Efficient Storage of Defect Maps for Nanoscale Memory

Nanoscale technology promises dramatic increases in device density, but reliability is decreased as a sideeffect. 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 (usable memory mapped as defective). Using a list-based technique for storing defect maps performs well for correlated errors, but poorly for randomly distributed defects. In this paper, we propose an algorithm for partitioning correlated defects from random ones. The motivation is to store the correlated defects using rectangular 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.