US 11,055,806 B2
Method and apparatus for directing application requests for rendering
Gregory A. Grebe, Orlando, FL (US); Jonathan Lawrence Campbell, Orlando, FL (US); and Layla A. Mah, Lowell, MA (US)
Assigned to ADVANCED MICRO DEVICES, INC., Sunnyvale, CA (US)
Filed by Advanced Micro Devices, Inc., Sunnyvale, CA (US)
Filed on Feb. 24, 2016, as Appl. No. 15/51,952.
Claims priority of provisional application 62/121,968, filed on Feb. 27, 2015.
Prior Publication US 2016/0253774 A1, Sep. 1, 2016
Int. Cl. G06T 15/00 (2011.01); G06T 1/20 (2006.01)
CPC G06T 1/20 (2013.01) 19 Claims
OG exemplary drawing
 
1. A method for providing efficient display rendering, implemented in a computer system including a display adapter including a plurality of processors, comprising:
determining, by a graphics processing unit (GPU) control application program interface (API) of the display adapter in communication with each of the processors of the plurality of processors, one or more processors in the system on which to execute one or more commands upon receipt of a control request for executing display rendering;
transmitting, by a GPU mask control through the GPU control API, a signal to a GPU mask device that is operatively coupled to each of the one or more processors indicating which of the one or more commands are to be executed by that processor;
forwarding, by the GPU mask device, respective commands of the one or more commands to the respective one or more processors indicated to execute their respective commands;
executing, by the one or more processors, their respective command;
transmitting, by a GPU transfer control through the GPU control API, a request to the GPU mask device for each of the one or more processors to transfer information to one another once processing is complete;
forwarding, by the GPU mask device, the request to transfer information to the respective one or more processors;
transmitting, by a GPU queue synch control through the GPU control API, a synch command to the GPU mask device, the synch command indicating at least one processor of the one or more processors is to synchronize rendering of an image based upon receiving the transferred information from another processor;
forwarding, by the GPU mask device, the synch command to the respective at least one processor; and
rendering, by the at least one processor to a display, based upon a respective command received from the GPU mask device, an image based upon the processed information by that processor and the received transferred information from at least another processor received by the at least one processor when the at least one processor receives the transferred information.