Topology preservation in a graphics pipeline by analyzing a geometry shader

Abstract

A graphics processing engine has a geometry shading stage having two modes of operation. In the first mode of operation, each primitive output by the geometry shading stage is independent, whereas in the second mode of operation, connectivity between input primitives is maintained by the geometry shading stage. The mode of operation of the geometry shading stage can be determined based on the value of control state data which may be generated at compile-time for a geometry shader based on analysis of that geometry shader.

What is claimed is: 
     
         1 . A method of controlling operation of a geometry shading stage in a graphics processing system, the method comprising:
 receiving a geometry shader for execution by the geometry shading stage; and   in response to determining that the geometry shader preserves connectivity of a topology of primitives, generating control state data configured to set the geometry shading stage into a mode of operation.   
     
     
         2 . The method according to  claim 1 , wherein in the mode of operation the connectivity of primitives output by the geometry shading stage is maintained. 
     
     
         3 . The method according to  claim 1 , further comprising analyzing the geometry shader to determine whether it preserves connectivity of the topology of primitives, wherein the analysis is implemented in a compiler. 
     
     
         4 . The method according to  claim 1 , further comprising outputting the control state data, wherein the outputting comprises:
 providing the control state data as an extension to a stream of graphics data input to the geometry shading stage; and   passing the control state data to the geometry shading stage in an API.   
     
     
         5 . The method according to  claim 1 , wherein the method further comprises:
 receiving the control state data; and   switching the geometry shading stage into the mode of operation dependent upon a value of the received control state data;   wherein in the mode of operation connectivity of primitives is maintained.   
     
     
         6 . The method according to  claim 5 , further comprising, in the mode of operation:
 receiving primitive data for a primitive, the primitive data referencing a plurality of vertices;   identifying those vertices referenced in the primitive data that have not been previously processed by the geometry shading stage;   processing only the identified vertices; and   emitting data for the primitive.   
     
     
         7 . The method according to  claim 6 , wherein emitted data for the primitive is vertex data describing one or more new vertices of the primitive. 
     
     
         8 . The method according to  claim 7 , wherein the connectivity for the new vertices is maintained from the referenced plurality of vertices for the received primitive data. 
     
     
         9 . The method according to  claim 6 , further comprising, in the mode of operation:
 storing an output from the processing of the identified vertices in a buffer, wherein the output comprises modified vertex data.   
     
     
         10 . The method according to  claim 5 , wherein the control state data relates to a particular geometry shader and is generated when the geometry shader is compiled. 
     
     
         11 . The method according to  claim 5 , further comprising:
 receiving primitive data as a stream of graphics data;   wherein the control state data is received as an extension to the stream of graphics data.   
     
     
         12 . The method according to  claim 5 , wherein the control state data is received from an application via an API. 
     
     
         13 . The method according to  claim 5 , wherein the geometry shading stage is operated in the mode of operation for stereoscopic rendering. 
     
     
         14 . A processor configured to perform the method as set forth in  claim 1 . 
     
     
         15 . The processor according to  claim 14 , wherein the processor is embodied in hardware on an integrated circuit. 
     
     
         16 . A method of manufacturing a processor, comprising inputting into an integrated circuit manufacturing system a computer readable dataset description of a processor as set forth in  claim 15 , which causes the integrated circuit manufacturing system to manufacture said processor. 
     
     
         17 . A non-transitory computer readable storage medium having stored thereon computer readable code configured to cause the method as set forth in  claim 1  to be performed when the code is run. 
     
     
         18 . A non-transitory computer readable storage medium having stored thereon a computer readable dataset description of an integrated circuit that, when processed in an integrated circuit manufacturing system, causes the integrated circuit manufacturing system to manufacture a processor configured to perform the method as set forth in  claim 1 . 
     
     
         19 . An integrated circuit manufacturing system configured to manufacture a processor configured to perform the method as set forth in  claim 1 . 
     
     
         20 . An integrated circuit manufacturing system comprising:
 a computer readable storage medium having stored thereon a computer readable dataset description of an integrated circuit that describes a processor configured to perform the method as set forth in  claim 1 ;   a layout processing system configured to process the integrated circuit description so as to generate a circuit layout description of an integrated circuit embodying the processor; and   an integrated circuit generation system configured to manufacture the processor according to the circuit layout description.