reorder unit test.

* Update CMake

* fix somme issues.

* Update

* Update

* Update

* Update

* Update and fix caused by input portconfig only support NCSP.

* Update Copyright

* Add more tests

* Apply review comments.

* Update

* Update

* Fix building error.

* Applied review comments.

* Update

* Update

* Update

* Fix CI

* Update

* Update Cmake
2022-06-11 21:09:26 +08:00
Mateusz Bencer
8e9eaaee91
[FakeQunatize] Use shape from HostTensor instead of FakeQuantize* (#11843) 2022-06-10 17:57:03 +03:00
mei, yang
38a81ec486
update and reorder supported paddle op list (#11601) 2022-06-10 18:46:11 +08:00
guozhong wang
408bdc9f81
add single IECore for core_threading test (#11796) 2022-06-10 08:25:12 +03:00
Bo Liu
79d3fbe3c1
remove limitation usage of brgemm for 'FullyConnected' Node (#11783) 2022-06-10 10:19:41 +08:00
Chenhu Wang
1066d4551f
fix_nms_ops_transformation (#11794)
* fix_nms_ops_transformation

* replace node when 5-9
2022-06-10 10:18:28 +08:00
Chenhu Wang
604dc4589c
[CPU] Deconvolution caching support (#11835)
* Deconvolution caching support

* get ride of deprecated name

Co-authored-by: mandrono <maxim.andronov@intel.com>
2022-06-10 10:17:59 +08:00
Chenhu Wang
e2e7417c2a
load_store_emitters_optimization_and_apply_to_interpolate (#11742)
* load_store_emitters_opt_and_apply_to_interpolate

* zmm_zero_is_always_needed_on_all_platform
2022-06-10 10:17:29 +08:00
opoluektov-lohika
d87233863d
Fix experimental detectron do ref impl (#10621) 2022-06-10 03:10:13 +03:00
Tomasz Dołbniak
0932c74ff8
GridSample operator (#11770) 2022-06-09 14:21:53 +00:00
Andrew Kwangwoong Park
5fa669785c
[GPU] Update reorder_inputs for data type conversion on fc layer (#11832)
Signed-off-by: Andrew Park <andrew.park@intel.com>
2022-06-09 15:18:28 +09:00
River Li
8faf8f2d89
OV 2.0 C API (#11700)
* Initial files & cmakefiles for ov 2.0 c api development

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

* Add all ov 2.0 C APIs define

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

* Fix review comments

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

* Disable test of OV 2.0 C APIs test for tmp

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

* Add related property key for ov 2.0 C-API

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

* Add description for ov_property_key_e

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

* Add EXECEPTION handling

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

* compiledModel add interface

* add inferrequest interface

* solve cpplint problem

* Finished OV 2.0 C-APIs PPP related development

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

* Fix code review issues

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

* Add ov::tensor API

* add compiled model func

* Finished C-API funs about core, model, node development

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

* [OV 2.0 C-API] add const to ov_output_node

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

* [OV 2.0 C-API] Using define GET_OV_ELEMENT_TYPE & GET_CAPI_ELEMENT_TYPE in tensor APIs

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

* [OV 2.0 C-API] add string initialize

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

* add inferrequest func

* add move construction to runtime_model

* supplement two infer request interface functions

* [OV 2.0 C-API] Add the common framwork of unit test

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

* modify ov_infer_request_get_profiling_info

* add tests dir

* restore CMakeLists.txt

* Fix the bug of COPY in Tensor

* [OV 2.0 C API] Finished core related function unite test

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

* Add ov:Tensor API test

* [OV 2.0 C API] fix some review issues

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

* add some infer request test

* add compiled model test

* [OV 2.0 C API] Finished preprocess related function unite test

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

* [OV 2.0 C API] Fix review issues

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

* [OV 2.0 C API] Modify to use default model

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

* transfer device_name from fix value to parameter

* add some infer request test

* remove compiled model get_property test

* add infer request tests

* Add ov::model Test and modify Tensor Test name

* Determine whether partial shape meets the standard

* Add get tensor name function and Modify reshape test case

* modify fixed tensor name,remove unnecessary comparison

* add ov_model_get_nodes_info, modify according to comments

* Update reshape test

* extract common function, modify interface about get tensor name,shape and type

* modify according comments

* [OV 2.0 C API] Finished hello classification with ov 2.0 c-api development

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

* [OV 2.0 C API] Fixed hello classification with ov 2.0 c-api review issues

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

* [OV 2.0 C API] delete inactive code hello classification with ov 2.0 c-api

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

* Fix clang format issue

* [OV 2.0 C API] rename

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

* Fix windows build erre

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

* Apply qsort for sorting data

Apply qsort for sarting data
Fix issues of "potentially uninitialized local pointer variable"

* Not use deprecated INSTANTIATE_TEST_CASE_P for c api gtest

INSTANTIATE_TEST_CASE_P is deprecated, should use INSTANTIATE_TEST_SUITE_P.

