Uncategorized

MultiXscale CoE is pleased to invite you to an upcoming webinar introducing two major platforms designed to support the computational materials science community: Lhumos, the new e-learning platform designed to support domain specific training in high-performance computing (HPC) and quantum and classical simulations of matter, and the recently upgraded Materials Cloud Archive repository. Lhumos (Learning HUb for MOdeling and Simulation) offers a wide range of training resources tailored to the materials science community and beyond. The portal provides access to video lectures, tutorials and exercises, practical codes and examples, recorded seminars, materials on electronic structure calculations, molecular dynamics, code optimization, and more. Supported by MaX, CECAM, MARVEL, MultiXscale, BioNT, E-CAM, and DOME 4.0, Lhumos is a collaborative initiative to promote capacity building and knowledge sharing in academia and industry. In the same session, we will also introduce the upgraded version of Materials Cloud Archive, supporting FAIR data sharing in computational materials science. This new version, fully redesigned and officially launched on June 23, 2025, is built on top of InvenioRDM, a robust data management framework developed at CERN. Learn about the new features of the redesigned Materials Cloud Archive, how to create and submit records, the publication process, and how the platform ensures long-term accessibility of data. Webinar Agenda: 4:00 PM CEST – Welcome Remarks 4:05 PM CEST – Live Showcase of the Lhumos Platform / Roberto Bendinelli (MARVEL – CECAM – MaX– BioNT) 4:25 PM CEST – The Upgraded Materials Cloud Archive / Valeria Granata (MARVEL – THEOS/EPFL – PSI) 4:45 PM CEST – Q&A Session *🔗**Join the webinar: here *🌐**Explore the platforms: *https://lhumos.org *https://archive.materialscloud.org

The tutorial given by Valentin Völkl (CERN) on 4th June 2025, in the framework of the event HPC Knowledge Portal annual meeting – HPCKP25 Barcelona, is already available on the website through this link. HPC Knowledge Portal annual meeting is a key global event for High-Performance Computing able to attract relevant professionals and main developers of leading software projects widely used by the HPC community. Abstract: What if you could avoid installing a broad range of scientific software from scratch on every supercomputer, cloud instance, or laptop you use or maintain. . . without compromising on performance? Installing scientific software is known to be a tedious and time-consuming task. The software stack continues to deepen as computational science expands rapidly, the diversity of system architectures increases, and interest in public cloud infrastructures is surging. Providing access to optimised software installations in a reliable, user-friendly, and reproducible way is a highly nontrivial task that affects application developers, HPC user support teams, and the users themselves. Although scientific research on supercomputers is fundamentally software-driven, setting upand managing a software stack remains challenging. Parallel filesystems like GPFS and Lustre are usually ill-suited for hosting software installations that involve a large number of small files, which can lead to slow software startup, and may even negatively impact overall system performance. While workarounds such as using container images are prevalent, they come with caveats, such as large image sizes, required compatibility with the system MPI, and issues with accessing GPUs. This tutorial aims to address these challenges by introducing CernVM-FS, a distributed read-only filesystem designed to efficiently stream software installations on-demand, and the European Environment for Scientific Software Installations (EESSI), a shared repository of optimised scientific software installations (not recipes) that can be used on a variety of systems, regardless of which flavor/version of Linux distribution or processor architecture is used, or whether it’s a full size HPC cluster, a cloud environment, or a personal workstation. The tutorial covers installing and configuring CernVM-FS, and the basic usage of EESSI.

The talk and PPT presentation given by MultiXscale experts Alan O’Cais (University of Barcelona and CECAM) and Helena Vela (Do IT Now) on 4th June 2025, in the framework of the event HPC Knowledge Portal annual meeting – HPCKP25 Barcelona, are already available on the website through this link. HPC Knowledge Portal annual meeting is a key global event for High-Performance Computing able to attract relevant professionals and main developers of leading software projects widely used by the HPC community. Abstract: Discover how EESSI (European Environment for Scientific Software Installation) is transforming the way scientific software is deployed and shared across HPC systems, cloud platforms, and even laptops. In this session, we’ll introduce the motivation behind EESSI, its architecture, and how you can start using a fully pre-built, modular software environment — no matter where you compute. We will also demonstrate deployment to a cloud instance and cloud-based Slurm clusters!

Our MultiXscale experts were proud to contribute to several key sessions at ISC High Performance Hamburg (Germany), organized from 10-13 June 2025. From cutting-edge discussions on scalable computing to deep dives into HPC applications, our team brought valuable insights to the table. Abstract: The MultiXScale CoE is an exascale-oriented application co-design and delivery for multiscale simulations. It is a collaborative project between members of the CECAM network and the EESSI community that will allow domain scientists to take advantage of the computational resources offered by EuroHPC JU. In this presentation we are going to focus on one of the lighthouse codes within MultiXScale, LAMMPS, which is used by a large number of computational scientists. We will discuss how the developers of new plugins for LAMMPS are testing on a wide range of systems with the help of the software.eessi.io and dev.eessi.io repositories. The dev.eessi.io repository allows developers to share pre-releases of their software so they can test it on systems where EESSI is available, this includes the EuroHPC systems Vega, Karolina and Deucalion. For example, on Vega, development codes of LAMMPS are already available for using and testing through dev.eessi.io. In this talk we will show all the CI infrastructure to provide pre-released versions of your software using the plugins under development in MultiXscale, with LAMMPS as an example.

