Adaptive Moving Read Reference Table for Memory Error Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Fixed Moving Read Reference (MRR) tables in non-volatile memory systems often lead to premature labeling of memory cells as unreadable due to excluded read reference values and repeated use of irrelevant entries, resulting in inefficient error correction and increased re-reads.
Innovation Solution
An adaptive MRR table is generated with a first portion having single MRR values and a second portion with multiple MRR values, ordered such that entries with the highest priority or count are used first, dynamically updating based on error correction capabilities and historical data to optimize read error recovery.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a fixed MRR table with fixed sequence is used, then the number of re-read attempts is limited, but many effective read reference values are excluded and irrelevant entries are repeatedly used
Solution Approach 1:
The MRR table is transformed from a static fixed sequence to a dynamic adaptive structure where entry priorities are continuously updated based on historical error data and correction outcomes. The system dynamically adjusts which read reference values are attempted first, adapting to different error patterns and memory cell states rather than following a predetermined sequence.
Solution Approach 2:
The system implements feedback mechanisms that monitor the results of each read attempt and error correction outcome. This feedback is used to update the priority rankings of MRR table entries, ensuring that previously successful read reference values are prioritized in future attempts while ineffective entries are deprioritized or removed from the sequence.
2Reliability
If numerous MRR attempts are made before ECC correction, then more read reference values are tested, but the process becomes time-consuming and complex
Solution Approach 1:
The MRR table is pre-populated with multiple potential read reference values and their priority rankings are established in advance based on historical data and error patterns. When a read error occurs, the system can immediately begin attempting corrections using the pre-ordered sequence without needing to perform real-time analysis or calculations, thus reducing latency while maintaining comprehensive error correction capability.
3Ease of manufacture
If fixed order MRR table entries are used, then implementation is simple, but memory cells are prematurely labeled as unreadable
Solution Approach 1:
The system changes the parameter of entry priority from a fixed static value to a dynamic value that can be adjusted based on performance metrics. Entries in the MRR table are assigned priority levels that can be modified according to their actual effectiveness in correcting read errors, allowing the system to adapt to different memory cell conditions and error patterns while maintaining a structured table format.
Data Source
AI summary
Examples are given for generating or providing a moving read reference (MRR) table for recovering from a read error of non-volatile memory included in a storage device. In some examples, priorities may be adaptively assigned to entries included in the MRR table. The entries may be ordered for use based on the assigned priorities. In other examples, the MRR table may be ordered for use such that entries with a single MRR value for each read reference value may be used first over entries having multiple MRR values for each read reference value. For these other examples, the MRR table may be adaptively reordered based on which entries were successful or unsuccessful in recovering from a read error but may still be arranged to have single MRR value entries used first for use to recover from another read error.