Nathan Bell, PhD


About the speaker

Nathan Bell joined NVIDIA Research in August 2008.  He received a bachelor’s degree in Computer Science from Georgia Institute of Technology and a PhD in Computer Science from the University of Illinois at Urbana-Champaign (UIUC).

Dr Bell contributes to several open source projects including Thrust—a high-level parallel template library—, Cusp—a library for sparse matrix operations—, and PyAMG—a library of algebraic multigrid solvers in Python.

His current research interests are:

  • sparse linear solvers, and iterative methods
  • algebraic multigrid methods
  • GPU computing and programming models

Sample publications

  • Implementing sparse matrix-vector multiplication on throughput-oriented processors, N. Bell, M. Garland, in Proceedings of the Supercomputing Conference, Portland, OR (2009)
  • Algebraic Multigrid for k-form Laplacians, N. Bell, L. Olson, Numerical Linear Algebra with Applications Vol. 15: 165–185 (2008).