US 11,740,687 B2
Variable power mode inferencing
Yongjune Kim, San Jose, CA (US); Cyril Guyot, San Jose, CA (US); and Won Ho Choi, San Jose, CA (US)
Assigned to Western Digital Technologies, Inc., San Jose, CA (US)
Filed by Western Digital Technologies, Inc., San Jose, CA (US)
Filed on Apr. 21, 2020, as Appl. No. 16/854,677.
Prior Publication US 2021/0325957 A1, Oct. 21, 2021
Int. Cl. G06F 1/26 (2006.01); G06F 1/32 (2019.01); G06F 1/3296 (2019.01); G06N 3/08 (2023.01); G06N 3/04 (2023.01)
CPC G06F 1/3296 (2013.01) [G06N 3/04 (2013.01); G06N 3/08 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method for performing multimode inferencing, comprising:
receiving machine learning model input data from a requestor;
processing the machine learning model input data with a machine learning model using processing hardware at a first power level to generate first output data, wherein the processing hardware comprises a processor operable at one of a plurality of power levels including the first power level and a second power level different from the first power level, each power level corresponding to a different performance level for the machine learning model;
enabling data quantization by a pre-processor after selecting the first power level;
selecting the second power level for the processing hardware based on comparing the first output data to a threshold value;
disabling data quantization by the pre-processor after selecting the second power level;
processing the machine learning model input data with the machine learning model using the processing hardware at the second power level to generate second output data; and
sending second output data to the requestor.