CS professor helps chart NSF’s future advanced computing strategy and programs
7/21/2016 9:27:00 AM
An internationally recognized expert on high-performance computing, CS Professor William D. Gropp, the Thomas M. Siebel Chair in Computer Science, recently co-chaired a National Academies study that guides the National Science Foundation’s future directions in advanced computing. The study’s recommendations aim to maintain America’s leadership in science and engineering, ensure that resources meet community needs, aid the scientific community in keeping up with the revolution in computing, and sustain the infrastructure for advanced computing.
Gropp and his team solicited input from more than 60 individuals, research groups, and organizations in the advanced computing field. Advanced computing capabilities, including computer systems and expert staff, are typically shared among multiple researchers, institutions and applications, and they help tens of thousands of researchers each year expand the frontiers of science and engineering.
By combining superfast and secure networks, cutting-edge parallel computing, efficient software, state-of-the-art scientific instruments, and massive datasets with expert staff, the NSF-funded advanced computing ecosystem lets researchers investigate highly complex and computationally intensive problems such as the origins of the universe, unraveling diseases, and climate prediction.
Among the study’s recommendations are that NSF should:
- sustain and grow its investments in advanced computing to ensure that the nation’s researchers can continue to work at the frontiers of science and engineering.
- collect community requirements and create roadmaps to set priorities better and make more strategic decisions about advanced computing beyond 2020.
- pay close attention to providing support for the revolution in data- driven science along with simulation, including large-scale simulations and/or data analytics that would otherwise be unavailable to researchers and continue to monitor the cost-effectiveness of commercial cloud services.
According to Gropp, the NSF’s support for advanced computing has been essential for the advancement of science and engineering.
“Partly as a result, the demand for advanced computing has been growing exponentially, and NSF and the computational science community need to work together to ensure the uninterrupted availability of the types of advanced computing needed by researchers,” Gropp said. “This study provides a framework that can guide the planning and use of advanced computing resources in a way that sustains the investment in people, software, and hardware for the next decade.”