초록 ▼

A system, method and computer program product are provided for branching during graphics processing. Initially, a first operation is performed on data. In response to the first operation, a branching operation is performed to a second operation. The first operation and the second operation are assoc

A system, method and computer program product are provided for branching during graphics processing. Initially, a first operation is performed on data. In response to the first operation, a branching operation is performed to a second operation. The first operation and the second operation are associated with instructions selected from a predetermined instruction set.

대표청구항 ▼

What is claimed is: 1. A method for branching during graphics processing, comprising: performing a first operation on data; in response to the first operation, branching to a second operation, utilizing a processor; and outputting a result of the graphics processing; wherein the first operation and

What is claimed is: 1. A method for branching during graphics processing, comprising: performing a first operation on data; in response to the first operation, branching to a second operation, utilizing a processor; and outputting a result of the graphics processing; wherein the first operation and the second operation are associated with instructions selected from a predetermined instruction set; wherein the first operation and the second operation include at least one of a branch operation, a call operation, a fraction operation, a no operation, a move operation, a multiply operation, an addition operation, a multiply and addition operation, a reciprocal operation, a reciprocal square root operation, a three component dot product operation, a four component dot product operation, a distance operation, a minimum operation, a maximum operation, an exponential operation, a logarithm operation, and a lighting operation; wherein at least one of the first operation and the second operation includes one of the three component dot product operation, the four component dot product operation, the no operation, the minimum operation and the maximum operation; wherein at least one of the first operation and the second operation includes the minimum operation, and the minimum operation determines a minimum associated with a plurality of data sources, and moves the minimum into a destination location; wherein the first operation and the second operation are each carried out utilizing a data structure; wherein the data structure includes a source location identifier indicating a location of the data, a source component identifier indicating a component of the location in which the data is located, a destination location identifier indicating a destination of the output result, and a destination component identifier indicating a component of the destination to which the result is output. 2. The method as recited in claim 1, wherein the branching to the second operation is performed if content of a predetermined register is true. 3. The method as recited in claim 1, wherein the branching to the second operation is performed based on a comparison. 4. The method as recited in claim 3, wherein the comparison includes a greater than operation. 5. The method as recited in claim 3, wherein the comparison includes a less than operation. 6. The method as recited in claim 3, wherein the comparison includes a greater than or equal operation. 7. The method as recited in claim 3, wherein the comparison includes a less than or equal operation. 8. The method as recited in claim 3, wherein the comparison includes an equal operation. 9. The method as recited in claim 3, wherein the comparison includes a not equal operation. 10. The method as recited in claim 1, wherein the branching to the second operation is performed based on a comparison involving zero. 11. The method as recited in claim 1, wherein the branching is performed to a label. 12. The method as recited in claim 1, wherein the branching involves a swizzle operation. 13. The method as recited in claim 1, wherein at least one of the first operation and the second operation includes the maximum operation, and the maximum operation determines a maximum associated with a plurality of data sources, and moves the maximum into a destination location. 14. The method as recited in claim 1, wherein at least one of the first operation and the second operation includes the minimum operation and the maximum operation, and the maximum operation and the minimum operation each utilize two vectors as input, and output one vector. 15. The method as recited in claim 1, wherein at least one of the first operation and the second operation includes the distance operation, and the distance operation calculates a distance vector. 16. The method as recited in claim 15, wherein the distance vector is calculated by calculating a distance of a first vector and a second vector, where the distance vector includes four components. 17. The method as recited in claim 16, wherein a first component of the four component distance vector is 1.0, a second component of the four component distance vector includes a second component of the first vector multiplied by a second component of the second vector, a third component of the four component distance vector includes a third component of the first vector, and a fourth component of the four component distance vector includes a fourth component of the second vector. 18. The method as recited in claim 1, wherein the branching to the second operation is performed based on a Boolean condition. 19. The method as recited in claim 1, wherein the branching to the second operation is performed if content of a condition code register is true. 20. The method as recited in claim 1, wherein the component of the location in which the data is located and the component of the destination to which the result is output each include a single component of a vector that includes four components, where a first component of the vector is indicated by a x subscript, a second component of the vector is indicated by a y subscript, a third component of the vector is indicated by a z subscript, and a fourth component of the vector is indicated by a w subscript. 21. The method as recited in claim 1, wherein the data is normalized by altering the data by a scaling bias prior to the first operation being performed on the data. 22. A computer storage medium for storing a computer program for branching during graphics processing, comprising: computer code for performing a first operation on data; and computer code for branching to a second operation in response to the first operation; wherein the first operation and the second operation are associated with instructions selected from a predetermined instruction set; wherein the first operation and the second operation include at least one of a branch operation, a call operation, a fraction operation, a no operation, a move operation, a multiply operation, an addition operation, a multiply and addition operation, a reciprocal operation, a reciprocal square root operation, a three component dot product operation, a four component dot product operation, a distance operation, a minimum operation, a maximum operation, an exponential operation, a logarithm operation, and a lighting operation; wherein at least one of the first operation and the second operation includes one of the three component dot product operation, the four component dot product operation, the no operation, the minimum operation and the maximum operation; wherein at least one of the first operation and the second operation includes the minimum operation, and the minimum operation determines a minimum associated with a plurality of data sources, and moves the minimum into a destination location; wherein the computer program is operable such that the first operation and the second operation are each carried out utilizing a data structure; wherein the data structure includes a source location identifier indicating a location of the data, a source component identifier indicating a component of the location in which the data is located, a destination location identifier indicating a destination of the output result, and a destination component identifier indicating a component of the destination to which the result is output. 23. A computer storage medium for storing an application program interface data structure for branching during graphics processing, comprising: an instruction set for performing a first operation on data, and in response to the first operation, branching to a second operation; wherein the instruction set includes operations including at least one of a fraction operation, a no operation, a move operation, a multiply operation, an addition operation, a multiply and addition operation, a reciprocal operation, a reciprocal square root operation, a three component dot product operation, a four component dot product operation, a distance operation, a minimum operation, a maximum operation, an exponential operation, a logarithm operation, and a lighting operation; wherein at least one of the first operation and the second operation includes one of the three component dot product operation, the four component dot product operation, the no operation, the minimum operation and the maximum operation; wherein at least one of the first operation and the second operation includes the minimum operation, and the minimum operation determines a minimum associated with a plurality of data sources, and moves the minimum into a destination location; wherein the instruction set is operable such that the first operation and the second operation are each carried out utilizing a data structure; wherein the data structure includes a source location identifier indicating a location of the data, a source component identifier indicating a component of the location in which the data is located, a destination location identifier indicating a destination of the output result, and a destination component identifier indicating a component of the destination to which the result is output.