On the Feasibility of Optical Circuit Switching for High Performance Computing Systems

  • Authors:
  • Kevin J. Barker;Alan Benner;Ray Hoare;Adolfy Hoisie;Alex K. Jones;Darren K. Kerbyson;Dan Li;Rami Melhem;Ram Rajamony;Eugen Schenfeld;Shuyi Shao;Craig Stunkel;Peter Walker

  • Affiliations:
  • Los Alamos National Laboratory;IBM T.J Watson Research Center;Dept. of Electrical Eng. University of Pittsburgh;Los Alamitos Natinal Laboratory;Dept. Computer Science University of Pittsburgh;Los Alamitos National Laboratory;Dept. of Computer Science, University of Pittsburgh;Dept. of Computer Science, University of Pittsburgh;IBM T.J Watson Research Center;IBM T.J Watson Research Center;Dept. of Computer Science, University of Pittsburgh;IBM T.J Watson Research Center;IBM T.J Watson Research Center

  • Venue:
  • SC '05 Proceedings of the 2005 ACM/IEEE conference on Supercomputing
  • Year:
  • 2005

Quantified Score

Hi-index 0.00

Visualization

Abstract

The interconnect plays a key role in both the cost and performance of large-scale HPC systems. The cost of future high-bandwidth electronic interconnects mushrooms due to expensive optical transceivers needed between electronic switches. We describe a potentially cheaper and more power-efficient approach to building high-performance interconnects.Through empirical analysis of HPC applications, we find that the bulk of inter-processor communication (barring collectives) is bounded in degree and changes very slowly or never. Thus we propose a two-network interconnect: An Optical Circuit Switching (OCS) network handling long-lived bulk data transfers, using optical switches; and a secondary lower-bandwidth Electronic Packet Switching (EPS) network. An OCS could be significantly cheaper, as it uses fewer optical transceivers than an electronic network. Collectives and transient communication packets traverse the electronic network. We present compiler techniques and dynamic run-time policies, using this two-network interconnect. Simulation results show that our approach provides high performance at low cost.