Photonic in-memory computing using continuous-time data

Harish Bhaskaran; Bowei Dong

doi:10.1117/12.2679472

4 October 2023 Photonic in-memory computing using continuous-time data

Harish Bhaskaran, Bowei Dong

Proceedings Volume PC12647, Active Photonic Platforms (APP) 2023; PC126470O (2023) https://doi.org/10.1117/12.2679472
Event: SPIE Nanoscience + Engineering, 2023, San Diego, California, United States

Abstract

Photonic computing is literally becoming big business with the rise of several private companies trying to commercialize this technology. One of the advantages of using photonics is of course the ability to multiplex in wavelength - in principle providing highly parallel information processing through a given set of "weights" or system variables. Effectively, this can greatly enhance throughput. However, the use of multiple wavelengths, while very feasible still requires use of several filters and multiplexers. Here we report a technique to parallelize data processing through photonic hardware accelerators, particularly in-memory computing systems both with or without photonic hardware.

Conference Presentation

Citation Download Citation

Harish Bhaskaran and Bowei Dong "Photonic in-memory computing using continuous-time data", Proc. SPIE PC12647, Active Photonic Platforms (APP) 2023, PC126470O (4 October 2023); https://doi.org/10.1117/12.2679472

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