VSORA's Single Chip Package Aids in Generative AI Integration

By Chad Cox

Production Editor

Embedded Computing Design

August 22, 2023

News

VSORA's Single Chip Package Aids in Generative AI Integration
Image Credit: VSORA

Paris, France. VSORA is releasing a single-chip architecture*, Jotunn4, to optimize Generative AI integrations. Jotunn4 delivers 1.6 petaflops with an efficiency of more than 50% within a 45 x 45 mm package. The current general efficiency range is 2-4%. Included is 192 GB of on-chip memory and an overall power consumption of less than 100W.

“As ChatGPT and other generative AI continue reaching a fevered pitch, the semiconductor industry needs to step up with supporting hardware,” remarks Khaled Maalej, VSORA founder and CEO. “That’s what we intend to do with our single-chip architecture to trounce the memory wall and accelerate generative AI implementations.”

ChatGPT-3.5 is operated by Jotunn4 completely on-chip. Implementations of algorithms are simplified when the VSORA high-level language and graph compiler development flow is utilized.

“The VSORA ChatGPT-on-chip architecture can unleash the unbounded potential of Generative AI such as ChatGPT,” states Nicolas von Bülow, managing partner at Clipperton Finance, a VSORA financial adviser. “It will spearhead a paradigm shift in the semiconductor industry.”

For more inforamtion, visit vsora.com.

*Editors Note: VSORA architecture is algorithm agnostic, allowing existing as well as new algorithms to be run on any VSORA chip.

 

Chad Cox. Production Editor, Embedded Computing Design, has responsibilities that include handling the news cycle, newsletters, social media, and advertising. Chad graduated from the University of Cincinnati with a B.A. in Cultural and Analytical Literature.

More from Chad