The mission of the Scientific Computing Group (SCG) is to accelerate scientific progress for users of the National Center for Computational Sciences (NCCS). We work directly with users and their software and data to reach the science goals of their allocated projects. The SCG has extensive experience in algorithms, utilizing, porting, tuning, and developing software on NCCS resources. We further endeavor to serve the data-movement, workflow, analysis, and visualization needs of our user community.
The Official Group link.
| Biography | |
|---|---|
![]() |
Sean Ahern is a computer scientist and the Visualization Task Leader for the National Center for Computational Sciences at Oak Ridge National Laboratory. Prior to joining Oak Ridge, he was Visualization Project Leader within the Advanced Scientific Computing program at Lawrence Livermore National Laboratory. He has extensive experience with distributed visualization and data processing on computational clusters. He has won two R&D 100 Awards for his work on the VisIt visualization system and the Chromium cluster rendering framework. He holds degrees in Computer Science and Mathematics from Purdue University. |
![]() |
Richard Barrett is a senior research scientist in the Scientific
Computing Group within the National Center for Computational Sciences
(NCCS) at ORNL, where he is also a member of the Future Technologies
group in the Computer Science and Math division. He specializes in
parallel computing, the use of advanced computer architectures,
programming methodology, tools for parallel computers, and numerical
algorithms in linear algebra.
Prior to joining ORNL, Barrett was a member of the technical staff at Los Alamos National Laboratory from 1994-2004, where he contributed to the design and implementation of several large scale applications, mainly high fidelity multi-physics simulations, as well as several open source or licensed software packages, including UPS, L7, Maya, and MCNP. Prior to going to Los Alamos he was a charter member of the Innovative Computing Laboratory at the University of Tennessee. While there he co-authored "Templates for the Solution of Linear Systems: Building Blocks for Iterative Methods", a book aimed at scientists and engineers looking to effectively incorporate algorithms for solving large, sparse linear systems of equations on distributed memory parallel processing computing architectures. |
![]() |
Jamison R. Daniel is presently full-time research staff in the
Scientific Computing Group at ORNL where his work involves
collaboration with DOE scientists to leverage visualization as an
instrument to expedite and discover scientific insight.
In 2002, Jamison was contracted by ORNL to port the rendering engine that powered the ORNL visualization CAVE from the SGI InfiniteReality shared memory architecture to a commodity Linux distributed memory cluster using off-the-shelf graphics technology. Jamison was contracted in 2003 by the Joint Institute of Computational Sciences to serve on a visualization effort that was responsible for the construction of a prototype powerwall that would demonstrate how the technology could benefit the DOE scientific community at large. In 2004, Jamison was awarded a research contract from the Oak Ridge Associated Universities to continue development on the infrastructure and rendering engines that power the EVEREST powerwall at ORNL. Jamison received his Masters of Computer Science from the University of Tennessee in 2004 where his research in advanced computer graphics and distributed graphic architectures lead to technologies that currently power the EVEREST facility at ORNL. |
![]() |
Dr. Mark R. Fahey is presently Research & Development Staff in the
Scientific Computing Group within the National Center for
Computational Sciences (NCCS) at ORNL. He has been the primary NCCS
liaison for the fusion researchers funded by the DOE; and as such, has
ported and/or optimized several of the DOE Fusion codes (AORSA, GYRO,
NIMROD, and M3D) on NCCS computers, which include a Cray X1E, Cray
XT3, SGI Altix, and an IBM Power4. He was from 2001-2003 a Research
Scientist as part of the Joint Institute for Computational Science at
ORNL. Prior to joining ORNL, Dr. Fahey was a Research Scientist at
the Engineering Research and Development Center in Vicksburg, MS from
1998 to 2001. There he was part of the Computational Migration Group
(CMG) and later became the Director of the CMG.
