Performance evaluation of fork and join synchronization primitives

Duda, Andrzej; Czachórski, Tadeusz

doi:10.1007/bf00263293

Cited by 40 publications

(15 citation statements)

References 7 publications

Supporting

Mentioning

Contrasting

Unclassified

Order By: Relevance

“…However, due to the complexity and nontractable characteristics of a TPG, most authors assume an infinite number of processors [GE89, FA83] or assume every task in a TPG runs on a specific processor in the system and every job has the same TPG [BA89,DU87]. In the former case no system delay, caused by waiting in the queue, was considered.…”

Section: Graphmentioning

confidence: 99%

Multiple feedback queue as a model of general purpose multiprocessor systems

Chang

Wallace

1992

Proceedings of the 1992 ACM Annual Conference on Communications - CSC '92

View full text Add to dashboard Cite

show abstract

Section: Graphmentioning

confidence: 99%

Multiple feedback queue as a model of general purpose multiprocessor systems

Chang

Wallace

1992

Proceedings of the 1992 ACM Annual Conference on Communications - CSC '92

View full text Add to dashboard Cite

show abstract

“…Le temps de réponse du traitement sera le maximum du temps de réponse de chacune des tâches. Dans le FORK-JOIN classique [1,2,3], il y a p tâches avec des arrivées groupées et chacune d'elles est affectée à un des p processeurs. Ici, il y a n tâches et elles peuvent être servies par n'importe lequel des serveurs, quand il est libre.…”

Section: 2 Le N P Fork-joinunclassified

“…Le modèle du système sous forme de réseau de files d'attente conduit à un problème de FORK-JOIN, qui est différent de ceux qui ont été étudiés dans [1], [2], ou [3]. On a un FORK lorsqu'un travail crée n tâches identiques qui seront traitées par p processeurs.…”

unclassified

Modélisation d'une architecture parallèle pour le traitement d'images

Houeix¹,

Becker²

1988

RAIRO-Oper. Res.

View full text Add to dashboard Cite

“…Split-merge (SM) is different from the F/J queueing system in that all of the tasks of an SM request need to complete service before the next SM request can be issued [Duda and Czachrski 1987]. There is a synchronization delay after the completion of the first task until all tasks are completed and before the next SM request can be issued.…”

Section: Introductionmentioning

confidence: 99%

Analysis of Fork/Join and Related Queueing Systems

Thomasian¹

2014

ACM Comput. Surv.

View full text Add to dashboard Cite

Fork/join (F/J) requests arise in contexts such as parallel computing, query processing in parallel databases, and parallel disk access in RAID. F/J requests spawn K tasks that are sent to K parallel servers, and the completion of all K tasks marks the completion of an F/J request. The exact formula for the mean response time of K = 2-way F/J requests derived under Markovian assumptions (R F/J 2 ) served as the starting point for an approximate expression for R F/J K for 2 < K ≤ 32. When servers process independent requests in addition to F/J requests, the mean response time of F/J requests is better approximated by R max K , which is the maximum of the response times of tasks constituting F/J requests. R max K is easier to compute and serves as an upper bound to R F/J K . We discuss techniques to compute R max K and generally the maximum of K random variables denoting the processing times of the tasks of a parallel computation X max K . Graph models of computations such as Petri nets-a more general form of parallelism than F/J requests-are also discussed in this work. Jobs with precedence constraints may require multiple resources, which are represented by a queueing network model. We also discuss various queueing systems related to F/J queueing systems and outline their analysis. ACM Reference Format:Alexander Thomasian. 2014. Analysis of fork-join and related queueing systems.

show abstract

Performance evaluation of fork and join synchronization primitives

Cited by 40 publications

References 7 publications

Multiple feedback queue as a model of general purpose multiprocessor systems

Multiple feedback queue as a model of general purpose multiprocessor systems

Modélisation d'une architecture parallèle pour le traitement d'images

Analysis of Fork/Join and Related Queueing Systems

Contact Info

Product

Resources

About