% 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{Halver:808537,
      author       = {Halver, Rene and Sutmann, Godehard},
      title        = {{M}ulti-threaded {C}onstruction of {N}eighbour {L}ists for
                      {P}article {S}ystems in {O}pen{MP}},
      volume       = {9574},
      address      = {Cham},
      publisher    = {Springer International Publishing},
      reportid     = {FZJ-2016-02275},
      isbn         = {978-3-319-32151-6 (print)},
      series       = {Lecture Notes in Computer Science},
      pages        = {153 - 165},
      year         = {2016},
      comment      = {Parallel Processing and Applied Mathematics / Wyrzykowski,
                      Roman (Editor), ISBN: 978-3-319-32151-6=978-3-319-32152-3},
      booktitle     = {Parallel Processing and Applied
                       Mathematics / Wyrzykowski, Roman
                       (Editor), ISBN:
                       978-3-319-32151-6=978-3-319-32152-3},
      abstract     = {The construction of neighbour lists based on the linked
                      cell method is investigated in the context of particle
                      simulation methods within the OpenMP shared memory
                      programming model. Various implementations are studied which
                      avoid memory collisions and race conditions. Performance and
                      optimisation considerations are made along with run time
                      behaviour and memory requirements. Performance models are
                      proposed, which reproduce the measured runtime behaviour and
                      which provide insight into the performance dependence on
                      specific system parameters. Benchmarks are performed for
                      different implementations on a number of multi-core
                      architectures and thread numbers up to 240 are considered on
                      the Xeon Phi architecture in the SMT mode, so that
                      performance can be studied for a large number of threads
                      working concurrently on the construction of linked cells on
                      a shared memory partition.},
      month         = {Sep},
      date          = {2015-09-06},
      organization  = {11th International Conference on
                       Parallel Processing and Applied
                       Mathematics, Krakow (Poland), 6 Sep
                       2015 - 9 Sep 2015},
      cin          = {JSC},
      ddc          = {004},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511)},
      pid          = {G:(DE-HGF)POF3-511},
      typ          = {PUB:(DE-HGF)8},
      UT           = {WOS:000400135500015},
      doi          = {10.1007/978-3-319-32152-3_15},
      url          = {https://juser.fz-juelich.de/record/808537},
}