Memory Control Circuit Iteration Decoding for Aging Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The correcting capability of error correcting codes in rewritable non-volatile memory modules is limited, leading to potential errors over the module's operating life, which affects data decoding accuracy.
Innovation Solution
A decoding method and memory control circuit unit that calculate a weight for each bit based on reliability information and syndrome, enabling iteration decoding to correct errors by determining which bits to update, thereby improving decoding accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If error correcting code is used in rewritable non-volatile memory module, then data reliability is improved, but correcting capability is limited and cannot adapt to increasing error rates over operating life
Solution Approach 1:
The patent applies dynamics by making the decoding process adaptive through iterative operations. The decoding circuit dynamically adjusts its correcting capability by performing multiple iteration decodings based on syndrome weights, allowing the system to adapt to varying error rates that occur over the memory module's operating life, thereby resolving the contradiction between initial reliability and long-term adaptability.
Solution Approach 2:
The patent changes the parameter of decoding iteration count dynamically. By calculating syndrome weights and determining the number of iteration decodings needed based on the detected error patterns, the system adjusts its correcting capability parameter to match the actual error conditions, enabling it to handle both low and high error rates effectively throughout its operational lifespan.
2Speed
If traditional decoding procedure is used, then decoding speed is maintained, but decoding accuracy deteriorates when error rate exceeds correction threshold
Solution Approach 1:
The patent applies partial action by performing iteration decodings selectively. Instead of always performing maximum iterations, the system calculates syndrome weights first and then performs only the necessary number of iteration decodings based on the detected error patterns. This partial approach maintains speed for low-error cases while achieving high accuracy when errors exceed the traditional correction threshold.
Solution Approach 2:
The patent implements feedback through the syndrome weight calculation mechanism. The decoding circuit continuously monitors decoding results through syndrome calculations and uses this feedback to determine whether additional iteration decodings are needed. This feedback loop enables the system to maintain high decoding accuracy by adapting the number of iterations based on actual error conditions, rather than using a fixed decoding procedure.
3Reliability
If error correction capability is increased to handle aging errors, then correcting capability is improved, but decoding complexity increases
Solution Approach 1:
The patent applies segmentation by dividing the decoding process into distinct stages: syndrome weight calculation, iteration count determination, and conditional iteration decodings. This segmentation allows the complex error correction task to be broken down into manageable steps, improving correcting capability while keeping the complexity organized and controllable through structured processing stages.
Solution Approach 2:
The patent performs preliminary action by calculating syndrome weights and determining the required number of iteration decodings before actually performing the error correction. This preliminary analysis allows the system to prepare an optimized decoding strategy in advance, enabling it to handle complex error patterns effectively while avoiding unnecessary computational overhead during the actual correction process.
Data Source
AI summary
A decoding method, a memory control circuit unit and a memory storage device are provided. The decoding method includes: transmitting a read command sequence for reading a plurality of memory cells in order to obtain a plurality of bits, and obtaining a plurality of reliability information corresponding to each of the bits. The decoding method also includes: calculating a sum of a plurality of reliability information matching a check condition among the plurality of reliability information, and adding a balance information to the sum in order to obtain a weight corresponding to a first bit among the bits and a first syndrome. The decoding method further includes: determining whether the bits have at least one error, and if the bits have the at least one error, executing an iteration decoding procedure according to the weight.