Experimenting task-based runtimes on a legacy computational fluid dynamics code with unstructured meshes

DOI10.1016/J.COMPFLUID.2018.03.076MaRDI QIDQ1615455zbMATH OpenOpenAlexFDO

Authors Emmanuel Jeannot, Yvan Fournier, Benjamin Lorendeau

Publication date 31 October 2018

Published in Computers and Fluids (Search for Journal in Brave)

Full work available at URL https://hal.inria.fr/hal-01901975/file/parcfd_2017_lorendeau.pdf

zbMATH Keywords

unstructured meshestasksCode\_Saturneruntime systemsPaRSEC

Mathematics Subject Classification ID

Software, source code, etc. for problems pertaining to fluid mechanics (76-04)

Recommendations

• Productivity, performance, and portability for computational fluid dynamics applications
• Optimizing Code\_Saturne computations on Petascale systems
• Semi-automatic porting of a large-scale Fortran CFD code to GPUs
• Optimization of a discontinuous Galerkin solver with OpenCL and StarPU
• Parallelization for unstructured adaptive mesh CFD algorithm

Cites work

• Code Saturne: a finite volume code for the computation of turbulent incompressible flows -- industrial applications
• Compact DAG representation and its symbolic scheduling
• Optimizing Code\_Saturne computations on Petascale systems

Cited in

(3)

• Optimization of a discontinuous Galerkin solver with OpenCL and StarPU
• Asynchronous task based Eulerian-Lagrangian parallel solver for combustion applications
• Superglue: a shared memory framework using data versioning for dependency-aware task-based parallelization

Describes a project that uses

Uses Software

• OmpSs
• DAGuE
• StarPU
• Code_Saturne

This page was built for publication: Experimenting task-based runtimes on a legacy computational fluid dynamics code with unstructured meshes

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q1615455)