Three-Stage Model of the Graphics Pipeline

1. The CPU subsystem. The application program running on the CPU, feeding commands to the graphics subsystem.

2. The geometry subsystem. The per-polygon operations, such as coordinate transformations, lighting, texture coordinate generation, and clipping.

3. The raster subsystem. The per-pixel operations, such as the simple operation of writing color values into the framebuffer, or more complex operations like depth buffering, alpha blending, and texture mapping.

Figure 11-1 : Three-Stage Model of the Graphics Pipeline Note that on some platforms, part of the geometry subsystem is implemented within the CPU subsystem, but the conceptual model is still useful. Note also that this three-stage model is simpler than the actual hardware implementation in the various models in the Silicon Graphics product line, but it is detailed enough for all but the most subtle tuning tasks.

The amount of work required from the different pipeline stages varies among applications. For example, consider a program that draws a small number of large polygons. Because there are only a few polygons, the pipeline stage that does geometry operations is lightly loaded. Because those few polygons cover many pixels on the screen, the pipeline stage that does rasterization is heavily loaded.

To speed up this program, you must speed up the rasterization stage, either by drawing fewer pixels, or by drawing pixels in a way that takes less time by turning off modes like texturing, blending, or depth-buffering. In addition, because spare capacity is available in the per-polygon stage, you can increase the work load at that stage without degrading performance. For example, you can use a more complex lighting model, or define geometries such that they remain the same size but look more detailed because they are composed of a larger number of polygons.