Preliminary Design Planning for the Leadership-Class Computing Facility

University Of Texas At Austin, Austin TX

Investigators

Abstract

Over the past decades, the role of computational and data science in advancing discovery has increased tremendously. NSF has played a central role in this transformation of scientific research as a funder of pioneering research activities and as a leader in enabling the use of High-Performance Computing (HPC), with Computation-based methods now becoming central to research in diverse areas of Science and Engineering (S&E). The NSF leadership-class computing facility (LCCF) program is intended to provide unique services and resources to enable discoveries in the largest and most computationally intensive S&E research frontiers that could not advance otherwise. This award supports the design and planning activities associated with the Preliminary Design (PD) of LCCF after successful completion of Conceptual Design (CD). The LCCF project proposes an advanced computing facility to enable discoveries in all fields of S&E requiring leadership computing capabilities, delivering a facility that will not only deal with the very largest challenges in S&E simulation, but also in Artificial Intelligence (AI), as well as the analysis of data from experimental and observational facilities. To deliver this goal, the LCCF project will provide a large-scale computing platform, called Horizon, with a ten-fold increase in the time-to-solution capability of the NSF's current largest system (Frontera), as well as a complete environment for managing data throughout the research lifecycle. The LCCF will also provide a software environment, supporting services, and training to ensure that researchers can effectively use the facility for maximum impact to enhance the scientific discovery process. Extensive plans for Education and Public Outreach are also planned which includes developing existing high impact formal learning programs for students, teachers, and parents, as well as construction for an informal learning environment that will be part of LCCF called the Computarium. The PD process will continue many of the activities from CD, but with a focus on improving the project plans and estimates sufficiently to make important decisions moving forward. Important PD goals are to make the final site selection for the facility, refine the science use cases into specific application targets with defined Figure of Merit performance increases, and choose the general direction of the Horizon system architecture. 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.