% 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:1019998,
      author       = {Hoppe, Fabian and Comito, Claudia and Gutiérrez Hermosillo
                      Muriedas, Juan Pedro and Götz, Markus and Hagemeier, Björn
                      and Knechtges, Philipp and Krajsek, Kai and Rüttgers,
                      Alexander and Streit, Achim and Tarnawa, Michael},
      title        = {{S}caling data-intensive analytics with {H}eat: a {P}ython
                      library for massively-parallel array computing and machine
                      learning},
      reportid     = {FZJ-2023-05813},
      year         = {2023},
      abstract     = {Manipulating and processing massive data sets is
                      challenging. For the vast majority of research communities,
                      those without a background in high-performance computing,
                      the standard approach involves breaking up and analyzing
                      data in smaller chunks, an inefficient and very
                      prone-to-errors process.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. Developed in collaboration by three
                      institutions of the Helmholtz Association (KIT, FZJ, DLR),
                      Heat: enables memory distribution of n-dimensional arrays,
                      adopts PyTorch as process-local compute engine (hence
                      supporting GPU-acceleration), provides memory-distributed
                      (i.e., multi-node, multi-GPU) array operations and
                      algorithms, optimizing asynchronous MPI-communication under
                      the hood, and wraps functionalities in NumPy- or
                      scikit-learn-like API to achieve porting of existing
                      applications with minimal changes.In this presentation, we
                      will provide an overview of the Heat library's features and
                      capabilities and discuss its role in the ecosystem of
                      distributed array computing and machine learning in Python.
                      Additionally, we will highlight Heat's role as a platform
                      for cross-discipline collaboration in data-intensive
                      research, and address technical and operational challenges
                      in Heat development.},
      month         = {Jun},
      date          = {2023-06-12},
      organization  = {Helmholtz AI Conference, Hamburg
                       (Germany), 12 Jun 2023 - 14 Jun 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/1019998},
}