
NOAA HPCC NGI
Computational
Grid Projects
Dan Schaffer, Paul Hyder, Mark Govett (FSL)
Chris Moore, Al Hermann (PMEL)
Brian Gross, Ron Bewtra (GFDL)
NOAA scientific research is supported by thousands of computers scattered throughout the laboratories ranging from individual workstations to large-scale clusters. Most of these resources are only available to local users. A lack of connectivity inhibits sharing between or even within labs. As a result, huge numbers of compute cycles go unused and opportunities are lost to increase the scale of scientific modeling. Meanwhile, advances in network backbone technologies and middleware offer a new opportunity to share these resources. Organizations such as NASA and NSF provide seamless, secure shared access to member computers via a computational grid constructed from these technologies. A computational grid is analogous to an electrical power grid in the sense that, once plugged in, a user theoretically has access to resources provided anywhere on the grid.
1. FY '03 Project - Using the TeraGrid for
NOAA Scientific
Computing
The objective of this
research is to determine how
NOAA can exploit grid technology for scientific computing. The
original intent was to explore the TeraGrid.
However, due to the
fact that the TeraGrid became available much later than expected, the
project
funds were instead used to construct a rudimentary grid consisting of
nodes located at FSL and PMEL. The Globus
toolkit is used to
connect the resources together. Much more detail can be found in
a FY
'03 Final Report for the FY '03
Proposal.
An FY
'03 Presentation
is also available. As the report and proposal discuss, one of the
deliverables was a prototype
coupled model. A second deliverable was a release of a
version of the Scalable Modeling System that support grid
computing. This release (2.8.0) can be found here. During
the
course of the project, a coupled
version
of the Weather Research and Forecast (WRF) and Regional Ocean Modeling
System (ROMS) models became available for testing across the
rudimentary grid. The final report discusses performance results
for that testing.
Prepared by Dan Schaffer
Date of last update:
May-2005