Paul Eller



I am a computer science PhD student at the University of Illinois at Urbana-Champaign with a research focus on scientific and high performance computing. My primary research interest is in developing and analyzing scalable numerical algorithms for extreme-scale computer systems. I have had summer internships at Sandia National Lab (Summer 2015/2016) and Argonne National Lab (Summer 2014). My advisor is Dr.William Gropp.

My PhD research is focused on investigating alternative formulations of Krylov subspace methods for solving systems of linear equations that perform well at scale on supercomputers. This research includes developing new scalable methods, analyzing the performance of parallel numeric methods in detail, and studying the performance of these algorithms within applications. I have been collaborating with other researchers on this project including Mark Hoemmen (Sandia National Lab), Paul Fischer (UIUC/Argonne National Lab), Richard Brower (Boston University), and Torsten Hoefler (ETH Zurich).

Prior to attending UIUC I spent four years working at the Engineer Research and Development Center Information Technology Laboratory in the DoD Supercomputing Research Center. My research focused on working with ERDC scientists to develop efficient parallel algorithms for a variety of hydrological, watershed, and acoustic applications that perform well on ERDC supercomputers.

I earned my Bachelor's and Master's degrees from Virginia Tech in computer science with a focus on scientific and high performance computing. I worked with Dr.Adrian Sandu to develop effective parallel numerical methods for atmospheric simulations for shared memory systems and systems with graphics processing units.