Storage Controller Data Reading via Voltage Adjustment and Buffer Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional methods for data reading in rewritable non-volatile memory modules require additional verified data storage, reducing available space and efficiency, and involve repetitive read operations with adjusted voltages, leading to resource waste and reduced decoding capability.
Innovation Solution
A data reading method that uses different read voltages to read a target physical page multiple times without preparing verified data, generates soft information from syndromes and codewords to find confidence values, and performs adjusted iterative decoding to enhance decoding capability and efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If verified data is stored in the rewritable non-volatile memory module to correct the log likelihood ratio table, then the decoding capability is improved, but the remaining available space of the memory module is reduced
Solution Approach 1:
The patent extracts the verified data from the rewritable non-volatile memory module and stores it in a separate buffer memory. This separation allows the memory module to maintain full capacity for user data while the buffer memory provides the necessary verified data for decoding operations, thus resolving the contradiction between decoding capability and available space.
Solution Approach 2:
The patent introduces a buffer memory as an intermediary component between the host system and the rewritable non-volatile memory module. This buffer memory stores verified data and assists the storage controller in decoding operations without consuming space in the memory module, acting as a mediator that improves reliability without reducing storage capacity.
2Reliability
If read retry operations are performed multiple times with different adjusted read voltages, then the probability of obtaining a valid codeword is improved, but the data reading efficiency is reduced
Solution Approach 1:
The patent performs preliminary actions by storing verified data in the buffer memory before read operations. This pre-prepared verified data enables the storage controller to quickly perform decoding operations without requiring multiple read retry operations, thus improving reading efficiency while maintaining the ability to obtain valid codewords.
Solution Approach 2:
The patent implements a feedback mechanism where the storage controller uses the verified data from the buffer memory to adjust and improve decoding operations. The controller compares decoded results with verified data and makes real-time adjustments, reducing the need for repeated read operations and improving overall reading efficiency.
3Reliability
If multiple read retry operations are performed without utilizing obtained adjust codewords, then the decoding probability is maintained, but the operation resources are wasted
Solution Approach 1:
The patent recovers and utilizes adjust codewords obtained from read retry operations instead of discarding them. The storage controller stores these adjust codewords in the buffer memory and uses them for subsequent decoding operations, transforming what would be wasted resources into valuable data that improves decoding probability while reducing energy consumption.
Data Source
AI summary
A data reading method is provided. The method includes: using a predetermined read voltage corresponding to a read operation to read a target physical page to obtain a read codeword syndrome of a read codeword; using a first adjust read voltage to read again the target physical page to obtain a first adjust codeword syndrome of a first adjust codeword; generating soft information of each of a plurality of target memory cells of the target physical page according to the read codeword and the first adjust cordword; identifying a target confidence table according to a size relative relation between the foregoing syndromes to find a confidence value of each of the target memory cells from the target confidence table; and performing an adjusted preset decoding operation according to the soft information and the confidence values to obtain a valid codeword, so as to complete the read operation.