MultiXscale CoE coordinator, Dr. Matej Praprotnik (National Institute of Chemistry) joined the PASC25 Interdisciplinary Dialogue. Watch the full video here. The Platform for Advanced Scientific Computing (PASC) Conference, co-sponsored by the Association for Computing Machinery (ACM) and the Swiss National Supercomputing Centre (CSCS), was held from 16 to 18 June 2025, at the FHNW Campus Brugg-Windisch, in Switzerland. The conference focused on exploring how supercomputing can be utilised to help address the 17 UN Sustainable Development Goals (SDGs), which underpin the 2030 Agenda for Sustainable Development, adopted by all UN member states in 2015. Examples of how supercomputing is already being used in this regard include its application to: The conference also placed an emphasis on best practices around reproducibility, and encourage participants to demonstrate that their results are reproducible.

EESSI, the European Environment for Scientific Software Installations that’s actively developed by MultiXscale partners, is being adopted as the main central software stack on MUSICA, the Multi-Site Computer Austria, the new national system in Austria. By relying on EESSI, the MUSICA support team is able to focus on site-specific aspects and use cases, rather than spending time on building out a central software stack from scratch. For more information, see https://docs.vsc.ac.at/systems/musica.html, https://docs.asc.ac.at/musica_test/ and https://asc.ac.at/news/2024/news-records/musica-enters-top500/

The interview with MultiXscale expert Lara Peeters (Ghent University) at insideHPC is available through the following link: “Vanguards of HPC-AI: Ghent University’s Lara Peeters Uses HPC to Fuse Image Analytics and Art”

Join our MultiXscale experts in the following sessions at ISC25 Hamburg Germany: “Supporting cutting edge development of LAMMPS with EESSI” by MultiXscale expert Helena Vela ⏱️ Friday 13 June📌 Hall X10 – 1st floor (Workshop) Abstract:The MultiXscale CoE is an exascale-oriented application co-design and delivery for multiscale simulations. It is a collaborative project between members of the CECAM network and the EESSI community that will allow domain scientists to take advantage of the computational resources offered by EuroHPC JU. In this presentation we are going to focus on one of the lighthouse codes within #MultiXScale, LAMMPS, which is used by a large number of computational scientists. We will discuss how the developers of new plugins for LAMMPS are testing on a wide range of systems with the help of the software.eessi.io and dev.eessi.io repositories.The dev.eessi.io repository allows developers to share pre-releases of their software so they can test it on systems where EESSI is available, this includes the EuroHPC systems Vega, Karolina and Deucalion. For example, on Vega, development codes of LAMMPS are already available for using and testing through dev.eessi.io. In this talk we will show all the CI infrastructure to provide pre-released versions of your software using the plugins under development in MultiXscale, with LAMMPS as an example. More information here: https://pop-coe.eu/news/events/readiness-of-hpc-extreme-scale-applications-2nd-edition#Vela ———————————————————————————————————————————————————————————————————————————————— Exhibition: MultiXscale will be present at the EuroHPC JU booth J30. Our HPC expert Helena Vela will give a presentation on 11 June, from 12h20 to 12h40 Further details here: https://eurohpc-ju.europa.eu/media-events/events/eurohpc-ju-isc-high-performance-2025-2025-06-10_en

MultiXscale experts Alan O’Cais (University of Barcelona and CECAM) and Helena Vela (Do IT Now) will present “From zero to cloud (the EESSI way)” on 4 June at 9h10, during the HPC Annual Meeting – HPCKP25 Barcelona 3-5 June. Register here to watch the talk online!! Abstract: Discover how EESSI (European Environment for Scientific Software Installation) is transforming the way scientific software is deployed and shared across HPC systems, cloud platforms, and even laptops. In this session, we’ll introduce the motivation behind EESSI, its architecture, and how you can start using a fully pre-built, modular software environment — no matter where you compute. We will also demonstrate deployment to a cloud instance and cloud-based Slurm clusters!

“The same software on any research infrastructure, wouldn’t that be EESSI?” by our MultiXscale expert Bob Dröge (University of Groningen) on 20 May, during the SURF Research Day 2025, the national conference connecting research, IT, and innovation in Hilversum (Netherlands). Abstract: Modern research often requires cloud or supercomputing infrastructure, but setting up your software environment on such systems can be challenging and time consuming. What if you could have the same software environment everywhere? The European Environment for Scientific Software installations (EESSI) provides a large, uniform stack of scientific software, ready to use on virtually any system in the world: from personal laptop, to a cloud VM, to the largest supercomputers in Europe. In this talk, you will learn how EESSI works, what possibilities it creates, and you will see it live in action. Installing scientific software on complex systems such as cloud VMs or a supercomputer can be a time-consuming hurdle, and may even discourage you from using the infrastructure that would – in theory – be most suitable for your work. It also means that, when you are set up on a system, you are unlikely to move anywhere else, even if better infrastructures become available. The European Environment for Scientific Software Installations (EESSI) is an open-source project that provides a large stack of scientific software, which can be easily made available on any system in the world. This allows you to start experimenting on a local laptop, and then seamlessly move to a cloud VM or supercomputer as your computational needs increase. Aside from alleviating the software installation burden, having the same software environment everywhere opens up many more unique opportunities. In this session we will show some examples, but also open the floor for informal discussion: which opportunities do you see? More info about the event: https://www.surf.nl/en/agenda/surf-research-day-2025