Dr. Fahey received his B.A. from St. Norbert College in 1992 and his Ph.D. from the University of Kentucky in 1999. His research at the University of Kentucky in scientific computing and numerical linear algebra covered topics such as sparse and dense matrix computations, eigenvalue problems, iterative solvers, probability theory, bilinear forms, and numerical integration techniques with demonstrated applicability to problems in chemistry and physics. |
![]() |
Ricky A. Kendall is the Group Leader for the Scientific Computing
Group within the National Center for Computational Sciences at Oak
Ridge National Laboratory. His responsibilities include providing the
expert staff and the resources they need to meet the needs of the NCCS
user community. Dr. Kendall has expertise in programming models for
high performance computing, optimization of collective communications,
and computational chemistry. He joined ORNL in August of 2005 after
six years as a principle investigator in the Scalable Computing
Laboratory at the Ames Laboratory. Dr. Kendall also holds an adjunct
appointment in the Department of Computer Science at Iowa State
University. Before moving to Iowa, Dr. Kendall was a computational
scientist at Pacific Northwest National Laboratory where he was one of
the lead developers the NWChem computational chemistry suite; NWChem
was a part of the Molecular Science Software Suite that won an R&D 100
award in 1999.
Dr. Kendall received his Ph.D. in theoretical and computational chemistry from the University of Utah in 1988 and his B.S. degree in chemistry from Indiana State University. |
![]() | Dr. Scott Klasky is presently
a senior research and development scientist in the Scientific
Computing Group within the National Center for Computational Sciences
(NCCS) at ORNL. Prior to joining ORNL, he was the head of
visualization and simulation data management at the Princeton Plasma
Physics laboratory. Klasky's tasks at ORNL include working with many
of the Fusion SciDAC projects (CEMM, SWIM, GPS, CPES), and developing
end-to-end solutions for these projects.
Dr. Klasky received his BS in Physics from Drexel University in 1989. He then received a Ph.D. in physics from the University of Texas at Austin in 1994. The topic of Klasky's thesis was in numerical methods to solve elliptical partial differential equations for numerical relativity. During his time as a student, Klasky also worked as a research assistant at the Center for High Performance Computing at Texas. His work there was in the visualization group, working on developing visualization software for researchers at Texas. After receiving his Ph.D., Klasky become a postdoctoral research associate at Texas, working on advanced computing techniques for the NSF funded grand challenge, "The Binary Black Hole Grand Challenge". Between 1996 and 1999, Klasky became a senior research scientist at the Northeast Parallel Architecture Center at Syracuse University. His research centered around collaborative visualization and advance numerical methods. |
![]() |
Jeff Kuehn joined Oak Ridge National Laboratory in February of
2005. Jeff's role encompasses the evaluation of next-generation high
performance computing systems and technologies. Often these systems
are the largest practicable configuration of potential interest to the
DOE Office of Science to enable meaningful comparison and to reduce
overall program risk. The pursuit of these research and evaluation
objectives often requires developing longterm relationships with
vendors to resolve issues including system performance, scalability,
usability, stability, and managability related to the system hardware,
interconnect, and software stack. Jeff has been active in the
organization of the SCxy Conference series, serving variously as the
Tutorials Chair, Technical Papers Chair and in 2005 the Program Chair.
Prior to joining ORNL, Jeff was a member of the Scientific Computing Division at National Center for Atmospheric Research from 1990 to 2004 where he served variously as the group lead, senior software engineer, and technical lead in the application support group for the facility's supercomputers. Jeff's first project at NCAR was the massive COS to UNICOS conversion effort, in which as technical lead, Jeff played a key role in porting and tuning each of NCAR's key simulation codes to Cray Research's UNIX-based operating system. Jeff also participated in multiple supercomputer procurements with contributions from developing requirements through analyzing responses and designing, implementing and running acceptance tests. Jeff developed several incentive award winning pieces of software including a redesign of the UNICOS fairshare scheduler, the first high performance netCDF implementation, a system to identify and characterize poorly performing applications based on process accounting records, and an automated and self-documenting system testing framework used for acceptance testing, qualifying system software upgrades, configuration changes, and validating hardware. In 1992, he was the first "Linux geek" in the organization, participating in the testing and debugging of the early X11 drivers for S3 video cards and SCSI drivers for Adaptec SCSI host adapter cards. From 1988 to 1990, Jeff worked at Cray Research, Inc. on both pre-sales and post-sales projects, including benchmarking, code optimization, customer course developement, and delivery. Jeff is credited with leading an extremely successful project to develop and document a process of programming language independent performance tuning from hardware principles. The 800+ page manual with examples in C and Fortran was widely acclaimed by customers and was used extensively to deliver internal and external training on porting, parallelizing, and tuning grand challenge applications on Cray systems. Jeff's undergraduate and graduate education were in the field of Mechanical Engineering where he specialized in thermodynamics and loathed creative writing projects. |
