GiMMiK—Generating bespoke matrix multiplication kernels for accelerators: Application to high-order Computational Fluid Dynamics

High-Order Entropy Stable Formulations for Computational Fluid Dynamics

A systematic approach is presented for developing entropy stable (SS) formulations of any order for the Navier-Stokes equations. These SS formulations discretely conserve mass, momentum, energy and satisfy a mathematical entropy inequality. They are valid for smooth as well as discontinuous flows provided sufficient dissipation is added at shocks and discontinuities. Entropy stable formulations...

High-order computational fluid dynamics tools for aircraft design.

Most forecasts predict an annual airline traffic growth rate between 4.5 and 5% in the foreseeable future. To sustain that growth, the environmental impact of aircraft cannot be ignored. Future aircraft must have much better fuel economy, dramatically less greenhouse gas emissions and noise, in addition to better performance. Many technical breakthroughs must take place to achieve the aggressiv...

On Composing Matrix Multiplication from Kernels

Matrix multiplication is often treated as a basic unit of computation in terms of which other operations are implemented, yielding high performance. In this paper initial evidence is provided that there is a benefit gained when lower level kernels, from which matrix multiplication is composed, are exposed. In particular it is shown that matrix multiplication itself can be coded at a high level ...

Application of computational fluid dynamics modelling to an ozone contactor#

Computational fluid dynamics (CFD) modelling has been applied to examine the operation of the pre-ozonation system at Wiggins Waterworks, operated by Umgeni Water in Durban, South Africa. A hydraulic model has been satisfactorily verified by experimental tracer tests. The turbulence effect induced by the gas injection was modelled by increasing the level of turbulence intensity at the ozone con...

Application of genetic algorithms to problems in computational fluid dynamics