Dynamic Soft Decoding Selection for Flash Memory Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Multi-level cell (MLC) flash memory devices used in SSDs face reliability issues due to gradual degradation from increased stresses, making them less suitable for enterprise applications, where endurance is critical.
Innovation Solution
A data storage system with a controller that dynamically selects soft decoding information by initiating multiple reads and decoding operations at different levels, determining success rates, and adjusting the order of decoding sets based on error correction performance to optimize decoding efficiency.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple decoding operations are performed at different read levels, then decoding reliability is improved, but processing time and computational complexity increase
Solution Approach 1:
The patent implements dynamic selection of decoding information sets based on real-time decoding success rates. The controller adaptively adjusts which decoding information set to use for subsequent read operations, transforming a static decoding process into a dynamic one that responds to actual performance feedback, thereby improving reliability without permanently increasing processing time
Solution Approach 2:
The system performs self-optimization by automatically determining decoding success rates and selecting the most effective decoding information sets without external intervention. The controller monitors decoding outcomes and autonomously adjusts its decoding strategy, allowing the system to serve itself and improve performance over time without additional processing overhead
2Measurement precision
If multiple decoding operations are performed at different read levels, then decoding accuracy is improved, but device complexity increases
Solution Approach 1:
The patent incorporates a feedback mechanism where the controller determines decoding success rates based on the outcomes of multiple decoding operations. This feedback is used to select the most effective decoding information sets for future operations. The feedback loop enables the system to improve decoding accuracy while managing complexity by focusing computational resources on the most promising decoding paths
Solution Approach 2:
The patent divides the decoding process into multiple stages, each using different decoding information sets corresponding to different read levels. By segmenting the decoding operations and evaluating their success rates, the system can identify and prioritize the most effective segments, improving overall accuracy while avoiding the need to implement all possible decoding paths simultaneously
Data Source
AI summary
Multiple reads of memory cells of a flash memory device are initiated at different read levels to obtain raw data. For each different read level, multiple decoding operations are initiated to decode the raw data, each decoding operation using a different one of a plurality of sets of decoding information associated with the different read level. Decoding success rates are determined for one or more of the plurality of sets based on the one or more of the plurality of sets being used to successfully decode data and, for each different read level, an order of the plurality of sets is determined based on the determined success rates. A selected set of decoding information is selected for use in decoding raw data obtained from a read performed at a respective read level based on the respective read level and the set order of the plurality of sets for the respective read level.