%0 Conference Paper
%A Fabian, Hoppe
%A Gutiérrez Hermosillo Muriedas, J. P.
%A Tarnawa, Michael
%A Philipp, Knechtges
%A Hagemeier, Björn
%A Krajsek, Kai
%A Alexander, Rüttgers
%A Markus, Götz
%A Comito, Claudia
%T Engineering a large-scale data analytics and array computing library for research: Heat
%I Electronic Communications of the EASST
%M FZJ-2025-03345
%P 1-26
%D 2025
%< Electronic Communications of the EASST
%X Heat is a Python library for massively-parallel and GPU-accelerated arraycomputing and machine learning. It is developed by researchers for researchers,with the ultimate goal to make multi-dimensional array processing and machinelearning for scientists (almost) as easy on a supercomputer as it is on a workstationwith NumPy or scikit-learn. This paper highlights the relevance of this project to theresearch software engineering community by giving a short, but illustrative overviewof Heat and discusses its role in the context of related libraries with a specific focuson its research software aspects.
%B Fourth Conference on Research Software Engineering in Germany, deRSE24
%C 5 Mar 2024 - 7 Mar 2024, Würzburg (Germany)
Y2 5 Mar 2024 - 7 Mar 2024
M2 Würzburg, Germany
%K Multi-dimensional Arrays (Other)
%K Machine learning (Other)
%K Data Science (Other)
%K Data analytics (Other)
%K High-Performance Computing (Other)
%K Parallel Computing (Other)
%K GPUs (Other)
%K Big Data (Other)
%K Research Software (Other)
%F PUB:(DE-HGF)8 ; PUB:(DE-HGF)7
%9 Contribution to a conference proceedingsContribution to a book
%R 10.14279/eceasst.v83.2626
%U https://juser.fz-juelich.de/record/1044789