Machine Learning Based Optimization Technique for High-Capacity V-NAND Flash Memory
Ji-Suk Kim, Earl Kim, Daehyeon Lee, Taeheon Lee, Daesik Ham, Miju Yang, Wanha Hwang, Jaeyoung Kim, Sang-Yong Yoon, Youngwook Jeong, Eun-Kyoung Kim, Ki‐Whan Song, Jaihyuk Song, Myungsuk Kim, Woo Young Choi · Proceedings - International Symposium for Testing and Failure Analysis · 2021
Abstract In the NAND flash manufacturing process, thousands of internal electronic fuses (eFuse) are tuned in order to optimize performance and validity. In this paper, we propose a machine learning optimization technique that uses deep learning (DL) and genetic algorithms (GA) to automatically tune eFuse values. Using state-of-the-art triple-level cell (TLC) V-NAND flash wafers, we trained our model and validated its effectiveness. Based on the findings of the evaluation and production data, the proposed optimization technique can reduce total turnaround time (TAT) by 70% compared with manual eFuse tuning.