4F optical neural network acceleration: an architecture perspective

Puneet Gupta; Shurui Li

doi:10.1117/12.2614731

2 March 2022 4F optical neural network acceleration: an architecture perspective

Puneet Gupta, Shurui Li

Proceedings Volume 12019, AI and Optical Data Sciences III; 120190B (2022) https://doi.org/10.1117/12.2614731
Event: SPIE OPTO, 2022, San Francisco, California, United States

Abstract

Low latency, high throughput inference on Convolution Neural Networks (CNNs) remains a challenge, especially for applications requiring large input or large kernel sizes. 4F optics provides a solution to potentially accelerate CNN inferences with Fourier optics and the well-known convolution theorem. However, existing 4F CNN accelerators suffer from various limitations that make the implementation of a multi-channel, multi-layer CNN not scalable or even impractical. In this paper, we discuss the limitations of 4F CNN accelerators including the positive sensor readout, intensity-only modulation and slow modulation frequency and methods to address them. We also propose the channel tiling method that can address an important throughput and precision bottleneck of high-speed, massively-parallel optical 4F computing systems, not requiring any additional optical hardware.

Conference Presentation

Citation Download Citation

Puneet Gupta and Shurui Li "4F optical neural network acceleration: an architecture perspective", Proc. SPIE 12019, AI and Optical Data Sciences III, 120190B (2 March 2022); https://doi.org/10.1117/12.2614731

ACCESS THE FULL ARTICLE

INSTITUTIONAL
Select your institution to access the SPIE Digital Library.

SELECT YOUR INSTITUTION

PERSONAL
Sign in with your SPIE account to access your personal subscriptions or to use specific features such as save to my library, sign up for alerts, save searches, etc.

PERSONAL SIGN IN

No SPIE Account? Create one

PURCHASE THIS CONTENT

SUBSCRIBE TO DIGITAL LIBRARY

50 downloads per 1-year subscription

Members: $195

Non-members: $335 ADD TO CART

25 downloads per 1 - year subscription

Members: $145

Non-members: $250 ADD TO CART

PURCHASE SINGLE ARTICLE

Includes PDF, HTML & Video, when available