Google says its AI supercomputer is faster, greener than Nvidia A100 chip


FILE PHOTO: The Google logo is pictured atop an office building in Irvine, California, U.S. August 7, 2017. REUTERS/Mike Blake

(Reuters) -Alphabet Inc's Google released on Tuesday new details about the supercomputers it uses to train its artificial intelligence models, saying the systems are both faster and more power-efficient than comparable systems from Nvidia Corp.

Google has designed its own custom chip called the Tensor Processing Unit, or TPU. It uses those chips for more than 90% of the company's work on artificial intelligence training, the process of feeding data through models to make them useful at tasks such as responding to queries with human-like text or generating images.

Save 30% OFF The Star Digital Access

Monthly Plan

RM 13.90/month

RM 9.73/month

Billed as RM 9.73 for the 1st month, RM 13.90 thereafter.

Best Value

Annual Plan

RM 12.33/month

RM 8.63/month

Billed as RM 103.60 for the 1st year, RM 148 thereafter.

Follow us on our official WhatsApp channel for breaking news alerts and key updates!

Next In Tech News

Is social media harmful for kids? Meta and YouTube face US trial after TikTok settles suit
It’s not a product. This habit will be the biggest luxury of 2026
Apple spent years downplaying AI chatbots. Now Siri Is becoming one
US judge signals Musk's xAI may lose lawsuit accusing Altman's OpenAI of stealing trade secrets
Apple stole our revolutionary camera technology, British company claims in US district court lawsuit
Exclusive-Saks ending e-commerce partnership with Amazon, source says
Nvidia's plan to invest up to $100 billion in OpenAI has stalled, WSJ reports
Musk's Starlink updates privacy policy to allow consumer data to train AI
Google defeats bid for billions of dollars of new penalties in US privacy class action
Analysis-Combining SpaceX with xAI may be simple for Musk Inc, but Tesla isn't so easy

Others Also Read