10-27, 16:45–17:10 (Europe/Berlin), Main stage
The European Environment for Scientific Software Installations (EESSI, pronounced as "easy") is a collaboration between different HPC sites and industry partners, with the common goal of setting up a shared repository of (optimized) scientific software installations that can be used on a variety of Linux systems, regardless of which (version of) Linux distribution or processor architecture is used.
From and end-user perspective, the software installations provided by EESSI are streamed in on-demand as the software is being used, with aggressive caching on various levels to improve startup performance.
As such, there is no need to explicitly install software or download a bulky container image prior to using a particular software package - just pick from the catalogue of available software and start using it.
Software installations in EESSI are optimized for the microarchitecture of the host CPU are automatically selected, which significantly benefits performance.
The software included in EESSI is built such that it is independent of the host OS (without resorting to containers), which significantly limits the effort required to provide software installations that can be used on a wide variety of Linux systems.
Next to providing a uniform software stack across different Linux systems (supercomputers, cloud, laptops) which enables true "mobility of compute" without sacrificing performance, EESSI enables various use cases like leveraging it in Continuous Integration (CI) environments like GitHub Actions to make software testing easier, facilitating HPC training, supporting truly portable workflows, and potentially significantly enhancing collaboration with developers and advanced users of scientific software.
In this talk we will introduce the European Environment for Scientific Software Installations (EESSI, pronounced as "easy"), a collaborative project to provide a shared repository of optimized scientific software installations that can be used on a variety of Linux systems.
We will discuss the goals of the project, explain the high-level design, present the use cases that EESSI enables, and give an overview of the current status of the project.
We use various open source projects in EESSI including:
- CernVM-FS (https://cernvm.cern.ch/fs) for distributing the software installations;
- Gentoo Prefix (https://wiki.gentoo.org/wiki/Project:Prefix) to make software installations independent of the host OS;
- EasyBuild (https://easybuild.io) to build (scientific) software optimized for specific CPU microarchitectures;
- Lmod (https://www.tacc.utexas.edu/research-development/tacc-projects/lmod) to provide an easy user interface for end users;
- archspec (https://github.com/archspec/archspec) for auto-detecting the microarchitecture of the host CPU at runtime;
- ReFrame (https://reframe-hpc.readthedocs.io) for testing the provided software installations;
- Apptainer (https://github.com/apptainer/apptainer) for creating an isolated environment to build software;
- Terraform (https://www.terraform.io) + Ansible (https://www.ansible.com) for setting up the necessary cloud infrastructure;
Links:
- website: https://www.eessi.io
- documentation: https://www.eessi.io/docs
- GitHub: https://github.com/eessi
- paper: https://doi.org/10.1002/spe.3075
- old recorded presentation on EESSI (2021): https://easybuild.io/eum21/#eessi
Lara Peeters is a Digital Art Historian, who holds master degrees in Art History (2021) and Digital Humanities (2022) from the KU Leuven (Belgium).
Since May 2023, she is a member of the HPC team at Ghent University (Belgium) where she was hired to work on the EESSI project (https://www.eessi.io), the European Environment for Scientific Software Installations, and the MultiXscale project (https://www.multixscale.eu), a EuroHPC JU Centre of Excellence in multiscale modelling.
In her free time she plays the double bass in an orchestra, rides horses, goes sailing, loves going to musea and listening to music.
Kenneth Hoste, a.k.a. 'boegel', is a computer scientist and FOSS enthusiast from Belgium. He holds a Masters (2005) and PhD (2010) in Computer Science from Ghent University. His dissertation topic was "Analysis, Estimation and Optimization of Computer System Performance Using Machine Learning".
Since October 2010, he is a member of the HPC team at Ghent University (Belgium) where he is mainly responsible for user support & training. As a part of his job, he is also the lead developer and release manager of EasyBuild (https://easybuild.io), a software build and installation framework for (scientific) software on High Performance Computing (HPC) systems.
He is also actively involved in EESSI (https://www.eessi.io), the European Environment for Scientific Software Installations, and in MultiXscale (https://www.multixscale.eu), a EuroHPC JU Centre of Excellence in multiscale modelling.
In his free time, he is a family guy and a fan of loud music, frequently attending gigs and festivals.
He enjoys helping people & sharing his expertise, and likes joking around.
He has a weak spot for stickers and beer.