Decentralized remapping of data parallel applications in distributed memory multiprocessors

Abstract

In this paper we present a decentralized remapping method for data parallel applications on distributed memory multiprocessors. The method uses a generalized dimension exchange (GDE) algorithm periodically during the execution of an application to balance (remap) the system's workload. We implemented this remapping method in parallel WaTor simulations and parallel image thinning applications, and found it to be effective in reducing the computation time. The average performance gain is about 20% in the WaTor simulation of a 256 × 256 ocean grid on 16 processors, and up to 8% in the thinning of a typical image of size 128 × 128 on eight processors. The performance gains due to remapping in the image thinning case are reasonably substantial given the fact that the application by its very nature does not necessarily favor remapping. We also implemented this remapping method, using up to 32 processors, for partitioning and re‐partitioning of grids in computational fluid dynamics. It was found that the GDE‐based parallel refinement policy, coupled with simple geometric strategies, produces partitions that are comparable in quality to those from the best serial algorithms. © 1997 John Wiley & Sons, Ltd.

Accelerating Distributed Graphical Fluid Simulations with Micro‐partitioning

“…Centralized dynamic load balancing algorithms [NH85] can bottleneck at the central node [MK13]. Fully distributed load balancing algorithms [XLD97, MK13] solve the scalability problem but converge slowly. Hierarchical load balancing algorithms [ZBMK11, JMM*13] adopt a multi‐level scheduling architecture, where lowest level schedulers balance loads within a group of nodes, and higher level schedulers balance loads between lower level schedulers.…”