NAND Flash Defect Management via Fine-Grained Memory Retirement

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Conventional nonvolatile storage systems face challenges in managing defects effectively, leading to potential data loss and reduced memory utilization due to hardware defects and high residual bit error rates, especially when using low-density parity-check (LDPC) coding schemes.

Innovation Solution

The implementation of a nonvolatile storage system with an NVM defect management policy engine that monitors trigger events and applies defect management policies to retire memory with increased granularity, focusing on regions likely to contain defects, using XOR data recovery and error correction mechanisms to maintain data integrity.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If conventional defect management is used in nonvolatile storage systems, then data loss is prevented to some extent, but memory utilization decreases due to retirement of large memory regions

Engineering Contradiction:
Improvedata integrityVSAvoidmemory utilization
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent segments the memory retirement process from coarse-grained block/page level to fine-grained defect-level segmentation. Individual defective memory elements are identified and retired separately rather than retiring entire blocks or pages, allowing healthy memory regions to remain usable and thus maintaining higher memory utilization while ensuring data integrity.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent applies local quality by treating different memory regions differently based on their actual condition. Instead of uniformly retiring entire memory blocks when a defect is detected, the system applies defect management locally to only the specific defective elements, preserving the functionality of surrounding healthy memory regions and optimizing overall memory utilization.

Inventive Principle:
Principle #3Local quality

2Productivity

If memory is retired with increased granularity focusing on defective regions, then memory utilization is maintained, but system complexity increases due to monitoring and policy application

Engineering Contradiction:
Improvememory utilizationVSAvoiddefect management complexity
Core Design Contradiction:
ProductivityVSDevice complexity

Solution Approach 1:

The defect management policy engine operates autonomously to monitor trigger events, detect defects, and apply appropriate retirement policies without requiring manual intervention. The system self-manages the complex tasks of tracking defective elements, determining retirement strategies, and updating memory management structures, thereby reducing operational complexity despite the sophisticated defect management approach.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The system performs preliminary actions by proactively monitoring trigger events and detecting defects before they cause data loss. The defect management policy engine continuously watches for indicators of potential defects and pre-emptsively applies retirement policies to defective regions, preventing future errors and simplifying subsequent error handling.

Inventive Principle:
Principle #10Preliminary action

3Reliability

If proactive defect management is implemented, then data loss is reduced and memory usage is maintained, but trigger event monitoring and policy application require additional processing

Engineering Contradiction:
Improvedata reliabilityVSAvoidprocessing overhead
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The system applies partial action by monitoring and applying defect management policies only to specific memory regions where trigger events indicate potential defects, rather than continuously processing the entire memory space. This selective approach reduces overall processing overhead while maintaining high data reliability in the monitored regions.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentEP3072134B1Defect management policies for NAND flash memory
Publication Date: 2023.10.04 INTEL CORP
  • EP3072134B1 patent drawingFigure 1a
  • EP3072134B1 patent drawingFigure 1b
  • EP3072134B1 patent drawingFigure 2

AI summary

Systems and methods of managing defects in nonvolatile storage systems that can be used to avoid an inadvertent loss of data, while maintaining as much useful memory in the nonvolatile storage systems as possible. The disclosed systems and methods can monitor a plurality of trigger events for detecting possible defects in one or more nonvolatile memory (NVM) devices included in the nonvolatile storage systems, and apply one or more defect management policies to the respective NVM devices based on the types of trigger events that resulted in detection of the possible defects. Such defect management policies can be used proactively to retire memory in the nonvolatile storage systems with increased granularity, focusing the retirement of memory on regions of nonvolatile memory that are likely to contain a defect.