[DOCS] ARM CPU plugin docs #10885

alvoron · 2022-03-10T20:06:17Z

TODO:

get disclaimer wording from Matthew and add it to device page
update the list of supported layers

ARM_CPU.md added ARM CPU is added to the list of supported devices

docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md

ilya-lavrenov · 2022-03-11T13:47:24Z

docs/OV_Runtime_UG/supported_plugins/ARM_CPU.md

+### Read-write properties
+All parameters must be set before calling `ov::Core::compile_model()` in order to take effect or passed as additional argument to `ov::Core::compile_model()`
+
+- ov::enable_profiling


I suppose you also support streams, pinning, etc
@apankratovantonp please, provide a full list of properties.

Thus these options are in the supported list they do not provide expected threading control. We even test only in latency (sync) mode only. I am going to enable tbb threading backend and provide full threading control as in the CPU plugin. It won't give any valuable throughput gain but give full threading control. So we can claim support of these options.

docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md

terfendail · 2022-03-11T19:11:29Z

docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md

+| Activation-Not                 | Supported     |Supported\*\*\*| Supported     | Not Supported | ?     | Supported     |
+| Activation-PReLU               | Supported     |Supported\*\*\*| Supported     | Not Supported | Supported     | Supported     |
+| Activation-ReLU                | Supported     |Supported\*\*\*| Supported     | Supported     | Supported     | Supported     |
+| Activation-ReLU6               | Supported     |Supported\*\*\*| Supported     | Not Supported | ?     | Supported     |


There is no spec for ReLU-6

terfendail · 2022-03-11T19:14:58Z

docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md

+| Cosh                           | Supported     | Supported\*\* | Not Supported | Not Supported |Supported\*\*\*\*| Supported     |
+| Crop                           | Supported     | Supported     | Supported     | Supported     | ?     | Supported     |
+| CTCGreedyDecoder               | Supported\*\* | Supported\*\* | Supported\*   | Not Supported |Supported\*\*\*\*| Supported     |
+| Deconvolution                  | Supported     | Supported     | Supported     | Not Supported | ? | Supported     |


There are no specs for Deconvolution and Crop.
However I've found mention of a Crop layer in the issue created in 2018

terfendail · 2022-03-11T19:18:35Z

docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md

+| Eltwise-Mul                    | Supported     |Supported\*\*\*| Supported     | Supported     | Supported     | Supported     |
+| Eltwise-NotEqual               | Supported     |Supported\*\*\*| Supported     | Not Supported | Supported\*   | Supported     |
+| Eltwise-Pow                    | Supported     |Supported\*\*\*| Supported     | Not Supported | Supported     | Supported     |
+| Eltwise-Prod                   | Supported     |Supported\*\*\*| Supported     | Supported     | ?     | Supported     |


There is no spec for Eltwise-Prod

terfendail · 2022-03-11T19:20:11Z

docs/OV_Runtime_UG/supported_plugins/Supported_Devices.md

+| Eltwise-Prod                   | Supported     |Supported\*\*\*| Supported     | Supported     | ?     | Supported     |
+| Eltwise-SquaredDiff            | Supported     |Supported\*\*\*| Supported     | Not Supported | Supported     | Supported     |
+| Eltwise-Sub                    | Supported     |Supported\*\*\*| Supported     | Supported     | Supported     | Supported     |
+| Eltwise-Sum                    | Supported     |Supported\*\*\*| Supported     | Supported     | ?     | Supported     |


There is no spec for Eltwise-Sum. Should it be considered CumSum layer?

Update the list of supported layers

alalek

Need to align:

The ARM® CPU plugin
The Arm® CPU plugin

alalek · 2022-03-12T15:55:50Z

docs/OV_Runtime_UG/supported_plugins/ARM_CPU.md

+## Introducing the Arm&reg; CPU Plugin
+The ARM&reg; CPU plugin is developed in order to enable deep neural networks inference on Arm&reg; CPU, using [Compute Library](https://github.com/ARM-software/ComputeLibrary) as a backend.
+
+The Arm&reg; CPU plugin is not a part of the Intel® Distribution of OpenVINO™ toolkit and is not distributed in pre-built form. To use the plugin, it should be buid from source code. Plugin build procedure is described on [How to build Arm&reg; CPU plugin](https://github.com/openvinotoolkit/openvino_contrib/wiki/How-to-build-ARM-CPU-plugin). 


should be built

described on ... page ?

alalek · 2022-03-12T15:57:47Z

docs/OV_Runtime_UG/supported_plugins/ARM_CPU.md

+
+- Floating-point data types:
+  - f32
+  - f16


F32 as it is used below in this form.

