US 12,079,063 B2
Power control systems and methods for machine learning computing resources
Mark Alan Lovell, Lucas, TX (US); and Robert Michael Muchsel, Addison, TX (US)
Assigned to Maxim Integrated Products, Inc., San Jose, CA (US)
Filed by Maxim Integrated Products, Inc., San Jose, CA (US)
Filed on Jun. 8, 2023, as Appl. No. 18/207,297.
Application 18/207,297 is a division of application No. 17/890,595, filed on Aug. 18, 2022, granted, now 11,747,887.
Application 17/890,595 is a division of application No. 17/335,759, filed on Jun. 1, 2021, granted, now 11,449,126, issued on Sep. 20, 2022.
Prior Publication US 2023/0324980 A1, Oct. 12, 2023
This patent is subject to a terminal disclaimer.
Int. Cl. G06F 1/32 (2019.01); G06F 1/3287 (2019.01); G06F 1/3296 (2019.01)
CPC G06F 1/3287 (2013.01) [G06F 1/3296 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A power control system for machine learning computing resources, the power control system comprising:
one or more computing resources that, in response to receiving from one or more memory elements a first set of parameters, process one or more layers of a neural network; and
a controller coupled to the one or more computing resources, the controller, in response to receiving a second set of parameters performs steps that reduce a power consumption of at least some of the one or more computing resources.