h1

% 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”.

@PHDTHESIS{Hhnerbach:826069,
      author       = {Höhnerbach, Markus},
      othercontributors = {Bientinesi, Paolo and Naumann, Uwe and Kelly, Paul},
      title        = {{A} framework for the vectorization of molecular dynamics
                      kernels},
      school       = {RWTH Aachen University},
      type         = {Dissertation},
      address      = {Aachen},
      publisher    = {RWTH Aachen University},
      reportid     = {RWTH-2021-08729},
      pages        = {1 Online-Ressource : Illustrationen, Diagramme},
      year         = {2020},
      note         = {Veröffentlicht auf dem Publikationsserver der RWTH Aachen
                      University 2021; Dissertation, RWTH Aachen University, 2020},
      abstract     = {This thesis introduces a domain-specific language (DSL) for
                      many-body potentials, which are used in molecular dynamics
                      (MD) simulations in the area of materials science. We also
                      introduce a compiler to translate the DSL into
                      high-performance code suitable for modern supercomputers. We
                      begin by studying ways to speedup up potentials on
                      supercomputers using two case studies: The Tersoff and the
                      AIREBO potentials. In both case studies, we identify a
                      number of optimizations, both domain-specific and general,
                      to achieve speedups of up to 5x; we also introduce a method
                      to keep the resulting code performance portable. During the
                      AIREBO case study, we also discover that the existing code
                      contains a number of errors. This experience motivates us to
                      include the derivation step, the most error-prone step in
                      manual optimization, in our automation effort.After having
                      identified beneficial optimization techniques, we create a
                      “potential compiler”, short PotC, which generates
                      fully-usable performance-portable potential implementations
                      from specifications written in our DSL. DSL code is
                      significantly shorter (20x to 30x) than a manual code,
                      reducing both manual work and opportunities to introduce
                      bugs.We present performance results on five different
                      platforms: Three CPU platforms (Broadwell, Knights Landing,
                      and Skylake) and two GPU platforms (Pascal and Volta). While
                      the performance in some cases remains far below that of
                      hand-written code, it also manages to match or exceed
                      manually written implementations in other cases. For these
                      cases, we achieve speedups of up to 9x compared to
                      non-vectorized code.},
      cin          = {123120 / 120000},
      ddc          = {004},
      cid          = {$I:(DE-82)123120_20140620$ / $I:(DE-82)120000_20140620$},
      typ          = {PUB:(DE-HGF)11},
      doi          = {10.18154/RWTH-2021-08729},
      url          = {https://publications.rwth-aachen.de/record/826069},
}