Large Scale Problem Solving Using Automatic Code Generation and Distributed Visualization

Andrei Hutanu, Erik Schnetter, Werner Benger, Eloisa Bentivegna, Alex Clary, Peter Diener, Jinghua Ge, Robert Kooima, Oleg Korobkin, Kexi Liu, Frank Löffler, Ravi Paruchuri, Jian Tao, Cornelius Toole, Adam Yates, Gabrielle Allen


Scientific computation faces multiple scalability challenges
in trying to take advantage of the latest generation compute,
network and graphics hardware. We present a comprehensive
approach to solving four important scalability challenges:
programming productivity, scalability to large numbers of
processors, I/O bandwidth, and interactive visualization of large
data. We describe a scenario where our integrated system is applied in the
field of numerical relativity. A solver for the governing
Einstein equations is generated and
executed on a large computational cluster; the simulation output is
distributed onto a distributed data server, and finally visualized
using distributed visualization methods and high-speed networks.
A demonstration of this system was awarded first place in the
IEEE SCALE 2009 Challenge.


Full Text: PDF


  • There are currently no refbacks.