Soft-Decision Data Compression for Error-Aware Memory Reads
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face issues with loss or overhead of soft decision data during transmission to a memory controller due to inefficient compression methods.
Innovation Solution
A memory device that compresses soft decision data using a fixed and variable compression ratio, determined based on error bits to be corrected, to generate compressed data segments, reducing information loss and overhead.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If a fixed compression ratio is used to compress soft decision data, then the compression process is simple and fast, but information loss occurs when error bits are present and overhead increases
Solution Approach 1:
The patent applies dynamic compression by adjusting the compression ratio based on the number of error bits detected in the data. When error bits are present, the compression ratio is reduced or suspended to preserve information integrity. When no error bits are detected, normal compression is applied to maintain transmission efficiency. This dynamic adjustment resolves the contradiction between compression speed and information loss.
Solution Approach 2:
The system implements feedback mechanisms where the compression process monitors error bit conditions and adjusts compression parameters accordingly. The feedback loop detects error bits in the SD data and dynamically modifies the compression ratio to prevent information loss while maintaining efficient compression operation.
2Reliability
If a low compression ratio is used to prevent information loss, then data integrity is maintained, but the compressed data size increases causing overhead
Solution Approach 1:
The patent applies local quality by differentiating compression strategies based on local error conditions in the data. Instead of uniformly applying low compression ratio to all data, the system selectively reduces compression only in regions where error bits are detected, while maintaining higher compression ratios in error-free regions. This localized approach preserves data integrity where needed while minimizing overall data size.
3Loss of information
If soft decision data is transmitted without compression, then no information is lost, but transmission overhead and bandwidth consumption increase
Solution Approach 1:
The system dynamically adjusts compression based on error conditions, applying compression only when data integrity can be maintained. This conditional compression approach reduces transmission volume significantly compared to uncompressed transmission, while preserving information completeness through error-aware compression ratio adjustment.
Data Source
AI summary
Provided is a memory device including a memory cell array, a page buffer circuit that acquires soft decision (SD) data including a plurality of SD data segments from a plurality of memory units in memory cell array using a soft read voltage, and a compression circuit that compresses the SD data into compressed data including a plurality of compressed data segments corresponding to the plurality of SD data segments, in which the compression circuit compresses the plurality of SD data segments based on a fixed compression ratio determined based on information associated with an error bit to be corrected using the SD data and a plurality of variable compression ratios respectively applied to the plurality of SD data segments.