|Graphics processor, video card|
|Wednesday, 15 November 2006|
A computer system typically relies upon its graphics system for producing visual output on a computer screen or display device. In order to enable desktop and other computers to rapidly process graphics and game technology, add-on units generally referred to as graphics cards or VGA cards are often installed in computer devices. Such cards include a dedicated graphics processing unit, called a GPU, one or more memory chips, and other required circuitry, all mounted to a circuit board including an edge connector that is adapted to plug into an available slot in the associated computer device. Graphics processors include a hardware architecture and programming instructions designed specifically to perform specialized tasks associated with video graphics. The typical GPU is a highly complex integrated circuit device optimized to perform graphics computations and write the results to the graphics memory. The graphics processing unit is a "slave" processor that operates in response to commands received from a driver program executing on a "master" processor, generally the central processing unit (CPU) of the system. A graphics card generally includes a specialized processor or processors that are tailor-made for graphics rendering, as well as an amount of memory so that a complete screen of graphics information, known as a frame, can be stored by the graphics card. This memory is generally known as a frame buffer of the graphics card. Graphics boards, or video cards, in early systems acted as simple interfaces between the CPU and the display device, and did not conduct any processing of their own. Traditionally graphics processing systems were implemented as fixed function computation units and more recently the computation units are programmable to perform a limited set of operations. Computation units are connected in a "shading pipeline" to perform shading operations. Processed graphics data including pixel color and depth values are output by the shading pipeline and written to output buffers in memory. As video graphics processing circuits continue to evolve, additional capabilities that allow video signals to be provided to a number of different outputs of the circuits exist. In such systems, the video signals are often broken down into their component parts and stored in memory. Modern graphics systems incorporate graphics processors with a great deal of processing power For example, modern computer displays have many more pixels, greater color depth, and are able to display images with higher refresh rates than earlier models. The images displayed are now more complex and may involve advanced rendering and visual techniques such as anti-aliasing and texture mapping. In many computer architectures, an accelerated graphics port (AGP) chip set is included. The AGP chip set provides an interface between the central processing unit system memory, graphics circuitry, and peripheral ports. The AGP chip set coordinates transport of data between such devices. A driver is used to control the graphics card in a computer system. The graphical processing system renders an image to display on a display device according to a display mode that is selected by the user. The graphical processing system supports a variety of display modes that are included in a display mode list. The display mode list generally is dependent on the graphical processing unit of the graphical processing system.
In computer graphics applications, complex shapes and structures are formed through the sampling, interconnection and rendering of more simple objects, referred to as primitives. Graphics primitives may include lines, characters, areas such as triangles and ellipses, and solid or patterned shapes such as polygons, spheres, cylinders and the like. These primitives, in turn, are formed by the interconnection of individual pixels. Color and texture are then applied to the individual pixels that comprise the shape based on their location within the primitive and the primitives orientation with respect to the generated shape; thereby generating the object that is rendered to a corresponding display for subsequent viewing. As computing systems continue to evolve, the graphical display requirements of the systems become more demanding. This is especially true in the area of three-dimensional (3D) graphics processing. In order to process 3D graphics images, the position of graphics primitives with respect to the display must be understood in all three dimensions. This includes the dimension of depth, often referred to as the Z dimension. The Z dimension describes the positioning of a video graphics primitive with respect to other video graphics primitives within the display frame in terms of the depth, or distance from the viewer, of the video graphics primitives. Graphics processor typically connects to its own dedicated graphics memory, which graphics processor uses for frame buffering, z-buffering, polygon data storage, etc. But when the computer runs graphics-intensive applications such as those that use 3D rendering, graphics processor may require dramatically more memory capacity to create high-quality graphics. Modern computers typically produce graphical output using a sequence of tasks known as a graphics pipeline. These tasks start with a mathematical representation of an image to be produced and finish with pixel data suitable for display on a video screen or other output device. Graphics processors that implement the functionality of graphics pipelines, such as graphics pipeline, may have user-programming capability, but such programmability typically is limited to vertex-oriented processing. The three-dimensional (3D) pipeline that processes the triangular primitives rasterizes these planar primitives to produce pixel data that is blended with additional pixel data stored in a frame buffer. The results produced in the frame buffer are then fetched and a display signal is generated such that the three-dimensional objects are shown on the display.