CC*: Campus Computing and the Computing Continuum: Campus Cluster Resource: Expanded High Performance Computing at Wayne State

CC*：校园计算和计算连续体：校园集群资源：韦恩州立大学扩展的高性能计算

• 批准号: 1925467
• 负责人: David Cinabro
• 金额: $ 39.99万
• 依托单位: Wayne State University
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2019
• 资助国家: 美国
• 起止时间: 2019-07-01 至 2020-06-30
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=1925467&HistoricalAwards=false
• 关键词: CC; Campus; Computing; Continuum; Cluster

Wayne State University has made investments in research computing including construction of a new data center, deployment of high-speed networks with global reach, and massive storage for globally accessible data. This NSF CC* project augments those existing high-performance computing resources through the addition of six high-speed, multiprocessor systems with a large amount of memory each with 1.5 terabytes and 3 NVIDIA graphic processing units (GPUs) capable of up to 120 trillion calculations per second in each system. Simulations that used to take months can be completed in days, thereby speeding research in many areas and expanding resources for the University's 275 research teams and 1,500 unique users of which 1,000 are students. The impact of this new equipment spreads across multiple disciplines including Computational Chemistry, Membrane Biophysics, Molecular Dynamics, Complex Materials and ground-breaking work in the study of Nuclear Matter and its various phases. Modeling relativistic heavy ion collisions that produce the Quark Gluon Plasma in reasonable wall times was beyond the capability of the old hardware, but with the new system such simulations can be made and help shed light on strongly coupled systems and inform the nature of the early Universe. The GPUs have special features called Tensor Flow Cores, of particular use in Artificial Intelligence, Deep Learning and Analytics. These augment research in urban and environmental health. The GPUs are also a boon for education in Wayne State's new Master of Science in Data Science joint program in Engineering, Computer Science and School of BusinessThis 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.

韦恩州立大学在研究计算方面进行了投资，包括建设一个新的数据中心，部署覆盖全球的高速网络，以及为全球可访问的数据提供大规模存储。 这个NSF CC* 项目通过增加六个高速多处理器系统来增强这些现有的高性能计算资源，这些系统具有大量内存，每个系统具有1.5 TB和3个NVIDIA图形处理单元（GPU），每个系统的计算能力高达每秒120万亿次。过去需要几个月的模拟可以在几天内完成，从而加快了许多领域的研究，并为大学的275个研究团队和1,500个独特的用户（其中1,000人是学生）扩展了资源。这种新设备的影响遍及多个学科，包括计算化学，膜生物物理学，分子动力学，复杂材料和核物质及其各个阶段研究的开创性工作。 对在合理的壁时间内产生夸克胶子等离子体的相对论重离子碰撞进行建模超出了旧硬件的能力，但使用新系统可以进行这种模拟，并有助于揭示强耦合系统并告知早期宇宙的性质。GPU具有称为张量流核心的特殊功能，特别适用于人工智能，深度学习和分析。 这些项目加强了城市和环境卫生方面的研究。 GPU也是韦恩州立大学工程、计算机科学和商学院新的数据科学联合项目理学硕士教育的布恩。该奖项反映了NSF的法定使命，并被认为值得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来支持。