High-Performance Computing Center Stuttgart

  • Menu

Hackathon: Porting and Optimization for Hunter

Participation in English or German is possible.
Learn how to use and program HLRS's system Hunter.

The Hackathon consists of two parts

  • a preparation phase with a discussion of your project and goals for the hackathon, taking place November 20 (online),

  • the actual coding phase, where you will work towards the defined goal, see below, and port your code to Hunter, taking place December 1-5 (hybrid).

HLRS's next supercomputer system called “Hunter” is available. As for every new system, users have to spend some effort into porting their code and workflow to the new environment. Furthermore, the vast majority of Hunter’s compute power will be delivered by the GPU part of the APU, which requires users to adapt their hot loops in order to offload them to the GPUs. In this hackathon we will hence support our users in doing both. This hackathon focuses on scientific codes but also dedicates time to users running part or all of their workflows with AI.

In order to offload to GPUs, multiple programming models (HIP, OpenMP device offloading, PSTL/do concurrent) are available depending on the programming language used. If you are unfamiliar with them, we offer a recap of OpenMP target offloading in the course Introduction to OpenMP Offloading with AMD GPUs. In the preparation phase, pros and cons of those models based on your situation could be discussed if you are just starting porting, and you and the support staff will decide together which are suitable goals for the coding phase and how to proceed.

In the coding phase, you will work towards your defined goals supported by HLRS user support staff, HPE and AMD specialists. So, most probably you will be porting and optimizing your code for the new system, i.e. building with suitable compilers, using CPE's performance analysis tools to identify 'hot loops' and offloading them to the GPU will be the main tasks.

Due to the large number of groups using HLRS’ systems but limited support staff, the number of participants needs unfortunately to be limited. In order to use the system as efficiently as possible, we have to focus on groups holding medium and large compute time budgets. We hence reserve the right to select attendees!

To allow for easy attendance, we decided to provide this workshop in a hybrid fashion. Besides meeting in person at HLRS, we will also setup breakout rooms in a Zoom session, which enable remote participants to communicate as well as share screens and remote control applications with support staff, hence providing the same options of interaction as meeting in person.

Target audience: Groups holding a compute time budget to be used on Hunter.

Location

This hybrid event will take place online and at
HLRS, University of Stuttgart
Nobelstraße 19
70569 Stuttgart, Germany
Location and nearby accommodations

Start date

Dec 01, 2025
09:00

End date

Dec 05, 2025
17:00

Language

English

Entry level

Advanced

Course subject areas

Bootcamp/Hackathon

Hardware Accelerators

Performance Optimization & Debugging

Topics

Artificial Intelligence

Big Data

Code Optimization

GPU Programming

MPI

MPI+OpenMP

OpenMP

Back to list

Prerequisites and content levels

Prerequisites

To participate in the Hackathon, you should already have an account on Hawk/Hunter and make sure to be able to access Hunter from the place you plan to work, e.g. via VPN. Please check with your PI if you are unsure if VPN access is enabled for your account. See https://kb.hlrs.de/platforms/index.php/VPN for how to set up VPN.

  • Furthermore, kindly provide the following details by submitting an email to training(at)hlrs.de and CC to Björn Dick: dick(at)hlrs.de by the workshop registration deadline.
    • Scientific domain you are working in,
    • name of your code including URL (if available),
    • Numerical approaches (should not be the majority of the provided details),
    • name of the compute time budget used,
    • programming language,
    • programming models used (MPI, OpenMP, etc.),
    • list of dependencies/libraries,
    • known issues with specific compilers
    • information on porting efforts done so far
    • IO requirements (what is written to disk? with which frequency? number of files generated per each of those I/O events? volume of those files?)
    • Size of your test case in terms of number of Hawk nodes used as well as expected runtime.
  • Running AI codes also necessitates information about:
    • The user's AI software stack.
    • IO requirements (e.g., dataset size, number of files, model size, number of checkpoints)
    • The workflow along with computational requirements (e.g., number of GPUs needed for model training/fine-tuning and hyperparameter tuning).
  • Additionally, we require that you bring your own code including a test case which is set up according to the following rules:
  • use case selection:
    • When processing the test case, your code should have a behavior and profile which is as close as possible to that of current and future production runs.
    • If possible, the test case should be representative for those production runs of your group which consume the largest part of your compute time budget.
  • number of cores:
    • In order to be representative, the test case should be in size comparable to the respective current and future production runs.
    • In order to save valuable resources and to allow for a productive workflow, it should, however, be as small as possible.
    • So, please, be prepared to reduce the size of your test case during the workshop! This can often be achieved by reducing the simulated domain or resolution and keep the computational load per core constant ("weak down scaling").
  • wall time:
    • In order to allow for a productive workflow, the wall time should be a few minutes only.
    • At the same time, it should cover all important parts of the code, i.e. computation, communication and I/O.
    • So take into account to reduce the number of simulated time steps and be prepared to increase I/O frequency to render investigation of I/O possible within such a low number of timesteps.

