% 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{Ksters:838787,
      author       = {Küsters, Anne and Wienke, Sandra and Arnold, Lukas},
      title        = {{P}erformance {P}ortability {A}nalysis for {R}eal-{T}ime
                      {S}imulations of {S}moke {P}ropagation {U}sing {O}pen{ACC}},
      volume       = {10524},
      address      = {Cham},
      publisher    = {Springer International Publishing},
      reportid     = {FZJ-2017-07311},
      isbn         = {978-3-319-67629-6 (print)},
      series       = {Lecture Notes in Computer Science},
      pages        = {477 - 495},
      year         = {2017},
      comment      = {High Performance Computing / Kunkel, Julian M. (Editor),
                      Chapter 35 ; ISSN: 0302-9743=1611-3349 ; ISBN:
                      978-3-319-67629-6=978-3-319-67630-2},
      booktitle     = {High Performance Computing / Kunkel,
                       Julian M. (Editor), Chapter 35 ; ISSN:
                       0302-9743=1611-3349 ; ISBN:
                       978-3-319-67629-6=978-3-319-67630-2},
      abstract     = {Real-time simulations of smoke propagation during fires in
                      complex geometries challenge engineers, physicists,
                      mathematicians and computer scientists due to the complexity
                      of fluid dynamics and the large number of involved physical
                      and chemical processes. Recently, several application
                      scenarios emerged that require real-time predictions during
                      an incident to support the rescue teams. Therefore, we
                      develop the CFD-based simulation software JuROr aiming to
                      run in real-time by leveraging parallel computer
                      architectures like CPUs and GPUs. For that, we parallelize
                      the code with OpenACC directives that promise maintenance of
                      a single source base by delegating some
                      architecture-agnostic optimizations to the compiler. We
                      investigate the performance portability of JuROr using
                      PGI’s OpenACC implementation across four Intel CPUs and
                      three NVIDIA GPUs. We present the achieved performance
                      shares as part of a roofline model where we focus on
                      traditionally-computed arithmetic code intensities, as well
                      as on a measurement approach based on performance counters.},
      month         = {Jun},
      date          = {2017-06-18},
      organization  = {ISC High Performance 2017,
                       Frankfurt/Main (Germany), 18 Jun 2017 -
                       22 Jun 2017},
      cin          = {JSC},
      ddc          = {004},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / ORPHEUS - Optimierung der Rauchableitung und
                      Personenführung in U-Bahnhöfen: Experimente und
                      Simulationen (BMBF-13N13266)},
      pid          = {G:(DE-HGF)POF3-511 / G:(DE-Juel1)BMBF-13N13266},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      doi          = {10.1007/978-3-319-67630-2_35},
      url          = {https://juser.fz-juelich.de/record/838787},
}