Stochastic Computing with Integrated Optics

TL;DR

This paper explores implementing stochastic computing using integrated optics to enhance processing speed and energy efficiency, demonstrating a high-speed optical architecture for polynomial functions with optimized design parameters.

Contribution

It introduces a novel optical architecture for stochastic computing, enabling faster processing and energy-efficient polynomial computations in the optical domain.

Findings

Achieved 1 GHz operation speed.

Reduced laser energy consumption to 20.1 pJ per bit.

Demonstrated robustness and power optimization in optical stochastic circuits.

Abstract

Stochastic computing (SC) allows reducing hardware complexity and improving energy efficiency of error resilient applications. However, a main limitation of the computing paradigm is the low throughput induced by the intrinsic serial computing of bit-streams. In this paper, we address the implementation of SC in the optical domain, with the aim to improve the computation speed. We implement a generic optical architecture allowing the execution of polynomial functions. We propose design methods to explore the design space in order to optimize key metrics such as circuit robustness and power consumption. We show that a circuit implementing a 2 nd order polynomial degree function and operating at 1Ghz leads to 20.1pJ laser consumption per computed bit.