% 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{Herten:824109,
      author       = {Herten, Andreas and Pleiter, Dirk and Brömmel, Dirk},
      title        = {{A}ccelerating {P}lasma {P}hysics with {GPU}s},
      school       = {Sapienza Università di Roma},
      reportid     = {FZJ-2016-06733},
      year         = {2016},
      abstract     = {JuSPIC is a particle-in-cell (PIC) code, developed in the
                      Simulation Lab for Plasma Physics of the Jülich
                      Supercomputing Centre. The open source code is based on PSC
                      by H. Ruhl, slimmed-down and rewritten in modern Fortran.
                      JuSPIC simulates particles under the influence of
                      electromagnetic fields, using the relativistic Vlasov
                      equation and Maxwell's equations (integrated using the
                      Finite Difference Time Domain scheme). The program uses a
                      regular mesh for the Maxwell fields and the particle
                      charge/current densities. Inside the mesh, quasi-particles
                      with continuous coordinates are modeled via distribution
                      functions. JuSPIC is part of the High-Q club, attesting that
                      it can efficiently scale to the full JUQUEEN supercomputer
                      (currently the #13 on the Top 500 list): 1.8 million threads
                      running on 458 thousand cores can collaboratively compute
                      plasma simulations. Local node-level parallelism is achieved
                      by means of OpenMP, communication between nodes relies on
                      MPI. To leverage the latest generation of supercomputers
                      coming equipped with dedicated accelerator technologies
                      (GPUs and other many-core architectures), JuSPIC is
                      currently being extended. In this poster we present a
                      GPU-accelerated version of the program, making use of
                      different programming models. We show first results of
                      performance studies, comparing OpenACC and CUDA. While
                      OpenACC aims to offer portability and flexibility by means
                      of few changes to the code, the performance of the generated
                      program might suffer in practice. To measure the deficit,
                      the compute-intensive parts of the program are in addition
                      also implemented in CUDA Fortran. To explore scalability
                      properties of the application for static particle
                      distributions on a heterogeneous architecture, we make use
                      of semi-empirical performance models.},
      month         = {Sep},
      date          = {2016-09-26},
      organization  = {Perspectives of GPU computing in
                       Science, Rome (Italy), 26 Sep 2016 - 28
                       Sep 2016},
      subtyp        = {After Call},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511)},
      pid          = {G:(DE-HGF)POF3-511},
      typ          = {PUB:(DE-HGF)24},
      url          = {https://juser.fz-juelich.de/record/824109},
}