Transformer and Its Variants for Identifying Good Dice in Bad Neighborhoods

Cheng Che Lu*, Chi Chih Chang*, Chia Heng Yen*, Shuo Wen Chang, Ying Hua Chu, Kai Chiang Wu*, Mango Chia Tso Chao

*此作品的通信作者

研究成果: Conference contribution同行評審

摘要

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.

原文English
主出版物標題Proceedings - 2024 IEEE 42nd VLSI Test Symposium, VTS 2024
發行者IEEE Computer Society
ISBN(電子)9798350363784
DOIs
出版狀態Published - 2024
事件42nd IEEE VLSI Test Symposium, VTS 2024 - Tempe, 美國
持續時間: 22 4月 202424 4月 2024

出版系列

名字Proceedings of the IEEE VLSI Test Symposium
ISSN(電子)2375-1053

Conference

Conference42nd IEEE VLSI Test Symposium, VTS 2024
國家/地區美國
城市Tempe
期間22/04/2424/04/24

指紋

深入研究「Transformer and Its Variants for Identifying Good Dice in Bad Neighborhoods」主題。共同形成了獨特的指紋。

引用此