In order to accelerate yield improvement in semiconductor manufacturing, it is important to prevent the root causes of product-specific failures, such as systematic defects and parametric defects, which are different for each product. We herein propose a method for the investigation of product-specific failures by estimating differences between the actual failing bit signatures (FBSs) and the predicted FBSs caused by random defects. In order to estimate these differences accurately, we have developed a novel algorithm by which to extract the critical area for each FBS. The total failure rate errors of FBSs are within 0.5% for embedded SRAMs. The proposed method identified the root causes of product-specific failures in 150 and 65 nm technology node products.

To improve product yield in high-product-mix semiconductor manufacturing, it is important to estimate the systematic yield inherent to each product and to extract problematic products that have low systematic yields. We propose a simplified and available yield model using a critical area analysis. This model enables the extraction of problematic products by the relationship between actual yields and the short sensitivities of the products. Furthermore, we present an enterprise-wide yield management system using this model and some useful applications. As a result, the system increases the efficiency of the yield management and enhancement dramatically.