Bone Structure Analysis with GPGPUs
Department of Computer Science, Eidgenossische Technische Hochschule Zurich
Eidgenossische Technische Hochschule Zurich, 2013
@phdthesis{kellenberger2013bone,
title={Bone Structure Analysis with GPGPUs},
author={Kellenberger, Daniel},
year={2013},
school={Master Thesis}
}
Osteoporosis is a disease that affects a growing number of people by increasing the fragility of their bones. To improve the understanding of the bone, large scaled computer simulations are applied. A fast, scalable and memory efficient solver for such problems is ParOSol. It uses the preconditioned conjugate gradient algorithm with a multigrid preconditioner. A modification of ParOSol is presented that profits from the exorbitant compute capabilities of recent GPGPUs. Different data-structures on the GPGPU are presented and compared. The fastest achieves a speedup of more than 5 while the code is scalable for huge numbers of GPGPUs.
July 20, 2013 by hgpu