% 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{Geimer:151320,
      author       = {Geimer, Markus and Shende, Sameer and Wesarg, Bert and
                      Wylie, Brian J. N.},
      title        = {{H}ands-on {P}ractical {H}ybrid {P}arallel {A}pplication
                      {P}erformance {E}ngineering},
      reportid     = {FZJ-2014-01299},
      year         = {2013},
      abstract     = {This tutorial presents state-of-the-art performance tools
                      for leading-edge HPC systems founded on the Score-P
                      community instrumentation and measurement infrastructure,
                      demonstrating how they can be used for performance
                      engineering of effective scientific applications based on
                      standard MPI, OpenMP, hybrid MPI+OpenMP, and increasingly
                      common usage of accelerators. Parallel performance
                      evaluation tools from the VI-HPS (Virtual Institute High
                      Productivity Supercomputing) are introduced and featured in
                      hands-on exercises with Scalasca, Vampir and TAU. We present
                      the complete workflow of performance engineering, including
                      instrumentation, measurement (profiling and tracing, timing
                      and PAPI hardware counters), data storage, analysis, and
                      visualization. Emphasis is placed on how tools are used in
                      combination for identifying performance problems and
                      investigating optimization alternatives. Using their own
                      notebook computers with a provided Linux Live-ISO image
                      containing the tools (booted from DVD/USB or within a
                      virtual machine) will help to prepare participants to locate
                      and diagnose performance bottlenecks in their own parallel
                      programs.},
      month         = {Nov},
      date          = {2013-11-17},
      organization  = {25th International Conference for High
                       Performance Computing, Networking,
                       Storage and Analysis, Denver (USA), 17
                       Nov 2013 - 22 Nov 2013},
      subtyp        = {After Call},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {411 - Computational Science and Mathematical Methods
                      (POF2-411) / ATMLPP - ATML Parallel Performance (ATMLPP)},
      pid          = {G:(DE-HGF)POF2-411 / G:(DE-Juel-1)ATMLPP},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/151320},
}