To solve the problem that the boundary between hardware and software appears obscure to an application, and for this reason, the existing graphics libraries are not suitable for the finely-tuned control.
There is provided a graphics processing system that includes a main processing unit 100 and a graphics processing unit (GPU) 200. The main processing unit 100 puts rendering commands generated using a graphics library 300 by the application 310 in the queue of a command buffer 10 in a main memory 120. In this process, the library function offered by the graphics library 300 is converted into the rendering commands, without any rendering attributes retained in the library. The GPU 200 reads and executes the rendering commands stacked in the command buffer 10, and generates rendering data in a frame buffer 20.
JP4922367 | Systems and methods for providing intermediate targets within a graphics system |
WO/2013/108873 | IMAGE PROCESSOR FOR ENDOSCOPE |
JPH06187317 | PARALLEL ARITHMETIC NETWORK |
ENGSTAD PAL-KRISTIAN
CERNY MARK EVAN
HOFFMAN NATHANIEL
OLICK JON
KANEKO MOTOI
WASHIZU YOSHINORI
JPH09179717A | 1997-07-11 | |||
JP2004302927A | 2004-10-28 | |||
JP2005202983A | 2005-07-28 | |||
JP2008524720A | 2008-07-10 | |||
JP2005521178A | 2005-07-14 | |||
JP2008538829A | 2008-11-06 |
WO2004055672A1 | 2004-07-01 | |||
WO2006068985A2 | 2006-06-29 | |||
WO2006099328A1 | 2006-09-21 |