Parallelization of structured, hierarchical adaptive mesh refinement algorithms
| Autor: | William Y. Crutchfield, John B. Bell, M.J. Lijewski, V E Beckner, C. A. Rendleman |
|---|---|
| Rok vydání: | 2000 |
| Předmět: |
Adaptive algorithm
Computer science business.industry Adaptive mesh refinement Numerical analysis General Engineering Parallel computing Grid Theoretical Computer Science Automatic parallelization Software Computational Theory and Mathematics Mesh generation Modeling and Simulation Key (cryptography) Computer Vision and Pattern Recognition business Algorithm |
| Zdroj: | Computing and Visualization in Science. 3:147-157 |
| ISSN: | 1432-9360 |
| DOI: | 10.1007/pl00013544 |
| Popis: | We describe an approach to parallelization of structured adaptive mesh refinement algorithms. This type of adaptive methodology is based on the use of local grids superimposed on a coarse grid to achieve sufficient resolution in the solution. The key elements of the approach to parallelization are a dynamic load-balancing technique to distribute work to processors and a software methodology for managing data distribution and communications. The methodology is based on a message-passing model that exploits the coarse-grained parallelism inherent in the algorithms. The approach is illustrated for an adaptive algorithm for hyperbolic systems of conservation laws in three space dimensions. A numerical example computing the interaction of a shock with a helium bubble is presented. We give timings to illustrate the performance of the method. |
| Databáze: | OpenAIRE |
| Externí odkaz: |
|
Full text from SpringerLink