Nvidia predicts doubling of AI performance

The development of graphics processing units (GPUs) will help the industry double its artificial intelligence performance every year, Nvidia, the world’s leading graphics computing firm, told an online tech forum on Tuesday.

Nvidia researchers are defining ways to make faster AI chips in systems with greater bandwidth that are easier to program, Bill Dally, Nvidia’s chief scientist, said in a keynote speech.

The company described the development as Huang’s Law — a prediction named after Nvidia CEO Jensen Huang that GPUs will double AI performance every year.

“If we really want to improve computer performance, Huang’s Law is the metric that matters, and I expect it to continue for the foreseeable future,” said Dally.

Huang’s Law follows Moore’s Law, a prediction by American engineer Gordon Moore in 1965 that the number of transistors on a computer chip would double every 18–24 months.