Head‐of‐line blocking avoidance in Slim Fly networks using deadlock‐free non‐minimal and adaptive routing. (14th February 2018)

• Record Type: Journal Article
• Authors: Yébenes, Pedro; Escudero‐Sahuquillo, Jesus; García, Pedro J.; Quiles, Francisco J.; Hoefler, Torsten
• Other Names: Sahuquillo Jesús Escudero guestEditor.; Garcia Pedro Javier guestEditor.; Bellatreche Ladjel guestEditor.; Leung Carson guestEditor.; Xia Yinglong guestEditor.; Baz Didier El guestEditor.
• Is Part Of: Concurrency and computation. Volume 31:Number 2(2019)
• Page Start: n/a
• Page End: n/a
• Publication Date: 2018-02-14
• Subjects: congestion management -- deadlock freedom -- high‐performance interconnection networks -- HoL blocking -- non‐minimal routing -- Slim Fly topology; Parallel processing (Electronic computers) -- Periodicals; Parallel computers -- Periodicals; 004.35
• DOI: 10.1002/cpe.4441
• Languages: English
• ISSNs: 1532-0626

Abstract

Summary: Interconnection network performance is a key issue in HPC systems and datacenters, especially as their number of end nodes grows, to cope with application needs. The network topology and the routing algorithm are important factors for performance and cost. Topologies such as fat‐tree or Dragonfly were proposed to maximize network performance while reducing network resources. One of the most promising topologies is Slim Fly, which offers high network bandwidth assuring low network diameter. However, adversarial traffic and/or congestion situations may degrade Slim Fly's performance dramatically. Non‐minimal routings, such as Valiant or UGAL, can mitigate the former problem while queuing schemes can handle the latter one. In this paper, we proposed a combined mechanism to provide Slim Fly network with both non‐minimal routing and queuing schemes by using several virtual networks to guarantee deadlock freedom. Each virtual network consists of a set of virtual channels to store packets separately according to a mapping policy. This diminishes the interaction among traffic flows, thus reducing head‐of‐line blocking. The results obtained from a simulation‐based evaluation show that our proposal enhances the performance in all the traffic cases, in contrast to other mechanisms whose performance drops in certain scenarios.