Next Article in Journal
Analysis of the Spatial Properties of Correlated Photon in Collinear Phase-Matching
Next Article in Special Issue
Accurate Power-Efficient Format-Scalable Multi-Parallel Optical Digital-to-Analogue Conversion
Previous Article in Journal
Numerical Analysis of Nonlinear Dynamics Based on Spin-VCSELs with Optical Feedback
 
 
Search for Articles:
Title / Keyword
Author / Affiliation / Email
Journal
Article Type
 
 
Advanced Search
 
Section
Special Issue
Volume
Issue
Number
Page
 
Journals
Photonics
Volume 8
Issue 1
10.3390/photonics8010011
photonics-logo
Submit to this Journal Review for this Journal Propose a Special Issue
► Article Menu

Article Menu

share Share announcement Help format_quote Cite question_answer Discuss in SciProfiles
first_page
settings
Order Article Reprints
Font Type:
Arial Georgia Verdana
Font Size:
Aa Aa Aa
Line Spacing:
Column Width:
Background:
Article

FOSquare: A Novel Optical HPC Interconnect Network Architecture Based on Fast Optical Switches with Distributed Optical Flow Control

by
Fulong Yan
1,
Changshun Yuan
2,*,
Chao Li
3 and
Xiong Deng
1
1
Institute for Photonic Integration (IPI), Technology University of Eindhoven, 5600AZ Eindhoven, The Netherlands
2
Hangzhou Innovation Institute, Beihang University, Hangzhou 310051, China
3
School of Electronic Engineering, Anhui University, Hefei 231699, China
*
Author to whom correspondence should be addressed.
Photonics 2021, 8(1), 11; https://doi.org/10.3390/photonics8010011
Submission received: 7 November 2020 / Revised: 30 December 2020 / Accepted: 31 December 2020 / Published: 4 January 2021
(This article belongs to the Special Issue Reconfigurable Photonic Interconnects)
Browse Figures
Versions Notes

Abstract

Interconnecting networks adopting Fast Optical Switches (FOS) can achieve high bandwidth, low latency, and low power consumption. We propose and demonstrate a novel interconnecting topology based on FOS (FOSquare) with distributed fast flow control which is suitable for HPC infrastructures. We also present an Optimized Mapping (OPM) algorithm that maps the most communication-related processes inside a rack. We numerically investigate and compare the network performance of FOSquare with Leaf-Spine under real traffic traces collected by running multiple applications (CG, MG, MILC, and MINI_MD) in an HPC infrastructure. The numerical results show that the FOSquare can reduce >10% latency with respect to Leaf-Spine under the scenario of 16 available cores.
Keywords: high performance computing; fast optical switch; network architecture; mapping algorithm high performance computing; fast optical switch; network architecture; mapping algorithm

Share and Cite

MDPI and ACS Style

Yan, F.; Yuan, C.; Li, C.; Deng, X. FOSquare: A Novel Optical HPC Interconnect Network Architecture Based on Fast Optical Switches with Distributed Optical Flow Control. Photonics 2021, 8, 11. https://doi.org/10.3390/photonics8010011

AMA Style

Yan F, Yuan C, Li C, Deng X. FOSquare: A Novel Optical HPC Interconnect Network Architecture Based on Fast Optical Switches with Distributed Optical Flow Control. Photonics. 2021; 8(1):11. https://doi.org/10.3390/photonics8010011

Chicago/Turabian Style

Yan, Fulong, Changshun Yuan, Chao Li, and Xiong Deng. 2021. "FOSquare: A Novel Optical HPC Interconnect Network Architecture Based on Fast Optical Switches with Distributed Optical Flow Control" Photonics 8, no. 1: 11. https://doi.org/10.3390/photonics8010011

APA Style

Yan, F., Yuan, C., Li, C., & Deng, X. (2021). FOSquare: A Novel Optical HPC Interconnect Network Architecture Based on Fast Optical Switches with Distributed Optical Flow Control. Photonics, 8(1), 11. https://doi.org/10.3390/photonics8010011

Note that from the first issue of 2016, this journal uses article numbers instead of page numbers. See further details here.

Article Metrics

Back to TopTop