Loading…
Attending this event?
May 21-23, Wolf Law School, Boulder CO
Tuesday, May 21 • 2:45pm - 3:15pm
Add Interactive HPC, Multipoint Data Staging, Job Routing, and Multi-Cloud to your Cluster with ProjectEureka

Sign up or log in to save this to your schedule, view media, leave feedback and see who's attending!

In this presentation we will discuss how Project Eureka will provide a way to seamlessly integrate interactive applications with the extension of Open OnDemand, data-management with and high performance-AI computing with the OmniScheduler meta-scheduler as part of your HPC cluster
We will discuss how as part of Project Eureka we have extended Open OnDemand to include a project based user interface that supports project level organization and self service capabilities providing a 'Collaborate First' ethos. This interface adds new functionality, but also maintains the existing security model maintaining the per-user-nginx user sandbox model.

Additionally we will discuss the OmniScheduler integration and its design to handle capabilities such as data/results staging, dynamic scratch, and data publishing with job directives. The design also includes standard configurations that will be provided by the UI for additional data management capabilities.

In the presentation we will also discuss how Project Eureka is designed to be cross cloud including on-prem by leveraging Terraform with a new Constellation layer that programmatically generates and maintains Terraform configurations. This will ultimately provide cross platform coverage of AWS, Google Cloud, Microsoft Azure for Cloud and Slurm & K8s/Kubevirt for on-prem integrations.

Tuesday May 21, 2024 2:45pm - 3:15pm MDT
Room 205
Feedback form isn't open yet.

Attendees (1)