The Exascale Computing Project's (ECP) Center for Efficient Exascale Discretizations (CEED) collaborates with application scientists, vendors, and software technology developers to create highly optimized discretization libraries and next-generation mini applications based on advanced high-order finite element methods.
These methods are providing simulation quality without increasing computational time.
CEED follows four interlinked research-and-development thrusts concentrating on customers--applications, hardware, software, and finite elements.
"CEED helps ECP applications by providing them with leading-edge simulation algorithms that can extract much more of the performance from exascale hardware than what's currently available," says CEED director Tzanio Kolev.
The first slate of ECP apps projects involving CEED includes ExaSMR, a coupled Monte Carlo neutronics and fluid flow simulation tool of small modular nuclear reactors, and MARBL, a next-generation multiphysics code at Lawrence Livermore National Laboratory.
CEED's collaboration with vendors ensures its discretization libraries will operate efficiently on the hardware in development, while also supplying feedback on changes that can augment the performance of high-order algorithms.
View Full Article
Abstracts Copyright © 2017 Information Inc., Bethesda, Maryland, USA