Integrated on-chip all-optical supernode executes deep neural network inference directly with light waves at sub-ns speeds

https://www.eurekalert.org/news-releases/1134883

"electronic AI subject to bottlenecks: catastrophic power dissipation, strict bandwidth, latency, overcome performing neural network math natively with light... avoids repeatedly converting signals between optical/ electronic... virtually no computational latency... scalable on-chip supernode architecture establishes a critical foundation for next-generation, high-throughput computing platforms optimized for edge intelligence and real-time machine learning tasks... matrix-vector multiplication"