ANDREY: Let's link to all 5 of the other HDDL-R docs here, as a list;
- 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
hddldaemon
service.
NOTE: This guide does not apply to Uzel* cards.
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
As of 8/13/2019, the following links were for the latest software:
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 script
withsudo
, 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
.
The hddldaemon
is a system service, a binary executable that is run to manage the computational workload on the board. It’s a required abstraction layer that handles inference, graphics processing, and any type of computation that should be run on the VPUs (video processing units). Depending on the board configuration, there will be 8 or 16 VPUs.
NOTE: Graphics and other specialized processing may require some custom development.
<IE>
refers to the following default OpenVINO Inference Engine Directories:
- Linux:
/opt/intel/openvino/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.
<IE>\external\hddl\config\hddl_service.config
DAVID: See this non-existent reference document for complete details.
Below are some possible configuration options.
NOTE: After changing a configuration file, the hddldaemon
must be restarted.
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)base
full
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:
tape
table
(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”
)
Programming a Python Application for the Intel® Vision Accelerator Design with Intel® Movidius™ VPUs for use with Intel® Distribution of OpenVINO™ toolkit
[DAVID] TBD will add after receiving source from Aleks Sutic.