Breaking News
German Statisticians Find the Same Result in Germany as the UK...
Greenwald: The Cynical And Dangerous Weaponization Of The "White Supremacist" Label
Is Peak Social Media Already Behind Us?
A Fearstorm Is Upon Us
Top Tech News
Check out the world's first FLOATING CITY! Flood-proof Oceanix - backed by the UN...
Wireless sensor grows into bone to monitor health data in real-time
One dollars worth of Melatonin reduces clotting, sepsis and death for Covid.
Budget Alpine home uses the sun as No-Bill climate-control
Fun Wind Turbine build that makes electricity
Taxi! To the Airport -- by Air, Please.
Getting Off the Electrical Grid - #SolutionsWatch
Rolls-Royce's electric plane hits 387 mph to lay claim as world's fastest
Diabolical -- How Digital ID Will Control Your Life
Lesson in joyful, smiling courage! Teacher Kath who lost all four limbs to sepsis and was...
Tesla Dojo, Supercomputers and AI
There does not seem to be a limit for neural nets to utilize more resources to get better and faster results.
Tesla is motivated to develop bigger, faster computers that are precisely suited to their needs.
The Google TPU architecture has not evolved as much over the last 5 years. The Google TPU chip is designed for the problems that Google runs. They are not optimized for training AI.
Tesla has rethought the problem of AI training and designed the Dojo AI supercomputer to optimally solve their problems.
If Tesla commercializes the AI supercomputer that will help to get to lower costs and greater power with more economies of scale.
One of the reasons that TSMC overtook Intel was that TSMC was making most of the ARM chips for cellphones. TSMC having more volume let them learn faster and drive down costs and accelerate technology.
99% of what neural network nodes do are 8 by 8 matrix multiply and 1% that is more like a general computer. Tesla created a superscalar GPU to optimize for this compute load.