The Triangle: a Multiprocessor Architecture for Fast Curve and Surface Generation.

Abstract

This paper describes the architecture and operation of the Triangle, a pipelined, parallel multiprocessor architecture for the computation and rendering of line segments, conic sections, spline curves, triangular patch surfaces, and tensor product surfaces. Based on a generalization of de Casteljau's algorithm for computing points on Bezier curves, the Triangle can be used as an accelerator to dramatically enhance the performance of standard graphics workstations. Although there is a wide spectrum of possible implementations, we estimate that a custom VLSI implementation that is currently being designed will be capable of peak rates well in excess of one million points of evaluation per second. Assuming a Motorola 68020 host, such a processor should be capable of completely recomputing 65 bicubic patches in real-time, at a density of 1,000 points per patch. Keywords: B-splines; Computer-aided geometric design; Curves and surfaces; Graphics hardware. (KR)

Open PDF

Document Details

Document Type
Technical Report
Publication Date
Aug 01, 1987
Accession Number
ADA195882

Entities

People

  • Thomas J. Holman
  • Tony Derose

Organizations

  • University of Washington

Tags

Communities of Interest

  • Materials and Manufacturing Processes

DTIC Thesaurus Topics

  • Accumulators
  • Algorithms
  • Blending
  • Computations
  • Computer Science
  • Computers
  • Coordinate Systems
  • Demographic Cohorts
  • Graphics
  • Multiprocessors
  • Polygons
  • Processing Equipment
  • Shift Registers
  • Spectra
  • Standards
  • Test And Evaluation
  • Triangles

Readers

  • Approximation Theory.
  • Graph Algorithms and Convex Optimization.
  • Parallel and Distributed Computing.