* Fix some review issues

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

* [Ov 2.0 C API] Add error info

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

* Fix some review issues

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

* Fix review issues

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

* polish error message for ov c api

* Redefined ov_shape_t, ov_partial_shape_t and ov_layout_t. Modified functions and test cases involving these variables

* Added the conversion between char* and partial_shape

* Add partial_shape_to_shape

* prune code

* modify split

* Use regex to split and search pattern

* Modify str_to_char_array delete

* Add the judgment of rank

* Fix compiling error

Fix issue: address of array 'shape.dims' will always evaluate to 'true'  if -Wpointer-bool-conversion

Co-authored-by: xuejun <Xuejun.Zhai@intel.com>
Co-authored-by: sunxiaoxia2022 <xiaoxia.sun@intel.com>
Co-authored-by: ruiqi <ruiqi.yang@intel.com>
2022-06-09 10:39:07 +08:00
Roman Baranchuk
0231637441
[CPU] GatherTree: dynamic shapes support (#11544) 2022-06-09 10:18:51 +08:00
Karol Blaszczak
fe41b8eacc
Docs multiplugin page-wide tabs merge (#11461) (#11784)
* Docs multiplugin page-wide tabs merge

porting to master changes aligning multi plugin with other articles already present in 22.1

* Update docs/snippets/MULTI4.cpp

* Update docs/snippets/MULTI4.cpp
2022-06-08 16:56:37 +02:00
hyunback kim
41a0d3a0f8
[GPU] Add oneDNN zero point value debug log. (#11817)
* [GPU] Add oneDNN zero point value debug log.

Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-06-08 22:01:16 +09:00
Sungeun Kim
2c4cb88862
[83906] DG2 Systolic engine not getting used for fp16 Action Recognition model (#11815)
* shallow feature convolution needs to set by zyx_fsv2

* bug fix: wrong get_output_layout calling in is_mixedLayout
2022-06-08 16:48:40 +09:00
Mykhailo Hnap
9ee9f880bd
[GPU] Implement Bucketize-3 (#11738)
* [GPU] Implement Bucketize-3

* Add i8 and u8 to evaluates map for bucketize op.
2022-06-08 15:47:19 +09:00
yanlan song
bd02415ad5
enable binder schedule for preview (#11763)
* 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>

Co-authored-by: Chen Peter <peter.chen@intel.com>
2022-06-08 10:02:33 +08:00
Tetiana Gubanova
a3cd2bcc49
[GPU] Implement Reverse operation (#11672)
* Reverse operation single-layer test

* Reverse CreateOp(), primitive and kernel selector

* Implement Reverse CL kernel

* Implement reverse GPU unit tests

* Add boolean as extended input type to reverse operation
2022-06-08 09:46:52 +09:00
Steve Yoo
263c184b97
Fix deformable convolution cl kernel for Multi-Groups (#11613)
* Fix deformable convolution cl kernel for multi group and add its test cases

* Add batch 2, 3, 4 test case to multiple groups
2022-06-08 09:45:42 +09:00
David Nam
755394c1cb
[GPU] Use IE_THROW() instead of throw std::runtime_error (#11769)
* Use IE_THROW() instead of throw std::runtime_error

* Change all of throw std::runtime_error into IE_THROW()
2022-06-08 09:44:59 +09:00
Karol Blaszczak
e70074d9db
DOCS-clear out the integrate_with_app article (#11799)
* DOCS-clear out the integrate_with_app article

* Update docs/OV_Runtime_UG/integrate_with_your_application.md

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

Co-authored-by: Yuan Xu <yuan1.xu@intel.com>
2022-06-07 21:52:27 +02:00
Karol Blaszczak
275f2adf52
DOCS-add supported PdPd models (#11804) 2022-06-07 21:51:17 +02:00
Eddy Kim
3a5805fce0
quick fix in tests (#11812) 2022-06-07 15:22:39 +00:00
hyunback kim
98f989302a
[GPU] Update to use immad with oneDNN test case. (#11808)
Update correct test case

Signed-off-by: hyunback <hyunback.kim@intel.com>
2022-06-07 17:08:23 +03:00
Felix Dohyun Kim
1c9cd04f96
[GPU] Enable blocked formats in Gather primitive (#11486)
* gather blocked format
* enable double blocked
* 5d test
* support cross dimension
* Add some disabled test for later use
* Support non-default planar formats
2022-06-07 17:50:09 +09:00
Felix Dohyun Kim
c1f4cc04de
[GPU] Enable blocked formats in Border primitive (#11652)
* fix default_value of border tensor parameters
* Enable all in/out layout
2022-06-07 17:39:57 +09:00
Min, Byungil
49942c2f80
[GPU] Forcing to use clDNN FC on small batch size (#11715)
+ forced to use clDNN FC due to perf drop

Signed-off-by: byungilm <byungil.min@intel.com>
2022-06-07 10:25:14 +03:00
Kelvin Choi
f9afe07c9d
[GPU] Add reorder between FC matmal and reshape (#11706) 2022-06-07 13:10:58 +09:00