Uncategorized

By Rodrigo Bartolomeu At the Joint Laboratory for Extreme-Scale Computing (JLESC) workshop, which comprises members from INRIA, the University of Illinois, Argonne National Laboratory, the Barcelona Supercomputing Centre, the Jülich Supercomputing Centre and the RIKEN Center for Computational Science, our partners at Forschungszentrum Jülich presented the latest developments in the performance-portable electrostatics library, at JLESC 18th Workshop, from 19 to 21 May 2026. The specialised audience of researchers and software developers shared common interests, focusing on performance tools, programming languages and advanced architectures. Our poster presented a library ready for Exascale computing that implements the Particle–Particle–Particle–Mesh (P3M) and Ewald summation methods within a single source code base. Building on the Kokkos programming model enables the library to abstract away memory layout and execution details, allowing the same kernels to run efficiently on CPUs and GPUs from NVIDIA and AMD. It uses Cabana for cache-friendly particle data structures and HeFFTe for scalable, architecture-aware FFTs. A key design principle is modularity: short- and long-range solvers are expressed as independent computational partitions. On systems that support heterogeneous partitioning, users can assign distinct resources to each partition to achieve better load balancing and overall throughput. Preliminary benchmarks on the MareNostrum 5 GPU partition nodes demonstrate close to ideal strong scaling up to 128 GPUs for the long-range kernel, while maintaining numerical accuracy. These results demonstrate that a portable implementation can meet the performance demands of Exascale workloads without the need for multiple code bases. Meaningful links: 1- https://www.fz-juelich.de/en/jsc/news/events/2026/18-jlesc-2026 2- https://jlesc.github.io

Meet our MultiXscale experts in the following sessions at ISC26 Hamburg (Germany): Tutorial: Introduction to EESSI: the European Environment for Scientific Software Installations 22 June 2026, 14:00 to 18:00. Hall X3 – 1st Floor This tutorial aims to address these challenges by introducing the European Environment for Scientific Software Installations (EESSI, pronounced as “easy”), a collaboration between various European HPC sites & industry partners. The goal of EESSI is to provide a shared repository of scientific software installations 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 is a full size HPC cluster, a virtual machine in the cloud, or a personal workstation. We cover the basics of EESSI, different use cases for EESSI, how to add software to EESSI, and highlight some more advanced features. We will also show how to engage with the community and contribute to the project. BoF session: European Environment for Scientific Software Installations (EESSI) 25 June 2026, 9:00 to 10:00, Hall G1 – 2nd Floor In this session, we will briefly present the current status of EESSI, give a quick demo of the user experience, and outline future plans with a view to setting priorities based on attendee feedback. Through a live poll we will foster interaction with attendees and trigger discussions. Questions and suggestions raised by attendees will be taken into account when revising the short term roadmap of EESSI.

Data and research software are central to scientific innovation. High-Performance Computing (HPC) facilities and Research Data Management (RDM) units already deliver the technical infrastructure and specialised training that academic and industrial communities depend on to engage with HPC at scale. Yet many domain scientists need foundational support before they are ready to make use of these specialised services. A new position paper calls for central Research Software Engineering (RSE) units in research institutions to bridge that gap, applying the same pooling logic in HPC and RDM units: shared expertise, mutualised costs, and clear career paths. RSE units act as catalysts in the digital transformation of academic research, supporting domain scientists in the initial porting of serial applications to parallel programming models, delivering targeted training to lower the barrier to entry into the HPC ecosystem, and sustaining the long-term maintenance and community-building activities required to safeguard the longevity of research software.

