Publications

Abstract not provided.

We discuss an electrostatics problem whose solution must lie in the set script capital L sign of all real n-by-n symmetric matrices with all row sums equal to zero. With respect to the Frobenius norm, we provide an algorithm that finds the member of script capital L sign which is closest to any given n-by-n matrix, and determines the distance between the two. This algorithm makes it practical to find the distances to script capital L sign of finite element approximate solutions of the electrostatics problem, and to reject those which are not sufficiently close. © 1999 Elsevier Science Inc. All rights reserved.

This document describes the implementation of periodic boundary conditions in the ALEGRA finite element code. ALEGRA is an arbitrary Lagrangian-Eulerian multi-physics code with both explicit and implicit numerical algorithms. The periodic boundary implementation requires a consistent set of boundary input sets which are used to describe virtual periodic regions. The implementation is noninvasive to the majority of the ALEGRA coding and is based on the distributed memory parallel framework in ALEGRA. The technique involves extending the ghost element concept for interprocessor boundary communications in ALEGRA to additionally support on- and off-processor periodic boundary communications. The user interface, algorithmic details and sample computations are given.

To ensure high levels of deterrent capability in the 21st century, new stockpile stewardship principles are being embraced at Sandia National Laboratories. The Department of Energy Accelerated Strategic Computing Initiative (ASCI) program is providing the computational capacity and capability as well as funding the system and simulation software infrastructure necessary to provide accurate, precise and predictive modeling of important components and devices. An important class of components require modeling of piezoelectric and ferroceramic materials. The capability to run highly resolved simulations of these types of components on the ASCI parallel computers is being developed at Sandia in the ElectroMechanical Modeling in Alegra (EMMA) code. This a simulation capability being developed at Sandia National Laboratories for high-fidelity modeling of electromechanical devices. these devices can produce electrical current arising from material changes due to shock impact or explosive detonation.

We describe the use of the object-oriented language C++ in the development of a hydrocode simulation system, PCTH. The system is designed to be horizontally and vertically portable from low-end workstations to next generation massively parallel supercomputers. The development of the PCTH system and the issues and rationale considered in moving to the object oriented paradigm will be discussed.