Computing the SVD efficiently with photonic chips

TL;DR

This paper explores how hybrid digital-photonic systems can efficiently compute the SVD, offering comparable speed to digital computers but with significantly lower energy consumption, promising for large-scale data processing.

Contribution

It demonstrates that hybrid photonic-digital systems can match CPU/GPU performance while reducing energy use in SVD computations.

Findings

Hybrid systems perform on par with large-scale CPU/GPU in runtime.

Hybrid systems significantly reduce energy consumption.

Photonic chips are promising for scalable data processing.

Abstract

In light of today's massive data processing, digital computers are reaching fundamental performance limits due to physical limitations and energy consumption. For specific applications, tailored analog systems offer promising alternatives to digital processors. In this work, we investigate the potential of linear photonic chips for accelerating the computation of the singular value decomposition (SVD) of a matrix. The SVD is a key primitive in linear algebra and forms a crucial component of various modern data processing algorithms. Our main insights are twofold: first, hybrid systems of digital controller and photonic chip asymptotically perform on par with large-scale CPU/GPU systems in terms of runtime. Second, such hybrid systems clearly outperform digital systems in terms of energy consumption.