CC* Campus Compute: Building a Computational Cluster for Scientific Discovery

CC* 校园计算：构建科学发现计算集群

• 批准号: 2346673
• 负责人: Greg Williams
• 金额: $ 29.44万
• 依托单位: University of Colorado at Colorado Springs
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2024
• 资助国家: 美国
• 起止时间: 2024-07-01 至 2026-06-30
• 项目状态: 未结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=2346673&HistoricalAwards=false
• 关键词: CC; Campus; Compute; Building; Computational

The University of Colorado Colorado Springs (UCCS) aims to strengthen its cyberinfrastructure to meet the evolving needs of research-oriented faculty and to facilitate the increasing demands of externally funded projects. This project aims to address the growing research mission that accompanies the increase in research activities. The project enables transformative research and supports a multitude of projects in areas such as magnetic dynamics, animal biomechanics, quantum mechanics, super-resolution bio-imaging, mobile hardware architecture exploration, genomics, bioinformatics, and computational fluid dynamics. The computing hardware consists of a heterogeneous mix of compute nodes to cater to various machine learning (ML) workloads. Components include GPU-accelerated nodes, multi-core CPUs, and specialized hardware that is developed for accelerating ML and AI workloads. A high speed fabric interconnects hardware and software. UCCS shares these computing resources with groups such as Open Science Grid (OSG). By contributing to the global pool of OSG resources, the system enables advanced research across the nation. The project supports student training in IT and cyberinfrastructure, fostering diversity in the project's personnel and impact. The technical insights gained will be shared extensively within research computing and scientific communities.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.

科罗拉多大学科罗拉多斯普林斯分校 (UCCS) 旨在加强其网络基础设施，以满足研究型教师不断变化的需求，并满足外部资助项目日益增长的需求。该项目旨在解决随着研究活动的增加而不断增长的研究任务。 该项目实现了变革性研究，并支持磁动力学、动物生物力学、量子力学、超分辨率生物成像、移动硬件架构探索、基因组学、生物信息学和计算流体动力学等领域的众多项目。计算硬件由异构计算节点组合组成，以满足各种机器学习 (ML) 工作负载的需求。组件包括 GPU 加速节点、多核 CPU 以及专为加速 ML 和 AI 工作负载而开发的专用硬件。高速结构将硬件和软件互连。 UCCS 与开放科学网格 (OSG) 等组织共享这些计算资源。 通过为全球 OSG 资源库做出贡献，该系统可以在全国范围内进行高级研究。该项目支持 IT 和网络基础设施方面的学生培训，促进项目人员和影响的多样性。获得的技术见解将在研究计算和科学界广泛分享。该奖项反映了 NSF 的法定使命，并通过使用基金会的智力价值和更广泛的影响审查标准进行评估，被认为值得支持。