Title :
PARED: a framework for the adaptive solution of PDEs
Author :
Castaños, Jose G. ; Savage, John E.
Author_Institution :
Dept. of Comput. Sci., Brown Univ., Providence, RI, USA
Abstract :
Describes our experience using PARED, an object-oriented system for the adaptive solution of partial differential equations (PDEs) in a distributed computing environment. PARED handles selective mesh refinement and coarsening, mesh repartitioning for load balancing and interprocessor mesh migration. PARED is an object-oriented system that runs on distributed memory parallel computers such as the IBM SP and networks of workstations. In this paper, we report on the use of PARED to solve 2D and 3D PDEs. We show that our object-oriented technology provides great flexibility with a small overhead to support the highly desirable adaptive features of PARED
Keywords :
IBM computers; adaptive systems; distributed memory systems; distributed programming; mathematics computing; mesh generation; object-oriented programming; partial differential equations; workstation clusters; IBM SP; PARED; adaptive solution; distributed computing environment; distributed memory parallel computers; flexibility; interprocessor mesh migration; load balancing; mesh repartitioning; object-oriented system; overhead; partial differential equations; selective mesh coarsening; selective mesh refinement; workstation networks; Boundary conditions; Computer science; Delay; Equations; Finite element methods; Load management; Mesh generation; Physics computing; Runtime; Shape measurement;
Conference_Titel :
High Performance Distributed Computing, 1999. Proceedings. The Eighth International Symposium on
Conference_Location :
Redondo Beach, CA
Print_ISBN :
0-7803-5681-0
DOI :
10.1109/HPDC.1999.805291
