Analysis of Work Stealing with latency - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Journal of Parallel and Distributed Computing Year : 2021

Analysis of Work Stealing with latency


We study the impact of communication latency on the classical Work Stealing load balancing algorithm. Our paper extends the reference model in which we introduce a latency parameter. By using a theoretical analysis and simulation, we study the overall impact of this latency on the Makespan (maximum completion time). We derive a new expression of the expected running time of a bag of independent tasks scheduled by Work Stealing. This expression enables us to predict under which conditions a given run will yield acceptable performance. For instance, we can easily calibrate the maximal number of processors to use for a given work/platform combination. All our results are validated through simulation on a wide range of parameters.
Fichier principal
Vignette du fichier
WS_JPDC.pdf (553.16 Ko) Télécharger le fichier
Origin Files produced by the author(s)

Dates and versions

hal-03356234 , version 1 (27-09-2021)



Nicolas Gast, Mohammed Khatiri, Denis Trystram, Frédéric Wagner. Analysis of Work Stealing with latency. Journal of Parallel and Distributed Computing, 2021, 153, pp.119-129. ⟨10.1016/j.jpdc.2021.03.010⟩. ⟨hal-03356234⟩
105 View
246 Download



Gmail Mastodon Facebook X LinkedIn More