Breaking News
The Deep State's Get-Out-Of-Jail-Free Card
Why Not Stop Mass Immigration into the United States?
French President Macron's Popularity Falls to Record Low of 16 Per Cent
Top Signs You're Heading for a Quagmire
Top Tech News
NASA Super Light Solar Sail Project Will Be 12-40 Times Lighter and Faster
Space Telescope Interferometer to Image Exoplanet Continents
Twenty-five years of "temporary": how 9/11 built a surveillance state Americans never vote
I'll Never Buy Another WALMART Battery!
Shoei GT-Air 3 Smart helmet drops with built-in AR for $1,500
Freezable titanium plate keeps your cooler chilled way longer than ice packs
Review: Affordable thermal device is made for discovering life outdoors
AI Whistleblower Tells Tucker How AI Could Kill All Humans by 2040
You Hate Flock? Well There's More...
Will Spiking Diesel Prices Drive Autonomous Trucking?
1.2 Trillion Transistors on a Wafer-Scale AI Chip
It is 56x larger than any other chip. It delivers more compute, more memory, and more communication bandwidth. This enables AI research at previously-impossible speeds and scale.
The Cerebras Wafer Scale Engine 46,225 square millimeters with 1.2 Trillion transistors and 400,000 AI-optimized cores.
By comparison, the largest Graphics Processing Unit is 815 square millimeters and has 21.1 Billion transistors.
Andrew Feldman and the Cerebras team have built the wafer-scale integrated chip. They have successfully solved issues of yield, power delivery, cross-reticle connectivity, packaging, and more. It has a 1,000x performance improvement over what's currently available. It also contains 3,000 times more high speed, on-chip memory, and has 10,000 times more memory bandwidth.
It has a complex system of water-cooling. It uses an irrigation network to counteract the extreme heat generated by a chip running at 15 kilowatts of power.