TY - GEN
T1 - Exploiting load imbalance patterns for heterogeneous cloud computing platforms
AU - Roloff, Eduardo
AU - Diener, Matthias
AU - Gaspary, Luciano P.
AU - Navaux, Philippe O.A.
N1 - Funding Information:
This research received funding from the EU H2020 Programme and from MCTI/RNP-Brazil under the HPC4E project, grant agreement no. 689772. This research received partial funding from CYTED for the RICAP Project, grant agreement no. 517RT0529. Additional funding was provided by FAPERGS in the context of the GreenCloud Project.
Funding Information:
This research received funding from the EU H2020 Programme and from MCTI/RNP-Brazil under the HPC4E project, grant agreement no. 689772. This re-searchreceived partialfundingfrom CYTEDfor the RICAP Project, grant agreement no. 517RT0529. Additional funding was provided by FAPERGS in the context of the GreenCloud Project.
Publisher Copyright:
© 2018 by SCITEPRESS - Science and Technology Publications, Lda. All rights reserved.
PY - 2018
Y1 - 2018
N2 - Cloud computing providers offer a variety of instance sizes, types, and configurations that have different prices but can interoperate. As many parallel applications have heterogeneous computational demands, these different instance types can be exploited to reduce the cost of executing a parallel application while maintaining an acceptable performance. In this paper, we perform an analysis of load imbalance patterns with an intentionally-imbalanced artificial benchmark to discover which patterns can benefit from a heterogeneous cloud system. Experiments with this artificial benchmark as well as applications from the NAS Parallel Benchmark suite show that the price of executing an imbalanced application can be reduced substantially on a heterogeneous cloud for a variety of imbalance patterns, while maintaining acceptable performance. By using a heterogeneous cloud, cost efficiency was improved by up to 63%, while performance was reduced by less than 7%.
AB - Cloud computing providers offer a variety of instance sizes, types, and configurations that have different prices but can interoperate. As many parallel applications have heterogeneous computational demands, these different instance types can be exploited to reduce the cost of executing a parallel application while maintaining an acceptable performance. In this paper, we perform an analysis of load imbalance patterns with an intentionally-imbalanced artificial benchmark to discover which patterns can benefit from a heterogeneous cloud system. Experiments with this artificial benchmark as well as applications from the NAS Parallel Benchmark suite show that the price of executing an imbalanced application can be reduced substantially on a heterogeneous cloud for a variety of imbalance patterns, while maintaining acceptable performance. By using a heterogeneous cloud, cost efficiency was improved by up to 63%, while performance was reduced by less than 7%.
KW - Cloud computing
KW - Cost efficiency
KW - Heterogeneity
KW - Load imbalance
UR - http://www.scopus.com/inward/record.url?scp=85048961451&partnerID=8YFLogxK
UR - http://www.scopus.com/inward/citedby.url?scp=85048961451&partnerID=8YFLogxK
U2 - 10.5220/0006807502480259
DO - 10.5220/0006807502480259
M3 - Conference contribution
AN - SCOPUS:85048961451
T3 - CLOSER 2018 - Proceedings of the 8th International Conference on Cloud Computing and Services Science
SP - 248
EP - 259
BT - CLOSER 2018 - Proceedings of the 8th International Conference on Cloud Computing and Services Science
A2 - Munoz, Victor Mendez
A2 - Ferguson, Donald
A2 - Helfert, Markus
A2 - Pahl, Claus
PB - SciTePress
T2 - 8th International Conference on Cloud Computing and Services Science, CLOSER 2018
Y2 - 19 March 2018 through 21 March 2018
ER -