Characteristic Science Applications for the Leadership Class Computing Facility

点击翻译按钮获取中文摘要

The goal of this project is to select, study, and transform a set of Characteristic Science Applications (CSAs) to enable next-generation science on the NSF Leadership-Class Computing Facility (LCCF). The CSAs were chosen to represent a broad range of science domains and computational approaches, and each CSA will comprise one or more computer codes and a challenge problem to be solved on the LCCF. The set of CSAs will enable the project to verify the design of the LCCF and validate that the facility is applicable across the broad range of science disciplines supported by the NSF when it is constructed. Furthermore, the transformations made to the codes and workflows in the CSAs will provide best practice models and implementation exemplars that will inform training materials, tutorials, and other educational content. This will ensure that the nation's science and engineering research community will be effective on the LCCF from day one of operations.The project plans to evaluate a broad selection of science applications and challenge problems, laying the foundations for a transformation of the computer codes in a way that will support the LCCF broad goal of enabling a ten-fold or more time to solution performance improvement over NSF's current leadership computing resource, Frontera. This capability improvement will come from a combination of increased scale of the LCCF primary computing system(s), increased capabilities of the components (on-node I/O bandwidth, inter-node I/O bandwidth, disk and memory bandwidth, access speed, cores, etc.) that make up the computing instrument, and improvements in the software codes that make up the set of science applications used to demonstration ten-fold performance improvement.This award reflects NSF's statutory mission and has been deemed worthy of support through evaluation using the Foundation's intellectual merit and broader impacts review criteria.