% 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”.

@TECHREPORT{Brmmel:828084,
      key          = {828084},
      editor       = {Brömmel, Dirk and Frings, Wolfgang and Wylie, Brian J. N.},
      title        = {{JUQUEEN} {E}xtreme {S}caling {W}orkshop 2017},
      number       = {FZJ-JSC-IB-2017-01},
      reportid     = {FZJ-2017-02087, FZJ-JSC-IB-2017-01},
      series       = {JSC Internal Report},
      pages        = {47 pp.},
      year         = {2017},
      abstract     = {From 23 to 25 January 2017, JSC organised its eighth IBM
                      Blue Gene Extreme Scaling Workshop. The entire 28-rack
                      JUQUEEN Blue Gene/Q was reserved for over 50 hours to allow
                      six selected code teams to investigate and improve the
                      scalability of their applications. Ultimately, all six codes
                      managed to run using the full complement of 458,752 cores
                      (most with over 1.8 million threads). MPAS-A (KIT/NCAR) and
                      the pe rigid body physics engine (FAU) were both able to
                      display strong scalability to 28 racks and thereby become
                      candidates for High-Q Club membership. MPAS-A returned after
                      participating in the 2015 workshop with a higher resolution
                      dataset and substantially improved file I/O using SIONlib to
                      successfully manage its largest ever global atmospheric
                      simulation. While the hydrology simulator ParFlow
                      (UBonn/FZJ-IGB) had recently demonstrated execution scaling
                      to the full JUQUEEN without file writing enabled, during the
                      workshop the focus was investigating file I/O performance
                      which remains a bottleneck. High-Q Club member KKRnano
                      (FZJ-IAS) investigated the scalability of a new solver
                      algorithm developed to handle a million atoms, while the
                      latest version of CPMD was tested with a large 1500-atom
                      system. Both of these quantum materials codes uncovered
                      performance limitations at larger scales. The final code was
                      a prototype multi-compartmental neuronal network simulator,
                      NestMC (JSC SimLab Neuroscience), which compared scalability
                      of different threading implementations. Detailed reports are
                      provided by each code-team, and additional comparative
                      analysis to the 28 High-Q Club member codes.},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / 513 - Supercomputer Facility (POF3-513) /
                      ATMLPP - ATML Parallel Performance (ATMLPP) / ATMLAO - ATML
                      Application Optimization and User Service Tools (ATMLAO)},
      pid          = {G:(DE-HGF)POF3-511 / G:(DE-HGF)POF3-513 /
                      G:(DE-Juel-1)ATMLPP / G:(DE-Juel-1)ATMLAO},
      typ          = {PUB:(DE-HGF)3 / PUB:(DE-HGF)29 / PUB:(DE-HGF)15},
      url          = {https://juser.fz-juelich.de/record/828084},
}