Memory Decoder LLR Adjustment Using Assist Read Error Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing error correction systems face challenges in optimizing the trade-off between accuracy, efficiency, and latency when correcting data bit errors in memory devices and transmission media.
Innovation Solution
The system adjusts log likelihood ratios (LLR) used by a decoder by determining an assist read (AR) zone based on assist reads of multibit memory cells, performing soft reads to determine bins associated with LLR values, and adjusting these values based on hard error percentages computed from collected statistics.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional error correction procedures are used, then error correction capability is provided, but accuracy, efficiency, and latency cannot be optimized simultaneously
Solution Approach 1:
The system performs assist reads before main read operations to determine assist read zones and pre-computes LLR adjustments based on error statistics. This preliminary characterization of memory regions and error patterns enables faster error correction during actual data retrieval, improving efficiency without sacrificing reliability
Solution Approach 2:
The system dynamically adjusts LLR values based on computed hard error percentages from assist reads. By changing the LLR parameters according to observed error rates in different memory zones, the error correction decoder can operate more efficiently with optimized confidence levels, resolving the trade-off between correction reliability and processing efficiency
2Measurement precision
If assist reads and statistics collection are performed, then LLR values are optimized for better accuracy, but additional time and processing are required
Solution Approach 1:
Assist reads and error statistic collection are performed in advance to establish LLR adjustment profiles for different memory zones. This preliminary work is done once or periodically, and the resulting adjustment tables are reused for multiple subsequent read operations, achieving high measurement precision without incurring latency penalty during actual data access
Solution Approach 2:
The system implements dynamic LLR adjustment where the adjustment values are computed based on real-time error statistics from assist reads. The LLR values adapt to the actual error conditions observed in each memory zone, providing optimized accuracy while the system can choose when to perform assist reads based on workload requirements, balancing precision and time trade-offs
Data Source
AI summary
Techniques for adjusting log likelihood ratios in a decoder may include determining an assist read (AR) zone based on performing assist reads (AR) of multibit memory cells of a memory. Soft reads of the multibit memory cells may be performed to determine a bin within the AR zone for each bit of the data stored in the memory cells. Each bin is associated with a log likelihood ratio (LLR) value. Error correction decoding on the data stored in the memory cells may be performed followed by collecting statistics on the decoded data for each bin in each AR zone. A hard error percentage may be computed for each AR zone based on the collected statistics, and one or more LLR values may be adjusted based on the hard error percentage.