![Hier klicken, um den Treffer aus der Auswahl zu entfernen](images/unchecked.gif) |
Titel |
Scalable geocomputation: evolving an environmental model building platform from single-core to supercomputers |
VerfasserIn |
Oliver Schmitz, Kor de Jong, Derek Karssenberg |
Konferenz |
EGU General Assembly 2017
|
Medientyp |
Artikel
|
Sprache |
en
|
Digitales Dokument |
PDF |
Erschienen |
In: GRA - Volume 19 (2017) |
Datensatznummer |
250150503
|
Publikation (Nr.) |
EGU/EGU2017-14973.pdf |
|
|
|
Zusammenfassung |
There is an increasing demand to run environmental models on a big scale: simulations over
large areas at high resolution. The heterogeneity of available computing hardware such as
multi-core CPUs, GPUs or supercomputer potentially provides significant computing power
to fulfil this demand. However, this requires detailed knowledge of the underlying hardware,
parallel algorithm design and the implementation thereof in an efficient system programming
language. Domain scientists such as hydrologists or ecologists often lack this specific
software engineering knowledge, their emphasis is (and should be) on exploratory building
and analysis of simulation models. As a result, models constructed by domain specialists
mostly do not take full advantage of the available hardware. A promising solution
is to separate the model building activity from software engineering by offering
domain specialists a model building framework with pre-programmed building
blocks that they combine to construct a model. The model building framework,
consequently, needs to have built-in capabilities to make full usage of the available
hardware.
Developing such a framework providing understandable code for domain scientists and
being runtime efficient at the same time poses several challenges on developers of such a
framework. For example, optimisations can be performed on individual operations or the
whole model, or tasks need to be generated for a well-balanced execution without explicitly
knowing the complexity of the domain problem provided by the modeller. Ideally, a
modelling framework supports the optimal use of available hardware whichsoever
combination of model building blocks scientists use. We demonstrate our ongoing work on
developing parallel algorithms for spatio-temporal modelling and demonstrate 1)
PCRaster, an environmental software framework (http://www.pcraster.eu) providing
spatio-temporal model building blocks and 2) parallelisation of about 50 of these
building blocks using the new Fern library (https://github.com/geoneric/fern/), an
independent generic raster processing library. Fern is a highly generic software
library and its algorithms can be configured according to the configuration of a
modelling framework. With manageable programming effort (e.g. matching data types
between programming and domain language) we created a binding between Fern and
PCRaster. The resulting PCRaster Python multicore module can be used to execute
existing PCRaster models without having to make any changes to the model code. We
show initial results on synthetic and geoscientific models indicating significant
runtime improvements provided by parallel local and focal operations. We further
outline challenges in improving remaining algorithms such as flow operations over
digital elevation maps and further potential improvements like enhancing disk I/O. |
|
|
|
|
|