Engineering a large-scale data analytics and array computing library for research: Heat

Authors

  • Fabian Hoppe Deutsches Zentrum für Luft- und Raumfahrt DLR
  • Juan Pedro Gutiérrez Hermosillo Muriedas Karlsruhe Institute for Technology (KIT), Scientific Computing Center (SCC), Karlsruhe (Germany)
  • Michael Tarnawa Forschungszentrum Jülich GmbH (FZJ), Jülich Supercomputing Centre (JSC), Jülich (Germany)
  • Philipp Knechtges German Aerospace Center (DLR), Institute of Software Technology, High-Performance Computing Department, Cologne (Germany)
  • Björn Hagemeier Forschungszentrum Jülich GmbH (FZJ), Jülich Supercomputing Centre (JSC), Jülich (Germany)
  • Kai Krajsek Forschungszentrum Jülich GmbH (FZJ), Jülich Supercomputing Centre (JSC), Jülich (Germany)
  • Alexander Rüttgers German Aerospace Center (DLR), Institute of Software Technology, High-Performance Computing Department, Cologne (Germany)
  • Markus Götz Karlsruhe Institute for Technology (KIT), Scientific Computing Center (SCC), Karlsruhe (Germany)
  • Claudia Comito Forschungszentrum Jülich GmbH (FZJ), Jülich Supercomputing Centre (JSC), Jülich (Germany)

DOI:

https://doi.org/10.14279/eceasst.v83.2626

Keywords:

Multi-dimensional Arrays, Machine learning, Data Science, Data analytics, High-Performance Computing, Parallel Computing, GPUs, Big Data, Research Software

Abstract

Heat is a Python library for massively-parallel and GPU-accelerated array computing and machine learning. It is developed by researchers for researchers, with the ultimate goal to make multi-dimensional array processing and machine learning for scientists (almost) as easy on a supercomputer as it is on a workstation with NumPy or scikit-learn. This paper highlights the relevance of this project to the research software engineering community by giving a short, but illustrative overview of Heat and discusses its role in the context of related libraries with a specific focus on its research software aspects.

Downloads

Published

2025-02-21

How to Cite

[1]
F. Hoppe, “Engineering a large-scale data analytics and array computing library for research: Heat”, ECEASST, vol. 83, Feb. 2025.