The Gordon Bell Prizes
Gordon Bell Prizes are awarded each year to recognize outstanding achievement in high-performance computing.
Now administered by the ACM,
financial support of the $10,000 award is provided by Gordon Bell, a pioneer in high-performance and parallel computing.
The purpose of the award is to track the progress over time of parallel computing,
with particular emphasis on rewarding innovation in applying high-performance computing to applications in science.
The prize has been awarded every year since 1987.
Prizes may be awarded for peak performance as well as special achievements in scalability, time-to-solution
on important science and engineering problems, and low price/performance.
Although the precise award descripion for
a given year depends on the entries for that year
three categories are generally recognized:
1. Peak Performance: This prize is given to
the entry demonstrating
the highest performance achieved in terms of operations per second on a genuine application program.
Recent winners have been well over 100 teraflop/s.
2. Price/Performance: This prize is given to
the entry demonstrating
the best price-performance ratio as measured in megaflop/s per dollar on a genuine application.
3. Special or Honorable Mention: The prize in this category may be given to an entry whose performance is
short of that of the Peak Performance prize, but which nevertheless utilizes innovative techniques to
produce new levels of performance on a real application. Such techniques may be, for instance, in mathematical algorithms, data structures, or implementations.
A submission will not be considered eligible for any of these award categories unless it describes sustained performance on a real scientific application, and achieves, as a minimum requirement, at least the rate achieved by the #500 entry of the most recent Top500 list -- see http://www.top500.org. Also, a submission must exhibit significant novelty -- a submission that is largely a repeat of a previous submission will not be considered.
ENTERING THE CONTEST
To be considered for a Gordon Bell Prize you must submit a paper describing your
work to the ACM/IEEE SC07 Conference. Note that Gordon Bell papers must be submitted
to a separate track from regular conference papers.
The Bell Prize committee will review these submissions, select a small number of finalists, and notify them
at the same time that SC07 papers are accepted. Finalists will be able to
improve their results during the period allowed for revision of papers accepted for the Technical Program.
The Prize Committee will select the winners based on the results in the final version of the paper and announce the winners at SC07.
ADVICE TO SUBMITTERS
You should familiarize yourself with the high standards set by previous winners.
In addition to the brief summaries given
below you can find more details on past winners in
Proceedings of the SCxy Conferences.
(See also, e.g., Alan H. Karp, Ewing Lusk, and David H. Bailey, "1997 Gordon Bell Prize Winners", IEEE Computer, vol 31, no. 1, January 1998, pp.86-92.)
For all categories, it is important to explain precisely how the performance was measured.
For price performance, you must also convince the judges that the price computation is fair and contains no "hidden costs."
In the special category, it is your responsibility to explain why this computation represents a
new level of achievement in its area. For all three categories, it is important that the computation represent a
genuine application, not a demo or benchmark. "Embarrassingly parallel" calculations, which require
only minimal data communication, have traditionally not been winners.
The algorithms used in the calculation must be described.
An important consideration in judging is whether or not the algorithms used are fundamentally
efficient for the given application. Professional practices for citing performance must be observed.
IMPORTANT DATES FOR 2007
New for SC07: A two-part submission process is being used for both Technical Papers
and Gordon Bell papers. You must register on the submission web site and submit
an abstract no later than April 6, 2007 (11PM EST). Then you have until
Monday, April 9, 2007 to upload your paper.
March 12, 2007: Submissions open
April 6, 2007: Submission deadline for Gordon Bell Prize Abstracts
April 9, 2007: Submission deadline for Gordon Bell Prize Papers
July 2, 2007: Acceptance Notification
July 31, 2007: Final version of paper due
SUBMISSION WEB SITE: http://sc-submissions.org
David Bailey, Lawrence Berkeley National Laboratory (Chair)
James Demmel, University of California, Berkeley
David Keyes, Columbia University
Mateo Valero, Technical University of Catalonia