HIGH-PERFORMANCE COMPUTATIONAL PLATFORM FOR MULTI-PHYSICS MODELING OF ADVANCED PROPULSION AND ENERGY SYSTEMS
Abstract
This proposal requests funding for a 9000-core (0.3 PetaFlops) AMD CPU cluster, including three 8-card Nvidia V100S GPU nodes (0.2 PetaFlops), and one 8-card Nvidia T4 GPU machinelearning (ML) specialty node, along with a 2 PetaByte high throughput data server. The facility is designed to have the capability of conducting unclassified research, which can be shared campuswide and potentially state- and nation-wide. The proposed facility will be housed and maintained as part of the UConn HPC facility, located at the UConn main campus in Storrs, CT. In addition, support and maintenance of hardware and software will be provided and by the University (see letter of support). The PIs have and will continue to work closely with AFOSR, AFRL, Pratt and Whitney (PW, see letter of support), and Raytheon Technologies Research Center (RTRC, see letter of support), in uncovering the complex physics in advanced propulsion technologies and energy systems. The partnership will further flourish with the strengthened research capabilities from the PIs and improved student training at UConn, enabled by the proposed facility.
Document Details
- Document Type
- DoD Grant Award
- Publication Date
- Mar 07, 2023
- Source ID
- FA95502210157
Entities
People
- Xinyu Zhao
Organizations
- Air Force Office of Scientific Research
- United States Air Force
- University of Connecticut