Implementation of an ADI method on parallel computers

DOI10.1007/BF01061485MaRDI QIDQ1116648zbMATH OpenFDO

Authors Raad A. Fatoohi, C. E. Grosch

Publication date 1987

Published in Journal of Scientific Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1007/BF01061485

zbMATH Keywords

ADI methodalternating direction implicit methodcyclic eliminationdiffusion equationGaussian eliminationMIMD machineparallel algorithmperformance analysisSIMD machine

Mathematics Subject Classification ID

Heat equation (35K05) Iterative numerical methods for linear systems (65F10) Numerical solution of discretized equations for boundary value problems involving PDEs (65N22) Parallel numerical computation (65Y05)

Review text

We discuss the implementation of an ADI method for solving the diffusion equation on three parallel/vector computers. The computers were chosen so as to encompass a variety of architectures. They are the MPP, an SIMD machine with 16-Kbit serial processors; Flex/32, an MIMD machine with 20 processors; and Cray/2, an MIMD machine with four vector processors. The Gaussian elimination algorithm is used to solve a set of tridiagonal systems on the Flex/32 and Cray/2 while the cyclic elimination algorithm is used to solve these systems on the MPP. The implementation of the method is discussed in relation to these architectures and measures of the performance on each machine are given. Simple performance models are used to describe the performance. These models highlighting the bottlenecks and limiting factors for this algorithm on these architectures. Finally conclusions are presented.

Recommendations

• A parallel DSDADI method for solution of the steady state diffusion equation
• Parameter choices for ADI-like methods on parallel computers
• scientific article; zbMATH DE number 1844549
• scientific article; zbMATH DE number 1756120
• scientific article; zbMATH DE number 3924019

Cites work

• A Survey of Parallel Algorithms in Numerical Linear Algebra
• scientific article; zbMATH DE number 3829220 (Why is no real title available?)
• scientific article; zbMATH DE number 3924012 (Why is no real title available?)
• Implementation of an ADI method on parallel computers

Cited in

(11)

• On optimal message vector length for block single parallel partition algorithm in a three-dimensional ADI solver
• Implementation of an ADI method on parallel computers
• Efficient decomposition and performance of parallel PDE, FFT, Monte Carlo simulations, simplex, and sparse solvers
• Stochastic modelling of diffusion equations. Implementation and performance of the Mixage3D code on a multinode parallel machine based on the transputer T9000
• A case study in scalability: An ADI method for the two-dimensional time-dependent Dirac equation
• A class of Adams-type parallel hybrid algorithms
• Alternating Direction Methods on Multiprocessors
• scientific article; zbMATH DE number 5353274 (Why is no real title available?)
• scientific article; zbMATH DE number 1756120 (Why is no real title available?)
• scientific article; zbMATH DE number 2201207 (Why is no real title available?)
• Multitasking a Navier-Stokes algorithm on the CRAY-2

This page was built for publication: Implementation of an ADI method on parallel computers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1116648)