Drift-Aware Read Operations in Memory Subsystems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in accurately retrieving data from memory cells due to drift in the state of the memory cell over time, leading to errors in read operations.
Innovation Solution
A memory sub-system is configured to estimate drift in the state of a memory cell in parallel with reading the cell, using a reference cell with similar drift characteristics. This allows for optional adjustments in read operations to improve data accuracy.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If traditional read operations are used without drift estimation, then read operation speed is maintained, but data accuracy deteriorates due to memory cell state drift
Solution Approach 1:
The system performs drift estimation using reference cells before executing the actual read operation on target memory cells. This preliminary drift characterization allows the system to pre-determine appropriate read voltage adjustments, eliminating the need for iterative voltage tuning during the actual read operation and thus maintaining fast read speeds while improving data accuracy.
Solution Approach 2:
Reference memory cells serve as intermediaries to measure drift characteristics. These reference cells are specifically designed to track drift without storing actual data, allowing the system to estimate drift for target cells without compromising the integrity or speed of actual data read operations. The reference cells act as a mediator between the drift phenomenon and the read operation control.
2Measurement precision
If drift estimation is performed for every read operation, then data accuracy is improved, but system complexity increases
Solution Approach 1:
The system uses reference cells that are copies or replicas of target memory cells, positioned nearby and experiencing similar environmental conditions. These reference cells replicate the drift behavior of target cells without requiring complex drift modeling or prediction algorithms, simplifying the overall system while maintaining accurate drift estimation.
Solution Approach 2:
The reference cells serve multiple functions: they track drift over time, provide calibration data for read voltage adjustments, and can be used across multiple read operations. This multi-functionality reduces the need for separate drift compensation mechanisms for each read operation, thereby reducing system complexity while maintaining improved accuracy.
3Measurement precision
If read voltage is adjusted based on drift estimation, then measurement precision is improved, but the read operation process becomes more complex
Solution Approach 1:
The system implements a feedback mechanism where drift estimation from reference cells automatically determines the read voltage adjustment for target cells. This closed-loop control eliminates the need for manual voltage calibration or complex decision logic, as the feedback from reference cells directly guides the voltage adjustment, maintaining operational simplicity while improving accuracy.
Data Source
AI summary
Systems, methods and apparatus to read target memory cells having an associated reference memory cell configured to be representative of drift or changes in the threshold voltages of the target memory cells. The reference cell is programmed to a predetermined threshold level when the target cells are programmed to store data. In response to a command to read the target memory cells, estimation of a drift of the threshold voltage of the reference is performed in parallel with applying an initial voltage pulse to read the target cells. Based on a result of the drift estimation, voltage pulses used to read the target cells can be modified and/or added to account for the drift estimated using the reference cell.