Nvidia turns to AI for design process improvements
 

Better than humans

Nvidia expects the complexity of integrated circuit design to increase exponentially in the coming years, and is looking to AI to help out.

During a talk at this year's GPU Technology Conference, Nvidia's chief scientist and senior vice president of research, Bill Dally, talked a great deal about using GPUs to accelerate various stages of the design process behind modern GPUs and other SoCs.

Nvidia believes that some tasks could be done better and much quicker using machine learning rather than humans doing by hand, freeing them to work on more advanced aspects of chip development.

Dally says Nvidia has identified four areas where using machine learning techniques can significantly impact the typical development timetable.

Mapping, where power is used in a GPU is an iterative process that takes three hours on a conventional CAD tool, but it only takes minutes using an AI model trained specifically for this task.

Once taught, the model can shave the time down to seconds. Of course, AI models trade speed for accuracy. Dally says Nvidia's tools already achieve 94 per cent accuracy.

https://fudzilla.com/news/ai/54732-n...s-improvements