![Hier klicken, um den Treffer aus der Auswahl zu entfernen](images/unchecked.gif) |
Titel |
CUDA GPU based full-Stokes finite difference modelling of glaciers |
VerfasserIn |
C. F. Brædstrup, D. L. Egholm |
Konferenz |
EGU General Assembly 2012
|
Medientyp |
Artikel
|
Sprache |
Englisch
|
Digitales Dokument |
PDF |
Erschienen |
In: GRA - Volume 14 (2012) |
Datensatznummer |
250060921
|
|
|
|
Zusammenfassung |
Many have stressed the limitations of using the shallow shelf and shallow ice approximations
when modelling ice streams or surging glaciers. Using a full-stokes approach requires either
large amounts of computer power or time and is therefore seldom an option for most
glaciologists. Recent advances in graphics card (GPU) technology for high performance
computing have proven extremely efficient in accelerating many large scale scientific
computations. The general purpose GPU (GPGPU) technology is cheap, has a low power
consumption and fits into a normal desktop computer. It could therefore provide a powerful
tool for many glaciologists.
Our full-stokes ice sheet model implements a Red-Black Gauss-Seidel iterative linear
solver to solve the full stokes equations. This technique has proven very effective when
applied to the stokes equation in geodynamics problems, and should therefore also preform
well in glaciological flow probems. The Gauss-Seidel iterator is known to be robust but
several other linear solvers have a much faster convergence. To aid convergence, the
solver uses a multigrid approach where values are interpolated and extrapolated
between different grid resolutions to minimize the short wavelength errors efficiently.
This reduces the iteration count by several orders of magnitude. The run-time is
further reduced by using the GPGPU technology where each card has up to 448
cores. Researchers utilizing the GPGPU technique in other areas have reported
between 2 - 11 times speedup compared to multicore CPU implementations on similar
problems.
The goal of these initial investigations into the possible usage of GPGPU technology in
glacial modelling is to apply the enhanced resolution of a full-stokes solver to ice streams and
surging glaciers. This is a area of growing interest because ice streams are the main drainage
conjugates for large ice sheets. It is therefore crucial to understand this streaming behavior
and it’s impact up-ice. |
|
|
|
|