Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2022

After unveiling its enterprise Cloud Services Platform on the first day of its Cloud Next conference at the Moscone Center in San Francisco, CA, Google used Day 2 of the result to announce ii new products that the visitor says will assistance customers "develop and deploy intelligent connected devices at scale".

The first, Edge TPU, is a new IoT-focused hardware chip for the edge environment, while the second, Cloud IoT Edge, is a software stack that extends Google Cloud's AI capability to gateways and connected devices. Together, Google says the 2 products will allow users to "build and railroad train ML (machine learning) models in the cloud, and so run them on Cloud IoT Border devices via the Border TPU hardware accelerator".

Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018

Edge TPU

Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018

Edge TPU is Google'south purpose-congenital ASIC chip that the company says is designed to run its TensorFlow Calorie-free motorcar learning (ML) models at the edge. According to Google'due south IoT VP, Injong Rhee, while designing the chip, the company was "hyperfocused" on optimizing for 'operation per watt' and 'performance per dollar' inside a small footprint.

"Edge TPUs are designed to complement our Deject TPU offer, so you lot can advance ML preparation in the cloud, then have lightning-fast ML inference at the edge. Your sensors become more than data collectors—they brand local, real-fourth dimension, intelligent decisions"

Cloud IoT Border

Cloud IoT Edge consists of two components: the Edge IOT Cadre gateway functions and Edge ML, a runtime that is based on the lightweight open up-source ML framework, TensorFlow Lite, and can run models on edge devices that are based on Android Things or Linux OS. It extends Google Cloud'due south data processing and machine learning capabilities to gateways, cameras and end devices, making IoT applications smarter, more than secure, and more reliable, co-ordinate to the company.

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

Border TPU Evolution Kit

Google Announces Edge TPU, Cloud IoT Edge at Cloud Next 2018

Google has also announced an Border TPU evolution kit that includes a system on module (SOM) that combines Google's Edge TPU, a NXP CPU, Wi-Fi, and Microchip'south secure element in a compact form gene. Information technology'll will be available to developers this Oct, says the company.