FAST: a multi-processed environment for visualization of computational fluid dynamics

  • Authors:

  • Gordon V. Bancroft;Fergus J. Merritt;Todd C. Plessel;Paul G. Kelaita;R. Kevin McCabe;Al Globus

  • Affiliations:

  • Sterling Federal Systems Inc., Palo Alto, California;Sterling Federal Systems Inc., Palo Alto, California;Sterling Federal Systems Inc., Palo Alto, California;Sterling Federal Systems Inc., Palo Alto, California;Sterling Federal Systems Inc., Palo Alto, California;Sterling Federal Systems Inc., Palo Alto, California

  • Venue:
  • VIS '90 Proceedings of the 1st conference on Visualization '90
  • Year:
  • 1990

Quantified Score

Hi-index 0.02

Visualization

Abstract

Three-dimensional, unsteady, multi-zoned fluid dynamics simulations over full scale aircraft is typical of problems being computed at NASA Ames' Numerical Aerodynamic Simulation (NAS) facility on CRAY2 and CRAY-YMP supercomputers. With multiple processor workstations available in the 10-30 Mflop range, we feel that these new developments in scientific computing warrant a new approach to the design and implementation of analysis tools. These larger, more complex problems create a need for new visualization techniques not possible with the existing software or systems available as of this writing and these visualization techniques will change as the supercomputing environment, and hence the scientific methods employed, evolve even further.Visualization of computational aerodynamics requires flexible, extensible, and adaptable software tools for performing analysis tasks. Flexible means the ability to handle a diverse range of problems. Extensible means the ability to interact at all levels of the software hierarchy, either through existing built-in functionality or through the implementation of custom "plug-in" modules. Adaptable means the ability to adapt to new software and hardware configurations through the use of modular structured programming methods, a graphics library standard, and the use of common network communication protocols (like UNIX sockets) for the distribution of processing.This paper discusses FAST (Flow Analysis Software Toolkit), an implementation of a software system for fluid mechanics analysis that is based on this approach.