Min-Sum LDPC Decoder with Weight-Based Scaling for NAND Flash

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

NAND flash-based storage devices face challenges with data reliability and lifespan due to increased fabrication process complexities, requiring more powerful error correction codes to overcome noise and interference, which irregular LDPC codes can address but with limitations in decoding efficiency.

Innovation Solution

A decoding method that classifies check nodes in a matrix with irregular check node weights into different groups, applies distinct scaling factors to constant node to variable node messages, and adds a compensation term to enhance the performance of the min-sum decoder.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If irregular LDPC codes are used to improve error correction capability, then data reliability is improved, but decoding efficiency deteriorates

Engineering Contradiction:

Improvedata reliabilityVSAvoiddecoding efficiency

Core Design Contradiction:

ReliabilityVSProductivity

Solution Approach 1:

The check nodes are segmented into different groups based on their weights (e.g., degree-2 check nodes, degree-3 check nodes, etc.). Each group is processed independently with its own scaling factor, allowing the decoder to handle irregular LDPC codes more efficiently by treating similar-weight check nodes uniformly while maintaining the benefits of irregularity.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

Different scaling factors are applied locally to different groups of check nodes based on their specific weight characteristics. This local optimization allows the decoding process to adapt to the varying requirements of different check node types, improving overall decoding efficiency while maintaining the error correction advantages of irregular LDPC codes.

Inventive Principle:

Principle #3Local quality

2Reliability

If scaling factors are applied to C2V messages to improve decoding accuracy, then codeword failure rate is reduced, but computational complexity increases

Engineering Contradiction:

Improvecodeword failure rateVSAvoidcomputational complexity

Core Design Contradiction:

ReliabilityVSDevice complexity

Solution Approach 1:

Check nodes are divided into discrete weight-based groups, with a specific scaling factor assigned to each group. This segmentation approach reduces the computational complexity compared to using different scaling factors for every individual check node, while still providing the accuracy benefits of group-specific optimization.

Inventive Principle:

Principle #1Segmentation

Solution Approach 2:

The scaling factor parameter is changed based on the check node weight group, allowing the system to optimize decoding accuracy for different types of check nodes. By changing this single parameter based on group classification, the system achieves improved reliability without the full computational burden of individualized processing.

Inventive Principle:

Principle #35Parameter changes

Data Source

PatentUS12132498B2Min-sum decoder for row-irregular low density parity check codes

Publication Date: 2024.10.29 SK HYNIX INC

AI summary

Decoding method and memory system that classify check nodes in a matrix having irregular check node weights into different groups according to the check node weights, apply different scaling factors to respective constant node to variable node (C2V) messages in the different groups of the check nodes, and optionally add a compensation term to at least one of the C2V messages of the MS decoder.