Controlling the Correlation of Cost Matrices to Assess Scheduling Algorithm Performance on Heterogeneous Platforms - Inria - Institut national de recherche en sciences et technologies du numérique Access content directly
Journal Articles Concurrency and Computation: Practice and Experience Year : 2017

Controlling the Correlation of Cost Matrices to Assess Scheduling Algorithm Performance on Heterogeneous Platforms

Abstract

Bias in the performance evaluation of scheduling heuristics has been shown to undermine the scope of existing studies. Improving the assessment step leads to stronger scientific claims when validating new optimization strategies. This article considers the problem of allocating independent tasks to unrelated machines such as to minimize the maximum completion time. Testing heuristics for this problem requires the generation of cost matrices that specify the execution time of each task on each machine. Numerous studies showed that the task and machine heterogeneities belong to the properties impacting heuristics performance the most. This study focuses on orthogonal properties, the average correlations between each pair of rows and each pair of columns, which measure the proximity with uniform instances. Cost matrices generated with two distinct novel generation methods show the effect of these correlations on the performance of several heuristics from the literature. In particular, EFT performance depends on whether the tasks are more correlated than the machines and HLPT performs the best when both correlations are close to one.
Fichier principal
Vignette du fichier
ccpe17.pdf (1.09 Mo) Télécharger le fichier
Origin : Files produced by the author(s)
Loading...

Dates and versions

hal-01664629 , version 1 (15-12-2017)

Identifiers

Cite

Louis-Claude Canon, Pierre-Cyrille Héam, Laurent Philippe. Controlling the Correlation of Cost Matrices to Assess Scheduling Algorithm Performance on Heterogeneous Platforms. Concurrency and Computation: Practice and Experience, 2017, 29 (15), pp.e4185 (27). ⟨10.1002/cpe.4185⟩. ⟨hal-01664629⟩
198 View
235 Download

Altmetric

Share

Gmail Facebook X LinkedIn More