Fuzzball transforms your on-premises or cloud environment into a user-friendly, manageable HPC cluster. In this talk, I’ll share exciting updates from the past year. Fuzzball is now generally available (GA) for on-prem installations and is also offered as a tech preview in the AWS Marketplace. This means you can try Fuzzball in your AWS account and deploy it directly on your on-prem cluster. We’ve also introduced Fuzzball Federate as a tech preview, enabling you to manage multiple Fuzzball clusters through a single console and unified user interface. Additionally, Fuzzball now includes a built-in workflow catalog, featuring CIQ-certified examples of popular applications in an easy-to-use format.
Warewulf is an open-source cluster provisioning and management system primarily targeting HPC deployments. Its latest feature release, v4.6, includes a ton of new features, including an automated upgrade process, a completely new kernel management system, a new REST API, better management of site-local overlays, more dynamic and expressive overlay templates, a brand new abstract resources system, and significant performance improvements for large clusters.
In this session we will go over these changes and more in detail and showcase a new web interface from CIQ built specifically for Warewulf utilizing its new REST API. We'll also take audience questions, with a look into the future of the v4.6 release series.
With the recent changes to the NIH Genomic Data Sharing Policy, more focus is being placed on compliance today. Organizations are looking for solutions to meet these new requirements. In this session we will discuss how Globus data management services allow users to confidently work with controlled-access data. We will cover all the product features that address managing controlled-access data to enable compliance with NIST SP 800-171. We will demonstrate how with High Assurance collections the service meets these new requirements.
Tired of wrestling with Slurm? This fast-paced, hands-on workshop will equip researchers with the essential tools and strategies to handle common challenges such as job failures, long queue times, and resource allocation issues. Whether you're a beginner or have some experience with SLURM, this workshop will enable you to design, build, and troubleshoot efficient HPC research workflows. If you would like to practice some of the hands-on exercises at the end of the session, register for a Research Computing account beforehand (this will take about 10 minutes).