![]() |
Dr. Bronson Messer is a Computational Scientist in the Scientific Computing group at NCCS. He has experience with large-scale supernova (both thermonuclear and core-collapse) simulations on a variety of platforms, including the Intel Paragon, the IBM Power family, the Cray C90, SV-1, X1E, XT3, and several others. In addition, he has worked on methods for nuclear network calculations and the application of genetic algorithms to the analysis of galaxy merger simulations. Prior to joining the NCCS, Dr. Messer was a Research Associate in the Department of Astronomy & Astrophysics at the University of Chicago, where he served as Deputy Group Leader for Astrophysics in the ASC Center for Astrophysical Thermonuclear Flashes. Prior to that appointment, Dr. Messer was a Research Associate with the Terascale Supernova Initiative at ORNL and the University of Tennessee. Dr. Messer was wholly educated at the University of Tennessee, earning his PhD in physics in 2000. |
![]() |
Dr. Richard Tran Mills is currently a computational scientist in
the Scientific Computing Group at the National Center for
Computational Sciences (NCCS) at ORNL. He joined the lab in 2004
after completing his Ph.D. in computer science (with specialization in
computational science) at the College of William and Mary, where he
was a Department of Energy Computational Science Graduate Fellow. He
completed his fellowship practicum at Los Alamos National Laboratory
in the Hydrology, Geochemistry, and Geology group in the Earth and
Environmental Sciences Division. As an undergraduate, he studied
geology and physics in the College Scholars program at the University
of Tennessee, Knoxville.
Dr. Mills' broad research interests are in developing and applying numerical methods and software to enable the solution of very computationally challenging problems in the natural sciences. Currently he is working on a diverse set of problems: improving the performance of sparse iterative solvers on modern vector computer architectures, coupling of MHD and energetic particle codes for simulation of magnetically confined plasmas, and modeling groundwater flow and reactive transport. |
![]() |
Dr. Arnold N. Tharrington is a computational scientist for the
Scientific Computing Group within the National Center for
Computational Sciences (NCCS) at Oak Ridge National Laboratories
(ORNL). He has recently joined ORNL and is currently the NCCS primary
liaison for the Computational Chemical Science (CCS) group.
Prior to joining ORNL, Dr. Tharrington was a Postdoctoral Fellow at the University of Utah's Center for Biophysical Modeling and Simulation. His research focused on application development of Multi State Empirical Valence Bond (MS-EVB) proton transfer models. Dr. Tharrington received his BS in physics from the College of Charleston and his PhD in physics from the University of Pittsburgh in which his graduate research was on computational simulations of phase transitions of finite atomic and molecular clusters. His current research interests are development of new force fields to describe proton transfer in biological systems and application development of highly vectorized parallel molecular dynamics algorithms. |
![]() |
Ross J. Toedte is currently a research staff member in the
Scientific Computing Group within the National Center for
Computational Sciences (NCCS) at Oak Ridge National Laboratory
(ORNL). His focus is scientific visualization in support of a variety
of basic science application areas including astrophysics, materials
science, chemistry, and combustion. He is a co-investigator of the DOE
SciDAC Terascale Supernova Initiative and has worked closely with
project physicists in the visualization of macro- and micro-scale
physics. He is also the facility manager for ORNL's EVEREST
visualization facility and was involved in its design.
Mr. Toedte has a B.A. from Southern Illinois University at Carbondale and has performed graduate studies in computer science at the University of Tennessee - Knoxville. His areas of interest, with regard to visualization, are multivariate data depiction, immersion, data management, and networking. |
![]() |
James B. White III (Trey) is presently Research & Development Staff in the Scientific Computing Group within the National Center for Computational Sciences (NCCS) at ORNL. He has been the primary NCCS liaison for climate research, and he has also worked in the areas of fusion and materials science. Prior to joining ORNL in 1999, Trey worked for the Ohio Supercomputer Center, both onsite in Columbus, Ohio, and remotely at the Engineering Research and Development Center in Vicksburg, Mississippi. He received a BS in Physics from Rhodes College in 1992 and an MS from the Ohio State University in 1996. Trey is interested in parallel programming models and languages, software design for high-performance computing, and grand-challenge computational science. |