Panel-Scale Reconfigurable Photonic Interconnects for Scalable AI Computation

TL;DR

This paper proposes a novel, large-scale reconfigurable photonic interconnect system on glass substrates that enables high-bandwidth, low-energy optical data links for scalable AI computing, integrating advanced photonic components.

Contribution

It introduces a new panel-scale photonic switch fabric enabling all-directional inter-panel communication without active repeaters, suitable for heterogeneous AI system integration.

Findings

Supports panel-edge-to-panel-edge communication over large areas

Achieves high data bandwidth density with WDM optical links

Offers low energy consumption and reconfigurability

Abstract

Panel-scale reconfigurable photonic interconnects on a glass substrate up to 500-mm x 500-mm or larger are envisioned by proposing a novel photonic switch fabric that enables all directional panel-edge-to-panel-edge reach without the need for active repeaters while offering high communication bandwidth, planar-direction reconfigurability, low energy consumption, and compelling data bandwidth density for heterogeneous integration of an in-package AI computing system on a single glass-substrate photonic interposer exceeding thousands of centimeters square. The proposed approach focuses on reconfigurable photonic interconnects, which are integration-compatible with commercial processor chiplets and 3D high-bandwidth memory (HBM) stacks on a large-area glass substrate, to create a novel panel-scale heterogeneously integrated interposer or package enabling low-energy and high-capacity wavelength-division-multiplexing (WDM) optical data links using advanced high-speed optical modulators, broadband photodetectors, novel optical crossbar switches with multi-layer waveguides, and in-package frequency comb sources.