How can mathematical models help in the prediction of storms and hurricanes? How do they help determine the uncertainty that underlies extreme weather conditions? Understanding these answers can help reduce the human and monetary costs associated with natural disasters. CSEM Student Lindley Graham working under ICES Professor Clint Dawson, and former ICES PostDoc Troy Butler who worked under Dawson and is now at the University of Colorado, explain how such models and simulations help us better understand natural disasters in this new video produced during the international meeting of the Society for Industrial and Applied Mathematics. Read more.Posted: Dec. 9, 2014
ICES Professor Keshav Pingali is featured on a TACC podcast discussing work with researchers at the University of Illinois at Urbana-Champaign which they presented at the technical program of the supercomputing conference SC14.
Pingali, a professor of computer science, presented the first parallel implementation of two widely used reordering algorithms for sparse matrix computations. The work relied on a project called Galois, a runtime system to "effectively find what can be done in parallel while running the program itself," explained Pingali. Read more.Posted: Dec. 2, 2014
Four CSEM students earned their Ph.D. degrees this semester.
Corey Bryant under advisers Clint Dawson and Serge Prudhomme;
Michele di Pierro under adviser Ron Elber;
Ju Liu under adviser Thomas Hughes;
and Avi Taicher under advisers Todd Arbogast and Marc Hesse.
Bryant has accepted a position with Cerner Corporation in Kansas City;
di Pierro has accepted a postdoc position with Rice University;
Liu has accepted a postdoc position with Hughes' research group at ICES; Taicher is still considering his options. Read more.
ICES scientists past and present were among the team of researchers who won the Best Poster Award at Supercomputing 2014 (SC14), an international conference for high performance computing technology and research.
The team included CSEM students Johann Rudi and Tobin Isaac; Director of the ICES Center for Computational Geosciences Omar Ghattas; former ICES research scientists Georg Stadler, New York University’s Courant Institute of Mathematical Sciences and Hari Sundar, University of Utah; and Michael Gurnis, California Institute of Technology. Read more.Posted: Nov. 25, 2014
Many of the phenomena we encounter in our everyday lives, including sound, heat, and fluid flow, can be explained by a class of mathematics called partial differential equations. These equations can be solved using numerical simulations to give researchers insight into a broad range of science.
For certain applications, the number of variables required in these numerical simulations can be in the billions. Solving large-scale problems of this magnitude requires not only unprecedented computing power, but also algorithms that can harness this power to take full advantage of large-scale supercomputing systems. Read more.Posted: Nov. 13, 2014