Non-volatile Memory Post-Write Read Error Management
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional error correction codes (ECC) in flash memory systems are resource-intensive and designed for worst-case error rates, leading to performance degradation and overhead, especially as the memory ages and error rates increase.
Innovation Solution
Implementing a post-write-read error management system that adapts by writing data to a higher density memory portion and then checking for excessive errors, rewriting data to a less error-prone portion if necessary, allowing for a smaller and more efficient ECC to correct fewer errors, thereby improving performance and reducing costs.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional ECC is designed for worst-case error rates, then reliability is improved, but device complexity and overhead increase
Solution Approach 1:
The patent changes the error rate parameter from worst-case (6σ) to a more practical level (3σ) based on statistical analysis of actual error distributions. This parameter change allows designing ECC for fewer error bits while maintaining adequate reliability for the majority of cases, reducing ECC complexity and overhead.
Solution Approach 2:
The patent applies partial action by correcting only the most probable error cases (within 3 standard deviations) rather than preparing for all possible worst-case scenarios. This partial correction approach handles the majority of error situations effectively while avoiding the excessive complexity of comprehensive worst-case ECC design.
2Productivity
If memory operates at higher density, then productivity is improved, but manufacturing precision requirements increase
Solution Approach 1:
The patent implements feedback by performing post-write-read operations to detect errors in newly programmed data. This feedback mechanism identifies errors that occur during writing to high-density memory, allowing the system to detect and correct issues without requiring higher manufacturing precision during the writing process itself.
Solution Approach 2:
The patent applies preliminary action by performing error detection (post-write-read) immediately after data writing before the data is used. This preliminary error detection allows the system to identify and handle erroneous data early, enabling high-density operation without compromising data integrity.
Data Source
AI summary
Data errors in non-volatile memory inevitably increase with usage and with higher density of bits stored per cell. The memory is configured to have a first portion operating with less error but of lower density storage, and a second portion operating with a higher density but less robust storage. Input data is written and staged in the first portion before being copied to the second portion. An error management provides checking the quality of the copied data for excessive error bits. The copying and checking are repeated on a different location in the second portion until either a predetermined quality is satisfied or the number or repeats exceeds a predetermined limit. The error management is not started when a memory is new with little or no errors, but started after the memory has aged to a predetermined amount as determined by the number of erase/program cycling its has experienced.