Global load balancing with parallel mesh adaption on distributed-memory systems

Rupak Biswas, Leonid Oliker, Andrew Sohn

Research output: Chapter in Book/Report/Conference proceedingConference contribution

4 Scopus citations


Dynamic mesh adaption on unstructured grids is a powerful tool for efficiently computing unsteady problems to resolve solution features of interest. Unfortunately this causes load imbalance among processors on a parallel machine. This paper describes the parallel implementation of a tetrahedral mesh adaption scheme and a new global load balancing method. A heuristic remapping algorithm is presented that assigns partitions to processors such that the redistribution cost is minimized. Results indicate that the parallel performance of the mesh adaption code depends on the nature of the adaption region and show a 35.5X speedup on 64 processors of an SP2 when 35% of the mesh is randomly adapted. For large-scale scientific computations, our load balancing strategy gives almost a sixfold reduction in solver execution times over non-balanced loads. Furthermore, our heuristic remapper yields processor assignments that are less than 3% off the optimal solutions but requires only 1% of the computational time.

Original languageEnglish (US)
Title of host publicationProceedings of the 1996 ACM/IEEE Conference on Supercomputing, SC 1996
PublisherAssociation for Computing Machinery
ISBN (Electronic)0897918541
StatePublished - 1996
Event1996 ACM/IEEE Conference on Supercomputing, SC 1996 - Pittsburgh, United States
Duration: Nov 17 1996Nov 22 1996

Publication series

NameProceedings of the International Conference on Supercomputing


Conference1996 ACM/IEEE Conference on Supercomputing, SC 1996
Country/TerritoryUnited States

All Science Journal Classification (ASJC) codes

  • General Computer Science


  • Distributed-memory machines
  • Dual graph
  • Load balancing
  • Mesh adaption
  • Processor reassignment
  • Unstructured grids


Dive into the research topics of 'Global load balancing with parallel mesh adaption on distributed-memory systems'. Together they form a unique fingerprint.

Cite this