公开(公告)号：US20240412334A1

公开(公告)日：2024-12-12

申请号：US18735050

申请日：2024-06-05

Applicant: Google LLC

Inventor： Raman Sarokin ,  Yu-Hui Chen ,  Juhyun Lee ,  Jiuqiang Tang ,  Chuo-Ling Chang ,  Andrei Kulik ,  Matthias Grundmann

IPC: G06T5/60 ,  G06T1/20 ,  G06T5/70

Abstract: Systems, methods, devices, and related techniques for accelerating execution of diffusion models or of other neural networks that involve similar operations. Some aspects include accelerating inference computations in neural networks, including inference computations utilized in denoising (also referred to as “diffusion”) neural networks.

公开(公告)号：US12271990B2

公开(公告)日：2025-04-08

申请号：US18091671

申请日：2022-12-30

Applicant: Google LLC

Inventor： Raman Sarokin ,  Juhyun Lee

IPC: G06T15/00 ,  G06T1/20 ,  G06T15/04

Abstract: Systems and methods of the present disclosure are directed to a method for optimizing utilization of graphics processors for machine learning inference tasks. The method includes simultaneously rendering, by a computing system comprising one or more computing devices, a plurality of textures from an input to a machine-learned model. The method includes generating, by the computing system, 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. The method includes processing, by the computing system using a Graphics Processing Unit (GPU), the plurality of textures with the plurality of shaders to obtain a machine-learning output for the machine-learned model.

公开(公告)号：US20230334747A1

公开(公告)日：2023-10-19

申请号：US18091671

申请日：2022-12-30

Applicant: Google LLC

Inventor： Raman Sarokin ,  Juhyun Lee

IPC: G06T15/00 ,  G06T15/04 ,  G06T1/20

CPC classification number: G06T15/005 ,  G06T1/20 ,  G06T15/04

Abstract: Systems and methods of the present disclosure are directed to a method for optimizing utilization of graphics processors for machine learning inference tasks. The method includes simultaneously rendering, by a computing system comprising one or more computing devices, a plurality of textures from an input to a machine-learned model. The method includes generating, by the computing system, 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. The method includes processing, by the computing system using a Graphics Processing Unit (GPU), the plurality of textures with the plurality of shaders to obtain a machine-learning output for the machine-learned model.