September 12, 2005
iGrid Chair DeFanti: 'Not at the End of the Rainbow Yet'
In a recent interview for GRIDtoday, Doug Ramsey of the University
of California, San Diego spoke with Tom DeFanti about the upcoming iGrid
2005 workshop and symposium, which will be held Sept. 26-30 in San
DeFanti -- iGrid 2005 co-chair, co-director of the Electronic
Visualization Laboratory at the University of Illinois-Chicago, and
senior research scientist with the UCSD division of Calit2 -- began by
joking: "Sometimes, I think of it as the visualization, networking and
Grid computing equivalent of a Grateful Dead concert."
GRIDtoday: How so?
TOM DEFANTI: This is not a typical conference. It's really a
workshop, and almost everyone who attends is contributing in one way or
another, and more than half are contributing content. We see iGrid as a
very intense workshop to develop new ideas and capabilities, and people
risk a lot in terms of trying things that have never been done before.
Many of the demonstrations will also be shown at Supercomputing 2005 in
November, and when they arrive at SC, they want to be sure everything
works. So at iGrid, it is okay if something doesn't work, because we
know we have six weeks more to make it work. Part of being a scientist
is that the answers are not anywhere near as interesting as the
questions. A workshop like iGrid provides enough answers to formulate
the next questions.
Gt: Can you trace the geneology of iGrid for us?
DEFANTI: The whole idea started when we networked McCormick
Place in Chicago and did remote visualization as part of SIGGRAPH 1992.
Three years later we connected IWAY at Supercomputing in San Diego, and
it was important because it was the first time anyone had gotten the
federal networks to talk to each other. That was just 10 years ago. It
was also one of the first conferences where the Web was used
extensively. We also learned how to build this international team, so
we staged the first iGrid at Supercomputing 1998 in Orlando, Fla.
Because we wanted to emphasize international collaboration, we decided
to push our luck and have the 2000 iGrid in Yokohama, Japan, then in
Amsterdam in 2002.
Gt: The vast majority of applications demonstrated at iGrid 2005 will also be international. Why that emphasis?
DEFANTI: The Supercomputing conference has always been
fundamentally a U.S.-focused show. But for iGrid, almost all of the
demonstrations have some international component because we were and
are funded by the National Science Foundation to support science and
engineering education across international networks. The idea was to
give people in the United States and their international colleagues a
chance to show off their stuff in a supportive environment. Obviously,
a real huge issue is to keep the U.S. preeminent in a sector where
funding is rising rapidly in other countries such as Canada, Korea,
Japan and China. The European Union's funding as a group way outstrips
U.S. funding in this area. We used to be the only act in town, but now
we're part of a global community and struggling to keep up.
Gt: How cohesive is the international networking community?
DEFANTI: To our great surprise and delight, when we did the
program in Yokohama it went very smoothly. Although there are many
cultural and other things that are very different in Japan and Asia,
the networking world is the same. They speak the same language. The
group of people we deal with -- technologists, scientists and engineers
-- all work together and like it. We discovered that communicating with
our Pacific Rim counterparts was no problem. They have the same
technology and the same culture of technology. The same holds true in
Gt: What is the core networking technology driving iGrid 2005?
DEFANTI: In 2002 in Amsterdam, we had 10-Gigabit circuits, so it
was the first time we had more bandwidth than we needed. But now we can
control lambdas, these wavelengths of light, so it's about user control
and application control of the lightpaths. Several different
demonstrations will involve controlling lightpaths and bringing things
in simultaneously from all over the world. There are also
demonstrations of equipment that does that, and applications that use
the extreme bandwidth. This bandwidth essentially now exceeds the
capacity of computers talking to each other singly, so you wind up
having parallel communications going on. Many of the experiments rely
on the traditional Internet, but a surprising number use lightpaths.
Gt: Whose networking equipment will be used during iGrid?
DEFANTI: We received a very nice donation from Cisco Systems,
and we have loaner equipment from Force10. The Cisco Catalyst switch
and the Force10 switch are the heart of our standard networking, and we
also got loaners from Nortel Networks to do the Layer 1 lightpath work,
which in the past year has become the basis of the next phase of
international networking. We are hoping that now we have this
capability here, the campus and the UC system will commit to making San
Diego one of the core hubs for lightpath networks, along with Chicago,
New York, Amsterdam, London, Tokyo and other Asian open Internet
San Diego is a rational place to install this capability on a permanent
basis, with both Calit2 and the San Diego Supercomputer Center here.
For iGrid, the networking in San Diego will connect through the
national CAVEwave, PacificWave and National LambdaRail to international
connections to the east and west, and through CENIC to UC-Irvine,
University of Southern California and other California destinations.
These aren't networks that people depend on for their banking, so we
can try adventurous things and floor the accelerator without worrying
about inconveniencing anybody.
Gt: Although iGrid will use the latest networking technology, most of the demonstrations will be application-based, right?
DEFANTI: It is fundamentally focused on applications and
content, and content is king. People want to spend money on
applications, they don't spend money on computer hardware for
hardware's sake. Scientists will use our technology if it helps them do
better science. So iGrid is very focused on applications, to show what
people are doing in a world of almost limitless bandwidth.
