Posted on by

Google’s latest offerings that bring AI to edge computing

Google has announced two products “aimed at helping customers develop and deploy intelligent connected devices at scale”  –  Edge TPU, a hardware chip, and Cloud IoT Edge, a software stack that extends Google Cloud’s powerful AI capability to gateways and connected devices.
Google said on its official blog that the new products will let companies build and train ML models in the Cloud, then run those models on the Cloud IoT Edge device through the power of the Edge TPU hardware accelerator.
 
Edge TPU is Google’s purpose-built ASIC chip designed to run TensorFlow Lite ML models at the edge. The design of Edge TPU is such it focuses on optimizing for “performance per watt” and “performance per dollar” within a small footprint.
Edge TPUs are designed to complement the Cloud TPU offering, to accelerate ML training in the Cloud, then have lightning-fast ML inference at the edge. Sensors running them, said Google, will become more than data collectors—they make local, real-time, intelligent decisions.
Edge TPU Chip

The Edge TPU chip, shown with a standard U.S. penny for reference

Cloud IoT Edge is the software that extends Google Cloud’s powerful data processing and ML capabilities to gateways, cameras, and end devices, “making IoT applications smarter, more secure and more reliable.”

It lets you execute ML models trained in Google Cloud on the Edge TPU or on GPU- and CPU-based accelerators. Cloud IoT Edge can run on Android Things or Linux OS-based devices.

Some of its key components are:

  • A runtime for gateway class devices, with at least one CPU, to locally store, translate, process, and derive intelligence from data at the edge, while seamlessly interoperating with the rest of Cloud IoT platform.
  • The Edge IoT Core runtime that more securely connects edge devices to the cloud, enabling software and firmware updates and managing the exchange of data with Cloud IoT Core.
  • The TensorFlow Lite-based Edge ML runtime that performs local ML inference using pre-trained models, significantly reducing latency and increasing the versatility of edge devices. Because the Edge ML runtime interfaces with TensorFlow Lite,

The Edge TPU development kit

This one, said Google, was to jump-start development and testing with the Edge TPU. The kit includes a system on module (SOM) that combines Google’s Edge TPU, a NXP CPU, Wi-Fi, and Microchip’s secure element in a compact form factor. It’ll will be available to developers this October. To request early access to the Edge TPU development kit, sign up via this form.

Edge TPU Deve kit

The Edge TPU development kit—SOM (above) and base board (below)

Image Credit: Google

 

Leave a Reply

Click here to opt out of Google Analytics