Statistical Engineering Division
Seminar Series
Data Intensive Analysis and Visualization Projects at ONRL
George Ostrouchov and Nagiza F. Samatova
Oak Ridge National Laboratory
Room 618, NIST North
May 6, 2004, 1:00pm
Terascale computing enables simulations of complex natural phenomena
on a scale not possible just a few years ago. With this opportunity,
comes a new problem - the massive quantities of data produced by'
these simulations. Facilitating analysis of these massive data sets
requires innovations in hardware, infrastructure, software, and
algorithms. We have made progress in several of these directions by
developing faster algorithms, parallel and distributed algorithms,
porting to new parallel hardware, integrating scalable infrastructure
components, and in developing application specific analysis and
visualization methodology. This talk will describe some of these
components and some experiences with astrophysics and climate
simulation data.
George Ostrouchov is a Senior Research Staff Member in the
Statistics and Data Sciences Group of the Computer Science and
Mathematics Division and Adjunct Professor of Statistics at the
University of Tennessee. He obtained his Ph.D. and M.Sc. in
Statistics from Iowa State University after undergraduate work in
mathematics and statistics at the University of Waterloo in Canada.
George's current responsibilities include research and management of
research in data intensive applications involving large-scale
computational problems in statistics and data analysis.
NIST Contact:
Charles Hagwood, x-2846.
