Computational & Technology Resources
an online resource for computational,
engineering & technology publications
Civil-Comp Proceedings
ISSN 1759-3433
CCP: 89
PROCEEDINGS OF THE SIXTH INTERNATIONAL CONFERENCE ON ENGINEERING COMPUTATIONAL TECHNOLOGY
Edited by: M. Papadrakakis and B.H.V. Topping
Paper 94

High-Throughput Computing in Engineering

M. Dolenc and M. Dolšek

Faculty of Civil and Geodetic Engineering, University of Ljubljana, Slovenia

Full Bibliographic Reference for this paper
, "High-Throughput Computing in Engineering", in M. Papadrakakis, B.H.V. Topping, (Editors), "Proceedings of the Sixth International Conference on Engineering Computational Technology", Civil-Comp Press, Stirlingshire, UK, Paper 94, 2008. doi:10.4203/ccp.89.94
Keywords: high-throughput computing, volunteer computing, parametric studies, performance-based earthquake engineering, civil engineering.

Summary
In science and engineering, general parametric studies are of high importance [1]. They usually consist of a number of repetitive, independent calculations that are therefore easily performed in parallel. Scientists and engineers involved in this type of work need a computing environment that delivers large amounts of computational power over a long period of time.

The paper explorers two kinds of computing environments that can deliver this kind of functionality: (1) volunteer computing (pioneered by the Distributed.Net project [2]) is a type of distributed computing in which computer owners donate their computing resources (such as processing power or storage) to one or more "projects" [3] and a (2) high-throughput computing (HTC) environment that reuses existing computing resources available on a network - usually within a single organisation [4]. The use of these kind of environments is driven the by fact that most PCs do nothing for 95 percent of a typical day as estimated by IBM research [5]. Volunteer computing and HTC environments can harnesses those wasted resources and put them to work solving problems, moving data more quickly or giving users more resources. In contrast to the two computing environments mentioned, high-performance computing (HPC) environments deliver a tremendous amount of power over a short period of time.

The paper introduces general concepts of computing environments, including technical aspects and different application scenarios suitable for the presented computing environments. The end-user scenarios focus on the use of parametric studies in earthquake engineering. First end-user scenario describes generating a seismic response database using available ground motion records (GMR). As new GMR data is constantly being added based on actual earthquakes the scenario is particularly suitable for volunteer computing. The second end-user scenario describes a probabilistic performance assessment of a structure as an example of a high-throughput computing environment. A probabilistic performance assessment of a structure is a difficult and time consuming task, especially due to the complex non-linear dynamic analyses, which are performed for a variety of ground motion records scaled to a number of intensities, and due to the many uncertainties involved in the nature of the problem.

We believe that with the general availability of broadband Internet connectivity, advancements in computer hardware and software as well as with advancements in scientific research, researchers will find more and more use for the computing environments described. We could easily envisage the future where researchers and end-users in general are not concerned with where to find the necessary computing power anymore.

References
1
M. Dolenc, J. Zevnik, K. Kurowski, "Parametric Studies on the InteliGrid Platform", in B.H.V. Topping, G. Montero, R. Montenegro, (editors), Proceedings of the Fifth International Conference on Engineering Computational Technology, Civil-Comp Press, Stirling, UK, paper 124, 2006. doi:10.4203/ccp.84.124
2
Distributed.Net project, http://distributed.net
3
P.D. Anderson, F. Gilles, "The Computational and Storage Potential of Volunteer Computing", IEEE/ACM International Symposium on Cluster Computing and the Grid, Singapore, May 16-19, 2006.
4
D. Thain, T. Tannenbaum, M. Livny, "Distributed Computing in Practice: The Condor Experience", Concurrency and Computation: Practice and Experience, Vol. 17, No. 2-4, pages 323-356, February-April, 2005. doi:10.1002/cpe.938
5
IBM Research News, http://www.ibm.com/news/us/en/2006/01/2006_01_20.html

purchase the full-text of this paper (price £20)

go to the previous paper
go to the next paper
return to the table of contents
return to the book description
purchase this book (price £95 +P&P)