A parallel solution of large-scale heat equation based on distributed memory hierarchy system

Authors:
Tangpei Cheng;Qun Wang;Xiaohui Ji;Dandan Li
Affiliations:
School of Information Engineering, China University of Geosciences (Beijing), Beijing, P.R. China;School of Information Engineering, China University of Geosciences (Beijing), Beijing, P.R. China;School of Information Engineering, China University of Geosciences (Beijing), Beijing, P.R. China;School of Information Engineering, China University of Geosciences (Beijing), Beijing, P.R. China
Venue:
ICA3PP'10 Proceedings of the 10th international conference on Algorithms and Architectures for Parallel Processing - Volume Part II
Year:
2010

Citing 7
Cited 0

Adapting a parallel sparse direct solver to architectures with clusters of SMPs

Parallel Computing - Special issue: Parallel and distributed scientific and engineering computing
An approximate inverse preconditioner and its implementation for conjugate gradient method

Parallel Computing
Relaxed RS0 or CLJP coarsening strategy for parallel AMG

Parallel Computing
Parallel Arnoldi eigensolvers with enhanced scalability via global communications rearrangement

Parallel Computing
Optimizing a conjugate gradient solver with non-blocking collective operations

Parallel Computing
A partitioning algorithm for block-diagonal matrices with overlap

Parallel Computing
GREMLINS: a large sparse linear solver for grid environment

Parallel Computing

Quantified Score

Hi-index	0.00

Visualization

Abstract

A parallel scheme for distributed memory hierarchy system is presented to solve the large-scale three-dimensional heat equation. Since managing interprocess communications and coordination is the main difficulty with the system, the local physics/global algebraic object paradigm is introduced. Domain decomposition method is used to partition the modeling area, as well as the intensive computational effort and large memory requirement. Efficient storage and assembly of sparse matrix and parallel iterative solution of linear system are considered and developed. The efficiency and scalability of the parallel program are demonstrated by completing two experiments on Linux cluster, in which different preconditioning methods are tested and analyzed. And the results demonstrate this method could achieve desirable parallel performance.