Importance

Loading Importance Indicators...

Abstract

A method for handling Z-values in accordance with the present invention. The Z-values correspond to vertices of a given primitive being processed within a graphics pipeline. The Z-values received by the pipeline are represented in a first floating point format (such as IEEE floating point format) which includes a mantissa portion and an exponent portion. The method comprises determining which of the Z-values for the given primitive has the largest value of the exponent portion. In one embodiment, this includes comparing current exponent values to a current greatest exponent value until all Z-values are tested. The method subsequently comprises generating a common Z exponent value in response to determining the largest exponent value for the given primitive. In one embodiment, the common Z exponent value is generated by subtracting a constant value from the largest exponent value. The method next comprises converting the Z-values of the given primitive to a fixed point format in which the mantissa portion is scaled to the common Z exponent value. The converted values are then forwarded with the primitive as graphics processing continues with a first set of operations which utilize the Z-values (represented in the fixed point format) and the common Z exponent value. Since it is likely the Z exponents for the given primitive are closely related, the Z-values may be represented with a single exponent value. After this first set of operations, the Z-values are converted back to a second floating point format. A second set of graphics operations (namely, hidden surface removal) is then performed using this second floating point format. By using the common Z exponent and the intermediate fixed point format for representation, Z-values of the given primitive are more efficiently handled throughout the rendering pipeline.

Loading the Abstract Image...

First Claim