By using this site, you agree to the Privacy Policy and Terms of Use.
Accept
Weekly DailyWeekly Daily
Notification Show More
Latest News
USDT Thunder International Ltd Ignites a Global Crypto Revolution with DeFi-Powered Wealth Ecosystem
July 4, 2025
Jogesh Mahal: Two Decades of Crafting Memories in Agartala
July 2, 2025
Shaping Destinies: How Bright Future Academy Became Agartala’s Beacon for Government Job Aspirants
July 2, 2025
Navigating the Future: Career Opportunities in Artificial Intelligence, Data Science, and Machine Learning
July 1, 2025
Veer Pet: Pioneering High-Quality Plastic Packaging Solutions from Durgapur
June 21, 2025
Aa
  • Home
  • Insider
  • Politics
  • Startup
  • Discover
  • Brand Stories
Reading: The Google’s AI Supercomputer Boasts Faster And More Eco-Friendly Performance Compared To Nvidia A100 Chip
Share
Aa
Weekly DailyWeekly Daily
  • ES Money
  • U.K News
  • The Escapist
  • Entertainment
  • Politics
  • Technology
  • Insider
Search
  • Home
  • Insider
  • Politics
  • Startup
  • Discover
  • Brand Stories
Follow US
Home » Blog » The Google’s AI Supercomputer Boasts Faster And More Eco-Friendly Performance Compared To Nvidia A100 Chip
Computer

The Google’s AI Supercomputer Boasts Faster And More Eco-Friendly Performance Compared To Nvidia A100 Chip

WM Team
WM Team Published April 5, 2023
Last updated: 2023/04/05 at 7:56 AM
Share
Google AI Supercomputer
SHARE

Google has unveiled new information regarding the supercomputers it uses to train its artificial intelligence models. According to the tech giant, its custom-designed Tensor Processing Unit (TPU) chips are faster and more energy-efficient than comparable systems from Nvidia.

These chips are utilized in over 90% of Google’s work on artificial intelligence training, powering tasks such as generating images and responding to queries with human-like text. Google published a scientific paper detailing how it combined over 4,000 of these chips into a supercomputer using its custom-built optical switches to connect individual machines.

The connections are essential for training large language models that have grown significantly in size and cannot be stored on a single chip.

By allowing for easy reconfiguration of connections between chips, Google said its supercomputers can avoid problems and improve performance. The tech giant also revealed that its chips are up to 1.7 times faster and 1.9 times more power-efficient than comparable systems based on Nvidia’s A100 chip. Google suggested that it is working on a new TPU that could compete with Nvidia’s H100, but did not provide any further details.

You Might Also Like

Embracing New Beginnings: Welcoming 2024 with Joy and Hope

Rajiv Gandhi Assassination Convict: Controversy

Churachandpur Unrest: Manipur Enforces Prohibitory Orders Amid Ethnic Clashes

Toshiba Delisting: Paving the Way for a New Era in Japanese Business

Udaan Layoffs: Restructuring Initiatives Lead to Workforce Reduction

TAGGED: Google AI Supercomputer, weeklymail, weeklymail.in
WM Team April 5, 2023
Share this Article
Facebook Twitter Whatsapp Whatsapp LinkedIn Email Copy Link Print
Leave a comment

Leave a Reply Cancel reply

You must be logged in to post a comment.

You Might Also Like

Fashion

Embracing New Beginnings: Welcoming 2024 with Joy and Hope

December 31, 2023
rajiv gandhi
news

Rajiv Gandhi Assassination Convict: Controversy

December 27, 2023
A child with Flag
Politics

Churachandpur Unrest: Manipur Enforces Prohibitory Orders Amid Ethnic Clashes

December 23, 2023
Technology

Toshiba Delisting: Paving the Way for a New Era in Japanese Business

December 20, 2023

2023 © Weekly Mail Network. All Rights Reserved.

Removed from reading list

Undo
Welcome Back!

Sign in to your account

Lost your password?