% 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{FabregatTraver:820439,
      author       = {Fabregat-Traver, Diego and Davidović, Davor and
                      Höhnerbach, Markus and Di Napoli, Edoardo},
      title        = {{H}ybrid {CPU}-{GPU} generation of the {H}amiltonian and
                      {O}verlap matrices in {FLAPW} methods},
      volume       = {10164},
      publisher    = {Springer-Verlag},
      reportid     = {FZJ-2016-05749},
      series       = {Lecture Notes in Computer Science},
      pages        = {200-211},
      year         = {2016},
      abstract     = {In this paper we focus on the integration of
                      high-performance numerical libraries in ab initio codes and
                      the portability of performance and scalability. The target
                      of our work is FLEUR, a software for electronic structure
                      calculations developed in the Forschungszentrum $J\'ulich$
                      over the course of two decades. The presented work follows
                      up on a previous effort to modernize legacy code by
                      re-engineering and rewriting it in terms of highly optimized
                      libraries. We illustrate how this initial effort to get
                      efficient and portable shared-memory code enables fast
                      porting of the code to emerging heterogeneous architectures.
                      More specifically, we port the code to nodes equipped with
                      multiple GPUs. We divide our study in two parts. First, we
                      show considerable speedups attained by minor and relatively
                      straightforward code changes to off-load parts of the
                      computation to the GPUs. Then, we identify further possible
                      improvements to achieve even higher performance and
                      scalability. On a system consisting of 16-cores and 2 GPUs,
                      we observe speedups of up to 5x with respect to our
                      optimized shared-memory code, which in turn means between
                      7.5x and 12.5x speedup with respect to the original FLEUR
                      code.},
      month         = {Oct},
      date          = {2016-10-04},
      organization  = {JARA High-Performance Computing
                       Symposium, Aachen (Germany), 4 Oct 2016
                       - 5 Oct 2016},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / Simulation and Data Laboratory Quantum
                      Materials (SDLQM) (SDLQM)},
      pid          = {G:(DE-HGF)POF3-511 / G:(DE-Juel1)SDLQM},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      eprint       = {1611.00606},
      howpublished = {arXiv:1611.00606},
      archivePrefix = {arXiv},
      SLACcitation = {$\%\%CITATION$ = $arXiv:1611.00606;\%\%$},
      doi          = {10.1007/978-3-319-53862-4_17},
      url          = {https://juser.fz-juelich.de/record/820439},
}