Solutions of a steady state free surface seepage problem on a Hypercube concurrent computer
- 1 March 1989
- journal article
- Published by Emerald Publishing in Engineering Computations
- Vol. 6 (3) , 225-236
- https://doi.org/10.1108/eb023778
Abstract
The advantages of using a multi‐CPU concurrent computer in solving a steady state free surface seepage problem are studied. The underlying computational task is the solution of a large set of linear equations with a projection operation numerous times. In the study, both Jacobi and SOR iteration methods with projection in a modified alternating iteration scheme are used to solve the problem with varied number of nodes (CPUs) and the timing results are compared between a 32 node Hypercube Concurrent Computer and a VAX 11/780 (single CPU). In addition, the performance and the feasibility of the Hypercube Concurrent Computer are discussed by comparing with the number of nodes used and with the VAX 11/780.Keywords
This publication has 10 references indexed in Scilit:
- Multisplittings and parallel iterative methodsComputer Methods in Applied Mechanics and Engineering, 1987
- A Nonlinear Parallel Algorithm with Application to the Stefan ProblemSIAM Journal on Numerical Analysis, 1986
- Application of vector processors to chemical‐enhanced oil recovery simulationCommunications in Applied Numerical Methods, 1986
- Alternating iteration and elliptic variational inequalitiesNumerische Mathematik, 1985
- Solution of Partial Differential Equations on Vector and Parallel ComputersSIAM Review, 1985
- The Binary Alloy Problem: Existence, Uniqueness, and Numerical ApproximationsSIAM Journal on Numerical Analysis, 1985
- Axisymmetric free surface seepageNumerische Mathematik, 1982
- Theory of variational inequalities with applications to problems of flow through porous mediaInternational Journal of Engineering Science, 1980
- A survey of free boundary value problems in the theory of fluid flow through porous media: variational inequality approach — Part IAdvances in Water Resources, 1980
- A Survey of Parallelism in Numerical AnalysisSIAM Review, 1971