Morten Madsen

Morten Madsen

About

2
Publications
318
Reads
How we measure 'reads'
A 'read' is counted each time someone views a publication summary (such as the title, abstract, and list of authors), clicks on a figure, or views or downloads the full-text. Learn more
69
Citations

Publications

Publications (2)
Article
Full-text available
We present performance results of a mixed-precision strategy developed to improve a recently developed massively parallel GPU-accelerated tool for fast and scalable simulation of unsteady fully nonlinear free surface water waves over uneven depths (Engsig-Karup et.al. 2011). The underlying wave model is based on a potential flow formulation, which...
Article
Full-text available
We implement and evaluate a massively parallel and scalable algorithm based on a multigrid preconditioned Defect Correction method for the simulation of fully nonlinear free surface flows. The simulations are based on a potential model that describes wave propagation over uneven bottoms in three space dimensions and is useful for fast analysis and...

Network

Cited By

Projects

Projects (2)
Project
The main objective with the present study has been to investigate parallel nu- merical algorithms with the purpose of running efficiently and scalably on modern many-core heterogeneous hardware. In order to obtain good efficiency and scalability on modern multi- and many-core architectures, algorithms and data structures must be designed to utilize the underlying parallel architecture. The architectural changes in hardware design within the last decade, from single to multi and many-core architectures, require software developers to identify and properly implement methods that both exploit concurrency and maintain numerical efficiency. The project delivered a state-of-the-art library referred to as DTU Compute GPULAB Library, developed at Department of Applied Mathematics and Computer Science, Technical University of Denmark. The unique implementations of novel algorithms in the library is used to achieve massive parallelism and scalability as exemplified through the implementation of a massively parallel OceanWave3D module for coastal, offshore and marine engineering applications that runs on desktops as well as the largest super clusters in the world with unprecedented performance and temporal and spatial resolution.
Project
A collaborative open source project to research, improve and develop robust, fast and accurate open source methodologies based on flexible-order finite difference methods for large-scale fully nonlinear and dispersive free surface modelling and nonlinear wave-structure methods for marine offshore engineering applications that takes into account bathymetry. The project has been developed and hosted since 2008 at Department of Applied Mathematics and Computer Science, Technical University of Denmark (DTU). See also the website http://www2.compute.dtu.dk/~apek/OceanWave3D/. Next to this project, a more recent project MarineSEM focus on unstructured Spectral Element Methods for nonlinear wave propagation, nonlinear wave-structure and nonlinear wave-body modelling. See the new MarineSEM project : https://www.researchgate.net/project/Spectral-Element-Methods-for-Nonlinear-Waves-Wave-Structure-and-Wave-Body-modelling