DATE: Monday, May 20, 2013
TIME: Noon - 1:00 pm
PLACE: GHC 8102
SPEAKERS: Paul Burkhardt, Chris Waring, U.S. National Security Agency, Research Directorate - R6
TITLE: An NSA Big Graph Experiment - slides
ABSTRACT:
Developing scalable graph algorithms in the Big Data era is an imposing challenge. Graph algorithms can be especially difficult to scale because of highly skewed data distribution and irregular data access patterns. Graphs at Big Data scales can exceed the physical memory of even the largest supercomputers which inhibit conventional algorithm implementations. Cloud technologies like Accumulo and MapReduce are promising for Big Graphs but require careful algorithm design to be effective. We present an experiment using Accumulo and MapReduce for Breadth-First Search (BFS) on the largest problem sizes in the Graph500.org industry benchmark.
BIO:
Paul Burkhardt is a Computer Science researcher at NSA. He received his Ph.D. from the University of Illinois at Urbana-Champaign. His current research interests are primarily focused on scalable graph algorithms and Big Data analytics.
Chris Waring is a Computer Science researcher at NSA. He received his M.S. in Computer Science from Florida State University. His current research interests are distributed computing and graph algorithms. He is also one of the founding developers of Accumulo.
HOST: Garth Gibson
VISITOR COORDINATOR: Jennifer Landefeld, 84740
SDI / ISTC SEMINAR QUESTIONS?
Karen Lindenfelser, 86716, or visit www.pdl.cmu.edu/SDI/