Instructors
John Mellor-Crummey, Professor, Computer Science, Rice University
Mellor-Crummey's research focuses on software technology for high performance parallel computing. His ongoing research includes work on tools for measurement and analysis of application performance, compiler and run-time technology for parallel and scientific computing, application performance modeling, and compiler technology for domain-specific languages. Past work has included developing techniques for execution replay of parallel programs, efficient software synchronization algorithms for shared-memory multiprocessors, and a system for efficiently detecting data races in executions of shared-memory programs using a combination of compile-time and run-time support.
In 2006, John Mellor-Crummey and Michael L. Scott were awarded the Dijkstra Prize in Distributed Computing for their paper Algorithms for Scalable Synchronization on Shared-Memory Multiprocessors, ACM Transactions on Computer Systems, February, 1991.
Vivek Sarkar, E.D. Butcher Professor, Computer Science, Rice University
Sarkar conducts research in programming languages, program analysis, compiler optimizations and virtual machines for parallel and high performance computer systems, and currently leads the Habanero Multicore Software Research project at Rice University (habanero.rice.edu). Prior to joining Rice, he was Senior Manager of Programming Technologies at IBM Research. His responsibilities at IBM included leading IBM's research efforts in programming model, tools, and productivity in the PERCS project during 2002- 2007 as part of the DARPA High Productivity Computing System program. His past projects include the X10 programming language, the Jikes Research Virtual Machine for the Java language, the ASTI optimizer used in IBM's XL Fortran product compilers, the PTRAN automatic parallelization system, and profile-directed partitioning and scheduling of Sisal programs.
Vivek became a member of the IBM Academy of Technology in 1995, the E.D. Butcher Professor of Computer Science at Rice University in 2007, and was inducted as an ACM Fellow in 2008. He holds a B.Tech. degree from the Indian Institute of Technology, Kanpur, an M.S. degree from University of Wisconsin-Madison, and a Ph.D. from Stanford University. In 1997, he was on sabbatical as a visiting associate professor at MIT, where he was a founding member of the MIT RAW multicore project.
William Symes, Noah Harding Professor, Computational and Applied Mathematics, Rice University
Symes' current research interests center around the relation between the coefficients of linear partial differential equations and their solutions, and on so-called inverse problems posed in terms of this relation. Inverse problems for PDEs governing wave propagation are important in seismology, where the solutions represent measurable physical fields and the coefficients mostly inaccessible distributions of mechanical properties in the Earth's subsurface.
Both modeling and inversion are of great importance in seismic exploration for oil and gas as well as in environmental and engineering geophysics, crustal studies, and ocean acoustics. Professor Symes's recent work has concentrated on velocity estimation, i.e., inference of the index of refraction of the earth's interior from seismic waves recorded at the surface. To further investigation of such problems in an industrial context, Professor Symes founded The Rice Inversion Project in 1992. This industrial research consortium is sponsored by a number of firms in the oil and computer industries. Its activities encompass theoretical investigations, development of algorithms and software, and experimentation with field data.
Tim Warburton, Associate Professor, Computational and Applied Mathematics, Rice University
Over the last decade Tim has developed and analyzed discontinuous Galerkin methods for the time-domain Maxwell's equations. He has recently extended this research agenda to include the development of high order, local artificial radiation boundary conditions to provide closure for external scattering simulations. Tim's work has been funded by the AFOSR, ARO, NSF ITR, NSF DMS, and Sandia National Laboratory. He has also contributed to the development of the Nektar, USEMe, and Sledge++ software for high order finite element and discontinuous Galerkin methods on unstructured and mixed element meshes.
Tim Warburton started his academic career as an undergraduate at Oxford University studying maths. Subsequently he studied for a PhD, advised by Karniadakis, in the Division of Applied Math at Brown University. His thesis work focused on the development of high order finite element methods for computational fluid dynamics. After post doctoral stints in the Computing Laboratory at Oxford University, and with Hesthaven at Brown University he spent three years as an assistant professor in the Department of Mathematics and Statistics at the University of New Mexico. Tim is currently an associate professor in the Department of Computational and Applied Math at Rice University.
Andreas Kloeckner, Graduate Student, Applied Mathematics, Brown University
Together with his advisor Jan Hesthaven, Andreas is working on efficient solvers for the Vlasov-Maxwell model of plasma physics. His research aims to provide a particle-field coupling that reaps the benefits of high-order unstructured Discontinuous Galerkin (DG) Maxwell field solvers while remaining faithful to the complicated phase space behavior displayed by the model. A collaboration with Tim Warburton provided the opportunity to explore the use of GPUs (Graphics Processing Units) for DG solvers. This work led to the discovery of techniques that allow a single commodity GPU to perform DG computations around 50 times faster than a single core of a conventional CPU. One cornerstone of this performance gain is GPU metaprogramming, a technique supported by Andreas's PyCUDA library.
After completing his degree in applied mathematics in Karlsruhe (Germany) working on the simulation of photonic crystals, Andreas joined Jan Hesthaven's group at Brown University to work towards a doctoral degree.
Other Support Staff
Roger Moye, Linux Cluster Administrator, Rice University
Roger Moye is a member of the Research Computing Support Group (RCSG) at Rice University which is responsible for the daily operations of our shared compute clusters. During the past four years he has been responsible for systems administration, development of a scalable user account management system, end user support, and system and job debugging and troubleshooting. He has also been responsible for development of web sites and web applications which support cluster operations and technical writing for user documentation, FAQs, and RCSG policies and procedures.
Roger received a B.S. in Computer Science from Lamar University in 1993. After 2 1/2 years with Lockheed Martin at NASA-Johnson Space Center he joined Rice in 1996 where he has served many roles for the Division of Information Technology including UNIX Systems Administrator and Team Leader in the Wiess School of Natural Sciences. He obtained a Red Hat Certified Engineer (RHCE) status in 2007 and is currently enrolled in graduate school at the University of Houston - Clear Lake where he is studying Systems Engineering. He is also a member of the National Science Foundation's TeraGrid Campus Champions program to assist with and promote the use of this national computing resource on campus.
Martin Ossowski, Research Application Developer, Rice University
Ossowski received his PhD in theoretical condensed matter physics in 1998 from the University of Nebraska ? Lincoln (UNL). Following graduation he continued to work as a post-doctoral research associate in the UNL's Department of Physics and Astronomy on the first-principles computational extensions to the Gordon-Kim rigid-ion electron-gas model applied to lattice dynamics and phase transitions in complex ionic solids. In 2000 he received the National Research Council Resident Research
Associateship Award and moved to Washington, DC to work in the Naval Research Laboratory's (NRL) Center for Computational Materials Science on the development of methods and algorithms for the efficient (order-N) application of the density-functional theory. The methods developed at NRL were successfully used to study electronic, structural, elastic, and vibrational properties of complex oxides. In 2003 Ossowski joined the Research Computing Core at the University of South Florida where he served as science consultant and coordinated development of multidisciplinary computational grant proposals. While there, he also served as a courtesy assistant professor in the Department of Chemical and Biomedical Engineering. In 2007 Ossowski moved to Rice where as a member of the Research Computing Support Group he helps write efficient codes.
