CaltechAUTHORS
  A Caltech Library Service

Efficiency of group implicit concurrent algorithms for transient finite element analysis

Ortiz, M. and Sotelino, E. D. and Nour-Omid, B. (1989) Efficiency of group implicit concurrent algorithms for transient finite element analysis. International Journal for Numerical Methods in Engineering, 28 (12). pp. 2761-2776. ISSN 0029-5981. http://resolver.caltech.edu/CaltechAUTHORS:20180104-144109186

Full text is not posted in this repository. Consult Related URLs below.

Use this Persistent URL to link to this item: http://resolver.caltech.edu/CaltechAUTHORS:20180104-144109186

Abstract

The performance of group implicit algorithms is assessed on actual concurrent computers. We show that, as the number of subdomains is increased, performance enhancements are derived from two sources: the increased parallelism in the computations; and a reduction in equation solving effort. Moreover, we show that these two performance enhancements are synergistic, in the sense that the corresponding speed-ups are multiplied, rather than merely added. Our numerical simulations demonstrate that, if n is the number of degrees of freedom of the structure, p the number of processors used in the computations, and s ⩾ p is the number of subdomains in the partition, the net speed-up is O(p√s) in 2D and O(ps) in 3D, asymptotically as n/s → ∞. In particular, speed-ups with respect to Newmark's method of O(p√s) in 2D and O(s) in 3D are obtained on a single-processor machine. Finally, simulations on a 32-node hypercube are presented for which the interprocessor communication efficiencies obtained are consistently in excess of 90 per cent.


Item Type:Article
Related URLs:
URLURL TypeDescription
https://dx.doi.org/10.1002/nme.1620281204DOIArticle
http://onlinelibrary.wiley.com/doi/10.1002/nme.1620281204/fullPublisherArticle
Additional Information:© 1989 John Wiley & Sons. Received 10 November 1988. Revised 21 February 1989. M. O. and E. D. S. gratefully acknowledge support from the NASA Langley Research Center under grant NAG-1-634. The computations on the Alliant FXS computer were performed at the Computational Mechanics Facility of the Division of Engineering at Brown University. The acquisition of this computer has been made possible, in part, by grants from the U.S. National Science Foundation and the Office of Naval Research.
Group:GALCIT
Funders:
Funding AgencyGrant Number
NASANAG–1–634
NSFUNSPECIFIED
Office of Naval Research (ONR)UNSPECIFIED
Record Number:CaltechAUTHORS:20180104-144109186
Persistent URL:http://resolver.caltech.edu/CaltechAUTHORS:20180104-144109186
Official Citation:Ortiz, M., Sotelino, E. D. and Nour-Omid, B. (1989), Efficiency of group implicit concurrent algorithms for transient finite element analysis. Int. J. Numer. Meth. Engng., 28: 2761–2776. doi:10.1002/nme.1620281204
Usage Policy:No commercial reproduction, distribution, display or performance rights in this work are provided.
ID Code:84090
Collection:CaltechAUTHORS
Deposited By: Lydia Suarez
Deposited On:05 Jan 2018 18:34
Last Modified:05 Jan 2018 18:34

Repository Staff Only: item control page