% 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{Baumeister:844645,
      author       = {Baumeister, P. F. and Rombach, B. and Hater, Thorsten and
                      Griessbach, S. and Hoffmann, L. and Bühler, M. and Pleiter,
                      D.},
      title        = {{S}trategies for {F}orward {M}odelling of {I}nfrared
                      {R}adiative {T}ransfer on {GPU}s},
      volume       = {32},
      address      = {Amsterdam},
      publisher    = {IOS Press},
      reportid     = {FZJ-2018-02040},
      series       = {Advances in Parallel Computing},
      pages        = {369 - 380},
      year         = {2018},
      comment      = {Parallel Computing is Everywhere},
      booktitle     = {Parallel Computing is Everywhere},
      abstract     = {Satellite-based remote sensing in the mid-infrared spectral
                      region can deliver a wealth of information on pressure,
                      temperature, clouds and aerosols, and trace gas
                      concentrations in the atmosphere. Interpreting the satellite
                      measurements requires to solve an inverse modelling problem
                      based on variational methods and a forward model evaluating
                      the radiative transfer equations. As state-of-the-art
                      satellite measurement campaigns require Petascale systems to
                      process the data in due time, graphical processing units are
                      employed for the high-throughput problem of computing the
                      forward model for a given atmospheric state. We explore
                      features of the considered architecture as well as relevant
                      performance signatures of the different implementations to
                      improve our understanding on opportunities for efficient
                      exploitation of GPU-accelerated architectures based on the
                      POWER2processor for this class of applications. Scalability
                      is a key aspect as the application is known to scale well on
                      massively-parallel architectures.},
      month         = {Sep},
      date          = {2017-09-12},
      organization  = {Parallel Computing, Bologna (Italy),
                       12 Sep 2017 - 15 Sep 2017},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / 513 - Supercomputer Facility (POF3-513)},
      pid          = {G:(DE-HGF)POF3-511 / G:(DE-HGF)POF3-513},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.3233/978-1-61499-843-3-369},
      url          = {https://juser.fz-juelich.de/record/844645},
}