Non-Volatile Memory Drift Detection via Bit Flipping
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face challenges in detecting drift in memory cells, which can lead to incorrect data reading and increased latency due to the need for higher read voltages after a certain time, potentially causing data corruption and requiring time-consuming error correction decoding.
Innovation Solution
The implementation of a technique where bits are encoded with more set values than reset values, allowing for detection of drift by reading the bits with a lower safe demarcation voltage and re-reading with a higher unsafe demarcation voltage if drift is detected, thereby reducing read latency and identifying silent data corruption.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a higher read voltage is used to read data from non-volatile memory cells after drift occurs, then data can be read, but read latency increases and the risk of writing 1s to 0 values increases
Solution Approach 1:
The system performs preliminary actions by encoding bits with more set values than reset values and using error correction codes to detect drift before it causes data corruption. This allows the system to prepare detection mechanisms in advance, enabling early identification of drift conditions without immediately resorting to higher read voltages, thus reducing latency while maintaining reliability.
Solution Approach 2:
The system implements feedback by continuously monitoring read errors and using error correction decoding to detect drift conditions. When drift is detected through feedback from error patterns, the system can switch to higher read voltages only when necessary, optimizing the balance between read speed and data integrity.
2Reliability
If error correction decoding is performed to correct drift-related errors, then data integrity is maintained, but read latency increases due to time-consuming decoding operations
Solution Approach 1:
The system applies partial action by using error correction codes that provide sufficient protection for drift detection without requiring full decoding operations for every read. The error correction mechanism is designed to handle the specific error patterns caused by drift, allowing the system to correct errors efficiently without performing excessive decoding that would increase latency.
3Difficulty of detecting and measuring
If bits are encoded with more set values than reset values, then drift detection becomes easier, but the complexity of the encoding scheme increases
Solution Approach 1:
The system changes the parameter of bit encoding by using a specific encoding scheme where bits are encoded with more set values than reset values. This parameter change makes drift detection easier because drift manifests as a measurable imbalance in the encoded bit patterns, while the encoding scheme itself remains a standard extension of existing bit encoding methods.
Data Source
AI summary
Provided are an apparatus, non-volatile memory storage device and method for detecting drift in in non-volatile memory. A determination is made as to whether bits to write have more of a first value than a second value. Each of the bits are flipped to another of the first or second value when the bits have more of the first value than the second value. Indication is made whether the bits were flipped or not flipped. Parity is calculated for the bits and the bits and the parity for the bits are written to a location in the non-volatile memory. The bits at the location in the non-volatile memory are read and each of the bits having the first value are flipped to the second value and each of the bits having the second value are flipped to the first value in response to indication that the bits were flipped.