Basic Machine Learning Approaches for the Acceleration of PDE Simulations and Realization in the FEAT3 Software
| dc.contributor.author | Ruelmann, Hannes | |
| dc.contributor.author | Geveler, Markus | |
| dc.contributor.author | Ribbrock, Dirk | |
| dc.contributor.author | Zajac, Peter | |
| dc.contributor.author | Turek, Stefan | |
| dc.date.accessioned | 2019-12-20T11:55:49Z | |
| dc.date.available | 2019-12-20T11:55:49Z | |
| dc.date.issued | 2019-12 | |
| dc.description.abstract | In this paper we present a holistic software approach based on the FEAT3 software for solving multidimensional PDEs with the Finite Element Method that is built for a maximum of performance, scalability, maintainability and extensibilty. We introduce basic paradigms how modern computational hardware architectures such as GPUs are exploited in a numerically scalable fashion. We show, how the framework is extended to make even the most recent advances on the hardware market accessible to the framework, exemplified by the ubiquitous trend to customize chips for Machine Learning. We can demonstrate that for a numerically challenging model problem, artificial neural networks can be used while preserving a classical simulation solution pipeline through the incorporation of a neural network preconditioner in the linear solver | en |
| dc.identifier.issn | 2190-1767 | |
| dc.identifier.uri | http://hdl.handle.net/2003/38462 | |
| dc.identifier.uri | http://dx.doi.org/10.17877/DE290R-20381 | |
| dc.language.iso | en | |
| dc.relation.ispartofseries | Ergebnisberichte des Instituts für Angewandte Mathematik;618 | de |
| dc.subject.ddc | 610 | |
| dc.title | Basic Machine Learning Approaches for the Acceleration of PDE Simulations and Realization in the FEAT3 Software | en |
| dc.type | Text | |
| dc.type.publicationtype | preprint | |
| dcterms.accessRights | open access | |
| eldorado.secondarypublication | false |