Using the IU Research Desktop for Interactive Supercomputing
Loading...
Can’t use the file because of accessibility barriers? Contact us
Date
Authors
Journal Title
Journal ISSN
Volume Title
Publisher
Indiana University Workshop in Methods
Permanent Link
Abstract
Indiana University has a long history of providing High Performance Computing (HPC) services to all faculty, students and staff free of charge. This includes access to HPC systems like Quartz, Big Red 200, Jetstream and a high performance desktop service called Research Desktop (RED).
RED provides students and researchers access to graphical applications, in a highly interactive fashion. The system has been designed to lower the barrier of entry and broaden adoption of traditional supercomputing resources. While the service provides all the normal HPC command line tools and allows for job submission to HPC systems, it is designed for users to run computationally demanding applications like MATLAB, Schrödinger, R-Studio and Jupyter right on the desktop. RED provides users with an environment that looks familiar to what they know from Microsoft Windows or Mac OSX, while offering the storage and compute resources of an HPC system. The Research Desktop allows for running applications for days and even weeks, as well as disconnecting and re-connecting to a session, making it easy for users to start and monitor long running computational workflows. The service has been available to IU faculty, students and staff for over 7 years.
This talk will give an overview of RED and will outline common use cases like running Jupyter Notebooks, R-Studio or Matlab. RED will be compared to the other HPC systems available to IU users like Quartz and Big Red 200. There will be time for Q&A as well as a live demonstration of RED.
Description
Robert Henschel is the Engagement Architect for the Research Engagement directorate in Research Technologies. He is responsible for working with IU faculty and research teams to facilitate the efficient use of IU’s High Performance Computing (HPC) systems and reduce time to science. Henschel has more than 20 years of experience in High Performance Computing, and his research interests focus on performance analysis of parallel applications and broadening adoption of HPC systems across all fields of science. Henschel has led the development of IU’s Research Desktop, which makes it easier for inexperienced users to get started with HPC and has allowed the university to leverage powerful compute and storage resources to serve a broad user base.