Memory Read Decoder Thresholding for MLC/TLC Error Correction
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The reliability of data retrieval from multi-level cell (MLC) and triple-level cell (TLC) nonvolatile memory devices is compromised due to overlapping threshold voltage distributions, leading to increased read errors, as the number of bits stored in each memory cell increases, causing variability in electrical characteristics and charge loss.
Innovation Solution
A controller and operating method that utilize a decoder with a check unit, calculation unit, setting unit, and flipping unit to calculate syndrome values, generate candidate vectors, and set a flipping function threshold value, enabling accurate data reading by flipping decision values of variable nodes with higher flipping function values than the threshold, thereby improving data reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If the number of bits stored in each memory cell is increased to improve storage density, then the storage capacity is improved, but the reliability of data retrieval deteriorates due to overlapping threshold voltage distributions and increased read errors
Solution Approach 1:
The patent applies preliminary action by performing syndrome calculation and flipping function computation before the actual data reading operation. The decoder pre-calculates syndrome values based on the parity check matrix and pre-determines flipping decisions based on flipping function values, so that when read errors occur due to overlapping threshold voltage distributions in MLC/TLC memory, the corrections are already prepared and can be applied immediately, thus maintaining high reliability despite increased storage density
Solution Approach 2:
The patent introduces an intermediary decoding mechanism that acts between the memory cell and the data retrieval process. The decoder with its check unit, calculation unit, and flipping unit serves as an intermediary layer that processes the raw data through syndrome calculation and flipping function evaluation, correcting errors caused by threshold voltage overlap before the data is fully retrieved, thus resolving the reliability issue while maintaining high storage capacity
2Reliability
If a complex decoding process is used to improve data reading accuracy, then the reliability is improved, but the decoding speed deteriorates
Solution Approach 1:
The patent segments the decoding process into distinct functional units: a check unit for syndrome calculation, a calculation unit for flipping function computation, and a flipping unit for decision-making. This segmentation allows each unit to operate independently and efficiently, processing different aspects of the decoding task simultaneously, thus maintaining high data reading accuracy while preventing the overall decoding speed from deteriorating due to the complexity of the multi-stage process
Solution Approach 2:
The patent changes the parameter representation by using flipping function values instead of traditional syndrome-only approaches. The flipping function values provide direct information about which bits need to be flipped, eliminating the need for complex iterative decoding processes. This parameter transformation maintains high decoding accuracy while significantly improving decoding speed by providing direct correction decisions
3Reliability
If the variable node degree is increased to improve error correction capability, then the reliability is improved, but the decoding complexity and time increase
Solution Approach 1:
The patent replaces the traditional mechanical iterative flipping process with a computational system based on flipping function values. Instead of repeatedly flipping bits based on syndrome checks (a mechanical iterative process), the system computes flipping function values that directly indicate which bits need correction. This substitution of computational approach for mechanical iteration reduces decoding complexity and time while maintaining high error correction capability even with increased variable node degrees
Data Source
AI summary
A controller is provided to include a processor reading data from a memory device, and a decoder receiving the data and decoding the data, the data being represented with check nodes and variable nodes. The decoder includes a check unit calculating syndrome values, a calculation unit receiving the decision values of the variable nodes and calculating flipping function values, a setting unit receiving the flipping function values and generating a candidate vector by dividing the flipping function values into groups and selecting at least some maximum values from the groups, the setting unit setting a flipping function threshold value, and a flipping unit receiving the flipping function threshold value, comparing the flipping function values of the variable nodes with the flipping function threshold value, and flipping a decision value of a target variable node having a greater flipping function value than the flipping function threshold value.