This event has concluded.
Date: 24 – 25 January 2024
Venue: Online
Participation: Limited to 40 participants from EuroHPC Joint Undertaking members (+ an additional seat for a member from each LUMI consortium country, NCC or Local Organization in order to strengthen supporting local users in each country).
Registration fee: free
Registration deadline: Wednesday 20th December 2023
This course gives practical tips on how to run GROMACS simulations efficiently on LUMI-G, i.e. on AMD GPUs. The participants will learn how to assess and tune GROMACS performance. In addition the course provides an overview on LUMI architecture, GROMACS heterogeneous parallelization, with a special attention to AMD GPU. The event is organized by BioExcel in collaboration with CSC and PDC
IMPORTANT: Before registering please read the following information carefully;
Target Participants
These sessions are aimed at GROMACS users, specifically interested in running efficient GROMACS simulation on LUMI-G and understanding how to tune and to assess GROMACS performance. After the course the participants should have the skills and knowledge needed to efficiently use GPU resources in GROMACS simulations and tune and assess GROMACS performance.
Prerequisites
Participants are required to;
- be familiar with molecular dynamics simulation and have working knowledge of GROMACS. Note: The fundamentals of molecular dynamics simulation or basic usage of GROMACS are not covered in this course.
- have experience in basic Linux/Unix skills, understand basic batch scripts and hands-on experience in using HPC systems. Ability to use the command line: navigate files and directories through shell commands, create/move/delete files and directories, construct command pipelines, edit/run shell scripts, use basic Slurm commands, submit job in a queue, find further help about the scheduler.
- have awareness of differences between hardware components (i.e. GPU vs CPU, memory and storage) Please consult the following materials, if you’re uncertain of your Linux or GROMACS skills:
- Lectures on the basis of molecular dynamics simulation (videolinks: part I, part II)
- MD with GROMACS tutorials (link)
- Linux commands, bash shell, a quiz and a link to intro course
- Introduction to HPC system (link)
Topics
- LUMI architecture
- GROMACS heterogeneous parallelization
- AMD GPU support in GROMACS
- Assessing and tuning performance of GROMACS simulations
The training includes two online sessions and participants are expected to attend both of them:
- Wednesday 24th January 2024 from 9:30 to 14:30 CET
- Thursday 25th January 2024 from 9:30 to 14:30 CET
Each session consists of lectures and hands-on exercises. GROMACS will be used in the exercise sessions. LUMI supercomputer will be used for the hands-on exercises. You need to apply for a user account, but we’ll provide the project and resources.
To register you will need to provide the following brief information:
- Your name and affiliation
- How you meet the prerequisites for the course
- What is your motivation to participate in the course
- If you already have a project or user account on LUMI
Prerequisites
Participants will be selected to maximise benefit by evaluating the match between content, motivation and current skills. Moreover geographical coverage and gender balance will be considered, but participation is limited to researchers affiliated to EuroHPC JU member states
The complete materials including lectures, hands-on instructions and Q&A session collaborative document are available via DOI:10.5281/zenodo.10556522 .
- Workshop Introduction
- LUMI architecture
- Brief intro to GROMACS
- GROMACS parallelization and algorithms background
- AMD GPU support in GROMACS
- How to run on LUMI
- Hands-on: experiment to find optimal run parameters using up to three model systems
Thursday 25th January, 9:30 – 15:15 CET
- Assessing and tuning performance of GROMACS simulations
- Hands-on on continues, you can also bring your own systems
- Overview and discussion on attendees results
Lecturers & Trainers
- Szilárd Páll (KTH, Royal Institute of Technology)
- Andrey Alekseenko (KTH, Royal Institute of Technology)
- Rasmus Kronberg (CSC)
- Alessandra Villa (KTH, Royal Institute of Technology)
- Cathrine Bergh (KTH, Royal Institute of Technology)
- Atte Sillanpää (CSC)
- Xavier Anthony Raj (CSC)