Merge pull request #34 from boegel/abstract

rewrite abstract to include CernVM-FS

Author: ocaisa

isc25/EESSI/abstract.tex

@@ -1,21 +1,32 @@
-What if there was a way to avoid having to install a broad range of scientific software from scratch on every HPC
-cluster or cloud instance you use or maintain, without compromising on performance?
+What if there was a way to avoid having to install 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 for supercomputers is known to be a tedious and time-consuming task. The application
 software stack continues to deepen as the
-HPC user community becomes more diverse, computational science expands rapidly, and the diversity of system architectures
+High-Performance Computing (HPC) user community becomes more diverse, computational science expands rapidly, and the diversity of system architectures
 increases. Simultaneously, we see a surge in interest in public cloud
 infrastructures for scientific computing. Delivering optimised software installations and providing access to these
 installations in a reliable, user-friendly, and reproducible way is a highly non-trivial task that affects application
 developers, HPC user support teams, and the users themselves.
 
-This tutorial aims to address these challenges by providing the attendees with the tools to \emph{stream} the optimised
-scientific software they need. The tutorial introduces European Environment for Scientific Software Installations
-(\emph{EESSI}), a collaboration between various European HPC sites \& industry partners, with the common goal of
-creating a shared repository of scientific software installations (\emph{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
+Although scientific research on supercomputers is fundamentally software-driven,
+setting up and managing a software stack remains challenging and time-consuming.
+In addition, parallel filesystems like GPFS and Lustre are known to be ill-suited for hosting software installations
+that typically consist of a large number of small files. This can lead to surprisingly slow startup performance of
+software, and may even negatively impact the overall performance of the system.
+While workarounds for these issues such as using container images are prevalent, they come with caveats,
+such as the significant size of these images, the required compatibility with the system MPI for distributing computing,
+and complications with accessing specialized hardware resources like GPUs.
+
+This tutorial aims to address these challenges by introducing the attendees to a way to \emph{stream}
+software installations via \emph{CernVM-FS}, a distributed read-only filesystem specifically designed
+to efficiently distribute software across large-scale computing infrastructures.
+The tutorial introduces the \emph{European Environment for Scientific Software Installations (EESSI)},
+a collaboration between various European HPC sites \& industry partners, with the common goal of
+creating a shared repository of optimised scientific software installations (\emph{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.
 
-We cover the usage of EESSI, different ways to accessing EESSI, how to add software to EESSI, and highlight some more 
-advanced features. We will also show attendees how to engage with the community and contribute to the project.
+We cover the installation and configuration of CernVM-FS to access EESSI, the usage of EESSI, how to add software
+installations to EESSI, how to install software on top of EESSI, and advanced topics like GPU support and performance
+tuning.