* Feature/azaytsev/cldnn doc fixes (#4600) * Legal fixes, removed the Generating docs section * Removed info regarding generating docs Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> * Feature/azaytsev/gna model link fixes (#4599) * Added info on DockerHub CI Framework * Feature/azaytsev/change layout (#3295) * Changes according to feedback comments * Replaced @ref's with html links * Fixed links, added a title page for installing from repos and images, fixed formatting issues * Added links * minor fix * Added DL Streamer to the list of components installed by default * Link fixes * Link fixes * ovms doc fix (#2988) * added OpenVINO Model Server * ovms doc fixes Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> * Updated openvino_docs.xml * Link Fixes Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> * Fix for broken CC in CPU plugin (#4595) * Azure CI: Add "ref: releases/2021/3" * Fixed clone rt info (#4597) * [.ci/azure] Enable CC build (#4619) * Formula fix (#4624) * Fixed transformation to pull constants into Loop body (cherry-pick of PR 4591) (#4607) * Cherry-pick of PR 4591 * Fixed typo * Moved a check into the parameter_unchanged_after_iteration function * Fixed KW hits (#4638) * [CPU] Supported ANY layout for inputs in inferRequest (#4621) * [.ci/azure] Add windows_conditional_compilation.yml (#4648) (#4655) * Fix for MKLDNN constant layers execution (#4642) * Fix for MKLDNN constant layers execution * Single mkldnn::engine for all MKLDNN graphs * Add workaround for control edges to support TF 2.4 RNN (#4634) Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Corrected PyYAML dependency (#4598) (#4620) 5.4.2 is absent on PyPI * [CPU] Statically analyzed issues. (#4637) * Docs api (#4657) * Updated API changes document * Comment for CVS-49440 * Add documentation on how to convert QuartzNet model (#4664) * Add documentation on how to convert QuartzNet model (#4422) * Add documentation on how to convert QuartzNet model * Apply review feedback * Small fix * Apply review feedback * Apply suggestions from code review Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Add reference to file Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Fixed bug in assign elimination transformation. (#4644) * [doc] Updated PyPI support OSes (#4643) (#4662) * [doc] Updated PyPI support OSes (#4643) * Updated PyPI support OSes * Added python versions for win and mac * Update pypi-openvino-dev.md * Update pypi-openvino-dev.md * Update pypi-openvino-rt.md * Update pypi-openvino-dev.md Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> * [IE][VPU]: Fix empty output of CTCGreedyDecoderSeqLen (#4653) * Allow the second output of CTCGreedyDecoderSeqLen to be nullptr in cases when it is not used but calculated in the Myriad plugin. In this case, parse the second output as FakeData * It is a cherry-pick of #4652 * Update the firmware to release version * [VPU] WA for Segmentation fault on dlclose() issue (#4645) * Document TensorFlow 2* Update: Layers Support and Remove Beta Status (#4474) (#4711) * Document TensorFlow 2* Update: Layers Support and Remove Beta Status Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Update documentation based on latest test results and feedback Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Remove ConvLSTM2D from supported layers list Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Document Dot layer without limitation Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Address feedback upon DenseFeatures and RNN operations Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Do a grammar correction Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Do a grammar correction based on feedback Signed-off-by: Roman Kazantsev <roman.kazantsev@intel.com> * Updated nGraph custom op documentation (#4604) * Updated nGraph custom op documentation * Fixed comments * [IE CLDNN] Fix missing variable initializations and types (#4669) * Fix NormalizeL2 creation in QueryNetwork (cherry pick from master PR 4310) (#4651) * Updated documentation about the supported YOLOv3 model from ONNX (#4722) (#4726) * Restored folded Operations for QueryNetwork (#4685) * Restored folded Operations for QueryNetwork * Fixed comment * Add unfolded constant operations to supported layers map * Add STN to list of supported models (#4728) * Fix python API for Loop/TensorIterator/Assign/ReadValue operations * Catch std::except in fuzz tests (#4695) Fuzz tests must catch all expected exceptions from IE. IE is using C++ std library which may raise standard exceptions which IE pass through. * Docs update (#4626) * Updated latency case desc to cover multi-socket machines * updated opt guide a bit * avoiding '#' which is interpreted as ref * Update CPU.md * Update docs/optimization_guide/dldt_optimization_guide.md Co-authored-by: Alina Alborova <alina.alborova@intel.com> * Update docs/optimization_guide/dldt_optimization_guide.md Co-authored-by: Alina Alborova <alina.alborova@intel.com> * Update docs/optimization_guide/dldt_optimization_guide.md Co-authored-by: Alina Alborova <alina.alborova@intel.com> * Update docs/optimization_guide/dldt_optimization_guide.md Co-authored-by: Alina Alborova <alina.alborova@intel.com> * Update docs/optimization_guide/dldt_optimization_guide.md Co-authored-by: Alina Alborova <alina.alborova@intel.com> Co-authored-by: Alina Alborova <alina.alborova@intel.com> * Blocked dims hwc 2021/3 (#4729) * Fix for BlockedDims * Added test for HWC layout * [GNA] Update documentation regarding splits and concatenations support (#4740) * Added mo.py to wheel packages (#4731) * Inserted a disclaimer (#4760) * Fixed some klockwork issues in C API samples (#4767) * Feature/vpu doc fixes 2021 3 (#4635) * Documentation fixes and updates for VPU * minor correction * minor correction * Fixed links * updated supported layers list for vpu * [DOCS] added iname/oname (#4735) * [VPU] Limit dlclose() WA to be used for Ubuntu only (#4806) * Fixed wrong link (#4817) * MKLDNN weights cache key calculation algorithm changed (#4790) * Updated PIP install instructions (#4821) * Document YOLACT support (#4749) * Document YOLACT support * Add preprocessing section * Apply suggestions from code review Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> * Add documentation on how to convert F3Net model (#4863) * Add instruction for F3Net model pytorch->onnx conversion * Fix style * Fixed dead lock in telemetry (#4873) * Fixed dead lock in telemetry * Refactored TelemetrySender.send function * Refactored send function implementation to avoid deadlocks * Unit tests for telemetry sender function * Added legal header * avladimi/cvs-31369: Documented packages content to YUM/APT IGs (#4839) * Documented runtime/dev packages content * Minor formatting fixes * Implemented review comments * Update installing-openvino-apt.md Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> * [DOC] Low-Precision 8-bit Integer Inference (#4834) * [DOC] Low-Precision 8-bit Integer Inference * [DOC] Low-Precision 8-bit Integer Inference: comment fixes * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * Update docs/IE_DG/Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * [DOC] LPT comments fix * [DOC] LPT comments fix: absolute links are updated to relative * Update Int8Inference.md * Update Int8Inference.md Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> Co-authored-by: Andrey Zaytsev <andrey.zaytsev@intel.com> * Avladimi/cherry pick from master (#4892) * Fixed CVS-48061 * Reviewed and edited the Customization instructions * Fixed broken links in the TOC * Fixed links * Fixed formatting in the IG for Raspberry * Feature/benchmarks 2021 3 (#4910) * added new topics, changed the intro text * updated * Updates * Updates * Updates * Updates * Updates * Added yolo-v4-tf and unet-camvid-onnx graphs * Date for pricing is updated to March 15th * Feature/omz link changes (#4911) * Changed labels for demos and model downloader * Changed links to models and tools * Changed links to models and tools * Changed links to demos * [cherry-pick] Extensibility docs review (#4915) * Feature/ovsa docs 2021 3 (#4914) * Updated to 2021-3, fixed formatting issues * Fixed formatting issues * Fixed formatting issues * Fixed formatting issues * Update ovsa_get_started.md * Clarification of Low Latency Transformation and State API documentation (#4877) * Assign/ReadValue, LowLatency and StateAPI clarifications * Apply suggestions from code review: spelling mistakes Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> * fixed wording * cherry-pick missing commit to release branch: low latency documentation * Resolve review