Peking University researchers develop new all-optical interconnect system linking standard electronic chips with specific algorithms
2 -MIN READ 2 -MIN

As AI models permeate ever more applications, the industry’s appetite for computational power has grown insatiable. The conventional response has been to pile on more GPUs and build ever-larger data centres in a seemingly endless race for energy and brute force.
The work was published in the journal National Science Review, and its corresponding authors include Shu Haowen and Wang Xingjun from Peking University. (A digital object identifier for the paper appears at the end of the story.)
The “joints” connecting these FPGAs are two custom-designed communication hardware components. The first is a silicon photonic transceiver chip running at 400 gigabits per second, responsible for converting electrical signals to optical and vice versa.