US 12,131,254 B2
Method and apparatus with neural network distributed processing
Jiseung Jang, Hwaseong-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on Jul. 2, 2020, as Appl. No. 16/919,661.
Claims priority of application No. 10-2020-0005273 (KR), filed on Jan. 15, 2020.
Prior Publication US 2021/0216863 A1, Jul. 15, 2021
Int. Cl. G06N 3/08 (2023.01); G06N 3/04 (2023.01)
CPC G06N 3/08 (2013.01) [G06N 3/04 (2013.01)] 25 Claims
OG exemplary drawing
 
1. A processor-implemented neural network distributed processing method, comprising:
obtaining a first operation cost comprising an operation time for processing an operation of a layer of a neural network, the operation time comprising a plurality of operation times each corresponding to a respective parallel processing method, and a switching time for transmitting output data of the operation of the layer to a subsequent layer of the neural network, according to a distribution strategy based on a plurality of operation devices;
generating an operation configuration corresponding to the neural network based on the obtained first operation cost;
performing a reduction operation on the generated operation configuration by merging a plurality of nodes of the neural network, based on the plurality of operation times; and
processing an operation of the neural network based on a reduced operation configuration obtained by performing the reduction operation.