A massively parallel adaptive finite element method with dynamic load balancing
- Rensselaer Polytechnic Inst., Troy, NY (United States). Dept. of Computer Science
- Sandia National Labs., Albuquerque, NM (United States)
- New Mexico Univ., Albuquerque, NM (United States). Dept. of Computer Science
We construct massively parallel, adaptive finite element methods for the solution of hyperbolic conservation laws in one and two dimensions. Spatial discretization is performed by a discontinuous Galerkin finite element method using a basis of piecewise Legendre polynomials. Temporal discretization utilizes a Runge-Kutta method. Dissipative fluxes and projection limiting prevent oscillations near solution discontinuities. The resulting method is of high order and may be parallelized efficiently on MIMD computers. We demonstrate parallel efficiency through computations on a 1024-processor nCUBE/2 hypercube. We also present results using adaptive p-refinement to reduce the computational cost of the method. We describe tiling, a dynamic, element-based data migration system. Tiling dynamically maintains global load balance in the adaptive method by overlapping neighborhoods of processors, where each neighborhood performs local load balancing. We demonstrate the effectiveness of the dynamic load balancing with adaptive p-refinement examples.
- Research Organization:
- Sandia National Labs., Albuquerque, NM (United States)
- Sponsoring Organization:
- USDOE, Washington, DC (United States)
- DOE Contract Number:
- AC04-76DP00789
- OSTI ID:
- 10156678
- Report Number(s):
- SAND-93-0936C; CONF-931115-2; ON: DE93012844
- Resource Relation:
- Conference: Supercomputing conference on high performance computing and communications,Portland, OR (United States),15-19 Nov 1993; Other Information: PBD: [1993]
- Country of Publication:
- United States
- Language:
- English
Similar Records
Parallel partitioning strategies for the adaptive solution of conservation laws
Parallel, adaptive finite element methods for conservation laws