Designing a state of art photonic AI accelerator

Mohamed F Fouda; Emanuel Peinke

doi:10.1117/12.2601612

6 October 2021 Designing a state of art photonic AI accelerator

Mohamed F Fouda, Emanuel Peinke

Proceedings Volume 11880, Emerging Applications in Silicon Photonics II; 118800P (2021) https://doi.org/10.1117/12.2601612
Event: SPIE Photonex, 2021, Glasgow, United Kingdom

Abstract

In this work, we discuss the requirements and challenges of designing a photonic computing chip that can be deployed in the latest commercial AI systems. Silicon Photonics have the potential to revolutionize AI computing by delivering unprecedented improvements in the power consumption and computational throughput of AI computations. Still, there are several challenges to be tackled. Among these are the need to design high-density photonic integrated circuits, designing photonic memory systems for data storage, and solving the bottleneck of the electrical-to-optical conversions. Several innovative photonic technologies have been introduced to address these challenges. The progress on implementing these technologies is discussed.

Conference Presentation

Citation Download Citation

Mohamed F Fouda and Emanuel Peinke "Designing a state of art photonic AI accelerator", Proc. SPIE 11880, Emerging Applications in Silicon Photonics II, 118800P (6 October 2021); https://doi.org/10.1117/12.2601612

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