I set f32 everywhere

* initial commit ARM_CPU.md added ARM CPU is added to the list of supported devices * Update the list of supported properties * Update Device_Plugins.md * Update CODEOWNERS * Removed quotes in limitations section * NVIDIA and Android are added to the list of supported devices * Added See Also section and reg sign to arm * Added Preprocessing acceleration section * Update the list of supported layers * updated list of supported layers * fix typos * Added support disclaimer * update trade and reg symbols * fixed typos * fix typos * reg fix * add reg symbol back Co-authored-by: Vitaly Tuzov <vitaly.tuzov@intel.com>

ilya-lavrenov · 2022-03-18T12:22:20Z

Ported as a part of #11040, please, check that everything is correct

* Added migration for deployment (#10800) * Added migration for deployment * Addressed comments * more info after the What's new Sessions' questions (#10803) * more info after the What's new Sessions' questions * generalizing the optimal_batch_size vs explicit value message * Update docs/OV_Runtime_UG/automatic_batching.md Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Update docs/OV_Runtime_UG/automatic_batching.md Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Update docs/OV_Runtime_UG/automatic_batching.md Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Update docs/OV_Runtime_UG/automatic_batching.md Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Update docs/OV_Runtime_UG/automatic_batching.md Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Update docs/OV_Runtime_UG/automatic_batching.md Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Perf Hints docs and General Opt Guide refactoring (#10815) * Brushed the general optimization page * Opt GUIDE, WIP * perf hints doc placeholder * WIP * WIP2 * WIP 3 * added streams and few other details * fixed titles, misprints etc * Perf hints * movin the runtime optimizations intro * fixed link * Apply suggestions from code review Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * some details on the FIL and other means when pure inference time is not the only factor * shuffled according to general->use-case->device-specifics flow, minor brushing * next iter * section on optimizing for tput and latency * couple of links to the features support matrix * Links, brushing, dedicated subsections for Latency/FIL/Tput * had to make the link less specific (otherwise docs compilations fails) * removing the Temp/Should be moved to the Opt Guide * shuffled the tput/latency/etc info into separated documents. also the following docs moved from the temp into specific feature, general product desc or corresponding plugins - openvino_docs_IE_DG_Model_caching_overview - openvino_docs_IE_DG_Int8Inference - openvino_docs_IE_DG_Bfloat16Inference - openvino_docs_OV_UG_NoDynamicShapes * fixed toc for ov_dynamic_shapes.md * referring the openvino_docs_IE_DG_Bfloat16Inference to avoid docs compilation errors * fixed main product TOC, removed ref from the second-level items * reviewers remarks * reverted the openvino_docs_OV_UG_NoDynamicShapes * reverting openvino_docs_IE_DG_Bfloat16Inference and openvino_docs_IE_DG_Int8Inference * "No dynamic shapes" to the "Dynamic shapes" as TOC * removed duplication * minor brushing * Caching to the next level in TOC * brushing * more on the perf counters ( for latency and dynamic cases) Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Updated common IE pipeline infer-request section (#10844) * Updated common IE pipeline infer-reqest section * Update ov_infer_request.md * Apply suggestions from code review Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com> Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> * DOCS: Removed useless 4 spaces in snippets (#10870) * Updated snippets * Added link to encryption * [DOCS] ARM CPU plugin docs (#10885) * initial commit ARM_CPU.md added ARM CPU is added to the list of supported devices * Update the list of supported properties * Update Device_Plugins.md * Update CODEOWNERS * Removed quotes in limitations section * NVIDIA and Android are added to the list of supported devices * Added See Also section and reg sign to arm * Added Preprocessing acceleration section * Update the list of supported layers * updated list of supported layers * fix typos * Added support disclaimer * update trade and reg symbols * fixed typos * fix typos * reg fix * add reg symbol back Co-authored-by: Vitaly Tuzov <vitaly.tuzov@intel.com> * Try to fix visualization (#10896) * Try to fix visualization * New try * Update Install&Deployment for migration guide to 22/1 (#10933) * updates * update * Getting started improvements (#10948) * Onnx updates (#10962) * onnx changes * onnx updates * onnx updates * fix broken anchors api reference (#10976) * add ote repo (#10979) * DOCS: Increase content width (#10995) * fixes * fix * Fixed compilation Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> Co-authored-by: Karol Blaszczak <karol.blaszczak@intel.com> Co-authored-by: Aleksandr Voron <aleksandr.voron@intel.com> Co-authored-by: Vitaly Tuzov <vitaly.tuzov@intel.com> Co-authored-by: Ilya Churaev <ilya.churaev@intel.com> Co-authored-by: Yuan Xu <yuan1.xu@intel.com> Co-authored-by: Victoria Yashina <victoria.yashina@intel.com> Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com>

