US 12,223,444 B2
Accelerator for processing inference tasks in parallel and operating method thereof
Ho Young Kim, Seoul (KR); Won Woo Ro, Seoul (KR); and Sung Ji Choi, Seoul (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-si (KR); and Industry-Academic Cooperation Foundation, Yonsei University, Seoul (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR); and Industry-Academic Cooperation Foundation, Yonsei University, Seoul (KR)
Filed on Jul. 12, 2021, as Appl. No. 17/372,788.
Claims priority of application No. 10-2021-0010439 (KR), filed on Jan. 25, 2021.
Prior Publication US 2022/0237487 A1, Jul. 28, 2022
Int. Cl. G06N 5/048 (2023.01); G06F 9/48 (2006.01); G06F 9/50 (2006.01)
CPC G06N 5/048 (2013.01) [G06F 9/4881 (2013.01); G06F 9/5038 (2013.01); G06F 9/5044 (2013.01); G06F 9/5066 (2013.01)] 20 Claims
OG exemplary drawing
 
1. A method of operating an accelerator, the method comprising:
determining whether any group shares weights of a first group from among groups;
determining a presence of an idle processing element (PE) array, in response to no group sharing the weights of the first group; and
selecting a second group having a memory time overlapping a computation time of the first group from among the groups, in response to the idle PE array being present.