Nonvolatile Memory Error Correction Using Weak String Weighting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing integration density and number of bits in nonvolatile memory devices lead to decreased data reliability, necessitating a technology to enhance data reliability while maintaining high memory capacity.
Innovation Solution
The method involves identifying weak strings of memory cells, storing this information as weak column data, and using it to modify the weighting of data bits during error correction operations, specifically by calculating log-likelihood ratios and applying different weights to bits from weak columns to improve error detection and correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the number of bits stored in one memory cell is increased to achieve higher capacity, then memory capacity is improved, but data reliability deteriorates
Solution Approach 1:
The patent performs preliminary identification of weak strings during a test operation before normal data storage. The memory controller identifies strings with higher error probabilities and stores this weak column information in advance. When data is subsequently stored, the system applies different weighting to bits from identified weak strings during error correction, preventing the reliability deterioration that would otherwise result from increased storage capacity.
2Quantity of substance
If the number of memory cells integrated in the same area is increased to achieve higher capacity, then memory capacity is improved, but data reliability deteriorates
Solution Approach 1:
The patent applies local quality by treating different memory strings differently based on their individual characteristics. Instead of uniform error correction across all strings, the system identifies specific weak strings and applies enhanced error correction weighting only to bits from those strings. This localized approach allows the system to maintain high integration density while compensating for reliability issues in specific problematic strings without affecting overall capacity.
3Reliability
If error correction weighting is applied to weak column bits, then data reliability is improved, but computational complexity increases
Solution Approach 1:
The system performs the computationally intensive task of identifying weak strings and determining appropriate weighting factors in advance, during a preliminary test operation. This preliminary action stores the weighting information for later use, so that during normal data processing, the system only needs to apply pre-determined weights rather than performing complex calculations in real-time. This significantly reduces the computational complexity during actual data operations while maintaining improved reliability.
Data Source
AI summary
Methods of operating nonvolatile memory devices include testing a plurality of strings of nonvolatile memory cells in the memory device to identify at least one weak string therein having a higher probability of yielding erroneous read data error relative to other ones of the plurality of strings. An identity of the at least one weak string may be stored as weak column information. This weak column information may be used to facilitate error detection and correction operations. In particular, an error correction operation may be performed on a first plurality of bits of data read from the plurality of strings using an algorithm that modifies a weighting of the reliability of one or more data bits in the first plurality of bits of data based on the weak column information. More specifically, an algorithm may be used that interprets a bit of data read from the at least one weak string as having a relatively reduced reliability relative to other ones of the first plurality of data bits.