US 12,242,968 B2
Parallel processing method and apparatus for neural network model
Jaeyeon Kim, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Sep. 17, 2020, as Appl. No. 17/023,496.
Claims priority of application No. 10-2020-0032233 (KR), filed on Mar. 16, 2020.
Prior Publication US 2021/0287085 A1, Sep. 16, 2021
Int. Cl. G06N 3/082 (2023.01); G06F 9/48 (2006.01); G06F 9/50 (2006.01); G06F 18/20 (2023.01); G06F 18/213 (2023.01); G06F 18/22 (2023.01); G06N 3/08 (2023.01)
CPC G06N 3/082 (2013.01) [G06F 9/5066 (2013.01); G06F 18/213 (2023.01); G06F 18/22 (2023.01); G06F 18/285 (2023.01); G06N 3/08 (2013.01); G06F 9/4881 (2013.01); G06F 2209/501 (2013.01)] 30 Claims
OG exemplary drawing
 
1. A parallel processing method, the parallel processing method comprising:
Extracting metadata of a target layer included in a target model based on a neural network;
measuring a similarity between the target layer and each of reference layers by comparing the metadata of the target layer to reference metadata of each of the reference layers;
selecting a corresponding layer among the reference layers based on the similarities, wherein, in response to an absence of a layer, from among the reference layers, having a same reference metadata as metadata of the target layer, selecting, from among the reference layers, a layer having most similar reference metadata to the metadata of the target layer as the corresponding layer;
adding, in response to the layer having most similar reference metadata to the metadata of the target layer being selected as the corresponding layer, reference layer information corresponding to the metadata of the target layer to a reference database (DB) in which reference metadata of each of the reference layers is stored;
generating a parallelization strategy for the target layer based on a reference parallelization strategy matching the corresponding layer; and
performing, by the neural network, parallel processing based on the generated parallelization strategy.