Google TPU chips to be made available to external developers

By Jonathan Dyble
In a blog post, Google has revealed that its AI accelerator chips have now been made available in a limited number to external customers looking to deve...

In a blog post, Google has revealed that its AI accelerator chips have now been made available in a limited number to external customers looking to develop machine learning technologies on the Google Cloud Platform.

The Cloud tensor processing units (TPUs) are Google’s in-house hardware accelerators that are designed to speed up machine learning (ML) programmes that have been developed using Google’s TensorFlow software.

See also:

Each TPU has been built with four AI-based application specific integrated circuits (ASICs), providing up to 180 teraflops of performance and 64GB of memory in a single chip, built specifically to be implemented in ML supercomputers.

“Since working with Google Cloud TPUs, we’ve been extremely impressed with their speed—what could normally take days can now take hours,” said Anatha Kancherla, Head of Software, Self-Driving Level 5, Lyft.

“Deep learning is fast becoming the backbone of the software running self-driving cars. The results get better with more data, and there are major breakthroughs coming in algorithms every week.”

The move comes less than two years after the company launched its TPU project back in 2016.

Share

Featured Articles

Study shows 91% of organisations fear ransomware attacks

Amid an economic downturn, staffing shortages and endless cyberattacks, financially motivated attacks are the top concern among IT professionals

Ransomware defence could keep the lights on for millions

A new algorithm could help prevent ransomware attacks on power companies in the United States which could cause national blackouts affecting millions

Now is the ideal time to drive deep tech disruption

Deep tech may seem like it's years away but now is the time for organisations to be building a deep tech strategy, according to insights by BCG

UK has a technology trust problem among older bank customers

Cloud & Cybersecurity

McLaren Racing & Alteryx Analytics: Data-driven to win

Enterprise IT

Bitcoin’s climate footprint is a step in the wrong direction

Data & Data Analytics