Redwood tests AI-designed silicon

Autonomous flow targets physical AI inference.

September 1, 2026

Jon Peddie

Architect Labs has put a concrete architecture behind its claim that AI can design an accelerator from specification through live hardware deployment. Redwood Nano runs transformer inference today on an AMD Versal FPGA, while an AI system generated its RTL, verification collateral, firmware, drivers, and compute kernels in under two weeks. The project remains a prototype and a projection, yet it offers silicon teams, ISVs, and CIOs a useful look at how hardware-software co-design could change. Architect Labs says Redwood is a frontier AI accelerator that is an automated system designed, verified, and deployed from scratch in under two weeks.

...

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

Redwood tests AI-designed silicon

Enjoy full access with a TechWatch subscription!

This content is restricted

Login