%0 Conference Paper
%A Garcia Garcia, Alberto
%A Beckmann, Andreas
%A Kabadshow, Ivo
%T Accelerating an FMM-Based Coulomb Solver with GPUs
%V 113
%C Cham
%I Springer International Publishing
%M FZJ-2016-06114
%@ 978-3-319-40526-1 (print)
%B Lecture Notes in Computational Science and Engineering
%P 485 - 504
%D 2016
%< Software for Exascale Computing - SPPEXA 2013-2015 / Bungartz, Hans-Joachim (Editor)   ; Cham : Springer International Publishing, 2016, Chapter 22 ; ISSN: 1439-7358=2197-7100 ; ISBN: 978-3-319-40526-1=978-3-319-40528-5
%X The simulation of long-range electrostatic interactions in huge particle ensembles is a vital issue in current scientific research. The Fast Multipole Method (FMM) is able to compute those Coulomb interactions with extraordinary speed and controlled precision. A key part of this method are its shifting operators, which usually exhibit O(p^4) complexity. Some special rotation-based operators with O(p^3) complexity can be used instead. However, they are still computationally expensive. Here we report on the parallelization of those operators that have been implemented for a GPU cluster to speed up the FMM calculations.
%B SPPEXA Symposium 2016
%C 25 Jan 2016 - 27 Jan 2016, München (Germany)
Y2 25 Jan 2016 - 27 Jan 2016
M2 München, Germany
%F PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
%9 Contribution to a conference proceedingsContribution to a book
%U <Go to ISI:>//WOS:000411331500022
%R 10.1007/978-3-319-40528-5_22
%U https://juser.fz-juelich.de/record/820847