US 12,340,247 B2
Electronic device for processing neural network model and method of operating the same
Junhyuk Lee, Suwon-si (KR); Hyunbin Park, Suwon-si (KR); Seungjin Yang, Suwon-si (KR); and Jin Choi, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on May 16, 2022, as Appl. No. 17/745,320.
Application 17/745,320 is a continuation of application No. PCT/KR2022/005700, filed on Apr. 21, 2022.
Claims priority of application No. 10-2021-0119368 (KR), filed on Sep. 7, 2021; and application No. 10-2021-0142991 (KR), filed on Oct. 25, 2021.
Prior Publication US 2023/0072337 A1, Mar. 9, 2023
Int. Cl. G06F 9/50 (2006.01); G06N 3/08 (2023.01); H04L 5/00 (2006.01)
CPC G06F 9/5016 (2013.01) [G06N 3/08 (2013.01); H04L 5/0064 (2013.01)] 16 Claims
OG exemplary drawing
 
1. An electronic device comprising:
memory storing one or more computer programs; and
one or more processors, including a resource management unit and a neural processing unit, communicatively coupled to the memory,
wherein the one or more computer programs include computer-executable instructions that, when executed by the one or more processors individually or collectively, cause the electronic device to:
obtain an execution request for a specific function operating based on a specific neural network model,
identify an available bandwidth of the memory through the resource management unit,
quantize the specific neural network model based on the available bandwidth of the memory through the neural processing unit,
identify a section including the available bandwidth of the memory from a predefined table, and
select a bit depth corresponding to the identified section as an activation bit depth.