Memory Device Error Correction Logic for Silent Data Corruption
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory devices often experience silent data corruption (SDC) where errors go undetected and uncorrected, leading to corrupted data despite error correction coding, due to the limitations in error detection and correction mechanisms.
Innovation Solution
A memory device with a logic chip that performs error correction decoding on codewords, identifying and processing errors as uncorrectable when they exceed the maximum correctable threshold, thereby preventing the transmission of corrupted data to external hosts and enhancing reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If error correction decoding is performed on all data units, then data reliability is improved, but device complexity increases due to the need to identify and manage uncorrectable errors
Solution Approach 1:
The patent divides data units into two categories: correctable data units and uncorrectable data units. By segmenting the error correction process this way, the system can selectively apply different handling mechanisms to different data units, improving reliability for critical data while managing complexity through structured classification.
Solution Approach 2:
The patent applies different error correction strategies to different data units based on their characteristics. Some data units receive full error correction treatment while others are handled differently, allowing the system to optimize reliability where needed without uniformly increasing complexity across the entire system.
2Measurement precision
If the error correction threshold is lowered to catch more errors, then detection precision is improved, but the number of false positive errors increases
Solution Approach 1:
The patent implements a feedback mechanism where the system continuously monitors error correction results and adjusts its threshold based on observed patterns. This allows the system to maintain high detection precision by learning from actual error patterns while reducing false positives through adaptive threshold adjustment.
Solution Approach 2:
The patent dynamically changes the error correction threshold parameter based on system conditions and observed error patterns. By adjusting the threshold parameter adaptively rather than using a fixed value, the system can optimize detection precision while minimizing false positives in different operational contexts.
Data Source
AI summary
A method for reading data from a memory includes; reading a codeword from the memory cells, correcting the errors when a number of errors in the codeword is less than a maximum number of correctable errors, correcting the errors when the number of errors in the codeword is equal to the maximum number of correctable errors and the errors correspond to a same sub-word line, and outputting signal indicating that the errors are an uncorrectable error when the number of errors of the codeword is equal to the maximum number of correctable errors and the errors correspond to different sub-word lines.