Affiliation:
1. Columbia University
2. University of Applied Sciences and Arts Western Switzerland
3. Massachusetts Institute of Technology
Abstract
Designing efficient interconnects to support high-bandwidth and low-latency communication is critical toward realizing high performance computing (HPC) and data center (DC) systems in the exascale era. At extreme computing scales, providing the requisite bandwidth through overprovisioning becomes impractical. These challenges have motivated studies exploring reconfigurable network architectures that can adapt to traffic patterns at runtime using optical circuit switching. Despite the plethora of proposed architectures, surprisingly little is known about the relative performances and trade-offs among different reconfigurable network designs. We aim to bridge this gap by tackling two key issues in reconfigurable network design. First, we study how cost, power consumption, network performance, and scalability vary based on optical circuit switch (OCS) placement in the physical topology. Specifically, we consider two classes of reconfigurable architectures: one that places OCSs between top-of-rack (ToR) switches—ToR-reconfigurable networks (TRNs)—and one that places OCSs between pods of racks—pod-reconfigurable networks (PRNs). Second, we tackle the effects of reconfiguration frequency on network performance. Our results, based on network simulations driven by real HPC and DC workloads, show that while TRNs are optimized for low fan-out communication patterns, they are less suited for carrying high fan-out workloads. PRNs exhibit better overall trade-off, capable of performing comparably to a fully non-blocking fat tree for low fan-out workloads, and significantly outperform TRNs for high fan-out communication patterns.
Funder
Advanced Research Projects Agency - Energy
National Security Agency
Subject
Computer Networks and Communications
Reference69 articles.
1. Empowering flexible and scalable high performance architectures with embedded photonics;Bergman,2018
2. Evaluating the impact of energy efficient networks on HPC workloads;Georgakoudis,2019
3. Exascale computing technology challenges;Shalf,2011
4. FatPaths: routing in supercomputers and data centers when shortest paths fall short;Besta,2020
5. Finding theKShortest Loopless Paths in a Network
Cited by
10 articles.
订阅此论文施引文献
订阅此论文施引文献,注册后可以免费订阅5篇论文的施引文献,订阅后可以查看论文全部施引文献
1. Flexible silicon photonic architecture for accelerating distributed deep learning;Journal of Optical Communications and Networking;2024-01-09
2. Finding Your Niche: An Evolutionary Approach to HPC Topologies;2023 IEEE High Performance Extreme Computing Conference (HPEC);2023-09-25
3. Overview of router architecture in high performance computing;3rd International Conference on Artificial Intelligence, Automation, and High-Performance Computing (AIAHPC 2023);2023-07-21
4. (OFC 20 ) Optical Switching will Innovate Intra Data Center Networks;Journal of Optical Communications and Networking;2023-07-19
5. GRAP: Group-level Resource Allocation Policy for Reconfigurable Dragonfly Network in HPC;Proceedings of the 37th International Conference on Supercomputing;2023-06-21