Notebookcheck Logo
, , , , , ,
search relation.
, , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , , ,

Edge TPUs revealed as the future of AI for Google at Next 2018

Google wants increased market coverage of enterprise data needs. (Source: Google)
Google wants increased market coverage of enterprise data needs. (Source: Google)
Google is aiming to bring its Cloud platform and AI solutions to the forefront of enterprise-level computing. The company outlined its plans to do so at its relevant Next '18 event in San Francisco this year. The Edge TPU, which could make Google's AI provision end-to-end, was also unveiled.
Deirdre O Donnell,

Google had previously emphasized its commitment to tensor processing units (TPUs) for its 'brand' of AI. Accordingly, attendees at the Next 2018 conference, an event mainly for enterprise-focused Google Cloud, were introduced to a new form of this technology: the Edge TPU.

The TPU is Google's take on the application-specific integrated circuit (ASIC). The ASIC, in turn, is a parallel-processing-oriented variation on a GPU for the purposes of neural network training. ASICs differ from GPUs in that they also supply libraries and instructions that allow the processor to operate on local data. Therefore, the ASIC may accelerate the training process compared to the GPU.

Google's existing TPUs run the company's proprietary TensorFlow training software in order to set up the desired neural network. The Edge TPU, on the other hand, is simply intended to carry out the tasks in question. This will enable Google to provision more AI components - i.e. software, data, and now both operating and executing hardware. In other words, it makes Google's AI services more end-to-end. An early example of Edge TPUs in action is found on LG production lines, where the units check TV panels for flaws.

Google also debuted its on-premises Google Kubernetes Engine (GKE On-Prem), which is intended to unify the data in a company's center and cloud environments. It is pretty clear from the Next 2018 sessions that Google wants to take over the world of enterprise data.

A 4-chip TPU board for Google Cloud. (Source: Google)
A 4-chip TPU board for Google Cloud. (Source: Google)


static version load dynamic
Loading Comments
Comment on this article
Deirdre O'Donnell
Deirdre O'Donnell - Senior Tech Writer - 5122 articles published on Notebookcheck since 2018
I became a professional writer and editor shortly after graduation. My degrees are in biomedical sciences; however, they led to some experience in the biotech area, which convinced me of its potential to revolutionize our health, environment and lives in general. This developed into an all-consuming interest in more aspects of tech over time: I can never write enough on the latest electronics, gadgets and innovations. My other interests include imaging, astronomy, and streaming all the things. Oh, and coffee.
contact me via: LinkedIn
Please share our article, every link counts!
> Notebook / Laptop Reviews and News > News > News Archive > Newsarchive 2018 08 > Edge TPUs revealed as the future of AI for Google at Next 2018
Deirdre O Donnell, 2018-08-16 (Update: 2020-09-24)