Award Abstract #0851743
REU Site: High Performance Filesystems and Data Visualization

NSF Org:	CCF Division of Computer and Communication Foundations
Initial Amendment Date:	March 17, 2009
Latest Amendment Date:	March 17, 2009
Award Number:	0851743
Award Instrument:	Standard Grant
Program Manager:	Tracy J. Kimbrel CCF Division of Computer and Communication Foundations CSE Directorate for Computer & Information Science & Engineering
Start Date:	May 1, 2009
Expires:	April 30, 2012 (Estimated)
Awarded Amount to Date:	$275000
Investigator(s):	Hans-Peter Bischof hpb@cs.rit.edu (Principal Investigator) Minseok Kwon (Co-Principal Investigator)
Sponsor:	Rochester Institute of Tech 1 LOMB MEMORIAL DR ROCHESTER, NY 14623 585/475-7525
NSF Program(s):	RSCH EXPER FOR UNDERGRAD SITES
Field Application(s):	0000912 Computer Science
Program Reference Code(s):	HPCC, 9251, 9218, 9152, 9150
Program Element Code(s):	1139

ABSTRACT

Simulations of galactic events such as black hole and galaxy mergers

allow scientists to understand the fundamental nature of the universe.

These simulations create terabytes of data, which are extremely difficult

and time consuming to analyze using traditional mathematical tools and

techniques. To address these challenges, scientists often use data

visualization, which provides a powerful and effective approach to

understand interactions and behavior of simulations such as visualizing

the radiation of gravity waves during a supermassive black hole merger.

Visualization systems require high performance file-systems for efficient

data management. Over the last three years, a collaborative effort

between the Computer Science Department and the Center for Computational

Relativity and Gravitation at Rochester Institute of Technology resulted

in a visualization framework called Spiegel that has been used successfully

to analyze and visualize the simulation of a variety of galactic events.

This REU site provides students with the opportunity, environment and support

to conduct research in data visualization and high-performance file systems

using Spiegel as the starting point. Working in a collaborative and

interdisciplinary environment, students develop solutions to a broad set

of research problems in performing computation on massive amounts of

multi-dimensional data. Consequently, students gain knowledge in understanding,

critiquing, and presenting research literature. This project offers students

opportunities to work on state-of-the-art computing techniques that are

increasingly vital for solving research problems in modern scientific

disciplines. Undergraduate students are encouraged to pursue interdisciplinary

graduate studies in STEM disciplines. With specific recruiting efforts that

target underrepresented groups such as women, minorities, and persons with

disabilities, especially deaf and hard-of-hearing students, this REU program

also aims to increase the size and diversity of the scientific workforce.

Please report errors in award information by writing to: awardsearch@nsf.gov.