A performance model for Krylov subspace methods on mesh-based parallel computers

DOI10.1016/0167-8191(95)00057-7MaRDI QIDQ672104zbMATH OpenOpenAlexFDO

Authors E. de Sturler

Publication date 27 February 1997

Published in Parallel Computing (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/0167-8191(95)00057-7

zbMATH Keywords

sparse matrixiterative methodslinear algebralinear systems of equationsdistributed memory multiprocessorskrylov subspace method

Mathematics Subject Classification ID

Computational methods for sparse matrices (65F50) Parallel numerical computation (65Y05) Iterative numerical methods for linear systems (65F10)

Recommendations

• Krylov Subspace Methods on Supercomputers
• The performance of parallel iterative solvers
• A Comparison of Preconditioned Nonsymmetric Krylov Methods on a Large-Scale MIMD Machine
• Modified Krylov acceleration for parallel environments
• Experiments with Krylov subspace methods on a massively parallel computer

Cited in

(19)

• A parallel version of QMRCGSTAB method for large linear systems in distributed parallel environments
• Recent computational developments in Krylov subspace methods for linear systems
• Reducing the effect of global communication in \(\text{GMRES} (m)\) and CG on parallel distributed memory computers
• A Communication Optimization Scheme for Basis Computation of Krylov Subspace Methods on Multi-GPUs
• An improved parallel hybrid bi-conjugate gradient method suitable for distributed parallel computing
• An improved GBPi-CG algorithm suitable for distributed parallel computing
• A parallel generalized global conjugate gradient squared algorithm for linear systems with multiple right-hand sides
• An improved generalized conjugate residual squared (IGCRS2) algorithm suitable for distributed parallel computing
• Experiments with Krylov subspace methods on a massively parallel computer
• Communication lower bounds and optimal algorithms for numerical linear algebra
• Improved QMRCGSTAB method in distributed parallel environments
• An improved bi-conjugate residual algorithm suitable for distributed parallel computing
• Scalable algorithms for the solution of Navier's equations of elasticity
• Minimizing synchronization in \(\text{IDR}(s)\).
• Multiple search direction conjugate gradient method I: methods and their propositions
• Multiple search direction conjugate gradient method II: theory and numerical experiments
• A parallel version of GPBi-CG method suitable for distributed parallel computing
• Conjugate residual squared method and its improvement for non-symmetric linear systems
• Accuracy of the $s$-Step Lanczos Method for the Symmetric Eigenproblem in Finite Precision

Describes a project that uses

Uses Software

• P-SPARSLIB

This page was built for publication: A performance model for Krylov subspace methods on mesh-based parallel computers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q672104)