% 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{Iwainsky:280948,
      author       = {Iwainsky, Christian and Shudler, Sergei and Calotoiu,
                      Alexandru and Strube, Alexandre and Knobloch, Michael and
                      Bischof, Christian and Wolf, Felix},
      title        = {{H}ow {M}any {T}hreads will be too {M}any? {O}n the
                      {S}calability of {O}pen{MP} {I}mplementations},
      volume       = {9233},
      address      = {Berlin, Heidelberg},
      publisher    = {Springer Berlin Heidelberg},
      reportid     = {FZJ-2016-00659},
      isbn         = {978-3-662-48095-3 (print)},
      series       = {Lecture Notes in Computer Science},
      pages        = {451 - 463},
      year         = {2015},
      comment      = {Euro-Par 2015: Parallel Processing / Träff, Jesper Larsson
                      (Editor)},
      booktitle     = {Euro-Par 2015: Parallel Processing /
                       Träff, Jesper Larsson (Editor)},
      abstract     = {Exascale systems will exhibit much higher degrees of
                      parallelism both in terms of the number of nodes and the
                      number of cores per node. OpenMP is a widely used standard
                      for exploiting parallelism on the level of individual nodes.
                      Although successfully used on today’s systems, it is
                      unclear how well OpenMP implementations will scale to much
                      higher numbers of threads. In this work, we apply automated
                      performance modeling to examine the scalability of OpenMP
                      constructs across different compilers and platforms. We ran
                      tests on Intel Xeon multi-board, Intel Xeon Phi, and Blue
                      Gene with compilers from GNU, IBM, Intel, and PGI. The
                      resulting models reveal a number of scalability issues in
                      implementations of OpenMP constructs and show unexpected
                      differences between compilers.},
      month         = {Aug},
      date          = {2015-08-24},
      organization  = {21st International Conference on
                       Parallel and Distributed Computing,
                       Vienna (Austria), 24 Aug 2015 - 28 Aug
                       2015},
      cin          = {JSC},
      ddc          = {004},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {511 - Computational Science and Mathematical Methods
                      (POF3-511) / ATMLPP - ATML Parallel Performance (ATMLPP)},
      pid          = {G:(DE-HGF)POF3-511 / G:(DE-Juel-1)ATMLPP},
      typ          = {PUB:(DE-HGF)8},
      UT           = {WOS:000363786800035},
      doi          = {10.1007/978-3-662-48096-0_35},
      url          = {https://juser.fz-juelich.de/record/280948},
}