% 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{Comito:1019996,
      author       = {Comito, Claudia and Hoppe, Fabian and Götz, Markus and
                      Gutiérrez Hermosillo Muriedas, Juan Pedro and Hagemeier,
                      Björn and Knechtges, Philipp and Krajsek, Kai and
                      Rüttgers, Alexander and Streit, Achim and Tarnawa, Michael},
      title        = {{H}eat: accelerating massive data processing in {P}ython},
      reportid     = {FZJ-2023-05811},
      year         = {2023},
      abstract     = {Manipulating and processing massive data sets is
                      challenging. In astrophysics as in the vast majority of
                      research communities, the standard approach involves
                      breaking up and analyzing data in smaller chunks, a process
                      that is both inefficient and prone to errors. The problem is
                      exacerbated on GPUs, because of the smaller available
                      memory.Popular solutions to distribute NumPy/SciPy
                      computations are based on task parallelism, introducing
                      significant runtime overhead, complicating implementation,
                      and often limiting GPU support to one vendor.This poster
                      illustrates an alternative based on data parallelism
                      instead. The open-source library Heat [1, 2] builds on
                      PyTorch and mpi4py to simplify porting of NumPy/SciPy-based
                      code to GPU (CUDA, ROCm, including multi-GPU, multi-node
                      clusters). Under the hood, Heat distributes massive
                      memory-intensive operations over multi-node resources via
                      MPI communication. From a user's perspective, Heat can be
                      used seamlessly in the Python array ecosystem. Supported
                      features:- distributed (multi-GPU) I/O from shared memory-
                      easy distribution of memory-intensive operations in existing
                      code (e.g. matrix multiplication)- interoperability within
                      the Python array ecosystem: Heat as a backend for your
                      massive array manipulations, statistics, signal processing,
                      machine learning...- transparent parallelism: prototype on
                      your laptop, run the same code on HPC cluster.I'll also
                      touch upon Heat's current implementation roadmap, and
                      possible paths to collaboration.[1]
                      https://github.com/helmholtz-analytics/heat[2] M. Götz et
                      al., "HeAT – a Distributed and GPU-accelerated Tensor
                      Framework for Data Analytics," 2020 IEEE International
                      Conference on Big Data (Big Data), Atlanta, GA, USA, 2020,
                      pp. 276-287, doi: 10.1109/BigData50022.2020.9378050.},
      month         = {Nov},
      date          = {2023-11-29},
      organization  = {CS $\&$ Physics Meet-Up by Lamarr $\&$
                       B3D, TU Dortmund (Germany), 29 Nov 2023
                       - 1 Dec 2023},
      subtyp        = {Outreach},
      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)24},
      url          = {https://juser.fz-juelich.de/record/1019996},
}