How to Nominate

The Gordon Bell Prize is awarded each year to recognize outstanding achievement in high-performance 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, engineering, and large-scale data analytics. Prizes may be awarded for peak performance or special achievements in scalability and time-to-solution on important science and engineering problems.  Finalists present their work each November at the annual SC Conference, and the award is presented at the SC Awards Ceremony accompanied by a prize of $10,000.  Financial support for the award is provided by Gordon Bell, a pioneer in high-performance and parallel computing.

Next Deadline:  April, 2015

Selection Criteria:  Individuals or teams may apply for the award.  Because the finalist submissions are included in the Conference Proceedings, they are similar to a technical paper.  However, submitters must follow a specific structure intended to explain their innovations, detail the performance levels achieved on one or more real-world applications, and articulate the implications of the approach for the broader HPC community.  The selection committee considers several criteria, not just the performance achieved:

  1. Evidence of important algorithmic and/or implementation innovations
  2. Clear improvement over the previous state-of-the-art
  3. Solutions that do not depend on one-of-a-kind architectures (systems that can only be used to address a narrow range of problems, or that cannot be replicated by others)
  4. Detailed performance measurements that demonstrate the submission’s claims in terms of scalability (strong as well as weak scaling), time to solution, and efficiency in using bottleneck resources (such as  memory size or bandwidth, communications bandwidth, I/O), as well as peak performance.  Candidates selected as finalists will be given the opportunity to update their results in early August.
  5. Achievements that are generalizable, in the sense that other scientists can learn and benefit from the innovations

Submitters should note that solving an important scientific or engineering challenge is important to demonstrate/justify the work, but scientific outcomes alone are not sufficient for this prize. Finalists are chosen on the basis of empirical performance measurements submitted with the paper (not extrapolated performance predictions). Submitters should be prepared to reproduce both performance and scientific results, and to answer specific questions about the scientific, engineering, analytic results, as deemed necessary by the committee.

Submissions:  Submissions for the Gordon Bell Prize must provide the information necessary for judging and comparison, but also be in a format suited for inclusion in the SC conference proceedings.  Only submissions meeting the format restrictions will be considered.  They are submitted using the online nomination form available at http://submissions.supercomputing.org.  (The submitters should also feel free to describe their work in the form of a normal full-length technical paper and submit it to the SC program for separate publication.)  Gordon Bell Prize submissions must include the following components:

  • Page limits refer to typical technical paper page standards:  11-point font or larger, single spaced text, fitting within 7.5” x 10” text area
  • Abstract focusing on the features that make this achievement a good candidate for the prize (150 word max)
  • Category submitting for (1+ of:  scalability, time-to-solution, peak performance)
  • Overview of the problem and its importance (1 p max)
  • Quantitative discussion of current state of the art for science and performance (1 p max)
  • Claims made for innovation and its implementation (2 pp max)
  • Specific application(s) used to measure performance (1 p max)
  • System and environment where performance was measured, including specific measurement methodology (1 p max)
  • Performance results, including scalability (weak and strong), time to solution, efficiency (of bottleneck resources), and peak performance (2 pp max)
  • Implications for future systems and applications (1 p max)
  • References (no page limit)

For questions on the above, please contact us at acm-awards@acm.org , or  Rosemary McGuinness , ACM Awards Committee Liaison.