An Optical XNOR-Bitcount Based Accelerator for Efficient Inference of Binary Neural Networks

TL;DR

This paper introduces a novel optical accelerator for binary neural networks using a single-MRR-based XNOR gate and a new bitcount circuit, significantly improving throughput and energy efficiency over previous photonic accelerators.

Contribution

It presents a new optical XNOR gate and a Photo-Charge Accumulator for BNN acceleration, enhancing area, energy efficiency, and throughput in photonic neural network accelerators.

Findings

Up to 62x increase in frames-per-second (FPS)

Up to 7.6x improvement in FPS per watt (energy efficiency)

Demonstrated on four modern BNNs with a custom simulator.

Abstract

Binary Neural Networks (BNNs) are increasingly preferred over full-precision Convolutional Neural Networks(CNNs) to reduce the memory and computational requirements of inference processing with minimal accuracy drop. BNNs convert CNN model parameters to 1-bit precision, allowing inference of BNNs to be processed with simple XNOR and bitcount operations. This makes BNNs amenable to hardware acceleration. Several photonic integrated circuits (PICs) based BNN accelerators have been proposed. Although these accelerators provide remarkably higher throughput and energy efficiency than their electronic counterparts, the utilized XNOR and bitcount circuits in these accelerators need to be further enhanced to improve their area, energy efficiency, and throughput. This paper aims to fulfill this need. For that, we invent a single-MRR-based optical XNOR gate (OXG). Moreover, we present a novel design of bitcount circuit which we refer to as Photo-Charge Accumulator (PCA). We employ multiple OXGs in a cascaded manner using dense wavelength division multiplexing (DWDM) and connect them to the PCA, to forge a novel Optical XNOR-Bitcount based Binary Neural Network Accelerator (OXBNN). Our evaluation for the inference of four modern BNNs indicates that OXBNN provides improvements of up to 62x and 7.6x in frames-per-second (FPS) and FPS/W (energy efficiency), respectively, on geometric mean over two PIC-based BNN accelerators from prior work. We developed a transaction-level, event-driven python-based simulator for evaluation of accelerators (https://github.com/uky-UCAT/B_ONN_SIM).