Decoding Method for Non-Volatile Memory Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing error checking and correction mechanisms in non-volatile memory modules struggle to efficiently locate and correct errors caused by repeated writing or data movement, leading to increased decoding failure probabilities.
Innovation Solution
A decoding method that performs a first decoding operation based on initial reliability information and, if it fails and meets a default condition, executes a second decoding operation using alternative reliability information with higher correction capabilities for specific error types, specifically designed for errors generated during programming operations in non-volatile memory modules.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single decoding operation with initial reliability information is performed, then decoding speed is maintained, but decoding failure probability increases for specific error types
Solution Approach 1:
The decoding process is divided into multiple stages: a first decoding operation using initial reliability information, and a second decoding operation using adjusted reliability information. This segmentation allows the system to handle different error types through different decoding paths, improving overall reliability without requiring all complexity upfront.
Solution Approach 2:
The reliability information is dynamically adjusted based on the results of the first decoding operation. When the first decoding fails to meet the default condition, the system transitions to the second decoding operation with modified reliability information, creating an adaptive decoding process that responds to actual error conditions.
2Reliability
If a first decoding operation with initial reliability information is performed first, then general decoding efficiency is maintained, but specific error types cannot be effectively corrected
Solution Approach 1:
The system performs a partial decoding operation first using initial reliability information to quickly handle cases with fewer errors. Only when this partial effort fails to meet the default condition does the system engage the more time-consuming second decoding operation, thus avoiding unnecessary time loss while still providing comprehensive error correction when needed.
Solution Approach 2:
The system uses feedback from the first decoding operation's results to determine whether to proceed to the second decoding operation. The default condition acts as a feedback threshold, allowing the system to efficiently correct errors by only activating the more resource-intensive second decoding path when actually needed.
3Measurement precision
If existing error checking and correction mechanisms are used, then basic error detection is achieved, but location and correction of specific error types becomes difficult
Solution Approach 1:
The system applies different reliability information characteristics to different decoding operations. The second reliability information is specifically adjusted to have higher correction capability for first type errors, creating a localized optimization that targets specific error types without compromising overall system operation.
Solution Approach 2:
The system changes the parameters of reliability information between the two decoding operations. By adjusting the reliability information parameters in the second operation, the system enhances its ability to locate and correct specific error types that were missed by the first decoding operation.
Data Source
AI summary
A decoding method, a memory storage device and a memory control circuit unit. The method includes: reading a plurality of bits from a plurality of first memory cells; performing a first decoding operation on the bits according to first reliability information; and performing a second decoding operation on the bits according to second reliability information if the first decoding operation fails and meets a default condition, and the second reliability information is different from the first reliability information, and a correction ability of the second reliability information for a first type error of the bits is higher than a correction ability of the first reliability information for the first type error. In addition, the first type error is generated by performing a specific programming operation on the first memory cells based on error data.