% 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”.

@MASTERSTHESIS{Haus:1033653,
      author       = {Haus, Katharina},
      title        = {{E}xtending a {P}erformance {A}nalysis {T}ool to {H}andle
                      {MPI} {M}essage {P}robing},
      school       = {FH Aachen - University of Applied Sciences},
      type         = {Bachelorarbeit},
      reportid     = {FZJ-2024-06525},
      pages        = {61 p.},
      year         = {2024},
      note         = {Bachelorarbeit, FH Aachen - University of Applied Sciences,
                      2024},
      abstract     = {In the realm of high-performance computing (HPC), exascale
                      systems have now reached a point of practical reality and
                      offer unprecedented computing power. As these systems become
                      more powerful, it is crucial to ensure that users can
                      effectively harness this power. It is essential to consider
                      scalability and performance optimization when developing
                      applications running on such systems to be able to fully
                      leverage their capabilities. Performance analysis is a
                      fundamental aspect of optimizing parallel applications. This
                      thesis addresses a specific gap in the Scalasca performance
                      analysis tool: MPI message probing. Message probing is
                      useful to determine the required buffer size for a pending
                      message. This work presents an extended event model that
                      captures probe calls and integrates them into Scalasca’s
                      analysis framework. The enhanced tool is evaluated across
                      various test cases, demonstrating its capability to identify
                      inefficiencies related to MPI message probing, especially
                      the Late Sender wait state. The results show that the
                      extended analysis provides a more comprehensive insight into
                      application behavior.},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5112 - Cross-Domain Algorithms, Tools, Methods Labs (ATMLs)
                      and Research Groups (POF4-511) / ATMLPP - ATML Parallel
                      Performance (ATMLPP)},
      pid          = {G:(DE-HGF)POF4-5112 / G:(DE-Juel-1)ATMLPP},
      typ          = {PUB:(DE-HGF)2},
      doi          = {10.34734/FZJ-2024-06525},
      url          = {https://juser.fz-juelich.de/record/1033653},
}