Artificial Intelligence Accelerators based on Graphene Optoelectronic Devices

TL;DR

This paper introduces a graphene-based optoelectronic architecture for matrix-vector multiplication that leverages nanomaterials to achieve high throughput and low power, enabling scalable machine learning hardware.

Contribution

It presents a novel graphene-based system for MVM with a methodology to handle imperfections, demonstrating its versatility across various ML algorithms.

Findings

High data throughput and ultralow power consumption achieved.

Methodology for accurate calculations with imperfect components.

Successful implementation of ML algorithms like SVD, SVM, and neural networks.

Abstract

Optical and optoelectronic approaches of performing matrix-vector multiplication (MVM) operations have shown the great promise of accelerating machine learning (ML) algorithms with unprecedented performance. The incorporation of nanomaterials into the system can further improve the performance thanks to their extraordinary properties, but the non-uniformity and variation of nanostructures in the macroscopic scale pose severe limitations for large-scale hardware deployment. Here, we report a new optoelectronic architecture consisting of spatial light modulators and photodetector arrays made from graphene to perform MVM. The ultrahigh carrier mobility of graphene, nearly-zero-power-consumption electro-optic control, and extreme parallelism suggest ultrahigh data throughput and ultralow-power consumption. Moreover, we develop a methodology of performing accurate calculations with imperfect components, laying the foundation for scalable systems. Finally, we perform a few representative ML algorithms, including singular value decomposition, support vector machine, and deep neural networks, to show the versatility and generality of our platform.