US 12,079,641 B2
Machine learning based power and performance optimization system and method for graphics processing units
Zhiwei Tang, San Diego, CA (US); Jing Wu, San Diego, CA (US); and Suolong Dong, San Diego, CA (US)
Assigned to Moore Threads Technology Co., Ltd., Beijing (CN)
Filed by MOORE THREADS TECHNOLOGY CO., LTD., Beijing (CN)
Filed on Aug. 3, 2022, as Appl. No. 17/879,986.
Prior Publication US 2024/0045699 A1, Feb. 8, 2024
Int. Cl. G06F 9/44 (2018.01); G06F 9/448 (2018.01); G06N 3/08 (2023.01); G06T 1/20 (2006.01); G06T 15/00 (2011.01)
CPC G06F 9/4482 (2018.02) [G06N 3/08 (2013.01); G06T 1/20 (2013.01); G06T 15/005 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A computer-implemented method to dynamically adjust operating conditions of a graphics processing unit (GPU), the method comprising:
training a machine learning model to determine operating voltages and frequencies to be provided to a GPU core of the GPU to execute a workload comprising a plurality of commands;
deploying the trained machine learning model to firmware of the GPU;
receiving a command in the workload to be executed by the GPU core; and
determining, by the trained machine learning model and based on the command, operating voltage and frequency for the GPU core to execute the command.