A parallel hashed Oct-Tree N-body algorithm
Proceedings of the 1993 ACM/IEEE conference on Supercomputing
A framework approach for developing parallel adaptive multiphysics applications
Finite Elements in Analysis and Design - Special issue: The fifteenth annual Robert J. Melosh competition
Managing complexity in massively parallel, adaptive, multiphysics applications
Engineering with Computers
Parallel-adaptive simulation with the multigrid-based software framework UG
Engineering with Computers
Parallel, fully automatic hp-adaptive 3D finite element package
Engineering with Computers
ParFUM: a parallel framework for unstructured meshes for scalable dynamic physics applications
Engineering with Computers
Efficient distributed mesh data structure for parallel automated adaptive analysis
Engineering with Computers
libMesh: a C++ library for parallel adaptive mesh refinement/coarsening simulations
Engineering with Computers
| Hi-index | 0.00 |
Multi-physics HPC applications with mixed discretization schemes, adaptive unstructured meshes, and parallel distributed data sets have inherent complexity that must be managed. Design concepts embedded in the mesh data structures will either segregate complexity from, or compound complexity throughout, such applications. A recent research effort at Sandia National Laboratories is focusing on performance modeling and analysis of these complex applications. For this effort portable compact mini-applications (a.k.a. "dwarf" applications) are being developed to approximate the performance of corresponding "real" applications. For one of these mini-applications a new, fully functional, component has been developed for parallel, heterogeneous, and dynamic unstructured meshes (phdMesh). This component will be made available at software.sandia.gov. A decade of experience with a variety of target applications has led to the concise concepts, object oriented design, and minimalistic application programmer interface (API) of the phdMesh component.