| Grid Computing |
 |
|
Grid computing is a model of distributed computing that uses geographically and administratively disparate resources. In grid computing, individual users can access computers and data transparently, without having to consider location, operating system, account administration, and other details. In grid computing, the details are abstracted, and the resources are virtualized.
Grid computing systems can be classified into two broad types. The
first type are heavy-weight, feature-rich systems that tend to concern
themselves primarily with providing access to large-scale, intra- and
inter-institutional resources such as clusters or
multiprocessors. Grid systems developed using the Globus Toolkit are
examples of this class. The second general class of Grid computing
systems is the Desktop Grid, in which cycles are scavenged from idle
desktop computers. The Berkeley Open Infrastructure for Network
Computing (BOINC), a descendant of the SETI@home project, is an example of middleware for public Desktop Grid
computing, as it harnesses resources that exist outside of
institutional control. We developed middleware that allows BOINC- and
Globus-based Grid systems to inter-operate and thus provides a means
for Globus-based computational Grids to incorporate a much greater
range of resources (Myers et al. submitted). Additionally, by decreasing the
startup cost for new Desktop Grid computing projects, it makes Desktop
Grids a viable option for a broader range of projects, and provides to
Desktop Grids features inherent in Globus (e.g., authentication,
authorization, file transfer).
We have also developed the Grid Service Base Library (GSBL), a Java
toolkit that aims to reduce the complexity of writing Grid services
under the Globus Toolkit (Bazinet et al. submitted). GSBL provides base classes
from which clients and services can extend; additionally, it provides
features for executing and managing remote jobs and file transfers.
As a complement to the GSBL library, the Grid Service Generator speeds
the development of Grid services by automatically creating the
skeleton files required by a GSBL service (Bazinet et al. submitted).
A more powerful expression of Grid services can be achieved through
use of Semantic Web technology, and together with several colleagues
we have done research on Semantic Web/Grid services (Lee et al. sumbitted),
and automatic workflow composition (Hashmi et al. 2004).
Research web site: The Lattice Project
Personnel:
Adam L. Bazinet
Michael P. Cummings
Collaborators:
John Fuetsch, PDI/DreamWorks
Nada Hashmi, College of Business
Administration, Saudi Arabia
Jeffrey C. Huskamp, University of Maryland
Sung Lee, Fujitsu Laboratories of America, Inc.
Daniel S. Myers, Massachusetts Institute of Technology
Taowei David Wang, University of Maryland
Further Information:
e-mail Michael P. Cummings
|
