Parallel hierarchical hybrid linear solvers for emerging computing platforms

DOI10.1016/J.CRME.2010.11.005MaRDI QIDQ553205zbMATH OpenOpenAlexFDO

Authors E. Agullo, L. Giraud, Abdou Guermouche, J. Roman

Publication date 26 July 2011

Published in Comptes Rendus. Mécanique. Académie des Sciences, Paris (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1016/j.crme.2010.11.005

zbMATH Keywords

sparse matricesparallel computationparallel architecturecomputer sciencehierarchical platformhybrid direct-iterative method

Mathematics Subject Classification ID

Direct numerical methods for linear systems and matrix inversion (65F05) Computational methods for sparse matrices (65F50) Parallel numerical computation (65Y05) Iterative numerical methods for linear systems (65F10) Parallel algorithms in computer science (68W10) Numerical algorithms for specific classes of architectures (65Y10)

Recommendations

• New parallel sparse direct solvers for multicore architectures
• Hybrid Parallel Linear System Solvers
• A domain-decomposing parallel sparse linear system solver
• Preparing sparse solvers for exascale computing
• On techniques to improve robustness and scalability of a parallel hybrid linear solver

Cited in

(2)

• Robust preconditioners via generalized eigenproblems for hybrid sparse linear solvers
• PHIST: a pipelined, hybrid-parallel iterative solver toolkit

Describes a project that uses

Uses Software

• LAPACK
• PaStiX
• METIS
• PT-Scotch
• MAGMA
• PLASMA
• DAGuE

This page was built for publication: Parallel hierarchical hybrid linear solvers for emerging computing platforms

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q553205)