Cluster management tools and user interfaces are often the neglected layer between the users, their applications and the cluster hardware. But can a thoughtfully architected HPC cluster software stack enable modern cluster design, regardless of where the hardware lives?
Exploring the choice between cloud, on-premise or a hybrid infrastructure for HPC often revolves around comparisons of capabilities and costs – where critical factors are often unknown. This makes the decision one based on best assumptions of the time, with consequences that last years.
The real magic of modern HPC infrastructure at the cluster management layer frees one from vendor and/or cloud lock-in and allows for infrastructure flexibility, modular expansion. Resulting in an agile infrastructure that is composable and enables experimentation.
Join us for this thought-provoking Q&A session as Dr Werner Scholz and Jakub Szarlat from XENON push the boundaries of HPC infrastructure and explore the important role the cluster software stack plays for the user experience, management, and future proofing the whole system.
- How can a modern software stack deliver flexibility, modular design, agile response to workloads?
- What is the best way to enable hybrid cloud workloads?
- Can on-premise clusters benefit from automation, scripting and an infrastructure-as-code approach?
The XENON team will answer these questions and explore how key decision vectors such as dataset size and location, workloads and applications, bandwidth and security all come in to play.
Watch this short 10 minute video to learn how containerised cluster management with the XENON Cluster Stack™.