Parallelization of Level Set Methods for Solving Solidification Problems
Authors:
Kai Wang Anthony Chang Jonathan A. Dantzig Laxmikant V. Kale
Parallel Programming Laboratory, Department of Computer Science, University
of Illinois at Urbana-Champaign
Publication Information Not Available.
Processor virtualization is a kind of parallelization technique which may be used to enhance the performance of parallel applications from the cache performance, overlapping of communication and computation. In this study, we use the processor virtualization technique to parallelize the level set method for solving solidification problems. Numerical results on a distributed memory machine are reported to show the performance of the resulting level set solver, and demonstrate the advantages of using processor virtualization.