Optical Comb-Based Monolithic Photonic-Electronic Accelerators for Self-Attention Computation

This paper adopts advanced monolithic silicon-photonics integrated-circuits manufacturing capabilities to realize system-on-chip photonic-electronic linear-algebra accelerators for self-attention computation in various applications of deep-learning neural networks and Large Language Models. With the features of holistic co-design approaches, optical comb-based broadband modulations, and consecutive matrix-multiplication architecture, the system/circuit/device-level simulations of the proposed accelerator can achieve 2.14-TMAC/s/mm² computation density and 27.9-fJ/MAC energy efficiency with practical considerations of power/area overhead due to photonic-electronic on-chip conversions, integrations, and calibrations.