% 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”.

@MISC{Corbin:1008814,
      author       = {Corbin, Gregor and Shende and Williams, William},
      title        = {{H}ands-on {P}ractical {H}ybrid {P}arallel {A}pplication
                      {P}erformance {E}ngineering},
      reportid     = {FZJ-2023-02486},
      year         = {2023},
      abstract     = {This tutorial presents state-of-the-art performance tools
                      for leading-edge HPC systems founded on the
                      community-developed Score-P instrumentation and measurement
                      infrastructure, demonstrating how they can be used for
                      performance engineering of effective scientific applications
                      based on standard MPI, OpenMP, hybrid combination of both,
                      and increasingly common usage of accelerators. Parallel
                      performance tools from the Virtual Institute – High
                      Productivity Supercomputing (VI-HPS) are introduced and
                      featured in hands-on exercises with Score-P, 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, tuning, 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, participants will conduct exercises on a
                      contemporary HPC system where remote access will be provided
                      for the hands-on sessions through AWS running an E4S
                      [http://e4s.io] image containing all of the necessary tools.
                      This will help to prepare participants to locate and
                      diagnose performance bottlenecks in their own parallel
                      programs.},
      month         = {May},
      date          = {2023-05-21},
      organization  = {ISC High Performance '23, Hamburg
                       (Germany), 21 May 2023 - 21 May 2023},
      subtyp        = {After Call},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / EUPEX - EUROPEAN PILOT FOR
                      EXASCALE (101033975) / ATMLPP - ATML Parallel Performance
                      (ATMLPP)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(EU-Grant)101033975 /
                      G:(DE-Juel-1)ATMLPP},
      typ          = {PUB:(DE-HGF)17},
      url          = {https://juser.fz-juelich.de/record/1008814},
}