As
the Web becomes faster and more powerful, if offers new opportunities,
some of which are not related only to information access. Several
research labs and commercial ventures are working on a concept of
"computing grid", developing services and software that can manage
complex physical systems of disparate, geographically separated
resources. The basic idea is simple - to combine the processing power
of thousands of networked computers to create a worldwide virtual
supercomputer(s). Tomorrow's computing grids will hopefully offer a
reliable source of computing power, similar to the modern electrical
power grid. According to the MIT Technology Review, "...
this summer, the National Science Foundation will begin to install the
hardware for the TeraGrid, a transcontinental supercomputer that should
do for computing power what the Internet did for documents. First,
clusters of high-end microcomputers will be set up at four sites: the
National Center for Supercomputing Applications at the University of
Illinois at Urbana-Champaign; the U.S. Department of Energys Argonne
National Laboratory outside Chicago; Caltech in Pasadena, CA; and the
San Diego Supercomputer Center at the University of California, San
Diego. Then, by early next year, those four clusters will be networked
together so tightly that they will behave as a single entity." The resemblance to the early Internet history is really striking...
We already described a number of grid computing projects in one of the previous feature articles.
You may notice a lack of commercially-oriented products and services,
but that is typical for the emerging technologies. However, the things
started to change dramatically in the last couple of months. New initiatives, services, systems, tools and resources are now appearing on a daily basis. Industry giants like IBM, Microsoft and Sun are actively involved in developing grid computing technology and bringing it to market.
"Big Blue" and a West Virginia startup Butterfly.net
recently announced the deployment of "the first-ever custom commercial
grid for the online video gaming market". The Butterfly Grid could
enable online video game providers to support a massive number of
players within the same game by allocating computing resources to the
most populated areas and most popular games. The Grid was built by
Butterfly.net over the last two years using IBM e-business
infrastructure technology that distributes the processing of video game
interaction across a network of server farms, enabling it to support
over one million simultaneous players from each facility in a 24/7
environment with automatic failover capability.
It may be a bit
awkward to see such cutting-edge technologies employed in the
entertainment industry. The reason is simple: the gaming market is
moving quickly, and it shows few - if any - signs of slowing down. It
is one of the very few technology sectors that wasn't devastated by the
implosion of the last years. However, the complexity of hosting and
maintaining online games has been a limiting factor for the growth of
the industry. Such issues are likely to become even more critical as
advanced game consoles such as Microsoft's Xbox and Sony's PlayStation
2 go online.
Butterfly Grid operates on top of the open-source Globus Project software: more details on it can be found in the Globus Project FAQ.
Video game providers can access the Grid to support their online
products by including the freely downloadable Butterfly Grid client
software libraries in the games they distribute. Game publishers who
use the Butterfly Grid service will pay monthly hosting fees depending
on usage. You can catch a glimpse of the things to come and learn about
the new genre of Massively Multiplayer Games (MMG) at the Cryptids Web site.
IBM is not alone in
its efforts to back up the grid computing philosophy. Another software
giant, Microsoft, is funding Globus with $1 million to make sure the
toolkit runs on Windows XP and on its .Net infrastructure. This came as
a rather unexpected move, considering the Microsoft's negative attitude
toward open-source projects, but it clearly indicates the importance of
distributed/grid computing concepts.
If you want to review other, mainly open-source, distributed and grid computing projects, Kirk Pearson
maintains a Web site that is a great starting point for further
research. Artificial Intelligence and related fields are natural
targets for many of these projects. See evolution@home, DALiWorld and The Golem Project for more details on the evolutionary/ALife approach to distributed computing.
