Method, apparatus, and computer program product for improved graphics performance

A method comprising:

• determining a first bounding region for a first set of graphics primitives, wherein the first bounding region is to enclose one or more of the first set of graphics primitives;
• performing back-face culling on the first set of graphics primitives based on the first bounding region, wherein some of the first set of graphics primitives are removed as a result of the back-face culling to generate a second set of graphics primitives;
• performing tessellation of the second set of graphics primitives to generate a third set of graphics primitives;
• determining whether one or more of the third set of graphics primitives overlap at least a first tile of a plurality of image tiles of an image frame to identify a fourth set of graphics primitives which contribute to image data within the first tile;
• performing vertex shading on input vertices of one or more of the fourth set of graphics primitives to generate output vertices having modified positional attributes;
• and
• generating output pixels based on the output vertices;
• and
• storing the output pixels in a frame buffer;
• wherein the operations of determining a first bounding region, performing back-face culling, performing tessellation, determining one or more of a fourth set of graphics primitives overlap at least a first tile, performing vertex shading, generating output pixels, and storing the output pixels are performed by one or more processing elements configured to execute graphics commands.

A non-transitory machine-readable medium having program code stored thereon which, when executed by a machine, causes the machine to perform the operations of:

• determining a first bounding region for a first set of graphics primitives, wherein the first bounding region is to enclose one or more of the first set of graphics primitives;
• performing back-face culling on the first set of graphics primitives based on the first bounding region, wherein some of the first set of graphics primitives are removed as a result of the back-face culling to generate a second set of graphics primitives;
• performing tessellation of the second set of graphics primitives to generate a third set of graphics primitives;
• determining whether one or more of the third set of graphics primitives overlap at least a first tile of a plurality of image tiles of an image frame to identify a fourth set of graphics primitives which contribute to image data within the first tile;
• performing vertex shading on input vertices of one or more of the fourth set of graphics primitives to generate output vertices having modified positional attributes;
• and
• generating output pixels based on the output vertices;
• and
• storing the output pixels in a frame buffer;
• wherein the operations of determining a first bounding region, performing back-face culling, performing tessellation, determining one or more of a fourth set of graphics primitives overlap at least a first tile, performing vertex shading, generating output pixels, and storing the output pixels are performed by one or more processing elements configured to execute graphics commands.

A system comprising:

• a system memory to store graphics instructions and data;
• and
• a graphics processing unit comprising:
• first circuitry to determine a first bounding region for a first set of graphics primitives, wherein the first bounding region is to enclose one or more of the first set of graphics primitives;
• second circuitry to perform back-face culling on the first set of graphics primitives based on the first bounding region, wherein some of the first set of graphics primitives are removed as a result of the back-face culling to generate a second set of graphics primitives;
• third circuitry to perform tessellation of the second set of graphics primitives to generate a third set of graphics primitives;
• fourth circuitry to determine whether one or more of the third set of graphics primitives overlap at least a first tile of a plurality of image tiles of an image frame, the fourth circuitry to identify a fourth set of graphics primitives which contribute to image data within the first tile;
• fifth circuitry to perform vertex shading on input vertices of one or more of the fourth set of graphics primitives to generate output vertices having modified positional attributes;
• and
• sixth circuitry to generate output pixels based on the output vertices;
• a frame buffer to store the output pixels;
• wherein the first circuitry, the second circuitry, the third circuitry, the fourth circuitry, fifth circuitry, and sixth circuitry are integrated within one or more processing elements configured to execute graphics commands.