Presenter

Daniel Ganellari is a PhD researcher at the institute of mathematics and scientific computing of the University of Graz, Austria. His main areas of research are parallel computational methods for PDEs and high performance computing with accelerators and mobile processors. His conference poster relates to his PhD thesis: ''Fast many core solvers for the Eikonal equations in cardiovascular simulations'' wherein a special focus is put on transferring the parallel Eikonal solver to android mobile embedded devices incorporating innovative mobile processors and accelerators such as Tegra X1. The poster presents the method used to reduce the memory footprint which improves the performance on such devices with limited high-memory bandwidth. It discusses a domain decomposition approach in CUDA for the Eikonal solver and its application on patient specific cardiac parametrization using automatic differentiation tools for the optimization process.