International Business Machines Corporation

Mark Christopher Fowler

Chandrasekhar Narayanaswami

Bengt-Olaf Schneider

Robert Spencer Horton

James Lewis Van Welzen

Mark Van Horn

Kirk Steffen Haskell

Thomas Y Kwok

Thomas Yu-Kiu Kwok

Steve Mastrianni

A method and apparatus for a computer graphics rendering system which slices the traditional geometry pipeline into two phases to improve overall graphics system utilization is described. The graphics system consists of a host processor and a graphics adapter. The host creates work items and feeds them to the graphics adapter. In the two phase method, the first phase computes the clipping status and immediately returns this status information, before completion of the actual clipping, to the application running on the host processor to minimize stalling the host processor and hence the application. The second phase performs the rest of the work necessary to draw the objects on the screen. The advantage of two phase method is that the host processor minimizes its wait (but only for model/view transformation and clipping status determination) for a return status from the graphics adapter for the current work item and gets to create the next work item from the application sooner.

Two phase rendering for computer graphics

While executing the standard graphics processing steps, problem polygons (i.e., those outside of a defined clip volume) are buffered for later processing, while the standard graphics processing continues, without the need for periodically reformatting data and performing clipping. After either a predefined number of polygons have been stored at the buffer location, or at such time as a change in the rendering state occurs, the buffered polygons are clipped.

Method and apparatus for deferred clipping of polygons

A parallel vector generator in which an Nx .times.Ny array of processors, each assigned to one particular pixel of each Nx .times.Ny block of contiguous pixels, operate concurrently to generate a pixel image of a line. Each processor of the array executes a version of the Bresenham line-drawing procedure that is modified so that iterations for pixels over which the processor has no control is eliminated. The processors are capable of processing lines having subpixel endpoints while using only integer arithmetic. Each processor contains a pair of parallel vector generators that are used to generate the endpoints of a triangle along each scan line.

Parallel vector generator and triangle generator incorporating same

Growing community of inventors

Colchester, VT, United States of America

Mark Christopher Fowler