Handling tens of thousands of cores with industrial/legacy codes: approaches, implementation and timings

DOI10.1016/j.compfluid.2012.09.030zbMath1290.76006MaRDI QIDQ2015972

Rainald Löhner, Joseph D. Baum

Publication date: 18 June 2014

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

Full work available at URL: https://doi.org/10.1016/j.compfluid.2012.09.030

zbMATH Keywords

massive parallelism

Mathematics Subject Classification ID

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

Related Items

Parallelizable adjoint stencil computations using transposed forward-mode algorithmic differentiation, Eddy resolving simulations in aerospace -- invited paper (Numerical Fluid 2014), A super-parallel mixed explicit discontinuous Galerkin method for the second-order Boltzmann-based constitutive models of rarefied and microscale gases, The simulation of dust effects from fragmenting charges

Uses Software

• CUDA
• FParser

Cites Work

• Edges, stars, superedges and chains
• Renumbering strategies for unstructured-grid solvers operating on shared-memory, cache-based parallel machines
• Running unstructured grid-based CFD solvers on modern graphics hardware
• Some useful strategies for unstructured edge-based solvers on shared memory machines
• Finite element flux-corrected transport (FEM-FCT) for the euler and Navier-Stokes equations
• Parallel Multilevel series k-Way Partitioning Scheme for Irregular Graphs
• Edge-based finite element scheme for the Euler equations
• Minimization of indirect addressing for edge-based field solvers
• Unnamed Item
• Unnamed Item
• Unnamed Item