Browse Prior Art Database

Hardware Clipping Comparator

IP.com Disclosure Number: IPCOM000060976D
Original Publication Date: 1986-Jun-01
Included in the Prior Art Database: 2005-Mar-09
Document File: 2 page(s) / 56K

Publishing Venue

IBM

Related People

Bryan, R: AUTHOR [+3]

Abstract

A hardware implementation of a clipping comparator is shown for handling cases of trivial except/reject in computer graphics. The hardware implementation can potentially reduce processing time by a factor of 3 to 5. In computer graphics, the primitives are points and lines. A box in three dimension or rectangle in two dimension is defined by the user to determine the visibility of the objects, that is, a point or portion of a line is visible if it is inside the box or rectangle. The process of removing the invisible part against the box is called clipping. In the two-dimensional case, let xmin, xmax, ymin, and ymax be the boundaries of the rectangle (clipping window). For each point, the Cohen- Sutherland algorithm defines the four-bit outcode.

This text was extracted from a PDF file.
At least one non-text object (such as an image or picture) has been suppressed.
This is the abbreviated version, containing approximately 52% of the total text.

Page 1 of 2

Hardware Clipping Comparator

A hardware implementation of a clipping comparator is shown for handling cases of trivial except/reject in computer graphics. The hardware implementation can potentially reduce processing time by a factor of 3 to 5. In computer graphics, the primitives are points and lines. A box in three dimension or rectangle in two dimension is defined by the user to determine the visibility of the objects, that is, a point or portion of a line is visible if it is inside the box or rectangle. The process of removing the invisible part against the box is called clipping. In the two-dimensional case, let xmin, xmax, ymin, and ymax be the boundaries of the rectangle (clipping window). For each point, the Cohen- Sutherland algorithm defines the four-bit outcode. Bit 1 is the sign bit of ymax-y; bit 2 is the sign bit y-ymin; bit 3 is the sign bit of xmax-x; and bit 4 is the sign bit of x-xmin. The outcode is shown in Fig. 1 for points x,y. Let outcode1 and outcode2 be the outcodes of the end points of a line, a. (outcode1) or (outcode2) = 0 means the line is inside the window - trivially accepted; b. (outcode1) and (outcode2) / 0 means it is entirely outside the window - trivially rejected. In the case of a point, it is inside if and only if the outcode is 0. The implementation of the above algorithm in software (or microcode) is quite time- consuming - setting up the outcode and testing for each point or end point takes 15-30 cycles. Described here is a design of a hardware implementation (Fig. 1) which would reduce the processing time for each point to 5 cycles. All the numbers discussed here are twos complement 32-bit integers. Let xmin,xmax,ymin,ymax,zmax,zmin denote the left,right,bottom, top,front,rear boundary of the clipping box. These numbers a...