The Extreme-scale Algorithms and Software Institute (EASI), formed by Oak Ridge National Laboratory, Sandia National Laboratories and the Universities of Illinois, Tennessee, and California Berkeley, focuses on closing the application-architecture performance gap through architecture-aware algorithms and libraries, and the supporting runtime capabilities to achieve scalable performance and resilience on heterogeneous architectures.
Specifically, EASI aims at: (1) studying and characterize the application-architecture performance gaps that we can address in the near-term and identify architecture features that future systems may want to incorporate; (2) developing multi-precision and architecture-aware implementations of Krylov, Poisson and Helmholtz solvers, and dense factorizations for heterogeneous multi-core systems; (3) exploring new methods of algorithm resilience, and develop new algorithms with these capabilities; (4) developing runtime support for adaptable algorithms dealing with resilience, scalability, and performance; (5) demonstrating architecture-aware algorithms in full U.S. Department of Energy (DOE) applications on large-scale DOE architectures; (6) distributing the new algorithms and supporting runtime capabilities through widely used software packages; and (7) establishing a strong outreach program to disseminate results, interact with colleagues and train students and junior members of our community.
Solutions
Funding Sources
- Office of Advanced Scientific Computing Research, Office of Science, U.S. Department of Energy
Participating Institutions
- Oak Ridge National Laboratory
- Sandia National Laboratory
- University of Illinois at Urbana-Champaign
- University of California at Berkeley
- University of Tennessee, Knoxville
Peer-reviewed Journal Publications
- Christian Engelmann. Scaling To A Million Cores And Beyond: Using Light-Weight Simulation to Understand The Challenges Ahead On The Road To Exascale. Future Generation Computer Systems (FGCS), volume 30, number 0, pages 59-65, January 1, 2014. Elsevier B.V, Amsterdam, The Netherlands. ISSN 0167-739X. DOI 10.1016/j.future.2013.04.014.
Peer-reviewed Conference Publications
- Christian Engelmann. Investigating Operating System Noise in Extreme-Scale High-Performance Computing Systems using Simulation. In Proceedings of the 11th IASTED International Conference on Parallel and Distributed Computing and Networks (PDCN) 2013, Innsbruck, Austria, February 11-13, 2013. ACTA Press, Calgary, AB, Canada. ISBN 978-0-88986-943-1. DOI 10.2316/P.2013.795-010.
Talks and Lectures
- Christian Engelmann. Scaling To A Million Cores And Beyond: A Basic Understanding Of The Challenges Ahead On The Road To Exascale. Invited talk at the 1st International Workshop on Extreme Scale Parallel Architectures and Systems (ESPAS) 2012, in conjunction with the 7th International Conference on High-Performance and Embedded Architectures and Compilers (HiPEAC) 2012, Paris France, January 24, 2012.
Symbols: Abstract, Publication, Presentation, BibTeX Citation