HPC for Researchers

[orbitfold]

Please note, this tutorial has been merged with #2 Accelerating massive data processing in Python with Heat, i.e., both will handled in one full-day tutorial.

Title

HPC for Researchers

Responsible person(s)

Dr. Vytautas Jančauskas (vytautas.jancauskas@dlr.de, DLR), Dr. Daniela Espinoza Molina (Daniela.EspinozaMolina@dlr.de, DLR), Antony Zappacosta (antony.zappacosta@dlr.de, DLR), Roman Zitlau (roman.zitlau@dlr.de, DLR)

Format

Hands-on session/Tutorial

Timeframe

Full day

Description

An introduction to HPC for reasearchers using Python. We will be using the HAICORE platform as an example. The "Helmholtz AI computing resources" (HAICORE) provide easy and low-barrier GPU access to the entire AI community within the Helmholtz Association. In this tutorial you will learn to:

• Gain access to the platform, set up 2FA and log-in.
• Understand basic HPC concepts (distributed computing, etc.)
• Set up your own software environment using conda.
• Request and use GPU and CPU resources through SLURM.
• Set up and use Dask to distribute your data science workflows.
• Accelerate your software with Numba.
• Write custom CUDA kernels in Python.

Requirements

Laptop, SSH client, text editor, Python skills
We can realistically handle around 25 participants at most

Data

https://syncandshare.desy.de/index.php/s/W8yyiWJN5ZpWGPg
https://syncandshare.desy.de/index.php/s/YdRT4e5XX4Loz3Z

[SusanneWenzel]

@orbitfold thank you for this contribution! Can you add your affiliations please

[SusanneWenzel]

@orbitfold reminder to add you affiliation and contact information

[orbitfold]

Hi @SusanneWenzel, updated, sorry for the delay

[SusanneWenzel]

@orbitfold @mrfh92 Do you have a schedule or any other information I should put on the website?

[mrfh92]

@SusanneWenzel see #2