A new routing scheme for Jellyfish and its performance with HPC workloads

Yuan, Xin; Mahapatra, Santosh; Nienaber, Wickus; Pakin, Scott; Lang, Michael

doi:10.1145/2503210.2503229

Cited by 31 publications

(35 citation statements)

References 9 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…This alleviates the need for equalizing configurations, thereby making it easy for others to use our tools, and to test arbitrary workloads. Yuan et al [48] compared the performance of fat trees and Jellyfish with HPC traffic and a specific routing scheme, concluding they have similar performance, which disagrees with our results. We replicated the method of [48] and were able to reproduce their result of similar throughput using the A2A TM ( Fig.…”

Section: Comparison With Related Workcontrasting

confidence: 99%

See 1 more Smart Citation

Measuring and Understanding Throughput of Network Topologies

Jyothi

Singla

Godfrey

et al. 2016

SC16: International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

Abstract-High throughput is of particular interest in data center and HPC networks. Although myriad network topologies have been proposed, a broad head-to-head comparison across topologies and across traffic patterns is absent, and the right way to compare worst-case throughput performance is a subtle problem.In this paper, we develop a framework to benchmark the throughput of network topologies, using a two-pronged approach. First, we study performance on a variety of synthetic and experimentally-measured traffic matrices (TMs). Second, we show how to measure worst-case throughput by generating a near-worst-case TM for any given topology. We apply the framework to study the performance of these TMs in a wide range of network topologies, revealing insights into the performance of topologies with scaling, robustness of performance across TMs, and the effect of scattered workload placement. Our evaluation code is freely available.

show abstract

Section: Comparison With Related Workcontrasting

confidence: 99%

“…15. Throughput comparison of Fat Tree and Jellyfish based on [48], showing the effect of two methodological changes and approximations still had to be made. Accounting for the different costs of building different topologies is an inexact process.…”

Section: Comparison With Related Workmentioning

confidence: 99%

Measuring and Understanding Throughput of Network Topologies

Jyothi

Singla

Godfrey

et al. 2016

SC16: International Conference for High Performance Computing, Networking, Storage and Analysis

View full text Add to dashboard Cite

show abstract

“…Recently, the advantage of random topologies has been reported for various communication patterns [5]. In the present study, we support the iterative implementation of above topologies, as the supercomputer expands.…”

Section: A Network Topologysupporting

confidence: 76%

Darkfiber Planning for Extensible HPC Network Design under Uncertainties

Chaix

Fujiwara

Koibuchi

2014

2014 Second International Symposium on Computing and Networking

View full text Add to dashboard Cite

Cabling negatively affects not only the expandability of HPC systems, but also the reliability of their communications. In effect, the deployment of a supercomputer requires thousands of kilometers of cables, which are generally buried under the floor. Hence, moving or replacing these fibers is impossible once a supercomputer is deployed. In this study, we propose to exploit an efficient cabling method to enable multiple topologies in a system expanded incrementally. This approach reduces the cost of implementing an HPC system stage after stage, while requiring a limited knowledge about the future target applications and the final size of the system.

show abstract

“…For Jellyfish, the k-shortest path routing is proposed to improve the network throughput [2]. Yuan et al propose the limited length spread k-shortest path routing (LLSKR), which improves the k-shortest path routing by more effectively exploiting path diversity [14]. Figure 1 shows the relationship between the throughput and the number k of paths used in the k-shortest path routing with 64 4-degree nodes.…”

Section: Maximizing Throughput By Routingmentioning

confidence: 99%

Traffic-Independent Multi-Path Routing for High-Throughput Data Center Networks

Kawano

Yasudo

Matsutani

et al. 2020

IEICE Trans. Inf. & Syst.

View full text Add to dashboard Cite

Network throughput has become an important issue for big-data analysis on Warehouse-Scale Computing (WSC) systems. It has been reported that randomly-connected inter-switch networks can enlarge the network throughput. For irregular networks, a multi-path routing method called k-shortest path routing is conventionally utilized. However, it cannot efficiently exploit longer-than-shortest paths that would be detour paths to avoid bottlenecks. In this work, a novel routing method called koptimized path routing to achieve high throughput is proposed for irregular networks. We introduce a heuristic to select detour paths that can avoid bottlenecks in the network to improve the average-case network throughput. Experimental results by network simulation show that the proposed k-optimized path routing can improve the saturation throughput by up to 18.2% compared to the conventional k-shortest path routing. Moreover, it can reduce the computation time required for optimization to 1/2760 at a minimum compared to our previously proposed method.

show abstract

A new routing scheme for Jellyfish and its performance with HPC workloads

Cited by 31 publications

References 9 publications

Measuring and Understanding Throughput of Network Topologies

Measuring and Understanding Throughput of Network Topologies

Darkfiber Planning for Extensible HPC Network Design under Uncertainties

Traffic-Independent Multi-Path Routing for High-Throughput Data Center Networks

Contact Info

Product

Resources

About