Runtime verification of scientific codes using statistics

Dinh, Minh Ngoc, Abramson, David and Jin, Chao (2016). Runtime verification of scientific codes using statistics. In: International Conference on Computational Science, ICCS 2016. International Conference on Computational Science, ICCS 2016, San Diego, CA, United States, (1473-1484). 6 - 8 June 2016. doi:10.1016/j.procs.2016.05.468


Author Dinh, Minh Ngoc
Abramson, David
Jin, Chao
Title of paper Runtime verification of scientific codes using statistics
Conference name International Conference on Computational Science, ICCS 2016
Conference location San Diego, CA, United States
Conference dates 6 - 8 June 2016
Convener ICCS
Proceedings title International Conference on Computational Science, ICCS 2016   Check publisher's open access policy
Journal name Procedia Computer Science   Check publisher's open access policy
Place of Publication Amsterdam, Netherlands
Publisher Elsevier BV
Publication Year 2016
Sub-type Fully published paper
DOI 10.1016/j.procs.2016.05.468
Open Access Status DOI
ISSN 1877-0509
Volume 80
Start page 1473
End page 1484
Total pages 12
Language eng
Abstract/Summary Runtime verification of large-scale scientific codes is difficult because they often involve thousands of processes, and generate very large data structures. Further, the programs often embody complex algorithms making them difficult for non-experts to follow. Notably, typical scientific codes implement mathematical models that often possess predictable statistical features. Therefore, incorporating statistical analysis techniques in the verification process allows using program's state to reveal unusual details of the computation at runtime. In our earlier work, we proposed a statistical framework for debugging large-scale applications. In this paper, we argue that such framework can be useful in the runtime verification process of scientific codes. We demonstrate how two production simulation programs are verified using statistics. The system is evaluated on a 20,000-core Cray XE6.
Keyword Debugging
Distributed memory
Parallel computing
Runtime verification
Scientific simulation
Q-Index Code E1
Q-Index Status Provisional Code
Institutional Status UQ

 
Versions
Version Filter Type
Citation counts: Scopus Citation Count Cited 0 times in Scopus Article
Google Scholar Search Google Scholar
Created: Tue, 23 Aug 2016, 13:23:17 EST by System User on behalf of Learning and Research Services (UQ Library)