skip to main content
OSTI.GOV title logo U.S. Department of Energy
Office of Scientific and Technical Information

Title: Applications of boundary element methods on the Intel Paragon

Abstract

This paper describes three applications of the boundary element method and their implementations on the Intel Paragon supercomputer. Each of these applications sustains over 99 Gflops/s based on wall-clock time for the entire application and an actual count of flops executed; one application sustains over 140 Gflops/s. These implementations are production quality: each accepts the description of an arbitrary geometry as input and computes the solution to a problem of commercial and research interest. The serial versions of the codes used in one of our applications are in commercial and government use at over forty-five sites for one code and at almost 200 sites for the second code. The common kernel for these applications is a dense equation solver based on LU factorization. It is generally accepted that good performance can be achieved by dense matrix algorithms, but achieving the excellent performance demonstrated here required the development of a variety of special techniques to take full advantage of the power of the Intel Paragon.

Authors:
 [1];  [1];  [1];  [1];  [2];  [3];  [3]
  1. Sandia National Labs., Albuquerque, NM (United States)
  2. New Mexico Univ., Albuquerque, NM (United States)
  3. Intel Corp., Beaverton, OR (United States). Supercomputer Systems Div.
Publication Date:
Research Org.:
Sandia National Lab. (SNL-NM), Albuquerque, NM (United States)
Sponsoring Org.:
USDOE, Washington, DC (United States)
OSTI Identifier:
10161914
Report Number(s):
SAND-94-1566C; CONF-941118-5
ON: DE94014135; BR: GB0103012
DOE Contract Number:  
AC04-94AL85000
Resource Type:
Conference
Resource Relation:
Conference: Supercomputing `94 meeting, Washington, DC (United States), 14-18 Nov 1994; Other Information: PBD: [1994]
Country of Publication:
United States
Language:
English
Subject:
97 MATHEMATICS AND COMPUTING; BOUNDARY ELEMENT METHOD; USES; SUPERCOMPUTERS; PERFORMANCE; 990200; MATHEMATICS AND COMPUTERS

Citation Formats

Womble, D. E., Greenberg, D. S., Wheat, S. R., Benner, R. E., Ingber, M. S., Henry, G., and Gutpa, S. Applications of boundary element methods on the Intel Paragon. United States: N. p., 1994. Web. doi:10.1109/SUPERC.1994.344333.
Womble, D. E., Greenberg, D. S., Wheat, S. R., Benner, R. E., Ingber, M. S., Henry, G., & Gutpa, S. Applications of boundary element methods on the Intel Paragon. United States. https://doi.org/10.1109/SUPERC.1994.344333
Womble, D. E., Greenberg, D. S., Wheat, S. R., Benner, R. E., Ingber, M. S., Henry, G., and Gutpa, S. 1994. "Applications of boundary element methods on the Intel Paragon". United States. https://doi.org/10.1109/SUPERC.1994.344333. https://www.osti.gov/servlets/purl/10161914.
@article{osti_10161914,
title = {Applications of boundary element methods on the Intel Paragon},
author = {Womble, D. E. and Greenberg, D. S. and Wheat, S. R. and Benner, R. E. and Ingber, M. S. and Henry, G. and Gutpa, S.},
abstractNote = {This paper describes three applications of the boundary element method and their implementations on the Intel Paragon supercomputer. Each of these applications sustains over 99 Gflops/s based on wall-clock time for the entire application and an actual count of flops executed; one application sustains over 140 Gflops/s. These implementations are production quality: each accepts the description of an arbitrary geometry as input and computes the solution to a problem of commercial and research interest. The serial versions of the codes used in one of our applications are in commercial and government use at over forty-five sites for one code and at almost 200 sites for the second code. The common kernel for these applications is a dense equation solver based on LU factorization. It is generally accepted that good performance can be achieved by dense matrix algorithms, but achieving the excellent performance demonstrated here required the development of a variety of special techniques to take full advantage of the power of the Intel Paragon.},
doi = {10.1109/SUPERC.1994.344333},
url = {https://www.osti.gov/biblio/10161914}, journal = {},
number = ,
volume = ,
place = {United States},
year = {Tue Nov 01 00:00:00 EST 1994},
month = {Tue Nov 01 00:00:00 EST 1994}
}

Conference:
Other availability
Please see Document Availability for additional information on obtaining the full-text document. Library patrons may search WorldCat to identify libraries that hold this conference proceeding.

Save / Share: