Graphics processing architecture employing a unified shader
A graphics processing architecture in one example performs vertex manipulation operations and pixel manipulation operations by transmitting vertex data to a general purpose register block, and performing vertex operations on the vertex data by a processor unless the general purpose register block does not have enough available space therein to store incoming vertex data; and continues pixel calculation operations that are to be or are currently being performed by the processor based on instructions maintained in an instruction store until enough registers within the general purpose register block become available.
1. A graphics processing system, comprising:
an arbiter circuit operative to select vertex data and pixel data from a plurality of inputs;
a unified-shader circuit, coupled to the arbiter circuit, comprising:
a register block operative to concurrently store the vertex data and the pixel data selected by the arbiter circuit;
a sequencer operative to store instructions used to perform vertex operations on the vertex data stored in the register block and pixel operations on the pixel data stored in the register block; and
a processor operative to execute floating-point operations according to the instructions stored in the sequencer,
wherein the unified-shader circuit is further operative to perform the vertex operations on the vertex data selected by the arbiter circuit and the pixel operations on the pixel data selected by the arbiter circuit; and
wherein the unified-shader circuit is further operative to, according to the instructions stored in the sequencer, perform a texture-fetch operation during the vertex operations.
2. The graphics processing system of claim 1 , further including a vertex storage block for maintaining vertex information.
3. The graphics processing system of claim 2 , wherein the vertex storage block includes a parameter cache operative to maintain appearance attribute data and a position cache operative to maintain position data.
4. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to generate a color attribute associated with the pixel data selected by the arbiter circuit.
5. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to generate a position attribute associated with the vertex data selected by the arbiter circuit.
6. The graphics processing system of claim 5 , wherein the unified-shader circuit is further operative to generate a color attribute associated with the pixel data selected by the arbiter circuit.
7. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to generate an appearance attribute that comprises at least one of the following: a color attribute, a lighting attribute, a texture attribute, a normal attribute, and a position attribute.
8. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to generate a depth value.
9. The graphics processing system of claim 1 , wherein the arbiter circuit comprises a multiplexer and an arbiter operative to provide a control signal to the multiplexer.
10. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to generate vertex position data and wherein the graphics processing system further comprises a primitive assembly operative to generate primitives from the vertex position data.
11. The graphics processing system of claim 10 , further comprising a rasterization engine, coupled to the primitive assembly, operative to generate pixel parameter data from the primitives generated by the primitive assembly.
12. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to generate color information in response to the arbiter circuit selecting the pixel data from the plurality of inputs.
13. The graphics processing system of claim 1 , wherein the unified shader circuit further comprises source registers operative to store operands provided by the register block, such that the operands are ready for execution by the processor.
14. The graphics processing system of claim 1 , wherein the unified-shader circuit is further operative to access a vertex cache to perform the texture-fetch operation during the vertex operations.
15. A graphics processing system, comprising:
an arbiter circuit operative to select vertex data and pixel data from a plurality of inputs; and
a unified-shader circuit, coupled to the arbiter circuit, comprising:
a register block operative to concurrently store the vertex data and the pixel data selected by the arbiter circuit;
a sequencer operative to store instructions used to perform the vertex operations on the vertex data stored in the register block and the pixel operations on the pixel data stored in the register block; and
a processor operative to execute floating-point operations according to the instructions stored in the sequencer,
wherein the unified-shader circuit is further operative to simultaneously perform vertex operations on the vertex data selected by the arbiter circuit and pixel operations on the pixel data selected by the arbiter circuit; and
wherein the unified-shader circuit is further operative to switch from executing the vertex operations to executing the pixel operations before the vertex operations have been completed.
16. The graphics processing system of claim 15 , wherein the sequencer is further operative to fetch data from a memory.
17. The graphics processing system of claim 15 , wherein the arbiter circuit is further operative to provide information to the register block in response to a control signal.
18. The graphics processing system of claim 17 , wherein the arbiter circuit comprises a multiplexer and an arbiter operative to provide the control signal to the multiplexer.
19. The graphics processing system of claim 15 , wherein the processor is further operative to execute instructions to generate color information in response to the arbiter circuit selecting the pixel data from the plurality of inputs.
20. The graphics processing system of claim 15 , wherein the processor is further operative to execute vertex calculations while pixel calculations are still in progress.
21. The graphics processing system of claim 15 , wherein the processor is further operative to generate position data and appearance data in response to the arbiter circuit selecting the vertex data from the plurality of inputs.