Non-Volatile Memory Read Disturbance Mitigation via Verification Reads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The increasing integration density and scaling down of semiconductor storage devices lead to issues such as increased missing data and deterioration in data reliability, particularly due to read disturbances affecting memory cells.
Innovation Solution
A method for operating a storage device with a non-volatile memory and memory controller that includes performing a reliability verification read on unselected memory cells, prohibiting writes to erased cells with high bit error rates, and executing read reclamation operations based on bit error rates to maintain data integrity.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If integration density of semiconductor storage device is increased, then cost per bit is reduced, but data reliability deteriorates due to read disturbances
Solution Approach 1:
The patent performs reliability verification reads on unselected memory cells before normal read operations. This preliminary detection of read disturbances allows the system to identify and mitigate potential data corruption issues before they affect actual data retrieval, thereby maintaining data reliability in high-density storage devices.
Solution Approach 2:
The patent implements a feedback mechanism where the memory controller monitors bit error rates from reliability verification reads and uses this information to determine whether read reclamation operations are needed. This closed-loop approach allows the system to adapt its behavior based on actual data quality, resolving the reliability issue in high-density devices.
2Volume of moving object
If scaling down of storage device is performed, then integration density increases, but missing data increases
Solution Approach 1:
The patent performs reliability verification reads on unselected memory cells before normal read operations. This preliminary detection of read disturbances allows the system to identify and mitigate potential data corruption issues before they affect actual data retrieval, thereby maintaining data reliability in high-density storage devices.
Solution Approach 2:
The patent changes the operational parameters by introducing reliability verification reads and conditionally executing read reclamation operations based on bit error rate thresholds. This parameter adjustment allows the system to compensate for the increased susceptibility to read disturbances inherent in scaled-down devices.
3Reliability
If reliability verification read is performed on all memory cells, then data reliability is improved, but operation time increases
Solution Approach 1:
The patent applies local quality by performing reliability verification reads selectively on unselected memory cells that are most susceptible to read disturbances, rather than uniformly checking all memory cells. This targeted approach maintains data reliability while minimizing the time overhead of verification operations.
Solution Approach 2:
The patent performs reliability verification reads on unselected memory cells (excessive action relative to standard reads) but only when necessary based on bit error rate conditions. This partial application of verification reads ensures data reliability is maintained without unnecessarily increasing operation time for all read operations.
Data Source
AI summary
A method of operating a storage device may include receiving a read command and a read address, performing a read operation on selected memory cells corresponding to a selected string selection line and a selected word line based on the read address and performing a reliability verification read on unselected memory cells. Data read by the read operation may be output to an external device, and data read by the reliability verification read may be not output to the external device.