Equipment: CC* Campus Compute: A High-Performance Computing System for Research and Education in Arkansas

University Of Arkansas, Fayetteville AR

Investigators

Abstract

This award updates computing resources in the Arkansas High Performance Computing Center (AHPCC) to support research and education in Arkansas, an EPSCoR state. AHPCC is based at the University of Arkansas and supports higher education institutions in the state, including the University of Arkansas at Pine Bluff (an HBCU), Arkansas Tech University, the University of Arkansas at Little Rock, the University of Arkansas for Medical Sciences, Philander Smith University (an HBCU), and others. This acquisition doubles all-user CPU capacity on a much more efficient system, adding 37 dual-socket server computers interconnected with a 100 Gb/s InfiniBand HDR-100 network and including supporting equipment such as an administrative Ethernet network, and two computer racks with power distribution, and water cooling. The system supports research aligned with data science engineering, artificial intelligence, computational physics, materials science, biology, chemistry, and biochemistry, and continues a tradition of high-impact discoveries enabled by AHPCC. Examples of cutting-edge science enabled by this acquisition include: model order reduction and physics-based machine learning algorithms, new 2D multiferroics and materials for neuromorphic computing, dynamics of soft capsules within nano-channels, and assessing global warming through microbial evolution. Research activities to recruit, train and prepare the STEM workforce are also supported, especially in data-analytics, for which there is a strong need from local companies. The research and technical teams publish research in journals and conferences and deliver lecture series and workshops that train statewide users on High Performance Computing technologies and attract new users. The award ensures an increased participation of highly qualified women and under-represented faculty and students, helping create a more diverse workforce. This instrument is part of the Open Science Grid Consortium. This award by the Office of Advanced Cyberinfrastructure is jointly supported by the Established Program to Stimulate Competitive Research (EPSCoR). 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.