 |
|
DAILY NEWS AND INFORMATION
FOR THE GLOBAL GRID COMMUNITY /
|
Special Features:
BANDWIDTH CHALLENGE TEAMS PUSH
PERFORMANCE ENVELOPE AT SC2003
Teams of scientists from research organizations around the world competed
recently in Phoenix to see who could move the most scientific data across
networks in the fourth annual High-Performance Bandwidth Challenge, held in
conjunction with SC2003, the international conference on high-performance
computing and networking.
Once the data were moved and the performance tracked, a team representing
the
Stanford Linear Accelerator Center, Caltech and Los Alamos National Laboratory
had achieved a new record from sustained throughput -- 23.21 gigabits per
second, surpassing last year's record by about 5 Gbits.
"While the results are impressive, the challenge is not just about blasting
bits across the network," said '03 Bandwidth Challenge Co-Chair Kevin Walsh of
the San Diego Supercomputer Center. "It's really about driving science and
this year's competition clearly illustrates the role of high performance, high
bandwidth networks in current scientific research in such areas as physics,
biology and chemistry, as well as computer science."
Walsh added that cutting-edge science carried out on an international scale
is
pushing currently available bandwidth, and projections are that Grid computing
advances will grow in tandem with increases in high performance, high
bandwidth networks.
For the fourth consecutive year, Qwest Communications sponsored prizes for
the
winning teams.
"Qwest is once again extremely pleased to sponsor the SC conference's
Bandwith
Challenge," said Dr. Wesley K. Kaplow, chief technology officer for Qwest
Government Services. "This year's set of participants have clearly
demonstrated that high-performance computing coupled with high-bandwidth
networking is the foundation for igniting international innovation and
collaboration."
This year's winners:
- Sustained Bandwidth Award: "Bandwidth Lust: Distributed Particle Physics
Analysis Using Ultra-High Speed TCP on The Grid." In what judges called the
"Moore's Law move over" award, the team demonstrated the best vision and
articulation of the need for high performance networks to serve science. The
team moved a total of 6551.134 gigabits of data, reaching 23.23 gigabits per
second. Team members are Harvey Newman, Julian Bunn, Sylvain Ravot, Conrad
Steenberg, Yang Xia and Dan Nae, Caltech; Les Cottrell and Gary Buhrmaster,
SLAC; Wu-chun Feng, LANL; and Olivier Martin, CERN/DataTAG.
- Tools Award: "High Performance Grid-Enabled Data Movement with GridFTP,"
which
emphasized creating common, standards-based tools that are the building blocks
for new applications, and demonstrating it capability with visualization.
Sustained high rate was 8.94 Gbits per second. Team members are William E.
Allcock, John M. Bresnahan, Ian Foster, Rajkumar Kettimuthu, Joseph M. Link
and Michael E. Link, Argonne National Laboratory; and Phil Andrews, Bryan
Banister, Haisong Cai, Steve Cutchin, Jay Dombrowski, Patricia Kovatch, Martin
W. Margo, Nathaniel Mendoza, Michael Packard and Don Thorp, Diego
Supercomputer Center.
- Application Foundation Award: "DataSpace," which used a Web service
framework
integrated with high-performance networking tools to provide an application
foundation for the use of distributed datasets. High sustained rate was 3.66
gigabits per second. Team members are Robert L. Grossman, Yunhong Gu, David
Hanley, Xinwei Hong and Michal Sabala, University of Illinois-Chicago; Joe
Mambretti, Northwestern University; Cees de Laat, Freek Dijkstra and Hans
Blom, University of Amsterdam; Dennis Paus, SURFNet; Alex Szalay, John Hopkins
University; and Nagiza F. Samatova and Guru Kora, Oak Ridge National
Laboratory.
- Application Award: "Multi-Continental Telescience," which emphasized user
interaction with science instruments, distributed collaboration, with
particular attention to ease of use by domain scientists. The team posted a
sustained rate of 1.13 gigabits per second. Team members are Steve Peltier,
Abel Lin and David Lee, UCSD BIRN; Francisco Capani, Universidad de Buenos
Aires; Oleg Shupliakov, Karolinska Institute; Shimojo Shinji, Tokokazu
Akiyama, Osaka University; H. Mori, Center for Ultra High Voltage Microscopy;
KDDI R&D Labs; Fang-pang Lin, NCHC; and Tom Hutton, SDSC.
