A Hybrid Flow for Memory Failure Bitmap Classification

Abstract

Failure bitmaps of manufactured memory arrays may contain the information of some systematic defects and have hence been used to monitor the process and to improve the memory yield. It is important to have an accurate flow to classify the memory failure bitmap signatures. The memory bitmap signature classification can be either dictionary based or machine learning based. This paper introduces a hybrid flow that can combine dictionary based and machine learning based methods. The proposed method can enhance the accuracy of signature classification, and more importantly, it has the capability of learning new memory bitmap signatures unseen before.

A Regularized Singular Value Decomposition-Based Approach for Failure Pattern Classification on Fail Bit Map in a DRAM Wafer

“…Depending on the number of failed cells, unit blocks of FBMs are categorized as functional or defective elements. Failing blocks are usually localized and formed specific failure patterns [8], [12], [22]. The failure patterns on FBMs can be classified into a single bit failure pattern and non-single bit failure pattern depending on the distribution type of failed blocks.…”