Newton W. and Wilma C.Thomas Endowed Chair of Theoretical and Computational Astrophysics
Director, Joint Institute for Computational Sciences
Director, Intel® Parallel Computing Center (Intel® PCC), Joint Institute for Computational Sciences
Anthony Mezzacappa is the Newton W. and Wilma C. Thomas Endowed Chair of Theoretical and Computational Astrophysics in the Department of Physics and Astronomy at the University of Tennessee, Knoxville, and Director of the Joint Institute for Computational Sciences (JICS), and Corporate Fellow (Emeritus) at Oak Ridge National Laboratory (ORNL). Previously, he was the group leader for Theoretical Physics in ORNL’s Physics Division and the group leader for Computational Astrophysics in ORNL’s Computer Science and Mathematics Division, where he created a new research program in theoretical and computational astrophysics. Before joining ORNL in 1996, Mezzacappa held postdoctoral appointments at the University of Pennsylvania and the University of North Carolina at Chapel Hill. He completed his B.S. degree in physics at M.I.T. in 1980, his M.A. degree in physics from Columbia University in 1982, and his Ph.D. in physics at the Center for Relativity at the University of Texas at Austin in 1988. He has worked in the areas of astrophysics and cosmology, and he specializes in the theory of core collapse supernovae.
R. Glenn Brook
Chief Technology Officer, Joint Institute for Computational Sciences
Director, Application Acceleration Center of Excellence
Deputy Director, Intel PCC, Joint Institute for Computational Sciences
Glenn Brook currently directs the Application Acceleration Center of Excellence (AACE) and serves as the Chief Technology Officer at the Joint Institute for Computational Sciences (JICS) between the University of Tennessee and Oak Ridge National Laboratory. He is the principal investigator for the Beacon Project, which is funded by the National Science Foundation and the University of Tennessee to explore the impact of emerging computing technologies on computational science and engineering. Through the Beacon Project, he has managed the deployment of clusters equipped with Intel® Xeon Phi™ coprocessor (including an energy-efficient supercomputer that tops the November 2012 Green500 list), the porting of numerous application codes to the Intel Xeon Phi coprocessor architecture, the investigation of related programming approaches, and the dissemination of related knowledge and best practices through presentations and training materials. He received his Ph.D. in Computational Engineering in 2008 from the University of Tennessee.
Jeremy C. Smith
Director and Governor’s Chair
Jeremy C. Smith specializes in computational molecular biophysics, with emphasis on the high-performance simulation of biological molecules. After a postdoctoral period at Harvard with 2013 Chemistry Nobel Prize winner Martin Karplus, he led research groups in France, Germany and the United States, ranging in size from 15 to 35 members. As of May 2014 he had supervised 74 postdoctoral fellows and graduate students and his more than 340 articles had been cited over 16000 times. Fifteen former group members have moved on to tenured university professorships, five are leading junior research groups and eight hold national laboratory staff scientist positions. In 2006 Smith became the first joint ORNL-UT Governor’s Chair and is presently Director of the ORNL Center for Molecular Biophysics. In 2008 he was named Honorary Professor of the University of Heidelberg.
The Intel PCC at JICS is currently working on the following projects:
Porting and Optimization of GROMACS
GROMACS is the most highly utilized molecular dynamics program in recent years; the number of publications utilizing GROMACS exceeds 10,000 and grows by nearly 2,000 annually. GROMACS is employed for true, enterprise-level science in socially important fields such as drug design and metabolic research; consequently, it’s porting and optimization for next-generation Intel machines is expected to catalyze advances for today's scientists and tomorrow's industry. A project team at the Intel PCC at JICS, led by world-renown computational molecular biophysicist Dr. Jeremy C. Smith, is working to include support for the Intel Xeon Phi coprocessor architecture in the official, publicly available version of GROMACS and to carry out the requisite optimization to ensure world-class results.
Porting and Optimization of BLAST
BLAST is a cornerstone of many bioinformatics tool chains for sequencing genomic data. Industries that rely on this data are transforming rapidly, and the scalabilities of life sciences tool chains are not currently keeping pace with the enormous data growth provided by next-generation sequencing technology. Through efforts led by Dr. Glenn Brook and Dr. Bhanu Rekepalli, the Intel PCC at JICS is working to propel this crucial technology forward by developing a comprehensive, state-of-the-art version of BLAST for the Intel Xeon Phi coprocessor architecture that leverages techniques employed to run at scale on today's largest supercomputers. The resulting software is expected to catalyze scientific advances and to fuel a future of biotechnology and personalized medicine.
Porting and Optimization of VisIt
VisIt is a leader in open source, scientific visualization technology, which currently sees usage on a host of Top500 resources. Veteran VisIt developers Sean Ahern and Dr. Hank Childs are working to leverage the highly threaded capabilities of the Intel Xeon Phi coprocessor to provide the massively parallel visualization capabilities demanded by exascale class high performance resources. This focused effort is expected to dramatically impact the performance of scientific visualization on Intel platforms for scientists, practitioners, and decision-makers in engineering, oil and gas exploration, automotive design, aerospace, climate change, astrophysics, and many other disciplines.
- HPC-BLAST: Distributed BLAST for Intel Xeon Phi Clusters
- "The Freedom To Discover" - Optimizing Genomic Sequence Searches to Next-Generation Intel® Architectures
- Jack Dongarra, Mark Gates, Azzam Haidar, Yulu Jia, Khairul Kabir, Piotr Luszczek and Stanimire Tomov, 11/2/2014, HPC Programming on Intel Many-Integrated-Core Hardware with MAGMA port to Intel Xeon Phi, University of Tennessee
- Azzam Haidar, Piotr Luszczek, Stanimire Tomov, and Jack Dongarra, 6/1/2014, Heterogeneous Acceleration for Linear Algebra in Multi-Coprocessor Environments, University of Tennessee
- Mark Gates, Azzam Haidar, and Jack Dongarra, 6/1/2014, Accelerating computation of eigenvectors in the nonsymmetric eigenvalue problem, University of Tennessee
- Khairul Kabir, Azzam Haidar, Stanimire Tomov, 5/28/2015, Performance Analysis and Design of a Hessenberg Reduction using Stabilized Blocked Elementary Transformations for New Architectures, University of Tennessee
- Khairul kabir, Azzam Haidar, Stanimire Tomov and Jack Dongarra , 5/31/2015, Performance Analysis and Optimisation of Two-Sided Factorization Algorithms for Heterogeneous Platform, University of Tennessee
- Hartwig Anzt, Stanimire Tomov, Jack Dongarra, 2/1/2015, Energy efficiency and performance frontiers for sparse computations on GPU supercomputers, University of Tennessee
- Khairul Kabir, Azzam Haidar, Stanimire Tomov, and Jack Dongarra, 3/5/2015, On the design, development, and analysis of optimized matrix-vector multiplication routines for coprocessors, University of Tennessee
- Dr. R. Glenn Brook & Shane Sawyer, 11/19/2014, HPC-BLAST: Scaling the Life Sciences for the Intel Many Integrated Core future, IXPUG