NSF funds Blue Waters project
Extending more than 50 years of supercomputing leadership, the University of Illinois at Urbana-Champaign and its National Center for Supercomputing Applications (NCSA) announced to build the world’s first sustained petascale computational system dedicated to open scientific research. This leadership-class project, called Blue Waters, is supported by a $208 million grant from the National Science Foundation.
“Blue Waters will be an unrivaled national asset that will have a powerful impact on both science and society,” said Thom Dunning NCSA director and a professor of chemistry at Illinois. “Scientists around the country—simulating new medicines or materials, the weather, disease outbreaks, or complex engineered systems like power plants and aircraft—are poised to make discoveries that we can only begin to imagine.”
“We are excited. Blue waters embodies an important piece of NSF’s vision for its Office of Cyberinfrastructure to provide the world’s leading scientists and engineers with unprecedented petascale computing resources to work at the frontiers of knowledge,” said Arden L. Bement, director of the National Science Foundation. “With this collaboration and investment, researchers may tackle previously unimaginable questions and realize unparalleled discoveries, generating new understanding about the Earth’s climate, the functioning of national and global economies, nanoscale engineering, the design of advanced materials, the evolution of the early universe, the molecular processes that sustain life … possibilities abound.”
The system will deliver sustained performance of more than one petaflop on many real-world scientific and engineering applications. A petaflop is computing parlance for 1 quadrillion calculations per second.
“Our community traditionally uses peak performance to measure the output of a system based on simple benchmarks. It’s a measure that’s never achieved in real life,” Dunning said. “With Blue Waters, we’re focused intently on sustained performance—genuine performance on codes that scientists and engineers use every day instead of unattainable benchmark figures.”