November 2006 A
High Productivity Computing Systems and the Path Towards Usable Petascale Computing
Suzy Tichenor, Council on Competitiveness
Albert Reuther, MIT Lincoln Laboratory


In the past several decades, HPC has made a large impact in the growth of the American economy, has helped build and maintain American competitiveness in the world economy, and has enabled many of the products and capabilities that we have today. However, Council on Competitiveness research has revealed that despite the opportunities to use HPC to increase productivity and competitiveness, many executives believe that their firms are failing to apply this technology as aggressively as possible. Some of the hindrances have occurred because of lack of talent and certain technical barriers. Another hindrance is a that many boardrooms in American companies see HPC systems as a cost of doing business without realizing the benefits that such a system can bring to the organization and the bottom line. We have presented a variety of benefits and costs that may be realized in organizations that purchase and use HPC systems. While the Research and Industry equations and examples are presented as two distinct scenarios, many actual situations may prompt a melding of the two. Overall, the examples show that HPC assets are not just cost, but that they actually can contribute to healthy earnings reports as well as more productive and efficient staff.

The Council on Competitiveness thanks the Advanced Simulation and Computing program (ASC) at the Department of Energy's National Nuclear Security Administration and the Defense Advanced Research Projects Agency’s High Productivity Computing Systems program for sponsoring Council on Competitiveness research that contributed to this article. At MIT Lincoln Laboratory, this work was sponsored by the Defense Advanced Research Projects Agency under Air Force Contract FA8721-05-C-0002. Opinions, interpretations, conclusions, and recommendations are those of the authors and are not necessarily endorsed by the United States Government. The authors also wish to thank Dimitri Kusnezov, director of the ASC program, for useful discussions.
The Council on Competitiveness is an organization of the top business, university and labor leaders in the United States, responsible for influencing the course of American competitiveness on regional, national and global scales. For additional information about its High Performance Computing project and copies of reports, surveys and case studies, see www.compete.org/hpc
1 ROI can be captured with a variety of corporate finance techniques, including benefit-costs ratio (BCR), net present value (NPV), and internal rate of return (IRR).
2 www.compete.org/hpc
3 "Partnering for Prosperity: Harnessing Our HPC Assets for Competitive Strength." Two Council on Competitiveness studies, both completed in January 2006: "Industrial Partnerships through the National Science Foundation's Supercomputing Resources," and "Industrial Partnerships through the NNSA's Academic Strategic Alliance Program." Available at www.compete.org/hpc .
4 For some background on using BCR, IRR, and NPV to evaluate projects, please refer to G. Tassey, “Method for Assessing the Economic Impacts of Government R&D,” Planning Report #03-1, National Institute of Science and Technology, Sept. 2003. For a through treatment please refer to S. Ross, R. Westerfield, and J. Jaffe, Corporate Finance, McGraw-Hill Irwin: New York, 2004.
5 The intent of these sections is not to teach a tutorial on corporate finance but rather to illuminate various ways in which the benefits and costs associated with evaluating investments in HPC assets can be viewed and analyzed. The formulas and methodologies suggested here are based on the experiences at MIT Lincoln Laboratory. Our intent is to encourage readers to think about how their organization values an HPC solution.
6 DARPA HPCS - www.darpa.mil/ipto/programs/hpcs/
7 Kepner, J. “HPC productivity model synthesis,” International Journal of High Performance Computing Applications, Vol. 18, No. 4, November 2004.
8 The time saved by users was calculated in a very conservative manner: time saved = (time system is in use) * (average number of users) * (1 – 1 / (Average number of CPUs per job) ). This formula assumes that all jobs are fine-grained, synchronous parallel jobs; often parallel jobs are less synchronous and more coarsely grained. The last term in that expression can be substituted with a less conservative term such as log2(Average number of CPUs per job) or just Average number of CPUs per job. Using the latter, we have calculated a BCR greater than 30.

Pages: 1 2 3 4 5 6 7

Reference this article
Tichenor, S., Reuther, A. "Making the Business Case for High Performance Computing: A Benefit-Cost Analysis Methodology," CTWatch Quarterly, Volume 2, Number 4A, November 2006 A. http://www.ctwatch.org/quarterly/articles/2006/11/making-the-business-case-for-high-performance-computing-a-benefit-cost-analysis-methodology/

Any opinions expressed on this site belong to their respective authors and are not necessarily shared by the sponsoring institutions or the National Science Foundation (NSF).

Any trademarks or trade names, registered or otherwise, that appear on this site are the property of their respective owners and, unless noted, do not represent endorsement by the editors, publishers, sponsoring institutions, the National Science Foundation, or any other member of the CTWatch team.

No guarantee is granted by CTWatch that information appearing in articles published by the Quarterly or appearing in the Blog is complete or accurate. Information on this site is not intended for commercial purposes.