Skip to content
New issue

Have a question about this project? Sign up for a free GitHub account to open an issue and contact its maintainers and the community.

By clicking “Sign up for GitHub”, you agree to our terms of service and privacy statement. We’ll occasionally send you account related emails.

Already on GitHub? Sign in to your account

tweaks to abstract to make it fit on a single page #36

Merged
merged 1 commit into from
Dec 17, 2024
Merged
Show file tree
Hide file tree
Changes from all commits
Commits
File filter

Filter by extension

Filter by extension

Conversations
Failed to load comments.
Loading
Jump to
Jump to file
Failed to load files.
Loading
Diff view
Diff view
45 changes: 20 additions & 25 deletions isc25/EESSI/abstract.tex
Original file line number Diff line number Diff line change
@@ -1,32 +1,27 @@
What if there was a way to avoid having to install a broad range of scientific software from scratch on every
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 for supercomputers is known to be a tedious and time-consuming task. The application
software stack continues to deepen as the
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.
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 non-trivial task that affects application developers, HPC user support teams, and the users themselves.

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.
setting up and 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 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
This tutorial aims to address these challenges by introducing (i) \emph{CernVM-FS},
a distributed read-only filesystem designed to efficiently \emph{stream} software installations on-demand,
and (ii) the \emph{European Environment for Scientific Software Installations (EESSI)},
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.
cluster, a cloud environment, or a personal workstation.

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.
Its covers installing and configuring CernVM-FS, the usage of EESSI,
installing software into and on top of EESSI, and advanced topics like GPU support and performance tuning.
3 changes: 2 additions & 1 deletion isc25/EESSI/main.tex
Original file line number Diff line number Diff line change
Expand Up @@ -55,7 +55,8 @@

\title{
\textbf{\LARGE Streaming Optimised Scientific Software: an Introduction to CernVM-FS and EESSI}\\
\vspace{2mm}{\Large \emph{ISC'25 tutorial proposal}}
%\vspace{2mm}{\Large \emph{ISC'25 tutorial proposal}}
\Large \emph{ISC'25 tutorial proposal}
}

\date{}
Expand Down
Loading