alvoron added 7 commits March 10, 2022 23:03

initial commit

f52be4d

ARM_CPU.md added ARM CPU is added to the list of supported devices

Update the list of supported properties

726e168

Update Device_Plugins.md

3d54d83

Update CODEOWNERS

cf7995b

Removed quotes in limitations section

afa2786

NVIDIA and Android are added to the list of supported devices

8693870

Added See Also section and reg sign to arm

ff9d64e

terfendail reviewed Mar 11, 2022

View reviewed changes

docs/OV_Runtime_UG/supported_plugins/Device_Plugins.md Outdated Show resolved Hide resolved

ilya-lavrenov added this to the 2022.1 milestone Mar 11, 2022

ilya-lavrenov added the port to master Required port to master from 2022.3 LTS label Mar 11, 2022

ilya-lavrenov reviewed Mar 11, 2022

View reviewed changes

alvoron and others added 2 commits March 11, 2022 18:30

Added Preprocessing acceleration section

ea126af

Update the list of supported layers

58c4851

terfendail reviewed Mar 11, 2022

View reviewed changes

alvoron added 2 commits March 12, 2022 10:12

Merge pull request #1 from terfendail/alvoron-arm-docs

392b1ad

Update the list of supported layers

updated list of supported layers

fc4acb1

alvoron added the do not merge label Mar 12, 2022

alalek reviewed Mar 12, 2022

View reviewed changes

alvoron added 2 commits March 12, 2022 21:56

fix typos

e3a0687

Added support disclaimer

446a6f6

alvoron marked this pull request as ready for review March 15, 2022 10:03

alvoron requested a review from a team as a code owner March 15, 2022 10:03

alvoron requested review from a team and avladimi and removed request for a team March 15, 2022 10:03

Merge branch 'releases/2022/1' into alvoron-arm-docs

3a068ec

ilya-lavrenov approved these changes Mar 15, 2022

View reviewed changes

alvoron added 5 commits March 15, 2022 14:00

update trade and reg symbols

d6afd07

fixed typos

76404a6

fix typos

ecca576

reg fix

6da600a

add reg symbol back

27bcbff

alvoron removed the do not merge label Mar 15, 2022

azhogov merged commit 6cf81ad into openvinotoolkit:releases/2022/1 Mar 15, 2022

alvoron deleted the alvoron-arm-docs branch March 15, 2022 14:24

ilya-lavrenov added ported to master Ported from 2022.x branches to master and removed port to master Required port to master from 2022.3 LTS labels Mar 18, 2022

Provide feedback

Saved searches

Use saved searches to filter your results more quickly

[DOCS] ARM CPU plugin docs #10885

[DOCS] ARM CPU plugin docs #10885

alvoron commented Mar 10, 2022 •

edited

Loading

ilya-lavrenov Mar 11, 2022

apankratovantonp Mar 11, 2022

terfendail Mar 11, 2022

terfendail Mar 11, 2022

terfendail Mar 11, 2022

terfendail Mar 11, 2022

alalek left a comment

alalek Mar 12, 2022

alalek Mar 12, 2022

alvoron Mar 12, 2022

ilya-lavrenov commented Mar 18, 2022

[DOCS] ARM CPU plugin docs #10885

[DOCS] ARM CPU plugin docs #10885

Conversation

alvoron commented Mar 10, 2022 • edited Loading

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

alalek left a comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

Choose a reason for hiding this comment

ilya-lavrenov commented Mar 18, 2022

alvoron commented Mar 10, 2022 •

edited

Loading