Abstract
The efficiency of discrete ordinates transport sweeps depends on the scheduling algorithm, the domain decomposition, the problem to be solved, and the computational platform. Sweep scheduling algorithms may be categorized by their approach to several issues. In this paper we examine the strategy of domain overloading for mesh partitioning as one of the components of such algorithms. In particular, we extend the domain overloading strategy, previously defined and analyzed for structured meshes, to the general case of unstructured meshes. We also present computational results for both the structured and unstructured domain overloading cases. We find that an appropriate amount of domain overloading can greatly improve the efficiency of parallel sweeps for both structured and unstructured partitionings of the test problems examined on up to 105 processor cores.
Acknowledgments
We thank the various members of the Predictive Science Academic Alliance Program project in the Departments of Nuclear Engineering and Computer Science at Texas A&M University for fruitful discussions on this topic, in particular, for working toward a common taxonomy and language for various sweep algorithms.
Work by the first author was conducted at Sandia National Laboratories (SNL). SNL is a multiprogram laboratory operated by Sandia Corporation, a wholly owned subsidiary of Lockheed Martin company, for the U.S. Department of Energy's (DOE's) National Nuclear Security Administration under contract DE-AC04-94AL85000. Work by the second author was conducted at Lawrence Livermore National Laboratory (LLNL). This work was performed under the auspices of the DOE by LLNL under contract DE-AC52-07NA27344.