Memory Page ECC Management for Erased-Word False Errors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in effectively managing data integrity with existing Error Correcting Codes (ECC) methods, particularly in detecting and correcting ECC errors during write and read operations.
Innovation Solution
A special error correction code algorithm (SECC) is implemented, using the formula SECC(X) = BECC(X) XOR BECC(W_E) XOR RC_E, to calculate and store redundancy codes for user data, ensuring accurate data management by avoiding false errors and correcting errors when necessary.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional ECC methods are used to detect and correct errors, then data integrity is improved, but false errors may be generated and data management complexity increases
Solution Approach 1:
The patent applies the 'Blessing in disguise' principle by converting the potentially harmful effect of erased words (which could cause false errors) into a beneficial feature. The SECC algorithm specifically handles erased words by using their reference binary codes to generate appropriate redundancy codes, thereby preventing false errors instead of merely reacting to them. This transforms the problematic presence of erased words into a controlled feature that enhances data integrity.
Solution Approach 2:
The patent changes the parameter of the error correction code algorithm from conventional BECC to SECC, which modifies how redundancy codes are calculated. The SECC algorithm uses the formula SECC(X) = BECC(X) XOR BECC(W_E) XOR RC_E, where W_E represents erased words. This parameter change in the algorithm's approach to handling erased words prevents false errors while maintaining data integrity.
2Reliability
If redundancy codes are calculated and stored for each word, then error correction capability is improved, but data management complexity and processing time increase
Solution Approach 1:
The patent applies 'Preliminary action' by pre-defining the reference binary codes for erased words before actual data storage occurs. These reference codes are prepared in advance and stored in the memory element, allowing the SECC algorithm to quickly generate redundancy codes without complex real-time calculations. This preliminary preparation simplifies the data management process while maintaining strong error correction capability.
3Difficulty of detecting and measuring
If existing ECC algorithms are used, then error detection is achieved, but error correction accuracy decreases and false corrections occur
Solution Approach 1:
The patent implements feedback mechanisms through the SECC algorithm that continuously verifies the consistency of redundancy codes with the original data. When data is read back, the algorithm compares the decoded data with the original user data and can identify when a word was actually erased rather than corrupted. This feedback loop prevents false corrections by distinguishing between genuine errors and erased words, thereby improving error correction accuracy.
Data Source
AI summary
A method for managing data stored in a page (P) within a memory element of a memory system including a controller, the page (P) including at least one encoded data (E) consisting in a binary code being formed by a word (W 0-N) and its associated redundancy code (RC 0-N), the method including a step of storing a user data in this page (P) implemented by the controller, this step including a sub-step of performing error correction code (ECC) calculations on the user data providing an associated redundancy code (RC 0-N) corresponding to an erased redundancy code (RC E) for this user data if it has a reference binary code (br) of an erased word (W E) the erased redundancy code (RC E) having a binary value similar to that of the reference binary code (br).