Efficient Storage of Defect Maps for Nanoscale Memory

Abstract

Nanoscale technology promises dramatic increases in device density, but reliability is decreased as a side-effect. With bit-error rates projected to be as high as 10%, designing a usable nanoscale memory system poses a significant challenge. Storing defect information corresponding to every bit in the nanoscale device using a reliable storage bit is prohibitively costly. Using a Bloom filter to store a defect map provides better compression at the cost of a small false positive rate (us-able memory mapped as defective). Using a list-based technique for storing defect maps performs well for cor-related errors, but poorly for randomly distributed de-fects. In this paper, we propose an algorithm for parti-tioning correlated defects from random ones. The mo-tivation is to store the correlated defects using rectan-gular ranges in a ternary content-addressable memory (TCAM) and random defects using a Bloom filter. We believe that a combination of Bloom filter and small size TCAM is more effective for storing defect map at high error rate. We show the results for different correlated distributions.