% 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”.

@ARTICLE{DiNapoli:819955,
      author       = {Di Napoli, Edoardo and Peise, Elmar and Hrywniak, Markus
                      and Bientinesi, Paolo},
      title        = {{H}igh-performance generation of the {H}amiltonian and
                      {O}verlap matrices in {FLAPW} methods},
      journal      = {Computer physics communications},
      volume       = {211},
      issn         = {0010-4655},
      address      = {Amsterdam},
      publisher    = {North Holland Publ. Co.},
      reportid     = {FZJ-2016-05522},
      pages        = {61-72},
      year         = {2017},
      abstract     = {One of the greatest efforts of computational scientists is
                      to translate the mathematical model describing a class of
                      physical phenomena into large and complex codes. Many of
                      these codes face the difficulty of implementing the
                      mathematical operations in the model in terms of low level
                      optimized kernels offering both performance and portability.
                      Legacy codes suffer from the additional curse of rigid
                      design choices based on outdated performance metrics (e.g.
                      minimization of memory footprint). Using a representative
                      code from the Materials Science community, we propose a
                      methodology to restructure the most expensive operations in
                      terms of an optimized combination of dense linear algebra
                      (BLAS3) kernels. The resulting algorithm guarantees an
                      increased performance and an extended life span of this
                      code, enabling larger scale simulations.},
      cin          = {JSC / JARA-HPC},
      ddc          = {004},
      cid          = {I:(DE-Juel1)JSC-20090406 / $I:(DE-82)080012_20140620$},
      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)16},
      UT           = {WOS:000390181300010},
      doi          = {10.1016/j.cpc.2016.10.003},
      url          = {https://juser.fz-juelich.de/record/819955},
}