Memory Die Retention Rating from Regular Scan Metrics
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for determining data retention capability of memory devices require complex firmware implementations and reduce available storage space, leading to increased latency and decreased Quality of Service (QoS) due to the need for stress-inducing operations.
Innovation Solution
Utilize data state metrics obtained from regular scans to rate data retention capability, eliminating the need for separate stress-inducing operations by mapping these metrics to corresponding scan frequencies.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If stress-inducing operations are performed to determine data retention capability, then measurement precision is improved, but device complexity and loss of time increase
Solution Approach 1:
The patent extracts the data retention assessment from complex stress-inducing operations and separates it into regular scan operations. By taking out the essential measurement function from the stressful test environment, the system uses normal operational scans to gather data retention information without requiring complex firmware implementations or dedicated stress test infrastructure.
Solution Approach 2:
The patent performs data retention assessment during regular scan operations before actual data loss occurs. By continuously monitoring data state metrics during normal operation and mapping them to scan frequencies, the system proactively identifies retention issues before they manifest as failures, eliminating the need for complex post-failure analysis or stress-induced testing.
2Measurement precision
If stress-inducing operations are performed to determine data retention capability, then measurement precision is improved, but loss of time increases
Solution Approach 1:
The patent merges data retention assessment with regular scan operations. Instead of performing separate stress-inducing operations that would increase latency, the system combines retention monitoring with existing scan workflows, allowing both functions to execute simultaneously without adding time overhead.
Solution Approach 2:
The patent maintains continuous data retention monitoring through regular scan operations rather than performing intermittent stress tests. This continuous assessment approach ensures that retention capability is constantly evaluated during normal operation, eliminating the time loss associated with stopping operations for dedicated stress testing.
3Measurement precision
If separate stress-inducing operations are performed, then data retention capability is accurately determined, but productivity decreases
Solution Approach 1:
The patent makes regular scan operations multi-functional by enabling them to simultaneously perform data retention assessment in addition to their primary scanning function. This universal approach eliminates the need for separate dedicated stress-test operations, allowing the same infrastructure to serve multiple purposes including retention monitoring, data verification, and performance optimization.
Solution Approach 2:
The patent enables the memory sub-system to self-assess its data retention capability using its own regular scan operations without requiring external stress-inducing operations. The system monitors its own data state metrics and automatically maps these to appropriate scan frequencies, making the retention assessment self-sufficient and eliminating the productivity loss associated with external testing operations.
4Measurement precision
If stress-inducing operations are performed, then data retention capability is determined, but available storage space is reduced
Solution Approach 1:
The patent extracts the retention assessment function from dedicated stress-test storage regions and relocates it to regular user data scan operations. By taking out the measurement function from specialized test areas, the system can use all available storage space for productive purposes while still performing accurate retention monitoring through scans of normally accessed data.
Data Source
AI summary
A system includes a memory device including a plurality of dies; and a processing device, operatively coupled with the memory device, to perform operations including: obtaining, by performing a plurality of scan operations on a die of the plurality of dies, a value of a data state metric characterizing the die; identifying, in a set of criteria, a particular criterion that is satisfied by the value of the data state metric, wherein each criterion of the set of criteria corresponds to a respective rating of a plurality of ratings; assigning, to the die, a rating corresponding to the particular criterion; and performing a plurality of subsequent scan operations on the die at a frequency determined by the rating.