Use Cases for High Performance Research Desktops
Robert Henschel, Jonas Lindemann, Anders Follin, Bernd Dammann, Cicada Dennis, Abhinav Thota
TL;DR
High Performance Research Desktops provide a persistent, graphical gateway to HPC systems that lowers entry barriers and enables end-to-end research workflows alongside traditional SSH-based access. The paper aggregates real-world use cases from Indiana University, Lund University, and Technical University of Denmark, detailing architectures, hardware, software, and policy decisions that support light interactive workloads, data management, visualization, and education from a desktop. It catalogs a broad set of use cases—graphical file management, pre/post processing, non-HPC work, teaching, client-server applications, and secure enclaves—to demonstrate the desktop’s versatility in enabling end-to-end HPC work. Looking forward, the authors outline concrete and speculative directions, including adopting modern desktop environments, deeper desktop-HPC integration (Run In Batch, Recently Run Jobs, Move to Archive), and building a shared community to disseminate best practices and tools.
Abstract
High Performance Research Desktops are used by HPC centers and research computing organizations to lower the barrier of entry to HPC systems. These Linux desktops are deployed alongside HPC systems, leveraging the investments in HPC compute and storage infrastructure. By serving as a gateway to HPC systems they provide users with an environment to perform setup and infrastructure tasks related to the actual HPC work. Such tasks can take significant amounts of time, are vital to the successful use of HPC systems, and can benefit from a graphical desktop environment. In addition to serving as a gateway to HPC systems, High Performance Research Desktops are also used to run interactive graphical applications like MATLAB, RStudio or VMD. This paper defines the concept of High Performance Research Desktops and summarizes use cases from Indiana University, Lund University and Technical University of Denmark, which have implemented and operated such a system for more than 10 years. Based on these use cases, possible future directions are presented.