MRI/Acq.: ISTeC High Performance Computing Infrastructure for Science and Eng Research
This award is funded under the American Recovery and Reinvestment Act of 2009 (Public Law 111-5).
Project Proposed: This project, acquiring High Performance Computing (HPC) instrumentation, aims to support much larger and more complex problems in science and engineering (especially for data intensive applications), add greater physical fidelity to existing models, facilitate application of HPC to new areas of research and discovery, and support training to attract new researchers. Filling the current void in cyberinfrastructure (CI) resources, the project is expected to change the culture of discovery at the institution, elevating HPC to the level of central infrastructure. Advanced networking will facilitate the interaction of Tier-3 system with other systems, and enhance researchers? abilities to utilize Tiers 1 and 2 systems worldwide. The principal focus of the system will be data- (and often compute-) intensive applications in NSF funded research areas, such as design of extreme ultraviolet lasers, weather forecasting, computational physics, climate change, atmospheric modeling, bioinformatics, network traffic analysis, robotics, computational electromagnetics, remote sensing, robust resource allocation, and magnetic materials. Tier -3 system will expand the domain and range of computations, allowing problems of greater fidelity including multi-physics algorithms and much finer spatial and temporal resolutions. The work is carried out with CSU-Pueblo, a Hispanic-serving institution, as full partner. Broader Impacts: The existing Tier-3 will share cycles of different architectures for educational purposes: workshops, seminars, expertise via affinity groups, instructors, courses, and students. The institution, a large producer of STEM graduates, will integrate HPC into the STEM curricula and K-12 teacher training programs with emphasis on inclusion of women and minorities. Member companies of the ISTeC Industrial Advisory Council have expressed interest in participating in the activities. Existing courses support the activity through teams consisting of application experts from diverse disciplines (breadth), and mathematicians (algorithms) and computists (mapping applications and algorithms to parallel architectures) (depth).
