The Leading Source for Global News and Information Covering the Ecosystem of High Productivity Computing
May 07, 2008
CHICAGO, May 7 -- Advanced networks are giving rise to a new kind of collaborative laboratory, or collaboratory, comprised of scientists in far-flung locations working together and sharing information as if in the same room, in real time, and aided by high-resolution imagery and high-definition (HD) video conferencing.
Over the past five years, a global team of researchers and networking engineers has been building the OptIPuter, a National Science Foundation-funded initiative to dynamically configure a distributed computational facility, where the optical network becomes the "backplane" connecting high-end computing, storage and visualization resources.
In that time, researchers at the University of Illinois at Chicago's (UIC) Electronic Visualization Laboratory (EVL) have been working on the collaboration and visualization tools that OptIPuter users will need to work together. To this end, EVL has helped develop and deploy the OptIPortal, a networked, scalable, high-resolution LCD tiled-display system that runs SAGE middleware to manage the multi-gigabit data streams displayed in such tiled visualization environments.
Now comes SAGE Visualcasting, the latest service of the SAGE middleware, and a pivotal bridging technology to the OptIPuter's next phase aimed at fostering on-demand, real-time collaborative work sessions among globally distributed scientific communities.
EVL's SAGE Visualcasting is a scalable, real-time image broadcasting service enabling multi-point collaborative work sessions. It is capable of managing tens of gigabits of network streaming in real time, and is application-centric, meaning that the user decides when and where to extend and expand a collaborative work session to include more participants. Users essentially set up multi-point HD "phone calls" without the need for multicast, a network-centric technology that requires network engineering support at all sites prior to working.
"We believe we've put together the best multi-site, multi-visualization, multi-HD video streaming solution on the planet," said EVL director Jason Leigh.
Using SAGE Visualcasting, researchers can discuss and share findings with local and distant colleagues while using visualization tools to analyze massive datasets -- such as neuroscientists accessing and controlling electron microscopes, geoscientists analyzing earthquake aftershocks, or climatologists studying global warming.
"SAGE Visualcasting is a core technology enabling the OptIPlanet Collaboratory," said Larry Smarr, OptIPuter principal investigator and director of the California Institute for Telecommunications and Information Technology (Calit2), a partnership of the University of California, San Diego and the University of California, Irvine.
SAGE Visualcasting dynamically adapts to the tiled-display wall configuration at each endpoint using a SAGE Bridge, a high-speed bridging system that distributes pixel data received from rendering clusters and HD camera systems to each endpoint. Moreover, SAGE Visualcasting is a subscription-based service, enabling participating sites to subscribe to the information they want to receive, taking network connectivity and display sizes into consideration. SAGE Bridge is deployed on a high-performance cluster equipped with a 10Gbps network interface.
In April, EVL ran a continuous five-way HD video teleconferencing session between UIC, the University of Michigan School of Information, SARA Computing and Networking Services supercomputing center in the Netherlands, and Korean research institutions Gwangju Institute of Science & Technology (GIST) and the Korea Institute of Science and Technology Information (KISTI).
Each participating site has a high-resolution tiled-display wall with different network bandwidth, computing power and display resolution. In the SAGE Visualcasting session, all participants had the ability to see and interact with the same high-resolution data, and to communicate with one another via HD videoconferencing.
All five of the participants sent HD data streams to a SAGE Bridge located at the StarLight optical exchange facility in downtown Chicago. In turn, SAGE Bridge replicated the streams from each site and sent them to the other four participating sites.
"The validation of this approach would have not been possible without our international research collaborators because it takes multiple sites over a wide range of distances to fully test this capability," said Leigh.
University of Michigan researcher Erik Hofer said, "We're happy to be part of this team so that we can understand how the scale and quality of this system opens new possibilities for creating virtual organizations that consist of top research teams from around the world."
SARA Division Manager for High-Performance Networking Paul Wielinga said, "The combination of videoconferencing, the sharing of data, and pushing data on the screens from various sources is something that will enable groups of geographically separated scientists to analyze the data together and discuss the results in a very flexible way."
JongWon Kim, leader of the GIST Networked Media Laboratory, said, "I believe this technology will allow us to interactively collaborate with multiple remote partners and thus boost our global collaboration capability to the next level."
