03-18, 18:40–18:50 (US/Eastern), CGIS Concourse
As computational methods in research evolve, many researchers face challenges using traditional High-Performance Computing (HPC) systems. At the University of Virginia Research Computing, we address this by leveraging Open OnDemand (OOD) as a user-friendly, browser-based platform for Interactive HPC (IHPC) and Slurm job management. OOD simplifies HPC access with popular applications, virtual desktops for GUI-based tools, and seamless connectivity without the need for a VPN or command-line interaction. To enhance usability, we’ve added custom utilities for monitoring account status, managing scratch filesystem files, and generating Slurm scripts with Service Unit (SU) estimates.
These innovations reduce barriers to HPC use, enabling researchers to focus on their work while accessing pow
With the expanding reliance of research on ever evolving computational methods, it is essential to recognize that most researchers lack the training necessary to effectively utilize traditional HPC systems. With the growing reliance on computational methods in research, many researchers lack the training required to effectively use traditional High-Performance Computing (HPC) systems. To ensure equitable access to HPC resources, innovative and user-friendly interfaces are essential, particularly for less-experienced users.
At the University of Virginia Research Computing, we leverage Open OnDemand (OOD) as our primary platform for Interactive High-Performance Computing (IHPC) and as a web portal for Slurm job submission, supporting both educational and research activities.
OOD empowers users to access the power and scalability of HPC systems for interactive data analysis and visualization through a browser-based interface, eliminating the need for a Virtual Private Network (VPN). As an operating system-agnostic platform, OOD is accessible from any device, offering popular applications and a virtual desktop environment for GUI-based tools. This approach significantly enhances usability, making HPC systems more approachable for researchers.
Drawing on our experience, we identified that many researchers primarily use HPC systems for a limited set of applications. To address this, we customized OOD’s framework to streamline access to these applications and utilities. Our tailored tools include:
- Account Status Checker: Displays the status of HPC accounts and storage usage.
- HPC Status: Monitors partition activity, showing running and pending jobs.
- Scratch Filesystem Monitor: Notifies users of files scheduled for deletion in the scratch filesystem.
- Slurm Script Generator: Assists in creating Slurm scripts based on user-defined parameters and estimates Service Unit (SU) consumption.
To further reduce barriers, we transitioned our onboarding training and “Intro to HPC” sessions entirely to OOD, eliminating the need for command-line interaction.
By integrating OOD with these custom utilities, we have simplified HPC access, reduced technical challenges, and enabled researchers to focus on advancing their work without needing to become HPC experts. This approach fosters productivity, innovation, and greater accessibility across diverse research domains.
I am Ahmad Sheikhzada, technical support manager at University of Virginia Research Computing organization. I hold a Ph.D. in computational condensed matter physics.