Get Started for FREE
Sign up with Facebook Sign up with X
I don't have a Facebook or a X account
 Your new post is loading...
Scoop.it!
The WSE (pronounced “wise”) is the largest commercial chip ever manufactured, built to solve the problem of deep learning compute. The WSE is 1.2 trillion transistors, packed onto a single 215mm x 215mm chip with 400,000 AI-optimized cores, connected by a 100Pbit/s interconnect. The cores are fed by 18 GB of super-fast, on-chip memory, with an unprecedented 9 PB/s of memory bandwidth. 
No comment yet.
Sign up to comment
Scoop.it!
Superlatives abound at Cerebras, the until-today stealthy next-generation silicon chip company looking to make training a deep learning model as quick as buying toothpaste from Amazon. Launching after almost three years of quiet development, Cerebras introduced its new chip today — and it is a doozy.
Farid Mheir's insight:
WHY IT MATTERS: this is a BIG deal in hardware design. Being able to fabricate such a large system enables capabilities to a scale previously unheard of. Read this article for a high level overview, watch the next blog post for an in depth description.
|
Curated by Farid Mheir
Get every post weekly in your inbox by registering here: http://fmcs.digital/newsletter-signup/
|
WHY IT MATTERS: this article and accompanying PDF presentation dive into the technical details of how it is now possible to put 1 trillion transistor on a chip designed for the sole purpose of machine learning. This is a BIG DEAL.
Slides and word document are here:
https://secureservercdn.net/198.12.145.239/a7b.fcb.myftpupload.com/wp-content/uploads/2019/08/HC31_1.13_Cerebras.SeanLie.v02.pdf