Reuse and Blend: Energy-Efficient Optical Neural Network Enabled by Weight Sharing

TL;DR

This paper introduces a reuse and blend architecture for optical neural networks that significantly reduces energy consumption and latency by enabling efficient weight sharing, addressing the scale limitations of micro-ring resonator arrays.

Contribution

The paper presents a novel R&B architecture that supports layer-wise and block-wise weight sharing in ONNs, reducing reprogramming needs and improving efficiency.

Findings

Achieves 69% energy savings

Reduces latency by 57%

Maintains comparable accuracy

Abstract

Optical neural networks (ONN) based on micro-ring resonators (MRR) have emerged as a promising alternative to significantly accelerating the massive matrix-vector multiplication (MVM) operations in artificial intelligence (AI) applications. However, the limited scale of MRR arrays presents a challenge for AI acceleration. The disparity between the small MRR arrays and the large weight matrices in AI necessitates extensive MRR writings, including reprogramming and calibration, resulting in considerable latency and energy overheads. To address this problem, we propose a novel design methodology to lessen the need for frequent weight reloading. Specifically, we propose a reuse and blend (R&B) architecture to support efficient layer-wise and block-wise weight sharing, which allows weights to be reused several times between layers/blocks. Experimental results demonstrate the R&B system can maintain comparable accuracy with 69% energy savings and 57% latency improvement. These results highlight the promise of the R&B to enable the efficient deployment of advanced deep learning models on photonic accelerators.