% 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{Kumbhar:811415,
      author       = {Kumbhar, Pramod and Hines, Michael and Ovcharenko,
                      Aleksandr and Alvarez, Damian and King, James and Sainz,
                      Florentino and Schürmann, Felix and Delalondre, Fabien},
      title        = {{L}everaging a {C}luster-{B}ooster {A}rchitecture for
                      {B}rain-{S}cale {S}imulations},
      volume       = {9697},
      address      = {Cham},
      publisher    = {Springer International Publishing},
      reportid     = {FZJ-2016-03899},
      isbn         = {978-3-319-41320-4 (print)},
      series       = {Lecture Notes in Computer Science},
      pages        = {363 - 380},
      year         = {2016},
      comment      = {Proceedings of the 31st International Conference High
                      Performance Computing},
      booktitle     = {Proceedings of the 31st International
                       Conference High Performance Computing},
      abstract     = {The European Dynamical Exascale Entry Platform (DEEP) is an
                      example of a new type of heterogeneous supercomputing
                      architecture that include both a standard multicore-based
                      “Cluster” used to run less scalable parts of an
                      application, and an Intel MIC-based “Booster” used to
                      run highly scalable compute kernels. In this paper we
                      describe how the compute engine of the widely used NEURON
                      scientific application has been ported on both the DEEP and
                      the Intel MIC platform. We discuss the design and
                      implementation of the core simulator with an emphasis on the
                      development workflow and implementation details that enable
                      the efficient use of the new “Cluster-Booster” type of
                      architectures. We describe optimizations of the data
                      structures and algorithms tailored to the Intel Xeon Phi
                      coprocessor which contributed to improve the overall
                      performance of NEURON by a factor 5. Validation of our
                      implementation has first been done on STAMPEDE supercomputer
                      in order to emulate the DEEP architecture performance.
                      Building on these results, we then explored opportunities
                      offered by the DEEP platform to efficiently support complex
                      scientific workflow.},
      month         = {Jun},
      date          = {2016-06-19},
      organization  = {31st International Conference High
                       Performance Computing, Frankfurt
                       (Germany), 19 Jun 2016 - 23 Jun 2016},
      cin          = {JSC},
      ddc          = {004},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {513 - Supercomputer Facility (POF3-513) / 511 -
                      Computational Science and Mathematical Methods (POF3-511) /
                      DEEP - Dynamical Exascale Entry Platform (287530)},
      pid          = {G:(DE-HGF)POF3-513 / G:(DE-HGF)POF3-511 /
                      G:(EU-Grant)287530},
      typ          = {PUB:(DE-HGF)8 / PUB:(DE-HGF)7},
      UT           = {WOS:000386513900019},
      doi          = {10.1007/978-3-319-41321-1_19},
      url          = {https://juser.fz-juelich.de/record/811415},
}