The physics of optical computing

TL;DR

This paper systematically explains the potential advantages of optical computing over electronic computing, focusing on how to harness multiple optical features for speed and energy efficiency, especially in neural network applications.

Contribution

It provides a detailed analysis of the physical features of optics that can be exploited in optical computer design, clarifying misconceptions about the role of light speed.

Findings

Optical computing offers potential speed and energy benefits through specific physical features.

Careful design combining multiple optical features is necessary for advantages over electronic processors.

Understanding optical features helps avoid pitfalls in developing optical computing architectures.

Abstract

There has been a resurgence of interest in optical computing over the past decade, both in academia and in industry, with much of the excitement centered around special-purpose optical computers for neural-network processing. Optical computing has been a topic of periodic study for over 50 years, including for neural networks three decades ago, and a wide variety of optical-computing schemes and architectures have been proposed. In this paper we provide a systematic explanation of why and how optics might be able to give speed or energy-efficiency benefits over electronics for computing, enumerating 11 features of optics that can be harnessed when designing an optical computer. One often-mentioned motivation for optical computing -- that the speed of light $c$ is fast -- is not a key differentiating physical property of optics for computing; understanding where an advantage could come from is more subtle. We discuss how gaining an advantage over state-of-the-art electronic processors will likely only be achievable by careful design that harnesses more than one of the 11 features, while avoiding a number of pitfalls that we describe.