Introduction to Scalable Deep Learning (PRACE-Trainingskurs, online)

14.03.2022 08:00 Uhr
18.03.2022 12:00 Uhr

(Kurs-Nr. 16520221 im Trainingsprogramm 2022 des Forschungszentrums Jülich)

Der Kurs findet als Online-Veranstaltung statt. Der Link zur Online-Plattform wird nur den akzeptierten Teilnehmer:innen bekannt gegeben.



In this course, we will cover machine learning and deep learning and how to achieve scaling to high performance computing systems. The course aims at covering all levels, from fundamental software design to specific compute environments and toolkits. We want to enable the participants to unlock the resource of machines like the JUWELS booster for their machine learning workflows. Different from previous years we assume that the participants have a background from a university level introductory course to machine learning. Suggested options for self-teaching are given below.

We will start the course with a presentation of high performance computing system architectures and the design paradigms for HPC software. In the tutorial, we familiarize the users with the environment. Furthermore, we give a recap of important machine learning concepts and algorithms and the participants will train and test a reference model. Afterwards, we introduce how deep learning algorithms can be parallelized for supercomputer usage with Horovod. Furthermore, we discuss best practicies and pitfalls in adopting deep learning algorithms on supercomputers and learn to test their function and performance. Finally we apply the gained expertise to large scale unsupervised learning, with a particular focus on Generative Adversarial Networks (GANs).

This course is a PRACE training course.


We assume that the participants are familiar with general concepts of machine learning and/or deep learning, such as widely used models, losses, regularization and basic model training / testing. Many excellent self-training resources are available such as:

Hands-on experience with ML/DL framework is required, first experience with HPC systems is helpful.


Wissenschaftler:innen, die Supercomputer für ML/DL-Workflows einsetzen wollen.


Nach diesem Kurs werden die Teilnehmer:innen in der Lage sein, Tensorflow- und Pytorch ML-Workflows auf HPC-Maschinen zu parallelisieren, wobei die HPC-Systemarchitektur berücksichtigt und typische Fallstricke und Engpässe umgangen werden.


Der Kurs wird auf Englisch gehalten.


5 halbe Tage


14. - 18. März 2022, 9.30 - 13.00 Uhr




maximal 40


Dr. Stefan Kesselheim, Dr. Jenia Jitsev, Roshni Kamath, Dr. Mehdi Cherti, Dr. Alexandre Strube, Jan Ebert, JSC


Dr. Stefan Kesselheim

Head of SDL Applied Machine Learning & AI Consultant team

  • Institute for Advanced Simulation (IAS)
  • Jülich Supercomputing Centre (JSC)
Gebäude 14.14 /
Raum 3023
+49 2461/61-85927
Letzte Änderung: 08.07.2022