Design of Array Processor Software for Nonlinear Structural Analysis.

Abstract

This paper presents ongoing research on the solution of large-scale nonlinear structural problems using a 32-bit minicomputer with an attached 64-bit array processor that communicate via a common memory interface. This configuration is typical of what we see as representative of future work stations with attached specialized processors. A user-oriented software package has been designed to allow the use of the given computer configuration by a typical engineer or a scientific user without a detailed knowledge of the operation of the array processor or/and the complex data handling necessary to create the manipulate the data associated with the solution of large problems. The software was then used to implement typical building blocks of a nonlinear finite element code, and performance measurements were taken. Several test examples are considered using 3-D beam finite elements and the Newton Raphson solution scheme. The array processor could not be utilized as yet, due to the lack of the proper vendor software. Hence, a simulator was designed to predict the performance of the software. The simulator was based on reliable time measurements obtained from previous work with the same array processor, using a 16-bit host computer, as well as experiments with the current 32-bit host computer. (Author)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Dec 01, 1983
Accession Number
ADA137767

Entities

People

  • H. A. Kamel
  • M. Jin
  • N. Sarigul
  • R. Kolar

Organizations

  • University of Arizona

Tags

Communities of Interest

  • Space

DTIC Thesaurus Topics

  • Application Software
  • Computations
  • Computer Programming
  • Computer Programs
  • Computers
  • Control Simulators
  • Engineering
  • Engineers
  • Finite Element Analysis
  • Host Computers
  • Measurement
  • Mechanical Engineering
  • Midrange Computers
  • Simulators
  • Software Development
  • Structural Analysis
  • Universities

Fields of Study

  • Engineering

Readers

  • Computer Science.
  • Finite Element Method (FEM) for solving Partial Differential Equations (PDEs)
  • Phased Array Antenna Design.