Storage Control Device Multi-Bit Error Correction via Data Pattern Ranking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
As storage device capacities increase, errors in written data become more frequent, leading to complex and time-consuming correction processes, especially when multiple-bit errors occur, which prolongs reading processing times.
Innovation Solution
A control device that classifies data blocks into patterns, counts their occurrences, and uses ranking information to select and replace erroneous data blocks with high-ranking patterns, facilitating high-speed correction of both single and multiple-bit errors by selecting data patterns with higher occurrence probabilities.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional error correction methods are used to detect and correct multiple-bit errors, then error correction reliability is improved, but processing time and computational load increase significantly
Solution Approach 1:
The patent pre-calculates and stores syndrome values and correction information for all possible error patterns in a lookup table during system initialization. When an error occurs, the system simply queries this pre-prepared table using the calculated syndrome as an index, obtaining the correction information instantly without performing complex real-time computations, thus resolving the contradiction between reliable error correction and fast processing
Solution Approach 2:
The patent creates a copy of correction information for various error patterns and stores it in a lookup table. Instead of computing correction algorithms in real-time, the system copies the pre-computed correction data from the table based on the syndrome value, significantly reducing processing time while maintaining correction reliability
2Reliability
If complex error correction processing is performed on all read data, then error detection and correction capability is improved, but processing load and time consumption increase
Solution Approach 1:
The patent applies partial action by first performing a simple parity check on read data to detect errors. Only when an error is detected does the system proceed to the more complex syndrome calculation and lookup table query process. This staged approach ensures that most error-free data passes through quickly with minimal processing, while maintaining full error correction capability when needed
Solution Approach 2:
The patent segments the error correction process into distinct stages: parity check stage, syndrome calculation stage, and correction information retrieval stage. By dividing the processing into segments, the system can quickly handle the majority of cases at the first stage and only engage deeper processing when necessary, improving overall processing efficiency
Data Source
AI summary
A control device configured to control a storage device includes a memory and a processor coupled to the memory and configured to store, into the storage device, a plurality of data blocks including a plurality of data patterns, classify the plurality of data blocks into the plurality of data patterns, for each of the plurality of data patterns, count numbers of the classified plurality of data blocks classified into each of the plurality of data patterns, read a first data block among the plurality of data blocks from the storage device, select a first data pattern from the plurality of data patterns based on the counted numbers when an error is detected in first data included in the first data block, replacing the first data included in the first data block with the selected first data pattern, and output the first data block including the first data pattern.