Dynamic Disturb Count for Thermal Write Disturb in Memory
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory sub-systems, such as solid-state drives, face challenges in accurately managing thermal write disturb in resistance variable memory cells, where neighbor cells are affected by the frequency and timing of writes, leading to incorrect data storage due to inadequate refresh mechanisms.
Innovation Solution
Implementing a disturb management system that increments a disturb count based on the time between writes to aggressor cells, allowing for more precise determination of when to refresh victim cells, thereby mitigating thermal write disturb by adjusting the refresh operation according to the frequency and timing of writes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed refresh threshold is used for victim cells, then the refresh mechanism is simple to implement, but it cannot accurately account for thermal write disturb when writes occur frequently within short time intervals
Solution Approach 1:
The patent applies dynamics by transitioning from a fixed refresh threshold to a dynamic disturb count mechanism that adapts to write patterns. The disturb count is incremented by different amounts based on the time interval between writes to aggressor cells, allowing the system to dynamically adjust refresh requirements according to actual thermal disturbance conditions.
Solution Approach 2:
The patent changes the parameter used for determining refresh needs from a fixed threshold to a variable disturb count that depends on time intervals between writes. By using time interval-based parameter changes, the system can accurately reflect thermal write disturb conditions and adjust refresh operations accordingly.
2Measurement precision
If the disturb count is incremented by a fixed amount for each write to aggressor cells, then the management process is simple, but it fails to account for the time interval between writes which affects thermal disturb magnitude
Solution Approach 1:
The patent applies parameter changes by making the disturb count increment variable rather than fixed. The increment amount changes based on the time interval between writes to aggressor cells, with larger increments for shorter time intervals that cause greater thermal disturbance, thereby improving measurement precision.
Solution Approach 2:
The system uses feedback from timing information about write operations to adjust the disturb count increment. By monitoring the time interval between writes and using this feedback to determine the appropriate increment amount, the system achieves more precise thermal disturb measurement.
3Reliability
If victim cells are refreshed frequently to prevent read errors, then data reliability is improved, but unnecessary refresh operations increase system complexity and energy consumption
Solution Approach 1:
The patent uses feedback from time interval monitoring to control refresh operations. By tracking the time between writes to aggressor cells and using this information to determine when victim cells need refreshing, the system avoids unnecessary refresh operations while maintaining data reliability.
Solution Approach 2:
The system performs preliminary tracking of write time intervals to aggressor cells before determining when victim cell refresh is actually needed. This preliminary action allows the system to predict thermal disturbance conditions and schedule refresh operations only when necessary, improving efficiency.
Applied Scientific Principles
This section explains which scientific principles are used to turn an abstract innovation direction into a practical engineering solution.
Function Achieved in This Case
This approach enhances the accuracy of data storage by refreshing victim cells at optimal times, reducing the likelihood of read errors caused by thermal write disturb, especially in scenarios with frequent and rapid writes to aggressor cells.
Implementation Method 1
neighbor cells are affected by the frequency and timing of writes, leading to incorrect data storage due to inadequate refresh mechanisms
Data Source
AI summary
An example method includes determining a time between writes in place to a particular memory cell, incrementing a disturb count corresponding to a neighboring memory cell by a particular count increment that is based on the time between the writes to the particular memory cell, and determining whether to check a write disturb status of the neighboring memory cell based on the incremented disturb count.