remarks Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> Co-authored-by: Svetlana Dolinina <svetlana.a.dolinina@intel.com> * DevCloud call outs (#4904) * [README.md] change latest release to 2021.3 * [49342] Update recommended CMake version on install guide in documentation (#4763) * Inserted a disclaimer * Another disclaimer * Update installing-openvino-windows.md * Update installing-openvino-windows.md * Update installing-openvino-windows.md * Feature/doc fixes 2021 3 (#4971) * Made changes for CVS-50424 * Changes for CVS-49349 * Minor change for CVS-49349 * Changes for CVS-49343 * Cherry-pick #PR4254 * Replaced /opt/intel/openvino/ with /opt/intel/openvino_2021/ as the default target directory * (CVS-50786) Added a new section Reference IMplementations to keep Speech Library and Speech Recognition Demos * Doc fixes * Replaced links to inference_engine_intro.md with Deep_Learning_Inference_Engine_DevGuide.md, fixed links * Fixed link * Fixes * Fixes * Reemoved Intel® Xeon® processor E family * fixes for graphs (#5057) * compression.configs.hardware config to package_data (#5066) * update OpenCV version to 4.5.2 (#5069) * update OpenCV version to 4.5.2 * Enable mo.front.common.extractors module (#5038) * Enable mo.front.common.extractors module (#5018) * Enable mo.front.common.extractors module * Update package_BOM.txt * Test MO wheel content * fix doc iframe issue - 2021.3 (#5090) * wrap with htmlonly * wrap with htmlonly * Add specification for ExperimentalDetectron* oprations (#5128) * Feature/benchmarks 2021 3 ehl (#5191) * Added EHL config * Updated graphs * improve table formatting * Wrap <iframe> tag with \htmlonly \endhtmlonly to avoid build errors * Updated graphs * Fixed links to TDP and Price for 8380 * Add PyTorch section to the documentation (#4972) * Add PyTorch section to the documentation * Apply review feedback * Remove section about loop * Apply review feedback * Apply review feedback * Apply review feedback * doc: add Red Hat docker registry (#5184) (#5253) * Incorporate changes in master Co-authored-by: Trawinski, Dariusz <dariusz.trawinski@intel.com> Co-authored-by: Vladislav Volkov <vladislav.volkov@intel.com> Co-authored-by: azhogov <alexander.zhogov@intel.com> Co-authored-by: Ilya Churaev <ilya.churaev@intel.com> Co-authored-by: Alina Kladieva <alina.kladieva@intel.com> Co-authored-by: Evgeny Lazarev <evgeny.lazarev@intel.com> Co-authored-by: Gorokhov Dmitriy <dmitry.gorokhov@intel.com> Co-authored-by: Roman Kazantsev <roman.kazantsev@intel.com> Co-authored-by: Mikhail Ryzhov <mikhail.ryzhov@intel.com> Co-authored-by: Nikolay Shchegolev <nikolay.shchegolev@intel.com> Co-authored-by: Ilya Lavrenov <ilya.lavrenov@intel.com> Co-authored-by: Maxim Vafin <maxim.vafin@intel.com> Co-authored-by: Anastasiya Ageeva <anastasiya.ageeva@intel.com> Co-authored-by: Anastasia Popova <anastasia.popova@intel.com> Co-authored-by: Maksim Doronin <maksim.doronin@intel.com> Co-authored-by: Andrew Bakalin <andrew.bakalin@intel.com> Co-authored-by: Mikhail Letavin <mikhail.letavin@intel.com> Co-authored-by: Anton Chetverikov <Anton.Chetverikov@intel.com> Co-authored-by: Ivan Tikhonov <ivan.tikhonov@intel.com> Co-authored-by: Andrey Somsikov <andrey.somsikov@intel.com> Co-authored-by: Maxim Shevtsov <maxim.y.shevtsov@intel.com> Co-authored-by: Alina Alborova <alina.alborova@intel.com> Co-authored-by: Elizaveta Lobanova <elizaveta.lobanova@intel.com> Co-authored-by: Andrey Dmitriev <andrey.dmitriev@intel.com> Co-authored-by: Helena Kloosterman <helena.kloosterman@intel.com> Co-authored-by: Tatiana Savina <tatiana.savina@intel.com> Co-authored-by: Edward Shogulin <edward.shogulin@intel.com> Co-authored-by: Svetlana Dolinina <svetlana.a.dolinina@intel.com> Co-authored-by: Alexey Suhov <alexey.suhov@intel.com> Co-authored-by: Sergey Lyubimtsev <sergey.lyubimtsev@intel.com> Co-authored-by: Dmitry Kurtaev <dmitry.kurtaev+github@gmail.com> Co-authored-by: Nikolay Tyukaev <nikolay.tyukaev@intel.com> Co-authored-by: Kate Generalova <kate.generalova@intel.com>
6.2 KiB
Intel® Movidius™ VPUs Setup Guide for Use with Intel® Distribution of OpenVINO™ toolkit
Note
: These steps are only required for IEI Mustang-V100-MX8-R10 card. IEI Mustang-V100-MX8-R11 card doesn't require any additional steps and it's completely configured using the general guidance.
