en
Proceedings chapter
English

On the Benefits of Anticipating Load Imbalance for Performance Optimization of Parallel Applications

Presented at Albuquerque (NM, USA), 23-26 Sept. 2019
PublisherIEEE
Publication date2019
Abstract

In parallel iterative applications, computational efficiency is essential for addressing large problems. Load imbalance is one of the major performance degradation factors of parallel applications. Therefore, distributing, cleverly, and as evenly as possible, the workload among processing elements (PE) maximizes application performance. So far, the standard load balancing method consists in distributing the workload evenly between PEs and, when load imbalance appears, redistributing the extra load from overloaded PEs to underloaded PEs. However, this does not anticipate the load imbalance growth that may continue during the next iterations. In this paper, we present a first step toward a novel philosophy of load balancing that unloads the PEs that will be overloaded in the near future to let the application rebalance itself via its own dynamics. Herein, we present a formal definition of our new approach using a simple mathematical model and discuss its advantages compared to the standard load balancing method. In addition to the theoretical study, we apply our method to an application that reproduces the computation of a fluid model with non-uniform erosion. The performance validates the benefit of anticipating load imbalance. We observed up to 16% performance improvement compared to the standard load balancing method.

Keywords
  • High performance computing
  • Load balancing
  • Performance optimization
  • Anticipation
Citation (ISO format)
BOULMIER, Anthony et al. On the Benefits of Anticipating Load Imbalance for Performance Optimization of Parallel Applications. In: IEEE International Conference on Cluster Computing, CLUSTER 2019. Albuquerque (NM, USA). [s.l.] : IEEE, 2019. p. 1–9. doi: 10.1109/CLUSTER.2019.8890998
Main files (1)
Proceedings chapter (Published version)
accessLevelRestricted
Identifiers
ISBN9781728147345
138views
0downloads

Technical informations

Creation06/25/2020 5:44:00 PM
First validation06/25/2020 5:44:00 PM
Update time03/15/2023 10:11:53 PM
Status update03/15/2023 10:11:52 PM
Last indexation10/19/2023 1:02:25 PM
All rights reserved by Archive ouverte UNIGE and the University of GenevaunigeBlack