# A Winograd-based Integrated Photonics Accelerator for Convolutional Neural Networks

## TL;DR

This paper proposes a photonics-based CNN accelerator utilizing Winograd filtering, demonstrating potential for significant energy efficiency improvements over electronic platforms while maintaining competitive speed and power performance.

## Contribution

It introduces a novel photonic accelerator design for CNNs based on Winograd filtering, highlighting its advantages in speed and energy efficiency.

## Key findings

- Photonic accelerator can match electronic platforms in speed and power.
- Potential to improve energy efficiency by up to three orders of magnitude.
- Photonic approach offers a promising alternative for high-performance CNN hardware.

## Abstract

Neural Networks (NNs) have become the mainstream technology in the artificial intelligence (AI) renaissance over the past decade. Among different types of neural networks, convolutional neural networks (CNNs) have been widely adopted as they have achieved leading results in many fields such as computer vision and speech recognition. This success in part is due to the widespread availability of capable underlying hardware platforms. Applications have always been a driving factor for design of such hardware architectures. Hardware specialization can expose us to novel architectural solutions, which can outperform general purpose computers for tasks at hand. Although different applications demand for different performance measures, they all share speed and energy efficiency as high priorities. Meanwhile, photonics processing has seen a resurgence due to its inherited high speed and low power nature. Here, we investigate the potential of using photonics in CNNs by proposing a CNN accelerator design based on Winograd filtering algorithm. Our evaluation results show that while a photonic accelerator can compete with current-state-of-the-art electronic platforms in terms of both speed and power, it has the potential to improve the energy efficiency by up to three orders of magnitude.