Poster 118: Self-Driving Reconfigurable Silicon Photonic Interconnects (Flex-LIONS) with Deep Reinforcement Learning

Authors: Roberto Proietti (University of California, Davis), Yu Shang (University of California, Davis), Xian Xiao (University of California, Davis), Xiaoliang Chen (University of California, Davis), Yu Zhang (University of California, Davis), SJ Ben Yoo (University of California, Davis)

Abstract: We propose a self-driving reconfigurable optical interconnect architecture for HPC systems exploiting a deep reinforcement learning (DRL) algorithm and a reconfigurable silicon photonic (SiPh) switching fabric to adapt the interconnect topology to different traffic demands. Preliminary simulation results show that after training, the DRL-based SiPh fabric provides the lowest average end-to-end latency for time-varying traffic patterns.

Best Poster Finalist (BP): no

Poster: PDF
Poster summary: PDF


Back to Poster Archive Listing