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

University Of Arkansas Little Rock, Little Rock AR

Investigators

Abstract

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 Network Analysis; - Hybrid Monte-Carlo/Data-Mining Modeling of the Structure-Property Relations of Polymeric 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 Interacting with Ligands, Neurotransmitters and Nano Materials; - Analysis of Soil conditions and Ground Motions for Earth Quake Related Applications