US 12,271,990 B2
Systems and methods for optimization of graphics processing for machine learning inference
Raman Sarokin, Zürich (CH); and Juhyun Lee, Palo Alto, CA (US)
Assigned to GOOGLE LLC, Mountain View, CA (US)
Filed by Google LLC, Mountain View, CA (US)
Filed on Dec. 30, 2022, as Appl. No. 18/091,671.
Claims priority of provisional application 63/331,593, filed on Apr. 15, 2022.
Prior Publication US 2023/0334747 A1, Oct. 19, 2023
Int. Cl. G06T 15/00 (2011.01); G06T 1/20 (2006.01); G06T 15/04 (2011.01)
CPC G06T 15/005 (2013.01) [G06T 1/20 (2013.01); G06T 15/04 (2013.01)] 18 Claims
OG exemplary drawing
 
1. A computing system for optimizing utilization of graphics processors for machine learning inference tasks, comprising:
one or more processors, wherein the one or more processors comprises a Graphics Processing Unit (GPU);
one or more non-transitory computer-readable media that collectively store instructions that, when executed by the one or more processors, cause the computing system to perform operations, the operations comprising:
simultaneously rendering, via a Multi-Render Target process of a WebGL application programming interface, a plurality of textures from an input to a machine-learned model;
generating a plurality of shaders based at least in part on a layout of the plurality of textures, wherein each of the plurality of shaders corresponds to at least one operator of a plurality of operators of the machine-learned model; and
processing, using the GPU, the plurality of textures with the plurality of shaders to obtain a machine-learning output for the machine-learned model.