See Also
- Intel® Movidius™ VPUs Programming Guide for use with the Intel® Distribution of OpenVINO™
- Intel® Vision Accelerator Design with Intel® Movidius™ VPUs HAL Configuration Guide
- Intel® Vision Accelerator Design with Intel® Movidius™ VPUs Workload Distribution User Guide
- Intel® Vision Accelerator Design with Intel® Movidius™ VPUs Scheduler User Guide
- Intel® Vision Accelerator Design with Intel® Movidius™ VPUs Errata
The IEI Mustang-V100-MX8 is an OEM version of the Intel® Vision Accelerator Design with Intel® Movidius™ VPUs. This guide assumes you have installed the Mustang-V100-MX8 and the Intel® Distribution of OpenVINO™ Toolkit.
Instructions in this guide for configuring your accelerator include:
- Installing the required IEI* BSL reset software
- Configuration settings for the
hddldaemonservice
Note
: This guide does not apply to Uzel* cards.
IEI Reset Software Installation
Using the IEI Mustang-V100-MX8 requires downloading and installing the most current software for your system.
Visit the IEI Download Center for the most current software and documentation. Search for Mustang-V100-MX8.
Download the appropriate software for your system, decompress the downloaded archive, enter the newly created directory, and run the install script:
On Linux*:
- Run the
install.sh scriptwithsudo, or asroot.
On Windows*, do one of the following:
- GUI: Double-click
install.bat - CLI: Open a console with administrator privileges, cd into the directory, and run
install.bat.
Mustang-V100-MX8 Service Configuration
The hddldaemon is a system service, a binary executable that is run to manage the computational workload on the board. It is a required abstraction layer that handles inference, graphics processing, and any type of computation that should be run on the video processing units (VPUs). Depending on the board configuration, there can be 8 or 16 VPUs.
Note
: Graphics and other specialized processing may require some custom development.
Conventions Used in This Document
<IE> refers to the following default OpenVINO™ Inference Engine directories:
- Linux:
/opt/intel/openvino_2021/inference_engine
- Windows:
C:\Program Files (x86)\IntelSWTools\openvino\inference_engine
If you have installed OpenVINO™ in a different directory on your system, you will need to enter your unique directory path.
Configuration File Location
<IE>\external\hddl\config\hddl_service.config
Service Configuration File Settings
Below are some possible configuration options.
NOTE: After changing a configuration file, the
hddldaemonmust be restarted.
Recommended Settings
device_snapshot_mode
Changes the output of the hddldaemon to display a table with individual VPU statistics.
Default Setting:
"device_snapshot_mode": "none"
Suggested Setting:
"device_snapshot_mode": "full"
Supported Settings:
none(default)basefull
device_snapshot_style
Default Setting:
"device_snapshot_style": "table"
Recommended Setting:
"device_snapshot_style": "table"
The table setting presents labels on the left for each column and is recommended as easier to read.
The tape setting prints the labels in each column.
Supported Settings:
tapetable(default)
user_group
Restricts the service to group members.
Recommended setting depends on your unique system configuration.
Default Setting
"user_group": "users"
The hddldaemon may be restricted to a privileged group of users. The appropriate group will vary according to the local system configuration.
Supported Settings:
Valid groups on the current system. The "users" group is a default group that exists on Windows and most Linux distributions.
Optional Recommended Settings:
"device_utilization" : "off"
This setting displays the percent of time each VPU is in use. It appears in the table column when turned on, or if "device_fps" is turned on.
"memory_usage" : "off"
This setting reports the amount of memory being used by each VPU.
"max_cycle_switchout": 3
Requires the squeeze scheduler. This setting might speed up performance significantly, depending on the app.
NOTE: This setting works in conjunction with:
max_task_number_switch_out.
"client_fps" : "off"
This setting reports the total FPS for the dispatching hddl_service (which will have one or more clients per app).
debug_service
"debug_service": "false"
(default: "true")