Houston, TX 77005
1:15 p.m. Friday, April 12, 2013
On Campus | Alumni
This thesis presents a GPU accelerated solver that implements a high order splitting scheme for a spectral element solution of the incompressible Navier Stokes (INS) equations. While others have implemented this scheme on clusters of processors using the Nek5000 code, to my knowledge this thesis is the first to explore its performance on the GPU. This work implements several of the Nek5000 algorithms using OpenCL kernels that take advantage of the GPU memory architecture, allowing for massively parallel computations. These rapid computations have the potential to significantly enhance computational fluid dynamics (CFD) simulations that arise in areas such as weather modeling or aircraft design procedures. I present convergence results for several test cases, namely channel, shear, Kovasznay, and lid-driven cavity flow problems, which agree with proven convergence results. Thus, this thesis shows that using GPUs on a single workstation to implement this splitting scheme achieves comparable results to those when using thousands of CPU-like processors.