Optimizing a graphics rendering pipeline using early Z-mode
One embodiment of the present invention sets forth an architecture for advancing the Z-test operation prior to pixel shading whenever possible. The current rendering state, as maintained by the setup engine, determines whether advancing the Z-test function above the shader engine for “early” Z-testing is possible or whether the Z-test function should be deferred until after shading operations for “late” Z-testing. Data is dynamically routed to each processing engine in the pipeline, so that the appropriate data flow for either early Z or late Z is dynamically constructed, as determined by the current rendering state. The same functional units are utilized in both early Z and late Z configurations.
1. A configurable graphics rendering pipeline for processing graphics primitives, the graphics rendering pipeline comprising:
a setup engine configured to determine whether processing should proceed in early Z-mode or late Z-mode;
a raster engine configured to receive a geometry primitive from the setup engine and convert the geometry primitive into one or more pixel primitives;
a shader engine configured to perform shading operations on one or more samples associated with a pixel primitive;
a Z-raster operations (ZROP) unit configured to perform Z-testing on each of the samples; and
a pre-raster operations (PROP) unit configured to modify, via one or more multiplexers, a data flow path between the shader engine and the ZROP unit to support both early Z-mode and late Z-mode, wherein the PROP unit includes a Z-resolve engine that is configured in both early Z-mode and late Z-mode to discard samples that do not pass the Z-testing performed by the ZROP unit,
wherein the samples associated with the pixel primitive are processed first by the ZROP unit and the Z-resolve engine and then by the shader engine when the graphics rendering pipeline is configured for early Z-mode, and the samples are processed first by the shader engine and then by the ZROP unit and the Z-resolve engine when the graphics rendering pipeline is configured for late Z-mode.
2. The graphics rendering pipeline of claim 1 , wherein the setup engine is configured to evaluate a rendering state associated with the geometry primitive to determine whether a change from early Z-mode to late Z-mode or from late Z-mode to early Z-mode should be made.
3. The graphics rendering pipeline of claim 2 , wherein the set up engine is configured to execute a flush operation prior to switching from early Z-mode to late Z-mode or from late Z-mode to early Z-mode.
4. The graphics rendering pipeline of claim 3 , wherein the setup engine is configured to instruct the PROP unit to modify the data flow path between the shader engine and the ZROP unit to switch from early Z-mode to late Z-mode or from late Z-mode to early Z-mode.
5. The graphics rendering pipeline of claim 1 , wherein the setup engine comprising a hysteresis counter that tracks the number of geometry primitives presented to the setup engine since the graphics rendering pipeline was last configured for late Z-mode.
6. The graphics rendering pipeline of claim 1 , wherein a hysteresis count is set to a count value, and the hysteresis count is advanced each time the setup engine receives a new geometry primitive while the graphics rendering pipeline is configured for late Z-mode.
7. The graphics rendering pipeline of claim 6 , wherein the setup engine is permitted to switch the graphics rendering pipeline configuration to early Z-mode when the hysteresis count equals a trigger value.
8. A computer system configured to process graphics primitives, the computer system comprising:
a memory; and
a processing unit that includes a configurable graphics rendering pipeline having:
a setup engine configured to determine whether processing should proceed in early Z-mode or late Z-mode;
a raster engine configured to receive a geometry primitive from the setup engine and convert the geometry primitive into one or more pixel primitives;
a shader engine configured to perform shading operations on one or more samples associated with a pixel primitive;
a Z-raster operations (ZROP) unit configured to perform Z-testing on each of the samples; and
a pre-raster operations (PROP) unit configured to modify, via one or more multiplexers, a data flow path between the shader engine and the ZROP unit to support both early Z-mode and late Z-mode, wherein the PROP unit includes a Z-resolve engine that is configured in both early Z-mode and late Z-mode to discard samples that do not pass the Z-testing performed by the ZROP unit,
wherein the samples associated with the pixel primitive are processed first by the ZROP unit and the Z-resolve engine and then by the shader engine when the graphics rendering pipeline is configured for early Z-mode, and the samples are processed first by the shader engine and then by the ZROP unit and the Z-resolve engine when the graphics rendering pipeline is configured for late Z-mode.
9. The computing system of claim 8 , wherein the setup engine is configured to evaluate a rendering state associated with the geometry primitive to determine whether a change from early Z-mode to late Z-mode or from late Z-mode to early Z-mode should be made.
10. The computing system of claim 9 , wherein the set up engine is configured to execute a flush operation prior to switching from early Z-mode to late Z-mode or from late Z-mode to early Z-mode.
11. The computing system of claim 10 , wherein the setup engine is configured to instruct the PROP unit to modify the data flow path between the shader engine and the ZROP unit to switch from early Z-mode to late Z-mode or from late Z-mode to early Z-mode.
12. The computing system of claim 8 , wherein the setup engine comprises a hysteresis counter that tracks the number of geometry primitives presented to the setup engine since the graphics rendering pipeline was last configured for late Z-mode.
13. The computing system of claim 8 , wherein a hysteresis count is set to a count value, and the hysteresis count is advanced each time the setup engine receives a new geometry primitive while the graphics rendering pipeline is configured for late Z-mode.
14. The computing system of claim 13 , wherein the setup engine is permitted to switch the graphics rendering pipeline configuration to early Z-mode when the hysteresis count equals a trigger value.
15. A method for switching the configuration of a graphics rendering pipeline between early Z-mode and late Z-mode, the method comprising:
receiving a geometry primitive;
determining whether the graphics rendering pipeline is configured for early Z-mode or for late Z-mode;
determining whether to switch, via one or more multiplexers included in a pre-raster operations (PROP) unit, the configuration of the graphics rendering pipeline from early Z-mode to late Z-mode or from late Z-mode to early Z-mode, wherein the PROP unit further includes a Z-resolve engine that is configured in both early Z-mode and late Z-mode to discard samples that do not pass the Z-testing performed by a Z-raster operations (ZROP) unit; and
executing a flush operation to complete in-progress work in the graphics rendering pipeline, if the configuration of the graphics rendering pipeline is to be switched.
16. The method of claim 15 , further comprising the step of advancing a hysteresis count upon receiving the geometry primitive, if the graphics rendering pipeline is determined to be configured for late Z-mode.
17. The method of claim 16 , wherein the step of determining whether to switch the configuration of the graphics rendering pipeline comprises determining whether the hysteresis count is equal to a trigger value, if the graphics rendering pipeline is determined to be configured for late Z-mode.
18. The method of claim 15 , further comprising the step of switching, via the one or more multiplexers, the configuration of the graphics rendering pipeline to early Z-mode by modifying a data flow path through the graphics rendering pipeline so that pixel primitives are transmitted to the ZROP unit and the Z-resolve engine before being transmitted to a shader engine.
19. The method of claim 15 , wherein the step of determining whether to switch the configuration of the graphics rendering pipeline comprises evaluating a rendering state associated with the geometry primitive.
20. The method of claim 15 , wherein the graphics rendering pipeline is configured for early Z-mode, and further comprising the step of switching the configuration to late Z-mode by modifying a data flow path through the graphics rendering pipeline so that pixel primitives are transmitted to a shader engine before being transmitted to the ZROP unit and the Z-resolve engine.