Gt: What are some of the recurring themes among applications to be demonstrated at iGrid?
DEFANTI: One that has emerged this year is high-definition
television (HDTV) over lightpaths, including streaming HDTV and
interactive HDTV. Attendees will also witness a new industry standard
called 4K. At 4096 by 2180 pixels, 4K is over four times the definition
of regular HDTV. Sony is lending us one of their first 4K projectors,
and NTT will stream 4K content from Japan to San Diego. And professor
Peter Otto is working with Skywalker Sound to synchronize audio for
these 4K demonstrations, and that should be very impressive. More and
more people are using this technology to see and interact with data
coming from sensors, and an HD camera can be a sensor. With the drop in
price of HD cameras from $100,000 to as little as $3,000, and with
networking increasingly built into these cameras, you can just plug
these things into a network and off you go. This will be a tremendous
push on network capacity, because an HD camera exceeds a Gigabit if you
don't compress it, and although 4K imagery can be compressed down to
under a Gigabit, it's huge in uncompressed form, and you want to keep
stuff uncompressed if you want to edit it or do post-production effects
Gt: How important is security as an issue for this year's applications?
DEFANTI: There is a lot of attention on security. Whether they
are dealing with medical images, or Hollywood movies, or remote
visualization for the military, all of these groups have extreme needs
for security for different reasons. One is legislated, one has to do
with intellectual property and money, and the other is for national
security. They are all very important, and increasingly people want to
move security to the network and away from the end user. I devote way
too much time every week to keeping my laptop safe, and I shouldn't
have to. We are trying to solve that problem for high-end images, so we
are doing an advanced security demo with Canada's Nortel Labs, where
they build the security into their switches. You wouldn't even know
it's there, but if someone tapped into the line, it looks like
Gt: So iGrid goes well beyond what many people would label 'Grid' computing or networking?
DEFANTI: The Grid should not only control computing and
disk-space resources, but also networking resources. To be clear, we
call it the LambdaGrid because it goes beyond the traditional Grid that
uses the shared Internet, into the realm of dedicated lightpaths, or
lambdas. The LambdaGrid gives scientists the option of having
schedulable or dedicated resources that are shared in some way, and the
cost of these resources is no longer the stumbling block. These
networks are expensive, but not extremely expensive any more. If you
take all the networks that we're putting into iGrid and you pay for
them, it's a fraction of the cost of the people who are using them. A
national or international network doesn't cost much more than a full
professor or a networking technician per year, so that changes the
Gt: What draws so many of your colleagues from around the world to iGrid?
DEFANTI: Over the years, we have developed an international
community of people who trust each other and who see the benefit of
teamwork with those in visualization, in networking, in computing, in
simulation, or in HD video. We lend and send each other pieces of
equipment that cost $50,000 or $500,000, and we know we'll get them
back. We trust each other with our technology and with some of the
secrets that we hold dearest. This is kind of our celebration of how
much we trust each other. Maxine Brown and I have been running
events for a long time, and like we did with SIGGRAPH, we want iGrid to
be a place where groups of people could show their exquisite technology
to fellow scientists. In iGrid, we are trying to get people to bring
stuff out of the lab and share it with each other. It's not like a
regular conference where you get up and show PowerPoints. There are
almost no canned presentations, although there will be a symposium
running concurrently to round out the information. But it's not the
dominant reason people come. They come to see the technology and
applications in action.
Gt: Since visualization is very important at iGrid, what other technologies will be used to showcase individual applications?
DEFANTI: Apart from Sony's 4K projector in the Calit2 digital
cinema, we have multiple, high-intensity projectors that are 1600x1200
pixels. We have a big stereo screen in a smaller auditorium, and we're
building a 100-megapixel screen in another. We will also have a desktop
virtual-reality device that shows 3-D images but requires no special
glasses and tracks your position by neural networks and video.
Important to the HDTV theme, NASA is bringing a personal HDTV stereo
device that also requires no glasses. We also have two setups with
lovely 63-inch Samsung plasma panels. These are all facilities so
people can show their work in the best way possible, but they also
serve another purpose: 49 different groups will be showcasing their
applications on a total of 10 different screens,' so they will be
sharing the visualization facilities. Sharing is not an inconsiderable
obstacle when you are pushing the limit of the technology, so these
groups will hopefully learn from each other.
Gt: You are a co-principal investigator on the Calit2-led
OptIPuter project. What do iGrid, Calit2 and the OptIPuter project have
DEFANTI: We decided to hold iGrid in the new Calit2 building to
force the immense capability and infrastructure of the building into
functional being in a huge rush. By rights, it should have taken a year
to bring this sort of network infrastructure into a 215,000-square-foot
building like this, but we're doing it in weeks. As for OptIPuter and
iGrid, they have similar goals. OptIPuter is using LambdaGrids to help
scientists see and move their data. But iGrid is a superset of the
OptIPuter: there are other people at iGrid with ideas -- some
complementary, some competing -- on how to architect this world where
bandwidth is no longer a constraint. We hope to witness applications
and technologies at iGrid that can be used in the OptIPuter. We are all
learning from one another, and as these things evolve into real
software products, companies will adopt the best of each technology.
We're not at the end of the rainbow yet.