Semidynamics announces 3 nm inference tape-out and a full-stack systems roadmap

Semidynamics moves to offer silicon.

February 4, 2026

David Harold

Semidynamics has taped-out a 3 nm AI inference chip and is expanding its scope into a vertically integrated offering that spans IP, silicon, boards, and rack-level systems. The company is positioning its design around a memory subsystem intended to improve inference efficiency and reduce exposure to premium-memory constraints. The announcement includes supportive statements from a wide group of European and global HPC/system partners, framing the effort as a European ecosystem play. Semidynamics announced it is moving into full-stack AI infrastructure, with a roadmap that includes inference chips, boards, and rack-scale systems aimed at next-generation data centers. The company says the

...

Enjoy full access with a TechWatch subscription!

TechWatch is the front line of JPR information gathering service, comprising current stories of interest to the graphics industry spanning the core areas of graphics hardware and software, workstations, gaming, and design.

A subscription to TechWatch includes 4 hours of consulting time to be used over the course of the subscription.

Already a subscriber? Login below

Semidynamics announces 3 nm inference tape-out and a full-stack systems roadmap

Enjoy full access with a TechWatch subscription!

This content is restricted

Login