Expand this Topic clickable element to expand a topic
Skip to content
Optica Publishing Group
Conferences > OFC > 2024 > Th4C > Th4C.3

A 160 TOPS Multi-dimensional AWGR-based accelerator for Deep Learning

C. Pappas, T. Moschos, A. Prapas, A. Tsakyridis, M. Moralis-Pegios, K. Vyrsokinos, and N. Pleros

Not Accessible

Your library or personal account may give you access

Abstract

We experimentally demonstrate a novel time-space-wavelength multiplexed AWGR-based photonic tensor multiplier that provides a total computational power of 163.8 TeraOP, offering a ~14x improvement compared to state-of-the-art waveguide-based optical accelerators.

© 2024 The Author(s)

PDF Article
More Like This
A TeraFLOP Photonic Matrix Multiplier using Time-Space-Wavelength Multiplexed AWGR-based Architectures

Christos Pappas, Theodoros Moschos, Miltiadis Moralis-Pegios, George Giamougiannis, Apostolos Tsakyridis, Manos Kirtas, Nikolaos Passalis, Anastasios Tefas, and Nikos Pleros
Th3G.1 Optical Fiber Communication Conference (OFC) 2024

Optics-informed Neural Networks: Bridging Deep Learning with Photonic Accelerators

M. Moralis-Pegios, A. Tsakyridis, C. Pappas, T. Moschos, G. Giamougiannis, S. Kovaios, I. Roumpos, M. Kirtas, N. Passalis, A. Tefas, and N. Pleros
Tu3F.1 Optical Fiber Communication Conference (OFC) 2024

Accelerate Distributed Deep Learning with a Fast Reconfigurable Optical Network

Wenzhe Li, Guojun Yuan, Zhan Wang, Guangming Tan, Peiheng Zhang, and George N. Rouskas
W2B.23 Optical Fiber Communication Conference (OFC) 2024

View More...
Select as filters
Select Topics Cancel
Top
       
© Copyright 2024 | Optica Publishing Group. All rights reserved, including rights for text and data mining and training of artificial technologies or similar technologies.
Privacy | Terms of Use