Memory Encoding Across Uneven Word-Line Error Rates
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Rewritable non-volatile memory modules exhibit varying error rates across different word lines due to physical characteristics, leading to inconsistent error checking and correcting capabilities during data encoding and decoding processes.
Innovation Solution
A data encoding method that divides the memory module into two areas, each using distinct encoding methods to generate encoded data, allowing for improved error checking and correcting capabilities, particularly for word lines with higher error rates by utilizing multi-frame and single-frame encoding algorithms.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If a single encoding method is used for all physical programming units, then the device complexity is reduced, but the error checking and correcting capability for high-error-rate word lines deteriorates
Solution Approach 1:
The patent divides the memory module into multiple areas based on error rates of word lines. Different encoding methods are applied to different areas: high-error-rate word lines use one encoding method while low-error-rate word lines use another. This segmentation allows optimized error correction for each area without applying complex encoding universally, thus improving reliability where needed while managing overall complexity.
Solution Approach 2:
The patent implements location-aware encoding where the encoding method is selected based on the specific characteristics of each word line or area. High-error-rate areas receive more robust encoding treatment, while low-error-rate areas use simpler encoding. This local quality approach ensures that error checking and correcting capability is enhanced precisely where it is most needed, rather than uniformly across all areas.
2Reliability
If robust error correction encoding is applied to all data, then the error checking and correcting capability is improved, but the processing time and productivity are reduced
Solution Approach 1:
The patent applies robust error correction encoding only partially - specifically to high-error-rate word lines that require it. Low-error-rate word lines use simpler or no error correction encoding. This partial action approach ensures that strong error correction is applied where necessary to maintain reliability, while avoiding the productivity penalty of applying it universally to all data.
3Reliability
If different encoding methods are used for different areas, then the error checking and correcting capability for high-error-rate word lines is improved, but the device complexity increases
Solution Approach 1:
The patent segments the memory module into multiple areas with different error characteristics. Each area is assigned an appropriate encoding method based on its error rate profile. This segmentation strategy improves decoding success rate for high-error-rate areas while managing system complexity by using simpler encoding for low-error-rate areas, rather than uniformly complex encoding throughout.
Data Source
AI summary
A data encoding method, a memory control circuit unit and a memory storage device are provided. The method includes: writing a first data into a first physical programming units; writing a second data into a second physical programming units; encoding by using the first data without using the second data to generate a first encoded data; encoding by using the second data and a first sub-data of the first data to generate a second encoded data; and writing the first encoded data and the second encoded data into a third physical programming unit and a fourth physical programming unit.