Nvidia says AI cuts 10-month, eight-engineer GPU design task to overnight job — company is still ‘a long way’ from AI designing chips without human input

Nvidia says it is trying to introduce artificial intelligence to every stage of the chip design process, drastically reducing development time. Notably, the company has revealed that porting a standard cell library, a task that previously took eight engineers 10 months to complete, can now be done overnight by a single GPU. However, the company’s chief scientist, William Dally, says that artificial intelligence is still not quite close to designing a processor completely by itself.

“We are trying to use AI wherever we can in our design process,” Dally told Google’s Jeff Dean. “I would love to have the end-to-end stage where I could simply say, ‘design me the new GPU,’ but I think we are a long way from that.”

Nvidia is already using AI across multiple stages of chip design, from circuit-level optimizations to system-level exploration, and achieves orders-of-magnitude productivity gains and, in some cases, better-than-human results, according to Dally.

Article continues below

At the lowest level, AI has already transformed standard cell development, one of the most time-consuming steps when transitioning to a new fabrication process. Porting a standard cell library of roughly 2,500–3,000 cells previously required a team of eight engineers working for about 10 months, according to Dally. Nvidia has replaced this work with a reinforcement learning system called…