- Distance x Bandwidth Product & Network Technology Award: "Transmission
Rate
Controlled TCP on Data Reservoir, University of Tokyo," which demonstrated
attention to the details of controlling multiple gigabit streams fairly over
extremely long distances. Achieved very high average pipe utilization of over
65 percent with real disk-to-disk transfer with a high sustained rate of 7.56
gigabits per second. Team members are Mary Inaba, Makoto Nakamura, Hiroaki
Kamesawa, Junji Tamatsukuri, Nao Aoshima and Kei Hiraki, University of Tokyo;
Akira Jinzaki, Junichiro Shitami, Osamu Shimokuni, Jun Kawai, Toshihide
Tsuzuki and Masanori Naganuma, Fujitsu Laboratories; Ryutaro Kurusu, Masakazu
Sakamoto, Yuuki Furukawa and Yukichi Ikuta, Fujitsu Computer
Technologies.
- Commercial Tools Award: "On-Demand File Access over a Wide Area with
GPFS,"
showing emergence and use of commercial system that demonstrates
high-performance without significant impact on remote systems. The team posted
a sustained rate of 8.96 gigabits per second. Team members are Phil Andrews,
Bryan Banister, Haisong Cai, Steve Cutchin, Jay Dombrowski, Patricia Kovatch,
Martin W. Margo, Nathaniel Mendoza, Michael Packard and Don Thorp, SDSC; and
Roger Haskin and Puneet Chaudhary, IBM.
- Distributed Infrastructure Award: "Trans-Pacific Grid Datafarm," a
geographically distributed file system which took advantage of multiple
physical paths to achieve high performance over long distances. The team
achieved a high rate of 3.57 gigabits per second. Team members are Osamu
Tatebe, Hirotaka Ogawa, Yuetsu Kodama, Tomohiro Kudoh, Satoshi Sekiguchi,
AIST; Satoshi Matsuoka and Kento Aida, Tokyo Institute of Technology; Taisuke
Boku and Mitsuhisa Sato, University of Tsukuba; Youhei Morita, KEK; Yoshinori
Kitatsuji, APAN Tokyo XP; and Jim Williams and John Hicks, TransPAC/Indiana
University.
- Both Directions Award: "Distributed Lustre File System Demonstration,"
which
proved that not all applications or bandwidth challenge entries move data only
in one direction. The team achieved a rate of 9.02 Gbits per second. Team
members are Peter Braam, Eric Barton, Jacob Berkma and Radika Vullikanti,
Cluster File Systems; Hermann Von Drateln, Acme Microsystems: Nic Huang,
Supermicron; Danny Caballes, John Szewc, Mike Allen, Rick Crowell and Matt
Eclavea, Foundry Networks; Dave Fellinger, Ryan Weiss and John Josephakis,
Data DirectNetworks; Jeff James and Matt Baker, Intel; Leonid Grossman and
Marc Kimball, S2io; Vicki Williams and Luis Martinez, Sandia National
Laboratories; Parks Fields, Los Alamos National Laboratory; Rob Pennington,
Michelle Butler, Tony Rimovsky, Patrick Dorn, Anthony Tong, National Center
for Supercomputing Applications; Phil Andrews, Patricia Kovatch and Kevin
Walsh, San Diego Supercomputer Center; Alane Alchorn, Jean Shuler, Keith
Fitzgerald, Dave Wiltzius, Bill Boas, Pam Hamilton, Chris Morrone, Jason King,
Danny Auble, Jeff Cunningham and Wayne Butman, Lawrence Livermore National
Laboratory.
Kaplow said that participants this year focused more on data storage and
movement than in years past, and there have been significant increases in
their capability -- especially in the face of problems caused by large
geographic distances.
"Next year, we are going to place additional emphasis on applications that
use
these facilities," Kaplow said. "Also, we have seen an increase in the use of
commercial and standards-based middleware to enable application development
which is key to enabling application writers to focus on their user
requirements and less on how to push gigabits across kilometers."
A graphical representation of each team's effort, along with detailed
statistics on the amount of data transferred, can be found at
scinet.supercomp.org/2003/bwc/results/index.html.
|