Memory Controller Read Reclaim via Disturbance Counting
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face performance and reliability issues due to uniform read reclaim operations that do not consider the varying effects of read disturbance phenomena across different memory blocks, leading to inefficient data retrieval and storage.
Innovation Solution
A controller that calculates a current read count by adding read disturbance counts to previous read counts for neighboring pages, determining when to perform a read reclaim operation based on these counts, thereby reflecting the state of each memory block and improving data retrieval efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If uniform read reclaim operations are performed on all memory blocks, then the operation simplicity is maintained, but the reliability deteriorates due to not considering varying read disturbance effects
Solution Approach 1:
The patent applies local quality by differentiating read reclaim operations based on the specific characteristics of each memory block. Instead of uniform treatment, the system calculates read disturbance counts individually for each memory block and applies read reclaim operations selectively based on these localized measurements, thereby improving reliability without requiring overly complex system-wide mechanisms
Solution Approach 2:
The patent implements feedback by measuring read disturbance counts through test read operations on each memory block and using these measurements to determine whether read reclaim operations are needed. This feedback loop allows the system to adapt read reclaim operations to actual memory block conditions, improving reliability while maintaining operational simplicity through automated decision-making
2Reliability
If read reclaim operations are performed frequently to improve reliability, then data retrieval reliability improves, but productivity deteriorates due to increased operation overhead
Solution Approach 1:
The system uses feedback from test read operations to measure actual read disturbance counts in each memory block. Read reclaim operations are triggered only when the measured count exceeds a threshold, ensuring operations are performed frequently enough to maintain reliability but not so frequently as to unnecessarily reduce productivity
Solution Approach 2:
The patent changes the parameter of read reclaim operation frequency based on measured read disturbance counts. Instead of fixed-frequency operations, the system dynamically adjusts operation timing based on actual memory block conditions, improving reliability when needed while maintaining productivity during normal operation
3Measurement precision
If test read operations are performed to calculate read disturbance counts, then measurement precision improves, but the use of energy increases due to additional read operations
Solution Approach 1:
The patent applies partial action by performing test read operations on only selected memory blocks or pages rather than exhaustively testing all memory blocks. This selective approach provides sufficient measurement precision to identify blocks needing read reclaim operations while limiting the energy consumption associated with comprehensive testing
Data Source
AI summary
A method for operating a controller that controls a memory device including a memory block formed of a plurality of pages: calculating a read disturbance count for each of neighboring pages of a target page in the memory block based on the number of times that a test read operation is performed on the target page; calculating a read count for each of the neighboring pages based on the read disturbance count during a read operation on the target page; and determining whether to perform a read reclaim operation based on the read counts of the pages in the memory block.