Memory Cell Degradation Prediction via Dual Polarity Sense
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory technologies face challenges in accurately predicting and compensating for degradation of resistance variable memory cells, leading to read disturb issues that reduce performance and lifetime, as error rates are not reliable indicators for refresh operations.
Innovation Solution
Implementing a method that uses the quantity of sense operations to determine when to perform double read operations with opposite polarities to assess the need for refresh operations, allowing for accurate prediction and compensation of read disturb in memory cells.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If refresh operations are performed based on error rates, then data reliability is maintained, but the timing of refresh operations is inaccurate leading to either premature refreshes or delayed refreshes that compromise performance and lifetime
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors the number of sense operations performed on memory cells and uses this information to determine when refresh operations are needed. The system compares the accumulated sense operation count against threshold values to trigger appropriate refresh actions, creating a closed-loop control system that adapts to actual cell degradation patterns rather than relying on imprecise error rate measurements.
Solution Approach 2:
The patent replaces the traditional error-rate-based refresh determination mechanism with a sense operation count-based mechanism. Instead of relying on probabilistic error rate measurements, the system uses direct counting of sense operations performed on each memory cell, providing a more precise and deterministic approach to trigger refresh operations at the optimal moment.
2Reliability
If sense operations are performed frequently to monitor memory cell state, then degradation is detected early, but the sense operations themselves contribute to read disturb and accelerate cell degradation
Solution Approach 1:
The patent performs preliminary monitoring by counting the number of sense operations performed on each memory cell and using this accumulated information to predict when refresh operations will be needed. This allows the system to prepare for necessary refresh actions in advance, reducing the need for frequent intervention and minimizing read disturb while still maintaining accurate degradation detection.
Solution Approach 2:
The patent uses partial monitoring by tracking only the quantity of sense operations rather than performing comprehensive continuous monitoring of all cell states. This partial action approach provides sufficient information to determine refresh timing without the excessive monitoring that would cause significant read disturb and accelerate degradation.
3Device complexity
If the memory system uses traditional error rate monitoring, then implementation is simple, but the system cannot reliably predict when refresh operations are needed leading to suboptimal performance
Solution Approach 1:
The patent implements a feedback mechanism that continuously monitors the number of sense operations performed on memory cells and uses this information to determine when refresh operations are needed. The system compares the accumulated sense operation count against threshold values to trigger appropriate refresh actions, creating a closed-loop control system that adapts to actual cell degradation patterns rather than relying on imprecise error rate measurements.
Solution Approach 2:
The patent replaces the traditional error-rate-based refresh determination mechanism with a sense operation count-based mechanism. Instead of relying on probabilistic error rate measurements, the system uses direct counting of sense operations performed on each memory cell, providing a more precise and deterministic approach to trigger refresh operations at the optimal moment.
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 effectively increases the performance and lifetime of memory cells by reliably identifying when refresh operations are needed, preventing erroneous data readings and extending the memory's operational lifespan.
Implementation Method 1
resistance variable memory cells can store data based on the resistance state of a storage element (e.g., a memory element having a variable resistance)... by applying sources of an electrical field or energy, such as positive or negative electrical pulses (e.g., positive or negative voltage or current pulses) to the cells
Implementation Method 2
by applying sources of an electrical field or energy, such as positive or negative electrical pulses (e.g., positive or negative voltage or current pulses) to the cells
Data Source
AI summary
The present disclosure includes apparatuses, methods, and systems for predicting and compensating for degradation of memory cells. An embodiment includes a memory having a group of memory cells, and circuitry configured to, upon a quantity of sense operations performed on the group of memory cells meeting or exceeding a threshold quantity, perform a sense operation on the group of memory cells using a positive sensing voltage and perform a sense operation on the group of memory cells using a negative sensing voltage, and perform an operation to program the memory cells of the group determined to be in a reset data state by both of the sense operations to the reset data state.