TY - GEN
T1 - Transformer and Its Variants for Identifying Good Dice in Bad Neighborhoods
AU - Lu, Cheng Che
AU - Chang, Chi Chih
AU - Yen, Chia Heng
AU - Chang, Shuo Wen
AU - Chu, Ying Hua
AU - Wu, Kai Chiang
AU - Chao, Mango Chia Tso
N1 - Publisher Copyright:
© 2024 IEEE.
PY - 2024
Y1 - 2024
N2 - Good-die-in-bad-neighborhood (GDBN) is a widely adopted method utilizing the fact that manufacturing defects tend to exhibit spatial dependency and form a cluster or specific pattern of bad dice on a wafer. Existing research studies on GDBN mainly focus on learning such spatial relationships within a limited observation window through simple mechanisms such as linear regression or multilayer perceptron model. In this paper, we propose MetaFormer-GDBN, a transformer-based deep learning model with the observation window extending to the entire wafer to include broader pattern information. The enhanced neighboring information and model capacity allow our method to capture more complex patterns of bad dice. Experiments show that compared to previous work, our method can achieve up to 50 % performance improvement, reducing the DPPM (defective parts per million) with minimal yield loss.
AB - Good-die-in-bad-neighborhood (GDBN) is a widely adopted method utilizing the fact that manufacturing defects tend to exhibit spatial dependency and form a cluster or specific pattern of bad dice on a wafer. Existing research studies on GDBN mainly focus on learning such spatial relationships within a limited observation window through simple mechanisms such as linear regression or multilayer perceptron model. In this paper, we propose MetaFormer-GDBN, a transformer-based deep learning model with the observation window extending to the entire wafer to include broader pattern information. The enhanced neighboring information and model capacity allow our method to capture more complex patterns of bad dice. Experiments show that compared to previous work, our method can achieve up to 50 % performance improvement, reducing the DPPM (defective parts per million) with minimal yield loss.
UR - http://www.scopus.com/inward/record.url?scp=85195240468&partnerID=8YFLogxK
U2 - 10.1109/VTS60656.2024.10538654
DO - 10.1109/VTS60656.2024.10538654
M3 - Conference contribution
AN - SCOPUS:85195240468
T3 - Proceedings of the IEEE VLSI Test Symposium
BT - Proceedings - 2024 IEEE 42nd VLSI Test Symposium, VTS 2024
PB - IEEE Computer Society
T2 - 42nd IEEE VLSI Test Symposium, VTS 2024
Y2 - 22 April 2024 through 24 April 2024
ER -