MIT researchers have developed a photonic-electronic reconfigurable SmartNIC called “Lightning” that accelerates modern computing by helping deep neural networks complete inference tasks like image recognition and language generation in chatbots. The prototype’s novel design enables impressive speeds, creating the first photonic computing system to serve real-time machine-learning inference requests. Despite its potential, a major challenge in implementing photonic computing devices is that they are passive, meaning they lack the memory or instructions to control dataflows. However, Lightning removes this obstacle to ensure data movement between electronic and photonic components runs smoothly.
