CC* Compute: A HPC Cluster for Science Research and Education at Tennessee Tech University

该奖项全部或部分由2021年美国救援计划法案（公法117-2）资助。田纳西理工大学（TN Tech）的研究人员正在对校园计算基础设施进行重大升级，这将显着提高大学研究人员和学生执行，增强和扩展其面向系统，面向算法或面向应用的研究活动的能力。这种增强的新计算基础设施补充了TN Tech已经进行、正在进行或计划中的其他投资。这个现代化的校园集群将使TN Tech能够通过扩大其目前NSF资助的网络培训活动来发展和维持HPC文化，以包括来自东南部资源有限的机构的数百名教师和他们的本科生。 这一新的集群将帮助TN Tech建立一个区域性的计算能力和劳动力发展资源，为该地区代表性不足的群体扩大机会。这一合同使TN Tech能够采购最先进的、具有成本效益的10节点GPU集群，支持20个NVIDIA A100 GPU、1280个AMD Epyc 2 CPU内核和5 TiB主内存，并连接100 Gbit/s Infiniband。 该群集提供了以前在园区内无法提供的功能。该项目团队预计在计算流体动力学，生物力学和地理空间分析，这将涉及四个合作大学的重大研究项目。17个正在进行的研究项目，包括3个教学项目，将直接受益于改善的基础设施。随着PI和计划中的内部咨询委员会吸引更多需要异构HPC的研究人员和学生，随着时间的推移，将启用更多的研究项目。项目团队预计将有100名左右的工学院博士。该奖项反映了NSF的法定使命，并通过使用基金会的知识价值和更广泛的影响审查标准进行评估，被认为值得支持。

This award is funded in whole or in part under the American Rescue Plan Act of 2021 (Public Law 117-2).Researchers at Tennessee Tech University (TN Tech) are making significant upgrades to the campus computing infrastructure that will significantly improve the university researchers’ and students’ ability to perform, enhance, and expand their systems-oriented, algorithms-oriented, or applications-oriented research activities. This enhanced new computing infrastructure complements other investments already made, in-progress, or in-planning at TN Tech. This modern campus cluster will enable TN Tech to grow and sustain the HPC culture by expanding on its current NSF-funded CyberTraining activities to include hundreds of faculty and their undergraduate students from resource-limited institutions from across the southeast. This new cluster will help TN Tech to build a regional resource for computational capacity and workforce development expanding opportunities to underrepresented groups in the region.This award allows TN Tech to procure a state-of-the-art, cost-effective 10 node GPU cluster supporting 20 NVIDIA A100 GPUs, 1280 AMD Epyc2 CPU cores, and 5 TiB of main memory connected with 100 Gbit/s Infiniband. The cluster provides capabilities not previously available on campus. This project team anticipates significant research projects in computational fluid dynamics, biomechanics, and geospatial analysis, which will engage four partner universities. Seventeen ongoing research projects including 3 teaching projects will directly benefit from the improved infrastructure. Additional research projects will be enabled over time as the PIs and the planned internal advisory committee attract additional researchers and students requiring heterogeneous HPC. The project team expects about 100 of College of Engineering Ph.D. students will use the HPC infrastructure for their research.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.