If you are unsure about how to set up your test case, please contact Björn Dick (see contact data below).

In general the language of instruction is German, but can be changed to English if required.

Instructors

HLRS, HPE and AMD user support staff

Learning outcomes

  • Knowledge about and practical experience with deploying your code in CPE.
  • Overview of available programming models for AMD APUs and how to use them.
  • Important knowledge about how to optimize your code for the APU and which performance metrics are important.

Handout

If handouts will be available, participants will get them as PDFs.

Hybrid course

This course will be hybrid, i.e. it will take place at HLRS on-site, but it will also be possible to attend remotely. Participants, remote as well as on-site, have to be aware and agree that they might appear in the live video stream taken by a camera in the back of the lecture room or by a webcam on laptops. The live stream will not be saved. We strongly recommend to attend this course on-site since on-site attendance is much more effective and efficient in our experience. Therefore we might give priority to on-site over remote participants during registration.

Dates

The Hackathon consists of two parts

  • a preparation phase with a discussion of your project and goals for the hackathon, taking place November 20,

  • the actual coding phase, where you will work towards your goal and optimize your code for Hunter, taking place December 1-5.

The first phase will be a virtual event. The second phase will be offered as a hybrid event. Please select for the hybrid event on which days you plan to be on-site at HLRS.

We expect you to participate in both phases, in the first at least to discuss your project and goals.

If you need a recap on APUs, OpenMP target offload, or AMD tools, attending the course Introduction to OpenMP Offloading with AMD GPUs would be an option. For subscribers of the HLRS training news, self-study materials are also available.

 

Agenda

- preliminary -

Local times: Central European Time Zone (Berlin).
Communication format: Face-to-face, via Slack, Zoom, and email.

Preparation Phase

November 20, 9-17 h
  • Tutor assignment
  • Development of agenda for your code
  • Develop to-dos (Compile & Profile)
  • Set up of test case toghether with tutors
  • Agree on checkpoints with tutors until the hackathon starts

Coding Phase

December 1-5, 8:45-9:00Local registration/drop in to Zoom
December 1-5, 9:00-17:30 (17:00 on Friday)Working on your code and workflow together with HLRS/HPE/AMD support staff

Registration information

Register via the button at the top of this page (will be available soon).

Please submit information about your code, see section Prerequisites and content levels, as soon as you applied for the workshop via email to training@hlrs.de. You can book individual days according to your and your project's needs, attending a full workshop in this case is not necessary.

Please apply before November 19, 2025.

Fees

  • Students without master’s degree or equivalent at a German university: 0 Euro
  • PhD students or employees at a German university or public research institute: 0 Euro

Further fee categories can be found in the registration page.

Our course fees include coffee breaks (in classroom courses only).

Contact

Björn Dick phone 0711 - 685 87189, bjoern.dick(at)hlrs.de
Tobias Haas phone 0711 685 87223, training(at)hlrs.de

HLRS Training Collaborations in HPC

HLRS is part of the Gauss Centre for Supercomputing (GCS), together with JSC in Jülich and LRZ in Garching near Munich. EuroCC@GCS is the German National Competence Centre (NCC) for High-Performance Computing. HLRS is also a member of the Baden-Württemberg initiative bwHPC.

Further courses

See the training overview and the Supercomputing Academy pages.

Related training
All training
BOOTCAMP: AI profiling

July 09 - 10, 2025

Online

Introduction to SYCL2020

August 18 - September 26, 2025

Online (flexible)

Six-day course in parallel programming with MPI/OpenMP

August 20 - 29, 2025

Online by ETH

Supercomputing Academy: Data Analysis with HPC

September 01 - October 10, 2025

Online (flexible)

Parallel Programming Workshop (Train the Trainer)

October 13 - 17, 2025

Stuttgart, Germany

Parallel Programming Workshop (MPI, OpenMP and Advanced Topics)

October 13 - 17, 2025

Stuttgart, Germany

Introduction to OpenMP Offloading with AMD GPUs

October 21 - 22, 2025

Online

Multi-GPU Deep Learning

October 28 - 31, 2025

Stuttgart, Germany

Supercomputing Academy: Parallel Programming with MPI

November 03 - December 05, 2025

Online (flexible)

GPU Programming using CUDA

November 11 - 20, 2025

Online

Advanced Parallel Programming with MPI and OpenMP

December 01 - 04, 2025

Online by JSC

Back to list

High-Performance Computing Center Stuttgart Nobelstraße 19, 70569 Stuttgart, Germany

Contact & Location

+49 711 685-87269 info(at)hlrs.de

A member of the Gauss Centre for Supercomputing, HLRS is one of three German national centers for high-performance computing.

www.gauss-centre.eu

HLRS is a central unit of the University of Stuttgart.

www.uni-stuttgart.de/en/

© 2025 HLRS. All rights reserved.