Word Line Error Assessment for Non-Volatile Memory Storage Utilization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for determining damaged word lines in rewritable non-volatile memory modules lead to excessive reduction in available storage space, as undamaged word lines are marked as bad, resulting in wasted space due to inefficient damage assessment.
Innovation Solution
A memory management method and storage controller that perform decoding operations on word lines to determine whether to mark them as bad based on error values and thresholds, allowing for precise identification of damaged word lines and improving storage utilization.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional methods mark entire physical blocks as bad when any word line is damaged, then reliability is improved by avoiding damaged areas, but storage space is excessively reduced due to marking undamaged word lines as bad
Solution Approach 1:
The patent segments the physical block into individual word lines for independent assessment. Instead of marking entire physical blocks as bad, the system evaluates each word line separately using decoding operations, allowing undamaged word lines to remain usable while isolating only the specific damaged word lines. This granular segmentation resolves the contradiction by preserving storage space while maintaining reliability.
Solution Approach 2:
The patent applies local quality assessment by determining the damage status of each word line individually rather than uniformly marking entire physical blocks. The decoding operation evaluates error values locally at the word line level, enabling precise identification of damaged areas while preserving the quality and usability of undamaged word lines within the same physical block.
2Measurement precision
If decoding operations are performed on all word lines to accurately identify damaged areas, then measurement precision is improved, but processing time and complexity increase
Solution Approach 1:
The patent implements partial action by performing decoding operations selectively rather than uniformly on all word lines. The system uses error values from decoding operations to identify suspicious word lines, then focuses detailed assessment on those specific areas. This approach achieves high measurement precision for damaged word line identification while reducing overall processing time by avoiding exhaustive decoding of every word line in the memory module.
Data Source
AI summary
A memory management method and a storage controller are provided. The method includes performing a decoding operation to a first data stored in a first word line among multiple word lines of a rewritable non-volatile memory module to determine whether the decoding operation is successful or failed, and obtain a first error value of the first word line; when the decoding operation is determined as successful, determining whether to mark the first word line as a bad word line according to the first error value and a first threshold; and when the decoding operation is determined as failed, obtaining a second error value of a second word line adjacent to the first word line, and determining whether to mark both of the first and second word lines as the bad word line according to the first error value, the second error value, and a first threshold.