Hyperbolic diffusion in flux reconstruction: optimisation through kernel fusion within tensor-product elements

DOI10.1016/J.CPC.2021.108235arXiv2107.14027OpenAlexW3215537021WikidataQ114192735 ScholiaQ114192735MaRDI QIDQ6159601FDOQ6159601

F. D. Witherden, Rob Watson, W. Trojak

Publication date: 20 June 2023

Published in: Computer Physics Communications (Search for Journal in Brave)

Abstract: Novel methods are presented in this initial study for the fusion of GPU kernels in the artificial compressibility method (ACM), using tensor product elements with constant Jacobians and flux reconstruction. This is made possible through the hyperbolisation of the diffusion terms, which eliminates the expensive algorithmic steps needed to form the viscous stresses. Two fusion approaches are presented, which offer differing levels of parallelism. This is found to be necessary for the change in workload as the order of accuracy of the elements is increased. Several further optimisations of these approaches are demonstrated, including a generation time memory manager which maximises resource usage. The fused kernels are able to achieve 3-4 times speedup, which compares favourably with a theoretical maximum speedup of 4. In three dimensional test cases, the generated fused kernels are found to reduce total runtime by $sim25\mathrm{\%}$, and, when compared to the standard ACM formulation, simulations demonstrate that a speedup of $2.3$ times can be achieved.

Full work available at URL: https://arxiv.org/abs/2107.14027

zbMATH Keywords

GPUflux reconstructionartificial compressibility methodhyperbolic diffusionkernel fusion

Mathematics Subject Classification ID

Numerical methods for partial differential equations, initial value and time-dependent initial-boundary value problems (65Mxx) Computer science (68-XX)

Cites Work

• MFEM: a modular finite element methods library
• PyFR: an open source framework for solving advection-diffusion type problems on streaming architectures using the flux reconstruction approach
• A calculation procedure for heat, mass and momentum transfer in three- dimensional parabolic flows
• Small-scale structure of the Taylor–Green vortex
• A new class of high-order energy stable flux reconstruction schemes
• A numerical method for solving incompressible viscous flow problems
• Fast Poisson solvers for spectral methods
• A first-order system approach for diffusion equation. II: Unification of advection and diffusion
• Multivariate polynomial approximation in the hypercube
• A comparison of vortex and pseudo-spectral methods for the simulation of periodic vortical flows at high Reynolds numbers
• Spatial eigensolution analysis of discontinuous Galerkin schemes with practical insights for under-resolved computations and implicit LES
• A high-order cross-platform incompressible Navier-Stokes solver via artificial compressibility with application to a turbulent jet
• The \textsc{deal.II} finite element library: design, features, and insights
• Locally adaptive pseudo-time stepping for high-order flux reconstruction
• Effective high-order energy stable flux reconstruction methods for first-order hyperbolic linear and nonlinear systems
• Advanced Computational Fluid and Aerodynamics
• Inline vector compression for computational physics

Cited In (2)

• An extended range of stable flux reconstruction schemes on quadrilaterals for various polynomial bases
• A high-order entropically-damped artificial compressibility approach on moving and deforming domains

This page was built for publication: Hyperbolic diffusion in flux reconstruction: optimisation through kernel fusion within tensor-product elements

Report a bug (only for logged in users!)Click here to report a bug for this page (MaRDI item Q6159601)