Minimization of indirect addressing for edge-based field solvers

DOI10.1002/CNM.494MaRDI QIDQ4543645zbMATH OpenOpenAlexFDO

Authors Rainald Löhner, Martin Galle

Publication date 8 August 2002

Published in Communications in Numerical Methods in Engineering (Search for Journal in Brave)

Full work available at URL https://doi.org/10.1002/cnm.494

zbMATH Keywords

grid renumberingloop structurevector-parallel machines

Mathematics Subject Classification ID

Parallel numerical computation (65Y05) Software, source code, etc. for problems pertaining to fluid mechanics (76-04) Basic methods in fluid mechanics (76M99)

Recommendations

• Edges, stars, superedges and chains
• Performance comparison of data-reordering algorithms for sparse matrix–vector multiplication in edge-based unstructured grid computations
• Cache-efficient renumbering for vectorization
• Some useful strategies for unstructured edge-based solvers on shared memory machines
• Renumbering strategies for unstructured-grid solvers operating on shared-memory, cache-based parallel machines

Cites work

• An unstructured grid-based, parallel free surface solver
• Edges, stars, superedges and chains
• Renumbering strategies for unstructured-grid solvers operating on shared-memory, cache-based parallel machines
• Some useful renumbering strategies for unstructured grids

Cited in

(11)

• Parallel edge-based solution of viscoplastic flows with the SUPG/PSPG formulation
• Parallel implementation of the finite element method using compressed data structures
• A Jacobian-free edge-based Galerkin formulation for compressible flows
• Edges, stars, superedges and chains
• Handling tens of thousands of cores with industrial/legacy codes: approaches, implementation and timings
• Detailed simulation of viral propagation in the built environment
• On the development of high-performance C++ object-oriented code with application to an explicit edge-based fluid dynamics scheme
• The simulation of dust effects from fragmenting charges
• Some useful strategies for unstructured edge-based solvers on shared memory machines
• Execution of a parallel edge-based Navier–Stokes solver on commodity graphics processor units
• A symmetric interior-penalty discontinuous Galerkin isogeometric analysis spatial discretization of the self-adjoint angular flux form of the neutron transport equation

This page was built for publication: Minimization of indirect addressing for edge-based field solvers

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q4543645)