Non-Volatile Memory Erase Block Stability Characterization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices (NVMDs) experience instability and error rates when erase blocks are partially filled, leading to data loss and reduced memory capacity due to the inability to detect and correct errors effectively, especially in recent 20 nanometer flash memory devices.
Innovation Solution
Characterizing NVMDs by identifying stability points within erase blocks through a method of programming, verifying, and recording sequences of contiguous pages to determine instability points, and stabilizing these blocks by writing dummy data until a stability point is reached before erasure.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If data is written to NVMDs in parallel to improve write speed, then write latency is reduced, but partially filled erase blocks are created causing data instability and errors
Solution Approach 1:
The system performs preliminary actions by characterizing erase blocks before use and stabilizing partially filled blocks before erasure. The controller identifies stability points in advance and ensures complete word lines are filled before initiating erasure operations, preventing instability-related errors.
Solution Approach 2:
The system implements feedback mechanisms where the controller monitors and tracks the state of erase blocks during parallel writes. When a stability point is detected or a word line becomes partially filled, the controller adjusts write operations accordingly, ensuring reliable data storage while maintaining high write speeds.
2Quantity of substance
If partially filled erase blocks are erased to maintain memory capacity, then available storage space is preserved, but error rates increase and data loss occurs
Solution Approach 1:
Before erasing an erase block, the system performs preliminary characterization to identify stability points and ensures all word lines are completely filled with stable data. This preliminary stabilization prevents errors during subsequent erasure operations while preserving memory capacity.
Solution Approach 2:
The system changes the state of erase blocks from unstable (partially filled) to stable (completely filled) by adjusting write operations. The controller modifies the filling parameter of word lines to ensure complete data writing before erasure, transforming the block state to prevent errors.
3Reliability
If stability points are characterized and tracked to prevent errors, then data reliability is improved, but device complexity increases
Solution Approach 1:
The system implements self-service by having the NVMD controller automatically perform characterization and tracking of stability points without external intervention. The controller monitors its own operations, identifies stability points, and manages erase block states independently, improving reliability while minimizing added complexity.
4Quantity of substance
If 20 nanometer flash memory devices are used to increase storage density, then memory capacity is improved, but susceptibility to errors in partially filled blocks increases
Solution Approach 1:
Before using 20nm flash memory blocks, the system performs preliminary characterization to identify stability points and ensures complete word line filling. This preliminary action prevents errors in the high-density memory structure that is more susceptible to instability.
Solution Approach 2:
The system changes operational parameters by ensuring word lines are completely filled before erasure in 20nm flash memory devices. The controller adjusts the filling completeness parameter to 100% for all word lines, preventing errors in the more error-prone high-density memory structure.
Data Source
AI summary
A sequence of contiguous pages in an erase block in a non-volatile memory device is programmed and erased. Next, all of the pages in the erase block are programmed with data. Then, the data is read back and verified to determine whether there is an error in the data. When there is an error in the data, then the last page in the sequence is identified as being unstable. If there is no error in the data, then the last page in that sequence is identified as being stable. Thus, the recorded information identifies a point of instability in the erase block. Instabilities can be stabilized by performing additional writes to fill the partially filled word line.