Effects of Ordering Strategies and Programming Paradigms on Sparse Matrix Computations

DOI10.1137/S00361445003820MaRDI QIDQ3151330zbMATH OpenOpenAlexFDO

Authors Leonid Oliker, Xiaoye Li, Parry Husbands, Rupak Biswas

Publication date 15 October 2002

Published in SIAM Review (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1137/s00361445003820

zbMATH Keywords

performancepreconditioningalgorithmorderinggraph partitioningparallel computationpreconditioned conjugate gradient methodsparse linear systemsself-avoiding walksmultithreadingmessage passinghybrid programmingpartitioning strategiesreverse Cuthill-McKee methodshared-memory directives

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Parallel numerical computation (65Y05) Complexity and performance of numerical algorithms (65Y20) Iterative numerical methods for linear systems (65F10) Numerical computation of matrix norms, conditioning, scaling (65F35)

Recommendations

• Scalable iterative solution of sparse linear systems
• Ordering techniques for the preconditioned conjugate gradient method on parallel computers
• Orderings for Parallel Conjugate Gradient Preconditioners
• Towards a cost-effective ILU preconditioner with high level fill
• Preconditioned CG methods for sparse matrices on massively parallel machines

Cited in

(9)

• Parallel finite element simulations of incompressible viscous fluid flow by domain decomposition with Lagrange multipliers
• Parallel implementations of streamline simulators
• A massive MPI parallel framework of smoothed particle hydrodynamics with optimized memory management for extreme mechanics problems
• A multi-stage preconditioner for the black oil model and its OpenMP implementation
• Parallel symmetric sparse matrix-vector product on scalar multi-core CPUs
• Algorithmic optimizations of a conjugate gradient solver on shared memory architectures
• scientific article; zbMATH DE number 1760021 (Why is no real title available?)
• Three-level hybrid vs. flat MPI on the Earth simulator: parallel iterative solvers for finite-element method
• The impact of memory organization on the performance of matrix calculations

Describes a project that uses

Uses Software

• Aztec
• Triangle
• BlockSolve95
• AztecOO

This page was built for publication: Effects of Ordering Strategies and Programming Paradigms on Sparse Matrix Computations

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3151330)