The performance of parallel algorithms by using both MPI and OPENMP

MaRDI QIDQ3068710zbMATH OpenFDO

Authors Dumitru Fanache

Publication date 17 January 2011

zbMATH Keywords

finite differences methodisoefficiencyJacobi methodparallel algorithmPoisson equationscalabilitythread

Mathematics Subject Classification ID

Laplace operator, Helmholtz equation (reduced wave equation), Poisson equation (35J05) Parallel numerical computation (65Y05)

Recommendations

• Hybrid MPI-openMP performance in massively parallel computational fluid dynamics
• Parallel application development with the hybrid MPI+OpenMP programming model
• Application of mixed MPI / OpenMP programming in a multi SMP cluster computer
• OpenMP versus MPI for PDE solvers based on regular sparse numerical operators
• A numerical study of an MPI/OpenMP implementation based on asynchronous threads for a three-dimensional splitting scheme in heat transfer problems

Cited in

(3)

• Performance comparisons of basic OpenMP constructs
• Performance characteristics for OpenMP constructs on different parallel computer architectures
• A numerical study of an MPI/OpenMP implementation based on asynchronous threads for a three-dimensional splitting scheme in heat transfer problems

This page was built for publication: The performance of parallel algorithms by using both MPI and OPENMP

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q3068710)