% 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{Lintermann:866740,
      author       = {Lintermann, Andreas},
      title        = {{EFFICIENT} {PARALLEL} {GEOMETRY} {DISTRIBUTION} {FOR}
                      {THE} {SIMULATION} {OF} {COMPLEX} {FLOWS}},
      publisher    = {Institute of Structural Analysis and Antiseismic Research
                      School of Civil Engineering National Technical University of
                      Athens (NTUA) Greece Athens},
      reportid     = {FZJ-2019-05809},
      pages        = {1277-1293},
      year         = {2016},
      comment      = {Proceedings of the VII European Congress on Computational
                      Methods in Applied Sciences and Engineering (ECCOMAS
                      Congress 2016) - Institute of Structural Analysis and
                      Antiseismic Research School of Civil Engineering National
                      Technical University of Athens (NTUA) Greece Athens, 2016. -
                      ISBN 978-618-82844-0-1 - doi:10.7712/100016.1885.5067},
      booktitle     = {Proceedings of the VII European
                       Congress on Computational Methods in
                       Applied Sciences and Engineering
                       (ECCOMAS Congress 2016) - Institute of
                       Structural Analysis and Antiseismic
                       Research School of Civil Engineering
                       National Technical University of Athens
                       (NTUA) Greece Athens, 2016. - ISBN
                       978-618-82844-0-1 -
                       doi:10.7712/100016.1885.5067},
      abstract     = {Highly resolved intrinsic geometrical shapes used in
                      three-dimensional parallel simulations offluid flows consume
                      a large portion ofthe available memory when loaded serially
                      on every process. This demands for a memory efficient
                      implementation of a distributed geometry which is however a
                      non-trivial task when complex spatial domain decomposition
                      methods for the flow domain are involved. To overcome this
                      problem, an algorithm to generate a parallel geometry during
                      the mesh generation is proposed that enables a low-memory
                      subdivision ofthe geometry based on the decomposition of the
                      flow field. The applied meshing method generates
                      computational grids that can be used for simulations on a
                      quasi-arbitrary number ofcores on which the geometry is
                      distributed in an efficient preprocessing step. This allows
                      reducing the number ofinstances ofthe geometry in the global
                      memory ofthesimulation toaboutone. The algorithm is used to
                      generate a parallel geometry for a large shape consisting of
                      $7x10^6$ triangles, i.e., for a geometry representing the
                      whole respiratory tract down to the 12th lung generation.
                      For this case, performance and memory consumption
                      measurements are given for simulations on 8,192 up to
                      131,072 cores and juxtaposed to results obtained from
                      simulations using non-parallel geometries. The findings show
                      that with thenewmethodnot onlythe memory usage could be
                      reduced by the factors of 1,802 and 19,936 for core numbers
                      of 8,192 and 131,072 but also a large speed-up factor
                      ofabout 51 is obtained in the geometry I/O and
                      preprocessing. Furthermore, the parallel geometry allows
                      using the sweet spot with respect to acombination of
                      distributed and sharedmemory parallelization leading to an
                      increase of the computational speed ofabout 1.43.},
      month         = {Jun},
      date          = {2016-06-05},
      organization  = {VII European Congress on Computational
                       Methods in Applied Sciences and
                       Engineering, Crete Island (Greece), 5
                       Jun 2016 - 10 Jun 2016},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511)},
      pid          = {G:(DE-HGF)POF3-511},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.7712/100016.1885.5067},
      url          = {https://juser.fz-juelich.de/record/866740},
}