US 11,869,114 B2
Efficient multi-GPU rendering by testing geometry against screen regions before rendering using a pretest GPU
Mark E. Cerny, Los Angeles, CA (US); Florian Strauss, San Mateo, CA (US); and Tobias Berghoff, San Mateo, CA (US)
Assigned to Sony Interactive Entertainment Inc., Tokyo (JP)
Filed by Sony Interactive Entertainment Inc., Tokyo (JP)
Filed on Mar. 1, 2022, as Appl. No. 17/684,105.
Application 17/684,105 is a continuation of application No. 16/780,680, filed on Feb. 3, 2020, granted, now 11,263,718.
Prior Publication US 2022/0188966 A1, Jun. 16, 2022
This patent is subject to a terminal disclaimer.
Int. Cl. G06T 1/20 (2006.01)
CPC G06T 1/20 (2013.01) 20 Claims
OG exemplary drawing
 
1. A method, comprising:
rendering graphics for an application using a plurality of graphics processing units (GPUs);
dividing responsibility for the rendering of geometry of the graphics between the plurality of GPUs based on a plurality of screen regions, each GPU having a corresponding division of the responsibility which is known to the plurality of GPUs;
performing in a frame period geometry testing at a pretest GPU on a plurality of pieces of geometry of an image frame generated by the application to generate information regarding each of the plurality of pieces of geometry and its relation to each of the plurality of screen regions, wherein the geometry testing determines whether each of the plurality of pieces of geometry overlaps the each of the plurality of screen regions; and
rendering in the frame period the plurality of pieces of geometry at each of the plurality of GPUs using the information generated for the each of the plurality of pieces of geometry wherein based on the information a GPU renders a corresponding piece of geometry that overlaps a screen region that is assigned to the GPU for rendering,
wherein each of a plurality of frame periods defines a target period of time over which a corresponding image frame of a plurality of image frames is generated for display.