Next Article in Journal
Distributed Sensory System of Surface Cracks Monitoring Based on Electrical Impedance Tomography
Next Article in Special Issue
Access Adaptive and Thread-Aware Cache Partitioning in Multicore Systems
Previous Article in Journal
A Receiving Antenna Allocation Scheme for Downlink MU-MIMO-OFDM Transmission
Article Menu
Issue 8 (August) cover image

Export Article

Open AccessArticle
Electronics 2018, 7(8), 130; https://doi.org/10.3390/electronics7080130

Evaluating the Impact of Optical Interconnects on a Multi-Chip Machine-Learning Architecture

Department of Transdisciplinary Studies, Seoul National University, Seoul 08826, Korea
*
Author to whom correspondence should be addressed.
Received: 30 June 2018 / Revised: 18 July 2018 / Accepted: 25 July 2018 / Published: 27 July 2018
(This article belongs to the Special Issue Distributed Computing and Storage)
Full-Text   |   PDF [953 KB, uploaded 27 July 2018]   |  

Abstract

Following trends that emphasize neural networks for machine learning, many studies regarding computing systems have focused on accelerating deep neural networks. These studies often propose utilizing the accelerator specialized in a neural network and the cluster architecture composed of interconnected accelerator chips. We observed that inter-accelerator communication within a cluster has a significant impact on the training time of the neural network. In this paper, we show the advantages of optical interconnects for multi-chip machine-learning architecture by demonstrating performance improvements through replacing electrical interconnects with optical ones in an existing multi-chip system. We propose to use highly practical optical interconnect implementation and devise an arithmetic performance model to fairly assess the impact of optical interconnects on a machine-learning accelerator platform. In our evaluation of nine Convolutional Neural Networks with various input sizes, 100 and 400 Gbps optical interconnects reduce the training time by an average of 20.6% and 35.6%, respectively, compared to the baseline system with 25.6 Gbps electrical ones. View Full-Text
Keywords: machine learning; accelerator; optical interconnect; multi-chip architecture; cluster; Convolutional Neural Network (CNN) machine learning; accelerator; optical interconnect; multi-chip architecture; cluster; Convolutional Neural Network (CNN)
Figures

Figure 1

This is an open access article distributed under the Creative Commons Attribution License which permits unrestricted use, distribution, and reproduction in any medium, provided the original work is properly cited (CC BY 4.0).
SciFeed

Share & Cite This Article

MDPI and ACS Style

Ro, Y.; Lee, E.; Ahn, J.H. Evaluating the Impact of Optical Interconnects on a Multi-Chip Machine-Learning Architecture. Electronics 2018, 7, 130.

Show more citation formats Show less citations formats

Note that from the first issue of 2016, MDPI journals use article numbers instead of page numbers. See further details here.

Related Articles

Article Metrics

Article Access Statistics

1

Comments

[Return to top]
Electronics EISSN 2079-9292 Published by MDPI AG, Basel, Switzerland RSS E-Mail Table of Contents Alert
Back to Top