Design of a parallel computational fluid dynamics code on a shared memory architecture

Harris L. Bergman, Jeff S. Vetter, Karsten Schwan, David N. Ku

Research output: Contribution to conferencePaperpeer-review

Abstract

To reduce computer run times with the use of a spectral element method (SEM) algorithm for the investigation of pulsatile flow through a coronary bifurcation, parallelization of a computational fluid dynamics (CFD) code onto a multicomputer was performed. Parallelism was attained by decomposing subroutine operations that consume huge amounts of time among processing units, with each unit operating on a fraction of the physical domain. Decomposition in this style lends itself to portability onto many shared memory architectures.

Original languageEnglish
Pages363-364
Number of pages2
StatePublished - 1995
Externally publishedYes
EventProceedings of the 1995 ASME International Mechanical Congress and Exposition - San Francisco, CA, USA
Duration: Nov 12 1995Nov 17 1995

Conference

ConferenceProceedings of the 1995 ASME International Mechanical Congress and Exposition
CitySan Francisco, CA, USA
Period11/12/9511/17/95

Fingerprint

Dive into the research topics of 'Design of a parallel computational fluid dynamics code on a shared memory architecture'. Together they form a unique fingerprint.

Cite this