Abstract
Many have stressed the limitations of using the shallow shelf and shallow ice approxima-
tions 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 com-
putations. 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 po-
werful 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 pre-
form 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 com-
pared 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.
tions 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 com-
putations. 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 po-
werful 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 pre-
form 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 com-
pared 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.
| Original language | Danish |
|---|---|
| Publication date | 25 Apr 2012 |
| Publication status | Published - 25 Apr 2012 |
| Event | EGU: General Assembly 2012 - Vienna, Austria Duration: 22 Apr 2012 → 27 Apr 2012 |
Conference
| Conference | EGU |
|---|---|
| Country/Territory | Austria |
| City | Vienna |
| Period | 22/04/2012 → 27/04/2012 |