% IMPORTANT: The following is UTF-8 encoded.  This means that in the presence
% of non-ASCII characters, it will not work with BibTeX 0.99 or older.
% Instead, you should use an up-to-date BibTeX implementation like “bibtex8” or
% “biber”.

@INPROCEEDINGS{GarciaGarcia:820847,
      author       = {Garcia Garcia, Alberto and Beckmann, Andreas and Kabadshow,
                      Ivo},
      title        = {{A}ccelerating an {FMM}-{B}ased {C}oulomb {S}olver with
                      {GPU}s},
      volume       = {113},
      address      = {Cham},
      publisher    = {Springer International Publishing},
      reportid     = {FZJ-2016-06114},
      isbn         = {978-3-319-40526-1 (print)},
      series       = {Lecture Notes in Computational Science and Engineering},
      pages        = {485 - 504},
      year         = {2016},
      comment      = {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},
      booktitle     = {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},
      abstract     = {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.},
      month         = {Jan},
      date          = {2016-01-25},
      organization  = {SPPEXA Symposium 2016, München
                       (Germany), 25 Jan 2016 - 27 Jan 2016},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / GromEx - Highly Scalable Unified Long-Range
                      Electrostatics and Flexible Ionization for Realistic
                      Biomolecular Simulations on the Exascale (230673686)},
      pid          = {G:(DE-HGF)POF3-511 / G:(GEPRIS)230673686},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      UT           = {WOS:000411331500022},
      doi          = {10.1007/978-3-319-40528-5_22},
      url          = {https://juser.fz-juelich.de/record/820847},
}