Parallel finite element computations on a network using NCS | Zendy

Bertrand F. H. | Zendy; Tanguy P. A. | Zendy

AI Assistant Blog Pricing

Home ZAIA Blog

Premium

Parallel finite element computations on a network using NCS

Author(s) -

Bertrand F. H.,

Tanguy P. A.

Publication year - 1992

Publication title -

aiche journal

Language(s) - English

Resource type - Journals

SCImago Journal Rank - 0.958

H-Index - 167

eISSN - 1547-5905

pISSN - 0001-1541

DOI - 10.1002/aic.690380211

Subject(s) - computer science , parallel computing , workstation , finite element method , computation , computational science , homogeneous , software , simple (philosophy) , distributed computing , algorithm , engineering , operating system , mathematics , philosophy , structural engineering , epistemology , combinatorics

Research has been carried out on the use of NCS (Network Computing System) to distribute the processing of a finite element application to multiple computers at once. Coarse‐grained parallelism of specific routines on loosely coupled CPUs has been implemented and tested. In a step‐by‐step fashion, the method of using NCS to convert finite element software POLY2D is explained for its application in parallel computing resources throughout a network. For the modeling of a simple conductive heat transfer problem, the distributed version of POLY2D on a homogeneous token ring network of nine Apollo workstations is used. Some timings given are compared to those obtained from a standard nondistributed simulation.

This content is not available in your region!

Continue researching here.

Having issues? You can contact us here

Accelerating Research