Research

Steven Dalton

Steven Dalton, Ph.D.
Research Scientist
Bio:

Steven Dalton joined NVIDIA Research in July 2014. He completed his Ph.D. in computer science at UIUC, where his research focused on mapping irregular operations on sparse matrices related to algebraic multigrid (AMG) methods to GPU architectures. Along with Nathan Bell, he was one of the primary contributors to our Cusp sparse linear algebra research library. He holds two Bachelor of Science degrees from Georgia Institute of Technology in the areas of Physics and Computer Science. He has held internships at several other organizations, including, the Federal Reserve Bank of Atlanta, Lawrence Livermore National Laboratory, and Argonne National Laboratory. He is also a 2012 recipient of the NVIDIA PhD Fellowship.

Research Interests:

His research interests include dense and sparse linear algebra, parallel graph algorithms, finite element methods, and sparse linear solvers and eigensolvers.

Publications:
Exposing Fine-Grained Parallelism in Algebraic Multigrid Methods