MRI: Acquisition of a Computing Cluster for High-End Applications in Science and Engineering (CHASE)

University Of Arkansas, Fayetteville AR

Investigators

Abstract

This project, from an institution in an EPCoR state, seeking a high performance computing cluster for high-end applications, aims at supporting research in middleware development for large scale, data intensive applications, and several scientific disciplines including computation chemistry, material science, DNA analysis, multi-scale modeling, and networks. Research activities include: Development of middleware tools (Array Files) for managing, locating, and indexing data for large-scale out-of-core computational chemistry applications. Developments in Computational Chemistry: a parallel distributed memory system and an efficient parallel version of the Fourier Transform Coulomb (FTC) method for large-density functional calculations. Studies in material science using a density-functional theory (DFT) computational approach (nanostructures of FE and piezoelectric oxides and semiconductor nanomaterials). DNA Sequence design for biotechnology and nanotechnology applications (to accelerate search for large sets of non-crosshybridizing DNA sequences). Multi-scale modeling: computation of electronic and optical properties of nanodevices and crack propagation in alloys and metals. Others: Finite modeling of volcano and tectonic deformation, next generation networking, geospatial DB, and data mining. Broader Impact: Greatly increasing the opportunity for collaboration and training, the cluster would serve as a valuable asset for researchers and their students across several disciplines in an EPSCoR state. The DNA sequence library will be made publicly available. Moreover, the infrastructure provides momentum to areas in curriculum development associated with computational science.