% 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{Gasper:187139,
      author       = {Gasper, F. and Goergen, K. and Shrestha, P. and Sulis, M.
                      and Rihani, J. and Geimer, M. and Kollet, S.},
      title        = {{I}mplementation and scaling of the fully coupled
                      {T}errestrial {S}ystems {M}odeling {P}latform
                      ({T}err{S}ys{MP} v1.0) in a massively parallel
                      supercomputing environment – a case study on {JUQUEEN}
                      ({IBM} {B}lue {G}ene/{Q})},
      journal      = {Geoscientific model development},
      volume       = {7},
      number       = {5},
      issn         = {1991-9603},
      address      = {Katlenburg-Lindau},
      publisher    = {Copernicus},
      reportid     = {FZJ-2015-00813},
      pages        = {2531 - 2543},
      year         = {2014},
      abstract     = {Continental-scale hyper-resolution simulations constitute a
                      grand challenge in characterizing nonlinear feedbacks of
                      states and fluxes of the coupled water, energy, and
                      biogeochemical cycles of terrestrial systems. Tackling this
                      challenge requires advanced coupling and supercomputing
                      technologies for earth system models that are discussed in
                      this study, utilizing the example of the implementation of
                      the newly developed Terrestrial Systems Modeling Platform
                      (TerrSysMP v1.0) on JUQUEEN (IBM Blue Gene/Q) of the Jülich
                      Supercomputing Centre, Germany. The applied coupling
                      strategies rely on the Multiple Program Multiple Data (MPMD)
                      paradigm using the OASIS suite of external couplers, and
                      require memory and load balancing considerations in the
                      exchange of the coupling fields between different component
                      models and the allocation of computational resources,
                      respectively. Using the advanced profiling and tracing tool
                      Scalasca to determine an optimum load balancing leads to a
                      $19\%$ speedup. In massively parallel supercomputer
                      environments, the coupler OASIS-MCT is recommended, which
                      resolves memory limitations that may be significant in case
                      of very large computational domains and exchange fields as
                      they occur in these specific test cases and in many
                      applications in terrestrial research. However, model I/O and
                      initialization in the petascale range still require major
                      attention, as they constitute true big data challenges in
                      light of future exascale computing resources. Based on a
                      factor-two speedup due to compiler optimizations, a
                      refactored coupling interface using OASIS-MCT and an optimum
                      load balancing, the problem size in a weak scaling study can
                      be increased by a factor of 64 from 512 to 32 768 processes
                      while maintaining parallel efficiencies above $80\%$ for the
                      component models.},
      cin          = {IBG-3 / NIC / JARA-HPC},
      ddc          = {910},
      cid          = {I:(DE-Juel1)IBG-3-20101118 / I:(DE-Juel1)NIC-20090406 /
                      $I:(DE-82)080012_20140620$},
      pnm          = {246 - Modelling and Monitoring Terrestrial Systems: Methods
                      and Technologies (POF2-246) / 255 - Terrestrial Systems:
                      From Observation to Prediction (POF3-255) / Scalable
                      Performance Analysis of Large-Scale Parallel Applications
                      $(jzam11_20091101)$ / ATMLPP - ATML Parallel Performance
                      (ATMLPP)},
      pid          = {G:(DE-HGF)POF2-246 / G:(DE-HGF)POF3-255 /
                      $G:(DE-Juel1)jzam11_20091101$ / G:(DE-Juel-1)ATMLPP},
      typ          = {PUB:(DE-HGF)16},
      UT           = {WOS:000344730900041},
      doi          = {10.5194/gmd-7-2531-2014},
      url          = {https://juser.fz-juelich.de/record/187139},
}