Original title: Massive parallel implementation of ODE solvers
Authors: Fischer, Cyril
Document type: Papers
Conference/Event: Programy a algoritmy numerické matematiky /16./, Dolní Maxov (CZ), 2012-06-03 / 2012-06-08
Year: 2013
Language: eng
Abstract: The paper maps the possibilities of exploitation of the massive parallel computational hardware (namely GPU) for solution of the initial value problems of ordinary differential equations. Two cases are discussed: parallel solution of a single ODE and parallel execution of scalar ODE solvers. Whereas the advantages of the special architecture in the case of a single ODE are problematic, repeated solution of a single ODE for different data can prot from the parallel architecture. However, special algorithms have to be used even in the latter case to avoid code divergence be- tween individual computational threads. The topic is illustrated on several examples.
Keywords: Graphical Processor Unit (GPU); NVIDIA CUDA; Ordinary Differential Equations (ODE)
Project no.: GA103/09/0094 (CEP), IAA200710902 (CEP)
Funding provider: GA ČR, GA AV ČR
Host item entry: Programs and Algorithms of Numerical Matematics 16, ISBN 978-80-85823-62-2

Institution: Institute of Theoretical and Applied Mechanics AS ČR (web)
Document availability information: Fulltext is available at the institute of the Academy of Sciences.
Original record: http://hdl.handle.net/11104/0220468

Permalink: http://www.nusl.cz/ntk/nusl-151835


The record appears in these collections:
Research > Institutes ASCR > Institute of Theoretical and Applied Mechanics
Conference materials > Papers