
Accession Number : ADA195882
Title : The Triangle: a Multiprocessor Architecture for Fast Curve and Surface Generation.
Descriptive Note : Technical rept.,
Corporate Author : WASHINGTON UNIV SEATTLE DEPT OF COMPUTER SCIENCE
Personal Author(s) : Holman, Thomas J ; DeRose, Tony
PDF Url : ADA195882
Report Date : Aug 1987
Pagination or Media Count : 38
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 realtime, at a density of 1,000 points per patch. Keywords: Bsplines; Computeraided geometric design; Curves and surfaces; Graphics hardware. (KR)
Descriptors : *MULTIPROCESSORS, *COMPUTER ARCHITECTURE, ALGORITHMS, ARCHITECTURE, COMPUTER AIDED DESIGN, CONICAL BODIES, GEOMETRY, GRAPHICS, GRAPHS, OPERATION, PARALLEL ORIENTATION, PEAK VALUES, RATES, SPECTRA, SURFACES, TENSORS, TRIANGLES
Subject Categories : Computer Hardware
Distribution Statement : APPROVED FOR PUBLIC RELEASE