Impact of adaptivity on the behavior of networks of workstations under bursty traffic

Silla, Federico; Malumbres, Manuel P.; Duato, J.; Dai, Donglai; Panda, Dhabaleswar K.

doi:10.1109/icpp.1998.708467

Cited by 20 publications

(12 citation statements)

References 22 publications

Supporting

Mentioning

Contrasting

Order By: Relevance

“…Very recently, Safaei et al [26] investigated the communication delay in torus networks using Poisson process to model the message arrival process. However, a number of studies [6,28,29] have revealed that traffic loads generated by many real-world applications exhibit the bursty and batch arrival nature, which possesses significantly different theoretical properties from the traditional Poisson arrival process and can considerably affect the queueing performance [16,17]. An analytical model has recently been reported in [22] to handle the bursty traffic in interconnection networks by adopting the Markov-Modulated Poisson Process (MMPP) to model the bursty nature of message arrival process.…”

Section: Introductionmentioning

confidence: 98%

Analytical modelling of networks in multicomputer systems under bursty and batch arrival traffic

Min

Ould‐Khaoua

et al. 2009

J Supercomput

View full text Add to dashboard Cite

The hypercube and torus are two important message-passing network architectures of high-performance multicomputers. Analytical models of multicomputer networks under the non-bursty Poisson traffic have been widely reported. Motivated by the convincing evidence of bursty and batch arrival nature of traffic generated by many real-world parallel applications in high-performance computing environments, we develop a new and concise analytical model in this paper for hypercube and torus networks in the presence of batch message arrivals modelled by the compound Poisson process with geometrically distributed batch sizes. The average degree of virtual channel multiplexing is derived by employing a Markov chain which can capture the batch arrival nature. An attractive advantage of the model is its constant computation complexity independent of the network size. The accuracy of the analytical performance results is validated against those obtained from simulation experiments of an actual system.

show abstract

Section: Introductionmentioning

confidence: 98%

Analytical modelling of networks in multicomputer systems under bursty and batch arrival traffic

Min

Ould‐Khaoua

et al. 2009

J Supercomput

View full text Add to dashboard Cite

show abstract

“…E-mail address: g.min@brad.ac.uk coordinates the synchronization activity of the system, is a typical situation that can produce hot-spots [15] . Moreover, the message arrival process in high-performance computing systems often reveals batch arrival natures [4,7,8] , which can significantly affect the queueing performance [16−20] . Therefore, it is important to take both the non-uniform message destination distribution and batch message arrivals into account when investigating the performance of interconnection networks.…”

Section: Introductionmentioning

confidence: 99%

An analytical model for torus networks in the presence of batch message arrivals with hot-spot destinations

Min

Ould‐Khaoua

et al. 2009

Int. J. Autom. Comput.

View full text Add to dashboard Cite

Interconnection networks are hardware fabrics supporting communications between individual processors in multicomputers. The low-dimensional k-ary n-cubes (or torus) with adaptive wormhole switching have attracted significant research efforts to construct high-performance interconnection networks in contemporary multi-computers. The arrival process and destination distribution of messages have great effects on network performance. With the aim of capturing the characteristics of the realistic traffic pattern and obtaining a deep understanding of the performance behaviour of interconnection networks, this paper presents an analytical model to investigate the message latency in adaptive-routed wormhole-switched torus networks where there exists hot-spot nodes and the message arrivals follow a batch arrival process. Each generated message has a given probability to be directed to the hot-spot node. The average degree of virtual channel multiplexing is computed by the GE/G/1/V queueing system with finite buffer capacity. We compare analytical results of message latency with those obtained through the simulation experiments in order to validate the accuracy of the derived model.

show abstract

“…As a consequence, network load is increased. Finally, some studies of interconnection network behavior under the traffic generated by real applications [15,8] show that network traffic is bursty and peak traffic may saturate the network. As a consequence, the interconnection network may reach the performance degradation point, potentially increasing application execution time.…”

Section: Motivation and Related Workmentioning

confidence: 99%

A simple and efficient mechanism to prevent saturation in wormhole networks

Baydal

López

Duato

Proceedings 14th International Parallel and Distributed Processing Symposium. IPDPS 2000

Self Cite

View full text Add to dashboard Cite

Both deadlock avoidance and recovery techniques suffer from severe performance degradation when the network is close to or beyond saturation. This performance degradation appears because messages block in the network faster than they are drained by the escape paths in the deadlock avoidance strategies or the deadlock recovery mechanism.Many parallel applications produce bursty traffic that may saturate the network during some intervals [14,8], significantly increasing execution time. Therefore, the use of techniques that prevent network saturation are of crucial importance. Although several mechanisms have been proposed in the literature to reach this goal, some of them introduce some penalty when the network is not fully saturated, require complex hardware to be implemented or do not behave well under all network load conditions. In this paper, we propose a new mechanism to avoid network saturation that overcomes these drawbacks.

show abstract

Impact of adaptivity on the behavior of networks of workstations under bursty traffic

Cited by 20 publications

References 22 publications

Analytical modelling of networks in multicomputer systems under bursty and batch arrival traffic

Analytical modelling of networks in multicomputer systems under bursty and batch arrival traffic

An analytical model for torus networks in the presence of batch message arrivals with hot-spot destinations

A simple and efficient mechanism to prevent saturation in wormhole networks

Contact Info

Product

Resources

About