% 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{Hoppe:1019997,
      author       = {Hoppe, Fabian and Comito, Claudia and Götz, Markus and
                      Gutiérrez Hermosillo Murieda, Juan Pedro and Hagemeier,
                      Björn and Knechtges, Philipp and Krajsek, Kai and
                      Rüttgers, Alexander and Streit, Achim and Tarnawa, Michael},
      title        = {{T}he {H}elmholtz {A}nalytics {T}oolkit ({H}eat) and its
                      role in the landscape of massively-parallel scientific
                      {P}ython},
      reportid     = {FZJ-2023-05812},
      year         = {2023},
      abstract     = {When it comes to enhancing exploitation of massive data,
                      machine learning methods are at the forefront of
                      researchers’ awareness. Much less so is the need for, and
                      the complexity of, applying these techniques efficiently
                      across large-scale, memory-distributed data volumes. In
                      fact, these aspects typical for the handling of massive data
                      sets pose major challenges to the vast majority of research
                      communities, in particular to those without a background in
                      high-performance computing. Often, the standard approach
                      involves breaking up and analyzing data in smaller chunks;
                      this can be inefficient and prone to errors, and sometimes
                      it might be inappropriate at all because the context of the
                      overall data set can get lost.The Helmholtz Analytics
                      Toolkit (Heat) library offers a solution to this problem by
                      providing memory-distributed and hardware-accelerated array
                      manipulation, data analytics, and machine learning
                      algorithms in Python. The main objective is to make
                      memory-intensive data analysis possible across various
                      fields of research ---in particular for domain scientists
                      being non-experts in traditional high-performance computing
                      who nevertheless need to tackle data analytics problems
                      going beyond the capabilities of a single workstation. The
                      development of this interdisciplinary, general-purpose, and
                      open-source scientific Python library started in 2018 and is
                      based on collaboration of three institutions (German
                      Aerospace Center DLR, Forschungszentrum Jülich FZJ,
                      Karlsruhe Institute of Technology KIT) of the Helmholtz
                      Association. The pillars of its development are... ...to
                      enable memory distribution of n-dimensional arrays, to adopt
                      PyTorch as process-local compute engine (hence supporting
                      GPU-acceleration), to provide memory-distributed (i.e.,
                      multi-node, multi-GPU) array operations and algorithms,
                      optimizing asynchronous MPI-communication (based on mpi4py)
                      under the hood, and to wrap functionalities in NumPy- or
                      scikit-learn-like API to achieve porting of existing
                      applications with minimal changes and to enable the usage by
                      non-experts in HPC.In this talk we will give an illustrative
                      overview on the current features and capabilities of our
                      library. Moreover, we will discuss its role in the existing
                      ecosystem of distributed computing in Python, and we will
                      address technical and operational challenges in further
                      development.},
      month         = {Aug},
      date          = {2023-08-14},
      organization  = {EuroSciPy, Basel (Switzerland), 14 Aug
                       2023 - 17 Aug 2023},
      subtyp        = {After Call},
      cin          = {JSC},
      cid          = {I:(DE-Juel1)JSC-20090406},
      pnm          = {5111 - Domain-Specific Simulation $\&$ Data Life Cycle Labs
                      (SDLs) and Research Groups (POF4-511) / 5112 - Cross-Domain
                      Algorithms, Tools, Methods Labs (ATMLs) and Research Groups
                      (POF4-511) / SLNS - SimLab Neuroscience (Helmholtz-SLNS)},
      pid          = {G:(DE-HGF)POF4-5111 / G:(DE-HGF)POF4-5112 /
                      G:(DE-Juel1)Helmholtz-SLNS},
      typ          = {PUB:(DE-HGF)6},
      url          = {https://juser.fz-juelich.de/record/1019997},
}