Artificial Intelligence IoT

Google launched single-board AI enabled, TPU based computer for Edge computing

Search Engine giant Google launched TPU based single-board computer and a USB accelerator for Edge computing. Google branded it with the name “Coral Dev Board” and this device is essentially a single-board computer with many I/O interfaces including CPU, TPU, USB ports, LAN Ports and display port. Google also released USB accelerator which can be used with Edge computing.

With the release of these hardware developers can develop application around these devices to make IoT Enabled smart solutions.

Google brings machine learning to the Edge devices through this hardware. This hardware is specially designed to run machine learning job on Edge devices. Developer can develop machine learning application using TensorFlow Lite which will use on-board TPU to run machine learning job efficiently.

Google “Coral Dev Board” is one-board Edge computing device with TPU and TensorFlow execution environment. Operating system of this device is modified Linux and comes with decent RAM. This one-board computer features  8GB eMMC storage, 1GB LPDDR4 RAM, Wi-Fi and Bluetooth 4.1. The “Coral Dev Board” has USB 2.0/3.0 ports, 3.5mm audio jack, DSI display interface and  MIPI-CSI camera interface.  On the display side it comes with HDMI 2.0a connector and for sound it has two Digital PDM microphones.

This device is designed with small form factor in mind and developers can use it for accelerated ML processing on the Edge devices. These days computing at Edge devices are becoming popular due various benefits it provides.

This device can also be used for prototyping IoT devices and system for other embedded solutions. Google is offering this device at a price of $149.0.

This device also provides support for attached and Google is also offering $25 MIPI-CSI 5-megapixel camera for the dev board.

Coral dev board can be used as a single-board computer when you need accelerated ML processing in a small form factor.  It can also be used as an evaluation kit for the SOM and for prototyping IoT devices and other embedded systems. This board is available for $149.00. Google has also announced a $25 MIPI-CSI 5-megapixel camera for “Coral Dev Board”.

Google also announced the availability of USB Accelerator for “Coral Dev Board”. The USB Accelerator is available at a cost of $75.

Availability of these devices will accelerate the development of new machine learning applications for Edge devices and IoT devices. Developer can use TensorFlow Lite programming language for building machine learning model for both these devices.

Google will release more accessories like PCI-E Accelerator, system for integrating TPU with legacy system in near future.

Google is coming up with TensorFlow 2.0 very soon which will further enhance the use of this programming language in Machine learning and Deep Learning.

18,976 total views, 6 views today

Arunk Kumar
Arun Kumar has rich 10 years of experience in technical journalism. He is reporter and technical news author. He is also interested in Photo journalism and reporting.
Contact author at:
Mobile: +91 9250143898
Address: G-26/128, Sector-3, Rohini Delhi - 110085 India.

Leave a Reply

Your email address will not be published. Required fields are marked *