Breaking News
Everything I Warned You About Just Happened... All in One Week
Your Grief, My Grief, Our Grief in the Loss of a Loved One
Vance: Federal Government Has Identified $230 Billion In Fraud Since March
Saudi Arabia's $5 Oil Detour Is Expensive... But Worth It
Top Tech News
What could possibly go wrong? Scientists use AI to design new viruses
Dual-motor suitcase drive underpins 3,000-hp hypercar
DoorDash Wins Federal Approval To Fly Its Own Delivery Drones
Shade-Resistant Solar Cells Retain 97% Efficiency After 2,000 Hours of Testing
20 Ancient Engineering SECRETS
Stonehenge Was Reanalyzed by AI -- And the Findings Are Hard to Explain
After Years Of Delays, Aptera Is Finally Preparing To Build Customer Cars
'When you kill it, it doesn't die': the jellyfish that has cracked the secret of immorta
Archer Aviation debuts Halo autonomous VTOL, Thunder's commercial twin
US Telecoms Slide On Starlink Mobile Threat; Bernstein Sees It As A "Jab, But No Knockout Yet**
Future Wafer Scale Chips Could Have 100 Trillion Transistors
They had 0.86 PetaFLOPS of performance on the single wafer system. The waferchip was built on a 16 nanomber FF process.
The WSE is the largest chip ever built. It is 46,225 square millimeters and contains 1.2 Trillion transistors and 400,000 AI optimized compute cores. The memory architecture ensures each of these cores operates at maximum efficiency. It provides 18 gigabytes of fast, on-chip memory distributed among the cores in a single-level memory hierarchy one clock cycle away from each core. AI-optimized, local memory fed cores are linked by the Swarm fabric, a fine-grained, all-hardware, high bandwidth, low latency mesh-connected fabric.
Wafer-scale chips were a goal of computer great Gene Amdahl decades ago. The issues preventing wafer-scale chips have now been overcome.
In an interview with Ark Invest, the Cerebras CEO talks about how they will beat Nvidia to make the processor for AI. The Nvidia GPU clusters take four months to set up to start work. The Cerebras can start being used in ten minutes. Each GPU needs two regular Intel chips to be usable.