Controlling and Assessing Correlations of Cost Matrices in Heterogeneous Scheduling
Proceedings of the 22nd International Conference on Euro-Par 2016: Parallel Processing - Volume 9833
Pages 133 - 145
Abstract
This paper 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 is a proximity measure with uniform instances Uniform instances are particular unrelated instances in which each execution time is proportional to the weight of the task and the cycle time of the machine. Cost matrices generated with a novel generation method 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.
References
[1]
Al-Qawasmeh, A.M., Maciejewski, A.A., Roberts, R.G., Siegel, H.J.: Characterizing task-machine affinity in heterogeneous computing environments. In: IPDPSW 2011
[2]
Al-Qawasmeh, A.M., Maciejewski, A.A., Siegel, H.J.: Characterizing heterogeneous computing environments using singular value decomposition. In: IPDPSW 2010
[3]
Al-Qawasmeh, A.M., Pasricha, S., Maciejewski, A.A., Siegel, H.J.: Power and thermal-aware workload allocation in heterogeneous data centers. Trans. Comput. 642, 477---491 2013
[4]
Ali, S., Siegel, H.J., Maheswaran, M., Hensgen, D.: Task execution time modeling for heterogeneous computing systems. In: HCW, pp. 185---199. IEEE 2000
[5]
Ali, S., Siegel, H.J., Maheswaran, M., Hensgen, D., Ali, S.: Representing task and machine heterogeneities for heterogeneous computing systems. Tamkang J. Sci. Eng. 33, 195---208 2000
[6]
Canon, L.C., Héam, P.C., Philippe, L.: Controlling and Assessing Correlations of Cost Matrices in Heterogeneous Scheduling. Technical report RR-FEMTO-ST-1191, FEMTO-ST, February 2016
[7]
Canon, L.-C., Philippe, L.: On the heterogeneity bias of cost matrices when assessing scheduling algorithms. In: Träff, J.L., Hunold, S., Versaci, F. eds. Euro-Par 2015. LNCS, vol. 9233, pp. 109---121. Springer, Heidelberg 2015
[8]
Canon, L.C., Philippe, L.: On the Heterogeneity Bias of Cost Matrices when Assessing Scheduling Algorithms. Technical report RR-FEMTO-ST-8663, FEMTO-ST, March 2015
[9]
Freund, R.F., Gherrity, M., Ambrosius, S., Campbell, M., Halderman, M., Hensgen, D., Keith, E., Kidd, T., Kussow, M., Lima, J.D., Mirabile, F., Moore, L., Rust, B., Siegel, H.J.: Scheduling resources in multi-user, heterogeneous, computing environments with SmartNet. In: HCW, pp. 184---199. IEEE 1998
[10]
Graham, R.L.: Bounds on multiprocessing timing anomalies. J. appl. math. 172, 416---429 1969
[11]
Ibarra, O.H., Kim, C.E.: Heuristic algorithms for scheduling independent tasks on nonidentical processors. J. ACM 242, 280---289 1977
[12]
Khemka, B., Friese, R., Pasricha, S., Maciejewski, A.A., Siegel, H.J., Koenig, G.A., Powers, S., Hilton, M., Rambharos, R., Poole, S.: Utility maximizing dynamic resource management in an oversubscribed energy-constrained heterogeneous computing system. Sustain. Comput. Inf. Syst. 5, 14---30 2014
[13]
Luo, P., Lü, K., Shi, Z.: A revisit of fast greedy heuristics for mapping a class of independent tasks onto heterogeneous computing systems. J. Parallel Distrib. Comput. 676, 695---714 2007
[14]
Maheswaran, M., Ali, S., Siegel, H.J., Hensgen, D., Freund, R.F.: Dynamic mapping of a class of independent tasks onto heterogeneous computing systems. J. Parallel Distrib. Comput. 592, 107---131 1999
Recommendations
Generating random correlation matrices based on partial correlations
A d-dimensional positive definite correlation matrix R = (ρij) can be parametrized in terms of the correlations ρi,i+1 for i = 1,..., d-1, and the partial correlations ρij|i+1,..,j-1 for j-i ≥ 2. These (d 2) parameters can independently take values in ...
On the Heterogeneity Bias of Cost Matrices for Assessing Scheduling Algorithms
Assessing the performance of scheduling heuristics through simulation requires one to generate synthetic instances of tasks and machines with well-identified properties. Carefully controlling these properties is mandatory to avoid any bias. We consider ...
Combining dissimilarity matrices by using rank correlations
Recently there has been increased interest in methods for aggregating multiple matrices observed on a fixed set of entities, where each matrix expresses a particular notion of the dissimilarity of one entity from another. An optimization-based procedure ...
Comments
Information & Contributors
Information
Published In
Publisher
Springer-Verlag
Berlin, Heidelberg
Publication History
Published: 24 August 2016
Qualifiers
- Article
Contributors
Other Metrics
Bibliometrics & Citations
Bibliometrics
Article Metrics
- 0Total Citations
- 0Total Downloads
- Downloads (Last 12 months)0
- Downloads (Last 6 weeks)0
Reflects downloads up to 14 Jan 2025