?Blueprint for the Future of High-Performance Networking?
|
11.19.03 -- As if to underscore the growing convergence of supercomputing and networking, researchers affiliated with Calit² and the OptIPuter project are among the principal contributors to a special edition of the Association of Computing Machinery (ACM) journal, Communications of the ACM (CACM). The November 2003 special issue is titled “Blueprint for the Future of High-Performance Networking,” and is now available in print and online (http://www.acm.org/cacm/).
The special issue of CACM Vol. 46, Issue 11, was guest-edited by Maxine D. Brown, OptIPuter project manager and associate director of the Electronic Visualization Laboratory (EVL) at the University of Illinois at Chicago (UIC). According to the publication, “the future of high-performance networking and the data-intensive applications that depend on it is in the hands of some of today's brightest computer scientists. Their efforts are making it possible for e-scientists to collaborate on projects sometimes so wide-ranging they embrace the entire universe from desktops worldwide.”
Calit² and OptIPuter investigators from UC San Diego, UIC and other universities are co-authors on each of the six articles in the special issue, as mentioned below. OptIPuter leaders are noted, and author names are followed by their university or other affiliation (in parentheses).
Maxine D. Brown, "Introduction," Special issue on Blueprint for the future of high-performance networking, Communications of the ACM, Volume 46, Issue 11, November 2003, pp. 30-33. Copyright 2003 by ACM, Inc.
“Data-intensive e-science is far removed from transaction-based e-business and streaming-based e-entertainment, yet today's best-effort routed networks must serve all users. But these networks are swamped by huge flows of data mixed with normal-bandwidth, short-lived traffic. Each type of traffic has a devastating effect on the other, Web pages take too long to open, and data is lost, requiring retransmission, especially when the networks do not offer scheduled services with guarantees of bandwidth or latency…”
Aaron Falk, Ted Faber, Joseph Bannister, Andrew Chien, Robert Grossman, Jason Leigh, "Transport Protocols for High Performance," Special issue on Blueprint for the future of high-performance networking, Communications of the ACM, Volume 46, Issue 11, November 2003, pp. 42-49. Copyright 2003 by ACM, Inc.
“The stability of today's Internet relies on the congestion control built into the Transmission Control Protocol (TCP). After the National Science Foundation's backbone network experienced repeated network-wide congestion collapses in the 1980s, Van Jacobson, then a researcher at Lawrence Berkeley National Laboratory, devised congestion-control algorithms for TCP allowing thousands of users to share a bottleneck in a stable manner. TCP maintains a congestion window governing how many bytes of data a sender may send without acknowledgment from the receiver…”
“Exponential advances in sensors, storage systems, and computers are producing data of unprecedented quantity and quality. Multi-terabyte and even petabyte (1,000TB) data sets are emerging as major assets. For example, the climate science community has access to hundreds of terabytes of observational data from NASA's Earth-observing system and simulation data from high-performance climate models; these data sources can yield new insights into global change…”Larry L. Smarr, Andrew A. Chien, Tom DeFanti, Jason Leigh, Philip M. Papadopoulos, "The OptIPuter," Special issue on Blueprint for the future of high-performance networking, Communications of the ACM, Volume 46, Issue 11, November 2003, pp. 58-67. Copyright 2003 by ACM, Inc.
“The OptIPuter exploits a new world of distributed Grid infrastructure in which the central architectural element is optical networking, not computers, creating "supernetworks," or networks faster than the computers attached to them. As in supercomputing a decade ago, parallelism makes this transition possible. But this time, parallelism takes the form of multiple wavelengths of light, or lambdas, capable of traversing individual strands of optical fiber…”
“The U.K. Research Councils define e-science as ‘large-scale science carried out through distributed global collaborations enabled by networks, requiring access to very large data collections, very large-scale computing resources, and high-performance visualization.’ These advanced computing technologies enable discipline scientists to study and better understand complex systems—physical, geological, biological, environmental, atmospheric—from the micro to the macro level, in both time and space…”Related Articles
HPCwire Interview with Optiputer's Maxine Brown