It doesn’t really make much sense to go faster than silicon node changes unless there is a lot of optimisation on architecture that needs doing. Historically all these refreshes between nodes were largely pointless with small benefits and preparing them took development effort away from the big changes. It’s progress in silicon that matters and brings the performance improvements and moving to a faster cadence hasn’t historically worked out well.
And the algorithm AI does magic to make our product more awesome than the competitor.
Yeah, the lack of formal definition of what is and is not considered ai definitely muddies the waters when talking about applications and capabilities.
It doesn’t really make much sense to go faster than silicon node changes unless there is a lot of optimisation on architecture that needs doing. Historically all these refreshes between nodes were largely pointless with small benefits and preparing them took development effort away from the big changes. It’s progress in silicon that matters and brings the performance improvements and moving to a faster cadence hasn’t historically worked out well.
I wonder when AI will be designing its own chips. Or parts of its chip.
Ai is already being incorporated into chip design tools like synopsys. TechTechPotato has an interesting interview with Aart de Geus that is relevant.
Ai is far off from making high level design improvments, but it can greatly reduce the workload on trace and route and other design steps.
The great thing about blanket terms like “AI” is that you can slap it on everything.
Yeah, the lack of formal definition of what is and is not considered ai definitely muddies the waters when talking about applications and capabilities.