I/O-efficient iterative matrix inversion with photonic integrated circuits

TL;DR

This paper introduces a novel photonic iterative processor that significantly reduces input/output bottlenecks in matrix inversion tasks, achieving faster computation times and higher IO efficiency than existing electronic and photonic methods.

Contribution

The paper presents a new photonic iterative processor design that enables IO-efficient, high-speed matrix inversion and differential equation solving using integrated optical loops.

Findings

Achieved a net inversion time of 1.2 ns.

Demonstrated at least tenfold IO efficiency improvement over existing photonic and electronic processors.

Enabled complex-valued computations with integrated optical loops.

Abstract

Photonic integrated circuits have been extensively explored for optical processing with the aim of breaking the speed bottleneck of digital electronics. However, the input/output (IO) bottleneck remains one of the key barriers. Here we report a novel photonic iterative processor (PIP) for matrix-inversion-intensive applications. The direct reuse of inputted data in the optical domain unlocks the potential to break the IO bottleneck. We demonstrate notable IO advantages with a lossless PIP for real-valued matrix inversion and integral-differential equation solving, as well as a coherent PIP with optical loops integrated on-chip, enabling complex-valued computation and a net inversion time of 1.2 ns. Furthermore, we estimate at least an order of magnitude enhancement in IO efficiency of a PIP over photonic single-pass processors and the state-of-the-art electronic processors for reservoir training tasks and MIMO precoding tasks, indicating the huge potential of PIP technology in practical applications.