The Conference for Research Software Engineering in Germany is a yearly event to foster synergies between scientist who code, domain experts and HPC practitioners. The 6th iteration (deRSE26) was located at the University of Stuttgart and co-organized by a member of the MultiXscale consortium. The event attracted 280 participants and featured 90 posters and 100 talks, workshops, and interactive sessions organised in 5 parallel sessions. A full day was dedicated to HPC, with a 3-hour workshop on the Jülich Benchmarking Environment and a 3-hour HPC Carpentry instructor on-boarding session. We also learned about regional HPC consulting services offered by HPC.nrw and bwRSE4HPC, the commissioning of the Tier-3 BinAC2 cluster to democratize access to HPC in academia, the new FutuRSI institute to support developers of research software, a national initiative at NFDI to catalogue research software and run interactive Jupyter notebooks in the cloud, and the EU-funded EVERSE project to catalogue research software and document their compliance with FAIR principles. We got updates on the multiscale and multiphysics simulation software ESPResSo, waLBerla and TrixiParticles.jl, on HPC workflows with pyiron/Semantikon/APE, and on porting applications to HPC with Coccinelle semantic patching. The event concluded with a guided tour of the Tier-1 HLRS supercomputer facility, where we learned about Cray computers, the upcoming AI Factory HammerHAI, sustainable computing, and how heat generated by the next flagship supercomputer Herder will be captured and redistributed into the University district heating network to reduce its carbon footprint. Many contributions to deRSE26 covered topics that MultiXscale actively engages in, namely porting software to HPC, software marketplaces, and HPC training. National and regional initiatives such as NFDI, FutuRSI, HPC.nrw and bwRSE4HPC show a need in academia to get better access to infrastructure, consulting services and training opportunities for software developers, similar to how National Competence Centres (NCCs) provide HPC and software-related services to industry and academia at the European level. The conference abstracts and slides can be obtained from the event website and the associated Zenodo community. *Group photo taken by Adam Pagan, licensed under CC-BY-4.0. Talk photos by Volodymyr Kushnarenko.

provided by EuroHPC CoE MultiXscale What if you no longer have to install a broad range of scientific software from scratch on every laptop, HPC cluster, or cloud instance you use or maintain, without compromising on performance? The European Environment for Scientific Software Installations (EESSI, https://eessi.io) comes to the rescue! In this webinar series we will provide a comprehensive overview of EESSI: why we started it, how it works, how you can use it, … You can register for the sessions here (either all of them, or selected ones). All sessions will be recorded. Recordings, slides, and materials used will be made publicly available shortly after each session via this page. Further details available here.

MultiXscale CoE coordinator, Dr. Matej Praprotnik (National Institute of Chemistry) joined the roundtable discussion “Codes That Drive a Better World: Challenges and Opportunities in the Development of Artificial Intelligence for Ensuring a Sustainable Future”, organized in the framework of the Food for Thought Festival on 16 March 2026 at the University of Ljubljana (Slovenia). The recording is already available on YouTube. Discover further details about the event here.

The SC Women’s History Month Profiles project started three years ago, and since then, it has highlighted more than 200 women whose work is shaping the High-performance computing (HPC) community across research, engineering, education, and leadership. The theme selected for this year “HPC Unites” reflects the collaborative nature of the field, bringing together people, disciplines, and institutions to solve complex challenges and drive innovation. Discover more about their profiles here

The new episode for “Supercomputing in Europe. HPC in Europe network” is out! This time is joined by MultiXscale experts Caspar van Leeuwen,⁠ Machine Learning Consultant at ⁠SURF⁠ and ⁠Helena Vela Beltran⁠, Computational Scientist at ⁠HPCNow! and Do IT Now Spain⁠. Both are actively contributing to the ⁠MultiXscale CoE⁠ and the ⁠EESSI project⁠, the European Environment for Scientific Software Installations, a common stack of scientific software installations for HPC systems and beyond, including PCs and cloud infrastructure. The interview and mixing is carried out by Apostolos Vasileiadis (ENCCS, Mimer AI Factory) Listen to the full interview here: Spotify: https://open.spotify.com/episode/0eYCo5VLyuujIIlrfAFP9o?si=HVN3qxdpTEagbaCSyB051w Apple podcasts: https://podcasts.apple.com/se/podcast/eessi-simplifying-software-installation-in-hpc-systems/id1768782069?i=1000758537611 Add the RSS feed to your favourite podcast app: https://anchor.fm/s/f01f82a4/podcast/rss

Since the blog post in Feb’25 announcing that EESSI will be integrated in the EuroHPC Federation Platform (EFP), we have been working hard on making this a reality. The Federated Software Catalog (FSC) component of EFP will use EESSI as a base. As a result, EESSI will soon be available on all EuroHPC supercomputers. In fact, EESSI is already available on the majority of them today! Read all the details on the EESSI blog post here