Document Type


Publication Date



As scientific research has extended far beyond the practicality and abilities of laboratory experiments, computational simulations have become the mainstay of enabling and furthering the research in a way never previously thought possible. It is becoming commonplace to model and simulate both the very large, such as black hole collisions in astrophysics, and the very small, such as subatomic particle behavior and interaction in high energy physics. In addition to the previous examples detailing extremes, practically every area of research currently utilizes and benefits from computational resources to simulate their work; financial modeling, weather forecasting, geological phenomena, geo-spatial data analysis, gene sequencing...the list is practically without end. Until recently, many researchers have had compute clusters in closets for which they must devote time and money for its housing and management. Many institutions are gradually adopting central research or high performance computing centers to reduce the overall cost to the university and researchers in deploying and maintaining research computing resources. These centers also help the university attract more computational researchers as well as garner more external funding by demonstrating their commitment to providing these facilities. While it would not be difficult to argue the worth of computational resources in the realm of academic research, a common sustainable funding model for such resources is strangely absent from the overall picture. One such model that is becoming a frequent topic of discussion in academic circles is the condominium model.


Position paper in the NSF-funded Workshop on Sustainable Research Computing Centers, Ithaca, NY.