The University of Pennsylvania has significantly advanced its AI research capabilities with the launch of ‘Betty’, a cutting-edge off-campus supercomputer designed to process massive datasets and deliver high-performance, adaptive results. Built using NVIDIA’s SuperPOD reference architecture, Betty features 31 eight-way GPU nodes connected via NDR400 InfiniBand, allowing researchers to scale single experiments across the entire system for more robust insights.
Highlighting the growing demands of AI, Kenneth Chaney, Associate Director of AI and Technology at Penn’s Advanced Research Computing Centre (PARCC), noted, “The needs for modern AI research have grown to a scale… where it is no longer feasible to be maintained by any one school.” The creation of Betty reflects Penn’s strategic move away from expensive, isolated lab servers, toward a centralised, high-performance computing environment accessible across disciplines.
The supercomputer is expected to have a transformative impact across the university. Marylyn Ritchie, Vice Dean of AI and Computing at the Perelman School of Medicine, emphasized the importance of this infrastructure: “In the future, we will be leveraging AI in all areas of research… I think we will see it adopted in many/most fields.” Ritchie also highlighted the system’s high energy demands — consuming one megawatt of power — which necessitated its location away from the main campus.
Betty is named in honour of Frances Elizabeth ‘Betty’ Snyder Holberton, one of the original six programmers of the ENIAC computer, which was also developed at Penn in the 1940s. This tribute connects Penn’s historical leadership in computing innovation with its future-forward investments in artificial intelligence.
Now fully operational and accessible to researchers regardless of their location, Betty is set to serve as a collaborative AI infrastructure, enabling scalable research and fostering interdisciplinary innovation. The system not only reinforces Penn’s position as a leader in AI research but also lays the groundwork for more inclusive and expansive scientific inquiry across all fields.
