CRI: II-EN: Stream Computing for Research and Education in Science and Engineering

CRI：II-EN：用于科学与工程研究和教育的流计算

• 批准号: 0855248
• 负责人: Kenji Yoshigoe
• 金额: $ 40万
• 依托单位: University of Arkansas Little Rock
• 依托单位国家: 美国
• 项目类别: Standard Grant
• 财政年份: 2009
• 资助国家: 美国
• 起止时间: 2009-09-01 至 2012-08-31
• 项目状态: 已结题
• 来源: https://www.nsf.gov/awardsearch/showAward?AWD_ID=0855248&HistoricalAwards=false
• 关键词: CRI; II; EN; Stream; Computing

This project supports the storage system enhancement to an existing high performance cluster (HPC) already located at PI?s institution to address continuously increasing I/O and data intensive computing need among the participating institutions and beyond. While sharing physical resources among multiple institutions is clearly cost-effective, protection of data and privacy is an ongoing concern that inhibits large-scale cooperative resource sharing. The multi-terabyte data storage system deployment at a remote institution with multi-gigabit connections achieves fast migration of research data for seamless computing while achieving maximum protection of the data at the remote site. The system allows research collaborators to stream real-time data to the HPC; thereby supporting remote HPC facilities for their computational needs. When successful, time-sensitive applications such as disaster response / emergency preparedness systems can be executed in an ad-hoc manner. The networked HPC infrastructure provides optimal access to areas of the state that remain less supported; thereby supporting the needs of the broader science and engineering communities. The acquired system will enable collaborative research including the following:- Data-Mining, Prediction and Data Analysis Frameworks Using Social NetworkAnalysis;- Hybrid Monte-Carlo/Data-Mining Modeling of the Structure-Property Relations ofPolymeric Materials;- Biomedical Image Processing (Treatment Planning/Tumor Detection/Genome wide high throughput SNP analysis of Human Spit);- Detection and Analyses of Electrophysiological Signals from Neurons Interactingwith Ligands, Neurotransmitters and Nano Materials;- Analysis of Soil conditions and Ground Motions for Earth Quake Related Applications

此项目支持对已位于PI？的现有高性能群集（HPC）进行存储系统增强。的机构，以满足不断增加的I/O和数据密集型计算的需求之间的参与机构和超越。虽然在多个机构之间共享物理资源显然具有成本效益，但数据和隐私保护是一个持续的问题，阻碍了大规模的合作资源共享。在具有多千兆位连接的远程机构部署的多TB数据存储系统实现了研究数据的快速迁移，以实现无缝计算，同时实现了对远程站点数据的最大保护。该系统允许研究合作者将实时数据流传输到HPC，从而支持远程HPC设施满足其计算需求。如果成功，可以以临时方式执行对时间敏感的应用程序，如灾害响应/应急准备系统。 联网的HPC基础设施为该州仍然不太受支持的地区提供了最佳访问，从而支持更广泛的科学和工程社区的需求。所收购的系统将实现以下合作研究：-使用社会网络分析的数据挖掘，预测和数据分析框架;-聚合物材料结构-性能关系的混合蒙特-卡罗/数据挖掘建模;-生物医学图像处理（治疗计划/肿瘤检测/人类Spit的全基因组高通量SNP分析）;- 检测和分析神经元与配体、神经递质和纳米材料相互作用的电生理信号;- 用于地震相关应用的土壤条件和地面运动分析