US 12,229,660 B2
Crossbar array apparatuses based on compressed-truncated singular value decomposition (C-TSVD) and analog multiply-accumulate (MAC) operation methods using the same
Youngnam Hwang, Hwaseong-si (KR); and Jaewon Yang, Suwon-si (KR)
Assigned to Samsung Electronics Co., Ltd., Suwon-Si (KR)
Filed by Samsung Electronics Co., Ltd., Suwon-si (KR)
Filed on May 13, 2021, as Appl. No. 17/319,679.
Claims priority of application No. 10-2020-0129509 (KR), filed on Oct. 7, 2020.
Prior Publication US 2022/0108159 A1, Apr. 7, 2022
Int. Cl. G06N 3/065 (2023.01); G06F 7/544 (2006.01); G06F 17/16 (2006.01); G06N 3/049 (2023.01)
CPC G06N 3/065 (2023.01) [G06F 7/5443 (2013.01); G06F 17/16 (2013.01); G06N 3/049 (2013.01)] 17 Claims
OG exemplary drawing
 
1. A compressed-truncated singular value decomposition (C-TSVD) based crossbar array apparatus, comprising:
an original crossbar array in an m×n matrix having n row input lines and m column output lines and including cells comprising resistance memory devices, or two partial crossbar arrays obtained by decomposing the original crossbar array based on C-TSVD, where m and n are natural numbers;
an analog to digital converter (ADC) configured to convert output values of column output lines of sub-arrays obtained by partitioning the original crossbar array or the two partial crossbar arrays through array partitioning;
an adder configured to sum up results of the ADC to correspond to the column output lines; and
a controller configured to control application of the original crossbar array or the two partial crossbar arrays,
wherein the C-TSVD based crossbar array apparatus corresponds to one layer of a neural network, and
wherein input values are input to the row input lines, a weight is multiplied by the input values and accumulated results are output as output values of the column output lines, and the weight corresponds the original crossbar array or the two partial crossbar arrays.