Gee Bum Koo, leader of the visualization group at KISTI Supercomputing Center, said, "A primary mission of KISTI is to provide its researchers with advanced computing platforms that support the sharing of information and collaborative work. I believe SAGE will be the key component in building such an environment."
All the participants in the SAGE Visualcasting demonstration are OptIPlanet Collaboratory members. The OptIPlanet Collaboratory is now being built through the deployment of OptIPuter-developed tools and techniques to early adopters and global user communities. An international 10Gbps network infrastructure is already in place due to the cooperative effort of the many research and education networks that participate in the Global Lambda Integrated Facility (GLIF) and make bandwidth available for application and middleware development.
SAGE Visualcasting is the doctoral research of Byungil Jeong who organized and conducted the April demonstration in conjunction with his dissertation defense. Dr. Jeong accepted a position with Sun Microsystems, Inc., in Santa Clara, California. EVL will continue to enhance and harden SAGE Visualcasting.
About Scalable Adaptive Graphics Environment (SAGE)
SAGE (www.evl.uic.edu/cavern/sage) is an integrated system used to simultaneously display multiple networked applications on high-resolution tiled displays. The SAGE architecture uses distributed rendering clusters connected by high-bandwidth networks to stream multiple applications to a class of scalable tiled displays that are fast becoming a standard for scientific distance collaboration. Using SAGE, several applications -- including high-resolution 2D imagery, 3D computer graphics and high definition video -- can be streamed and viewed simultaneously. SAGE and SAGE Visualcasting are being developed by the Electronic Visualization Laboratory at the University of Illinois at Chicago as part of the NSF-funded OptIPuter project. SAGE Visualcasting research was also funded in part by the Technology Research, Education, and Commercialization Center (TRECC), a program of the University of Illinois at Urbana-Champaign, funded by the Office of Naval Research and administered by the National Center for Supercomputing Applications.
More Information
EVL: www.evl.uic.edu/cavern/optiputer
GLIF: www.glif.is
OptIPuter: www.optiputer.net
U. Michigan: www.si.umich.edu
SARA: www.sara.nl/expertise/expertise_05_07_eng.html
KISTI: www.kisti.re.kr/english/Main.jsp?menu_id=103016
GIST: netmedia.gist.ac.kr
-----
Source: Electronic Visualization Laboratory, University of Illinois at Chicago
While the Microsoft juggernaut has been touting the joys of its new Windows HPC Server 2008, the Linux HPC contingent has been somewhat less vocal of late. But now Red Hat has come up with its version of an integrated cluster solution.
Read More...
Even though the cost of servers still dominates the datacenter budget, storage is actually on a steeper growth curve. HPC storage, in particular, is being singled out as high-growth opportunity. Vendors are scrambling to keep up.
Read More...
Google datacenters most energy efficient; Cluster Resources to demo Moab Hybrid Cluster; Red Hat Linux releases HPC distro. John West recaps those stories and more in our weekly wrap-up.
Read More...
Oct 07 | GCN.com | Sun Microsystems has been busy building a lot more intelligence into Lustre, a file system used for large-scale cluster computing. Read more...
Oct 06 | The Register | Does the HP Oracle Database Machine represent InfiniBand's big chance to break out its HPC niche? Read more...
Oct 06 | BusinessWeek | A body scan can save a lot of time in the fitting room, and fields from medicine to architecture are adopting 3D computing applications. Read more...
Oct 03 | UCSD News | Despite the evolution of computer science over the past 30 years, structural engineering -- hindered by a reluctance to adapt to digital innovations -- has remained relatively unchanged as a discipline. Read more...
Oct 02 | New York Times | Silcon Valley is starting to feel the effects of the credit crunch. Read more...
Sep 04 | | Disk drives are approximately 250 times denser today than a decade ago. This is good news for users who are creating, manipulating and storing more data than ever before. It gives them an opportunity to derive more value from their stored data and lowers the capital acquisition and operating expense associated with that data.
BlueArc's Titan architecture represents an evolutionary step in file servers by creating a hardware-based file system that can scale bandwidth, IOPS, and overall data capacity well beyond conventional software-based devices. With its ability to virtualize a massive storage pool of up to four usable petabytes of tiered storage, Titan can scale with growing data requirements, offering a competitive advantage for businesses, researchers, or other enterprises seeking to better manage data growth while still ensuring optimal performance.
Get updates and insights on the High Productivity Computing industry delivered driectly to your inbox.