Skip to content

On-Site HPC Trainings and Tutorials

We propose periodical on-site events for our users. They are free of charge and can be attended by anyone from the University of Luxembourg faculties and interdisciplinary centers. Additionally, we also accept users from LIST, LISER and LIH. If you are part of another public research center, please contact us.

Forthcoming Events

HPC School for Beginners

This event aims to equip you with essential skills and knowledge to embark on your High-Performance Computing journey. The event is organized each trimester and is composed of six half day sessions.

Limited spots available per session (usually 30 max). Priority to University's staff. Eligible for ECTS with the doctoral school.

Upcoming Sessions

Sessions planned in March, June, September and November 2026.

March session

  • Monday March 9th, 8:30am to 12:30pm
  • Tuesday March 10th, 8:30am to 12:30pm
  • Monday March 16th, 8:30am to 12:30pm
  • Tuesday March 17th, 8:30am to 12:30pm
  • Monday March 23rd, 8:30am to 12:30pm
  • Tuesday March 24th, 8:30am to 12:30pm

Location: Belval Campus, TBA

Prerequisites

  • No specific knowledge required
  • Bring your own computer (Linux, macOS, and Windows are welcome)
  • An active HPC account. You can request one here.

Session 1 - Accessing the Cluster and Command Line Introduction

Learn how to:

  • Access the HPC cluster and set up your machine
  • Use the command line interface effectively (manage your files, run software, ...). Gain confidence in interacting with the cluster environment.
  • Transfer data to and from the cluster

Session 2 - HPC Basics: Job Submission and Monitoring

Learn:

  • The inner workings of the university HPC clusters
  • How to submit and manage computational tasks.
  • How to monitor and optimize job performance.

Session 3 - Working with Software Environments and Containers

Learn how to:

  • Set up isolated software environments
  • Create and use containers in the HPC systems

Session 4 - Advanced Job Submission

  • Understand the allocation of resources in HPC systems
  • Optimize your job submission workflow
  • Configure your code to access cores, memory channels, and GPUs efficiently and prevent over-subscription.

Session 5 - Optimizing Storage Access

Learn about:

  • The different storage tiers and their characteristics
  • Using parallel file systems effectively
  • Optimizing storage access patterns

Session 6 - Reproducibility

Learn how to:

  • Improve the reproducibility of your workflows by creating reproducible setups
  • Manage your dependencies
  • Version, store, and share your workflows and code

Resources

Machine Learning for Beginners

This two-days course introduces participants to Machine Learning (ML) and Deep Learning (DL) on HPC. During the course, we will cover the fundamentals of ML and DL, work through practical exercises on model training, and explore how to speed up computations using HPC resources, distributed computing, and GPU acceleration. The course combines theory, coding exercises, and HPC applications to give participants both a solid foundation and practical skills.

Limited spots available per session (20 max).

Upcoming Sessions

No sessions are planned at the moment. Future sessions will be announced here, please wait for announcements or contact the HPC team via email to express your interest.

Training Outcomes

By the end of the course, participants will:

  • Understand key ML and DL concepts and techniques;
  • Gain hands-on experience with data preprocessing, model training, and evaluation;
  • Learn how to use HPC resources for accelerated ML workloads;
  • Explore distributed computing and GPU acceleration tools;

Course Structure

Day 1 - ML Foundations

  • Introduction to ML - AI & ML, types of ML, key concepts;
  • Exploratory Data Analysis (EDA) in Jupyter Notebook - Loading, preprocessing, and visualizing;
  • Supervised Learning - Regression vs. Classification, model evaluation, hands-on exercises;
  • Introduction to Neural Networks.

Day 2 - DL & HPC Acceleration

  • DL & CNNs - Building and training DL models;
  • Distributed computing on HPC;
  • Accelerated ML & DL.

Requirements

  • Having an HPC account to access the cluster.
  • Basic knowledge of SLURM (Beginners HPC School).
  • A basic understanding of Python programming.
  • Familiarity with Jupyter Notebook (installed and configured).
  • A basic understanding of NumPy and linear algebra.

Python HPC School

In this workshop, we will explore the process of improving Python code for efficient execution. Chances are, you 're already familiar with Python and Numpy. However, we will start by mastering profiling and efficient NumPy usage as these are crucial steps before venturing into parallelization. Once your code is fine-tuned with Numpy we will explore the utilization of Python's parallel libraries to unlock the potential of using multiple CPU cores. By the end, you will be well equipped to harness Python's potential for high-performance tasks on the HPC infrastructure.

Target Audience Description

The workshop is designed for individuals who are interested in advancing their skills and knowledge in Python-based scientific and data computing. The ideal participants would typically possess basic to intermediate Python and Numpy skills, along with some familiarity with parallel programming. This workshop will give a good starting point to leverage the usage of the HPC computing power to speed up your Python programs.

Upcoming Sessions

No sessions are planned at the moment. Future sessions will be announced here, please wait for announcements or contact the HPC team via email to express your interest.

First Day – Jupyter Notebook on ULHPC / Profiling Efficient Usage of NumPy

Program

  • Setting up a Jupyter Notebook on an HPC node - 10am to 11am
  • Taking time and profiling Python code - 11am to 12pm
  • Lunch break - 12pm to 2pm
  • NumPy basics for replacing Python loops for efficient computations - 2pm to 4pm

Requirements

  • Having an HPC account to access the cluster.
  • Basic knowledge on SLURM (beginners HPC school).
  • A basic understanding of Python programming.
  • Familiarity with Jupyter Notebook (installed and configured).
  • A basic understanding of Numpy and linear algebra.

Second Day – Improving Performance with Python Parallel Packages

Program

  • Use case understanding and Python implementation - 10am to 10:30am
  • NumPy implementation - 10:30am to 11am
  • Python’s Multiprocessing - 11am to 12pm
  • Lunch break - 12pm to 2pm
  • PyMP - 2pm to 2:30pm
  • Cython - 2:30pm to 3pm
  • Numba and final remarks - 3pm to 4pm

Requirements

  • Having an HPC account to access the cluster.
  • Basic knowledge of SLURM (Beginners HPC School).
  • A basic understanding of Python programming.
  • Familiarity with Jupyter Notebook (installed and configured).
  • A basic understanding of NumPy and linear algebra.
  • Familiarity with parallel programming.