Refresh Address Mapping for Weak Memory Cells
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for refreshing storage elements in wireless communication devices with low retention times are inefficient, as they often require frequent refresh commands for all memory cells, including those with stronger retention times, leading to unnecessary power consumption and reduced device performance.
Innovation Solution
A system that identifies 'weak' storage elements with lower retention times and groups them with 'strong' elements having distinct bank offsets onto a single refresh address, allowing for targeted and efficient refresh operations using a combination of refresh circuitry and one-time programmable memory to map refresh addresses, thereby reducing the frequency of unnecessary refreshes.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the frequency of refresh commands is increased to maintain data integrity in memory cells with low retention times, then data integrity is improved, but power consumption increases and device performance deteriorates
Solution Approach 1:
The patent segments the memory array into multiple banks and identifies specific weak rows within those banks that require frequent refreshing. By segmenting the refresh operation to target only the necessary weak storage elements rather than refreshing all memory cells uniformly, the system maintains data integrity for vulnerable cells while reducing power consumption from unnecessary refresh operations on stable cells.
Solution Approach 2:
The patent applies local quality by implementing differentiated refresh strategies for different regions of the memory array. Specifically, weak rows are identified and assigned higher refresh frequencies while strong rows use standard refresh rates. This localized approach ensures that only the specific areas with data integrity issues receive intensive refreshing, thereby optimizing the balance between reliability and power consumption.
2Reliability
If additional refresh commands are issued for each memory cell with low retention time, then data integrity is improved, but the number of refresh commands increases and device performance deteriorates
Solution Approach 1:
The patent segments the memory system into multiple banks with distinct row addresses and identifies specific weak rows within those banks. By organizing weak rows into bank-specific groups and using segmented refresh address generation, the system can issue targeted refresh commands only to the necessary weak storage elements, avoiding the performance degradation that would result from issuing additional refresh commands for every memory cell.
Solution Approach 2:
The patent performs preliminary identification of weak rows during a testing phase before normal operation. The results of this preliminary action are stored in a lookup table that guides subsequent refresh operations. This preliminary classification allows the system to efficiently manage refresh commands during operation without needing to continuously identify weak cells, thereby maintaining device performance while ensuring data integrity.
3Reliability
If all memory cells are refreshed uniformly, then data integrity is maintained across the entire memory array, but power consumption increases due to unnecessary refreshes of cells with stronger retention times
Solution Approach 1:
The patent implements local quality by applying different refresh frequencies to different regions of the memory array based on their individual retention characteristics. Weak rows that require frequent refreshing are identified and targeted with higher refresh rates, while strong rows with adequate retention times use standard refresh rates. This localized differentiation maintains data integrity across the entire memory array while significantly reducing power consumption from unnecessary refresh operations on stable cells.
Solution Approach 2:
The patent applies partial action by refreshing only the specific weak rows that require it, rather than performing excessive full-array refreshes. The refresh operation is partially applied to the entire memory array, with intensified refreshing only where needed for weak storage elements. This approach maintains overall data integrity while eliminating the power waste associated with uniformly refreshing all cells regardless of their actual retention needs.
Data Source
Figure 1
Figure 2A~2B
Figure 3
AI summary
A method of performing refresh operations on a storage device includes identifying word lines coupled to weak storage elements. The method also includes grouping a plurality of word lines having distinct bank offsets onto a single refresh address. Each of the plurality of word lines is coupled to a corresponding weak storage element. The method further includes performing a refresh of the single refresh address.