A scalable RBF-FD method for atmospheric flow
2015 (English)In: Journal of Computational Physics, ISSN 0021-9991, E-ISSN 1090-2716, Vol. 298, 406-422 p.Article in journal (Refereed) Published
Radial basis function-generated finite difference (RBF-FD) methods have recently been proposed as very interesting for global scale geophysical simulations, and have been shown to outperform established pseudo-spectral and discontinuous Galerkin methods for shallow water test problems. In order to be competitive for very large scale simulations, the RBF-FD methods needs to be efficiently implemented for modern multicore based computer architectures. This is a challenging assignment, because the main computational operations are unstructured sparse matrix-vector multiplications, which in general scale poorly on multicore computers due to bandwidth limitations. However, with the task parallel implementation described here we achieve 60-100% of theoretical speedup within a shared memory node, and 80-100% of linear speedup across nodes. We present results for global shallow water benchmark problems with a 30 km resolution.
Place, publisher, year, edition, pages
2015. Vol. 298, 406-422 p.
Shallow water, Scattered node, Task parallel, Distributed memory, Multicore, Radial basis function, RBF-FD
Computational Mathematics Fluid Mechanics and Acoustics
IdentifiersURN: urn:nbn:se:kth:diva-173128DOI: 10.1016/j.jcp.2015.06.003ISI: 000358796700023ScopusID: 2-s2.0-84932624924OAI: oai:DiVA.org:kth-173128DiVA: diva2:855096
FunderSwedish Research CouncilSwedish National Infrastructure for Computing (SNIC), SNIC2014-3-102
QC 201509182015-09-182015-09-072015-09-18Bibliographically approved