Memory Controller Decoding With Rollback for Large-Block ECC Errors
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Memory systems face challenges in efficiently decoding data protected by multi-dimensional error correction codes, particularly when errors occur in large blocks, leading to decoding failures and stagnation due to the complexity of correcting errors across multiple component codes.
Innovation Solution
A memory system with a memory controller that performs iterative decoding processes, including bounded distance decoding and multi-bit flip decoding, with a rollback mechanism and parameter adjustment to manage decoding failures and stagnation, ensuring successful error correction.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multi-dimensional error correction coding is used to protect data in memory systems, then data reliability is improved, but decoding complexity increases and decoding failures occur when errors occur in large blocks
Solution Approach 1:
The patent segments the decoding process into multiple stages: first performing bounded distance decoding on component codes, then performing decoding exceeding bounded distance on error symbol groups that failed initial decoding. This segmentation allows the system to handle errors in a structured manner, reducing overall decoding complexity while maintaining high reliability.
Solution Approach 2:
The patent implements a dynamic decoding approach where the decoding process adapts based on the results of previous decoding attempts. When bounded distance decoding fails, the system dynamically transitions to decoding exceeding bounded distance for specific error symbol groups, and includes a rollback mechanism that adjusts decoding parameters based on detected stagnation, making the decoding process flexible and adaptive rather than static.
2Measurement precision
If bounded distance decoding is performed repeatedly on component codes, then decoding accuracy is improved, but decoding process stagnation occurs when errors occur in large blocks
Solution Approach 1:
The patent implements a feedback mechanism through stagnation detection that monitors the decoding process. When stagnation is detected (indicating that repeated bounded distance decoding is not making progress), the system provides feedback to switch to decoding exceeding bounded distance for error symbol groups, and can trigger rollback processes to adjust decoding parameters, preventing infinite loops and improving time efficiency.
Solution Approach 2:
The decoding process is made dynamic by allowing transitions between different decoding modes based on performance. The system starts with bounded distance decoding for accuracy, but dynamically switches to decoding exceeding bounded distance when stagnation is detected, and can rollback to adjust parameters, creating a flexible adaptive process that balances accuracy with time efficiency.
3Reliability
If decoding exceeding bounded distance is performed in units of component codes for error symbol groups, then error correction capability is improved, but device complexity increases
Solution Approach 1:
The patent segments the error correction process by applying decoding exceeding bounded distance only to error symbol groups that failed initial bounded distance decoding, rather than processing all data uniformly. This selective approach targets specific error-prone areas, improving error correction capability while avoiding unnecessary complexity in processing error-free data.
Solution Approach 2:
The patent applies different decoding strategies to different parts of the data based on local error conditions. Error symbol groups undergo decoding exceeding bounded distance while other data uses standard bounded distance decoding. This local differentiation optimizes error correction capability where needed while maintaining overall system efficiency and managing complexity.
Data Source
AI summary
A memory system of an embodiment includes a non-volatile memory and a memory controller. The memory controller executes a first decoding process of reading data encoded by an error correction code from the non-volatile memory and repeatedly executing bounded distance decoding on a symbol group protected by each of component codes included in N component code groups; executes a second decoding process of repeatedly executing decoding exceeding a bounded distance in units of component codes for an error symbol group determined to include an error due to a syndrome of a component code included in the N component code groups when the first decoding process fails; executes a rollback process when the first decoding process executed after the second decoding process fails; and changes a parameter used in the second decoding process and further executes the second decoding process when it is detected that the second decoding process is not progressed.