Memory Controller Read Voltage Estimation via Histogram Feedback
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory systems with non-volatile memory cells face accuracy issues in reading data due to changes in threshold voltage over time, leading to bit errors and incorrect data retrieval.
Innovation Solution
A memory system that includes a memory controller capable of generating a histogram of threshold voltage levels, estimating read voltages using a read voltage estimation model, and updating model parameters based on observation values to improve read voltage accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If the read voltage is adjusted to compensate for threshold voltage changes, then data reading accuracy is improved, but the system complexity increases due to the need for continuous voltage calibration
Solution Approach 1:
The patent implements a feedback mechanism where the memory controller continuously monitors read operation results and automatically adjusts read voltages based on detected errors or performance degradation. This closed-loop control eliminates the need for complex manual calibration systems while maintaining high reading accuracy through automatic adaptation to threshold voltage drift.
Solution Approach 2:
The memory system performs self-calibration by using its own read operations to detect threshold voltage changes and automatically adjust read voltages without external intervention. The memory controller monitors its own performance and adjusts parameters autonomously, reducing system complexity by eliminating separate calibration hardware or manual adjustment mechanisms.
2Reliability
If the threshold voltage distribution is monitored continuously to maintain read accuracy, then data retrieval reliability is improved, but the measurement and detection difficulty increases
Solution Approach 1:
The patent introduces an intermediary histogram representation that simplifies the monitoring of threshold voltage distribution. Instead of directly measuring complex voltage distributions, the system uses histogram bins to represent voltage levels, making it easier to detect shifts in the distribution and trigger appropriate read voltage adjustments while maintaining high reliability.
3Measurement precision
If a read voltage estimation model is used to predict optimal read voltages, then the accuracy of voltage estimation is improved, but the device complexity increases due to the model parameters
Solution Approach 1:
The patent manages model complexity by dynamically adjusting the number and granularity of histogram bins based on operating conditions. The system can increase bin resolution when high precision is needed and reduce bins when conditions are stable, allowing accurate voltage estimation while adapting computational complexity to actual needs rather than maintaining fixed high complexity.
Data Source
AI summary
A memory system includes a non-volatile memory having a plurality of memory cells and a memory controller. The memory controller is configured to generate a histogram indicating, with respect to each of a plurality of threshold voltage levels for multi-level cell (MLC) reading, a number of memory cells at the threshold voltage level, based on data read from the plurality of memory cells using a plurality of reference read voltages, estimate a plurality of read voltages for MLC reading of the plurality of memory cells as estimation values by inputting the histogram into a read voltage estimation model, determine, through MLC reading of the plurality of memory cells using a plurality of sets of read voltages, a set of read voltages for MLC reading as observation values, and update one or more parameters of the read voltage estimation model based on the estimation values and the observation values.