Memory Cell Decoding With Hard-Soft Switching for Read Reliability
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing methods for decoding data from non-volatile solid state memory cells often fail to achieve convergence, particularly due to noise and charge leakage, leading to errors in data retrieval, as they rely solely on hard data without confidence information.
Innovation Solution
The implementation of opportunistic decoding methods that utilize both hard and soft decoding processes, where hard data is initially decoded before soft data becomes available, and if convergence is not achieved, the decoder switches to soft decoding processes that incorporate confidence information from additional read operations and noise statistics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Speed
If hard decoding process is used initially before soft data is available, then decoding speed is improved, but decoding reliability deteriorates due to lack of confidence information
Solution Approach 1:
The patent performs hard decoding as a preliminary action before soft data is available. The controller initiates hard decoding immediately upon receiving hard data, without waiting for soft data from additional read operations. This preliminary decoding attempt can quickly succeed if the data quality is good, improving overall decoding speed while maintaining reliability through the fallback mechanism to soft decoding if convergence fails.
2Reliability
If soft decoding process is used with confidence information, then decoding reliability is improved, but decoding complexity increases
Solution Approach 1:
The patent segments the decoding process into two distinct stages: hard decoding followed by soft decoding. The hard decoding stage uses simple binary decisions without confidence information, while the soft decoding stage uses confidence information from additional read operations. This segmentation allows the system to use complex soft decoding only when necessary (when hard decoding fails), reducing overall complexity while maintaining high reliability.
3Measurement precision
If additional read operations are performed to obtain soft data, then data accuracy is improved, but read time increases
Solution Approach 1:
The patent implements a dynamic read strategy where the number of additional read operations performed to obtain soft data is adaptive. The controller performs additional reads to generate soft data only when the hard decoding process fails to achieve convergence. If hard decoding succeeds, no additional reads are performed. This dynamic approach optimizes the balance between data accuracy and read time based on actual decoding needs.
Data Source
AI summary
Approaches for decoding data read from memory cells of a nonvolatile, solid state memory involve attempting to decode hard data using a hard decoding process prior to a time that soft data is available to the decoder. The hard data includes information about the digital symbols stored in the memory cells without data confidence information. The soft data includes information about the digital symbols stored in the memory cells and data confidence information. In response to the hard decoding process failing to achieve convergence, after the soft data becomes available to the decoder, the soft data is decoded using a soft decoding process. The decoder generates an output of the decoded data after the hard decoding process or the soft decoding process achieves convergence.