Summary of BOXER-8521AI: POWER AI EDGE COMPUTING WITH GOOGLE® EDGE™ TPU
The BOXER-8521AI is a rugged, fanless AI Edge platform from AAEON that integrates the Google Edge TPU SoM and PoE PD for flexible, remote deployments. It supports dual power input (PoE PD and DC) for redundancy, offers up to 4 TOPS (2 TOPS/W) performance via NXP i.MX 8M plus Edge TPU coprocessor, and runs TensorFlow Lite with AutoML Vision Edge compatibility for streamlined model training and deployment.
Parts used in the BOXER-8521AI:
- AAEON BOXER-8521AI chassis (rugged, fanless)
- Google Edge TPU System-on-Module (SoM)
- NXP i.MX 8M SoC (quad Cortex-A53, Cortex-M4F)
- PoE PD port (Power over Ethernet Powered Device)
- DC-input power connector
- Flexible I/O loadout (networking and peripheral interfaces)
- Support for TensorFlow Lite software stack
- Compatibility with Google AutoML Vision Edge
AAEON, an industry leader in rugged AI Edge platforms, announces the BOXER-8521AI is now available on a mass-market scale. Winner of the 2021 Taiwan Excellence Award, the BOXER-8521AI combines the flexibility of PoE PD deployment with the Google® Edge™ TPU in a rugged, fanless system designed to bring AI Edge Computing to where it’s needed.
Recently awarded the Taiwan Excellence Award for 2021, the BOXER-8521AI is focused on providing flexibility in deployment and connectivity. The BOXER-8521AI features a PoE PD port, allowing the system to be deployed further away from its power source, as well as enable internet connection and remote monitoring of the system over the same single cable, reducing the complexity of installation. Additionally, by utilizing both the PoE PD port and DC-input, the system can continue operating even if one power supply is cut off.
The BOXER-8521AI powers AI Edge Computing thanks to the Google Edge TPU System-on-Module (SoM) with a rugged chassis and flexible I/O loadout. The Google Edge TPU combines the NXP i.MX 8M SoC (quad Cortex-A53, Cortex-M4F) with the Google Edge TPU coprocessor to deliver speeds up to 4 TOPS at an energy-efficient 2 TOPS per Watt.
Thanks to the Google Edge TPU, developers and users who deploy the BOXER-8521AI have access to Google’s suite of training software, AutoML Vision Edge. This innovative software helps developers quickly develop and train AI models utilizing Google’s vast cloud services, and then export the model to the BOXER-8521AI and Google Edge TPU. The system supports TensorFlow Lite, a framework that allows for more efficient models, better system performance and processing speeds.
Read more: BOXER-8521AI: POWER AI EDGE COMPUTING WITH GOOGLE® EDGE™ TPU
- What is the main processor architecture used in the BOXER-8521AI?
The system uses the NXP i.MX 8M SoC with quad Cortex-A53 and a Cortex-M4F. - Does the BOXER-8521AI support Power over Ethernet?
Yes, it features a PoE PD port for PoE deployment and network connectivity over a single cable. - Can the BOXER-8521AI continue operating if one power source fails?
Yes, using both the PoE PD port and DC-input allows continued operation if one power supply is cut off. - What AI accelerator does the BOXER-8521AI include?
It includes the Google Edge TPU coprocessor as part of the Edge TPU SoM. - How much inference performance does the BOXER-8521AI deliver?
The Google Edge TPU delivers speeds up to 4 TOPS at an energy-efficient 2 TOPS per Watt. - Which machine learning frameworks are supported on the BOXER-8521AI?
The system supports TensorFlow Lite and is compatible with models from AutoML Vision Edge. - What benefit does AutoML Vision Edge provide for BOXER-8521AI users?
AutoML Vision Edge helps developers quickly develop and train AI models using Google's cloud services and export them to the BOXER-8521AI and Edge TPU. - Is the BOXER-8521AI designed for harsh environments?
Yes, it is a rugged, fanless system intended for AI Edge deployments.
