Abstract
Dynamic load balancing(DLB) for parallel systems has been studied extensively; however, DLB for distributed systems is relatively new. To efficiently utilize computing resources provided by distributed systems, an underlying DLB scheme must address both heterogeneous and dynamic features of distributed systems. In this paper, we propose a DLB scheme for Structured Adaptive Mesh Refinement(SAMR) applications on distributed systems. While the proposed scheme can take into consideration (1) the heterogeneity of processors and (2) the heterogeneity and dynamic load of the networks, the focus of this paper is on the latter. The load-balancing processes are divided into two phases: global load balancing and local load balancing. We also provide a heuristic method to evaluate the computational gain and redistribution cost for global redistribution. Experiments show that by using our distributed DLB scheme, the execution time can be reduced by 9%- to using parallel DLB scheme which does not consider the heterogeneous and dynamic features of distributed systems.
Highlights
Structured Adaptive Mesh Refinement (SAMR) is a type of multiscale algorithm that dynamically achieves high resolution in localized regions of multidimensional numerical simulations
We proposed a dynamic load balancing scheme for distributed systems
While our dynamic load balancing (DLB) takes into consideration the two features, the experiments presented in this paper focus on the heterogeneity and dynamic load of the networks due to the limited availability of distributed system testbeds
Summary
Structured Adaptive Mesh Refinement (SAMR) is a type of multiscale algorithm that dynamically achieves high resolution in localized regions of multidimensional numerical simulations. To efficiently utilize the computing resources provided by distributed systems, the underlying dynamic load balancing (DLB) scheme must take into consideration the heterogeneous and dynamic features of distributed systems. We proposed a dynamic load balancing scheme for distributed systems This scheme takes into consideration (1) the heterogeneity of processors and (2) the heterogeneity and dynamic load of the networks. While our DLB takes into consideration the two features, the experiments presented in this paper focus on the heterogeneity and dynamic load of the networks due to the limited availability of distributed system testbeds.
Talk to us
Join us for a 30 min session where you can share your feedback and ask us any queries you have