MRI: Acquisition of a GPU Computing Cluster for UMass institute of Applied Life Sciences

这一努力，获得了一个支持图形处理单元（GPU）的高性能计算（HPC）集群，使计算密集型活动能够利用基础发现来增强转化影响。高级生命科学研究所（als）处理大数据集，其中计算起着不可或缺的作用。目前由马萨诸塞州绿色高性能计算中心（MGHPCC）提供的集群不足以满足当前在许多领域支持活动的需求，包括原子和粗粒度模拟、机器学习以及下一代生物信息学和数据科学的统计分析。GPU集群将为ials下属的27个院系和7个学院的250个研究实验室提供长期稳定的运行和管理。GPU设施提供高速单精度和双精度操作以及极端并行性，以增强有助于开放科学运动的当前活动。这一基础设施有助于整合区域教育、外联、多样性和经济活动。GPU设备将通过Internet2链接和MGHPCC的区域计算伙伴关系提供给研究人员。GPU/CPU混合设计、混合精度速度和机器学习优化架构增加了资源，可以继续开发和分发强大的分子建模、从头算动力学以及开源软件包中的计算和统计工具，从而在重大社会问题上取得快速进展。利用基础设施很可能会带来新的发展和发现，包括新的gpu支持的建模和仿真技术，可以阐明药物传递的分子机制，可再生能源和化学合成的计算设计催化剂，下一代信息学和大数据的先进计算分析工具，以及提高对乳腺癌风险和耐药性的理解。该奖项反映了美国国家科学基金会的法定使命，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 effort, acquiring a Graphic Processing Unit (GPU)-enabled High-Performance Computing (HPC) cluster, enables computation intensive activities with the aim to leverage fundamental discoveries to enhance translational impacts. The Institute for Advanced Life Science (IALS) deals with big datasets where computation plays an integral role. The current cluster provided by the Massachusetts Green High Performance Computing Center (MGHPCC) is inadequate to meet current demands to support activities in many areas including atomistic and coarse-grained simulations, machine learning, and statistical analysis for next-generation bioinformatics and data science. Providing long-term stability for operation and management, the GPU cluster will serve 250 IALS-affiliated research labs across 27 departments and 7 colleges. The GPU facility offers high speed single and double precision operations as well as extreme parallelism, to enhance current activities that contribute to the open science movement.This infrastructure contributes to efforts to integrate regional education, outreach, diversity, and economic activities. The GPU facilities will be made available to researchers through Internet2 links and regional computing partnerships at MGHPCC. The hybrid GPU/CPU design, mixed precision speed, and machine learning-optimized architecture adds resources to continue development and distribution of powerful molecular modeling, ab initio dynamics and computational and statistical tools in open source packages, enabling rapid progress on problems of great societal import. Utilizing the infrastructure will most likely lead to new developments and discoveries including novel GPU-enabled modeling and simulation technologies that may elucidate molecular mechanism of drug delivery, computational design catalysts for renewable energy and chemical synthesis, advanced computational analysis tools for next generation informatics and big data, and improved understanding of risk and resistance to breast cancer.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.