Memory Erase Policy Selection for Retention and Latency Tradeoffs

Resolve Bottlenecks,
Find Innovative SolutionsGenerate Solutions

Solution Overview

Problem

Conventional memory systems use a single type of erase operation without considering how erase operations affect system performance for specific erase policy implementations, leading to inefficiencies in data retention and system performance.

Innovation Solution

Dynamically select an erase operation based on the erase policy and workload, using alternating erase operations for better data retention and reducing the fringing field between erase voltage application, while balancing erase time and data retention.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Device complexity

If a single type of erase operation is used, then device complexity is reduced, but data retention and system performance deteriorate

Engineering Contradiction:

Improveerase operation typesVSAvoiddata retention

Core Design Contradiction:

Device complexityVSReliability

Solution Approach 1:

The patent implements dynamic erase operation selection where the memory subsystem automatically chooses between uniform erase operations and alternating erase operations based on real-time workload analysis and erase policy evaluation. This dynamic adaptation allows the system to optimize data retention without permanently increasing operational complexity.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the erase operation parameter (uniform vs. alternating) based on workload characteristics and policy requirements. By modifying this key parameter dynamically, the system achieves better data retention for policies requiring it, while maintaining simplicity for policies where it is not needed.

Inventive Principle:

Principle #35Parameter changes

2Reliability

If alternating erase operations are used, then data retention is improved, but erase time increases

Engineering Contradiction:

Improvedata retentionVSAvoiderase time

Core Design Contradiction:

ReliabilityVSLoss of time

Solution Approach 1:

The system dynamically selects between uniform and alternating erase operations based on workload analysis. When the workload indicates low sensitivity to erase time, alternating operations are used to maximize data retention. When erase time is critical, the system switches to uniform operations, thus adapting the time-retention tradeoff to actual system needs.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The memory subsystem continuously monitors workload characteristics and evaluates erase policy requirements to provide feedback on the optimal erase operation type. This feedback mechanism enables real-time adjustment between uniform and alternating operations, optimizing the balance between data retention and erase time based on actual system conditions.

Inventive Principle:

Principle #23Feedback

3Loss of time

If uniform erase operations are used, then erase time is reduced, but data retention deteriorates

Engineering Contradiction:

Improveerase timeVSAvoiddata retention

Core Design Contradiction:

Loss of timeVSReliability

Solution Approach 1:

The system dynamically adapts the erase operation type based on workload analysis and erase policy evaluation. When the workload and policy indicate that data retention is critical, the system switches from uniform to alternating erase operations. Otherwise, it maintains uniform operations for faster erasing, thus dynamically optimizing the time-retention tradeoff.

Inventive Principle:

Principle #15Dynamics

Solution Approach 2:

The system changes the erase operation parameter (uniform vs. alternating) based on real-time conditions. By modifying this parameter according to workload characteristics and policy requirements, the system achieves fast erasing when retention is not critical, while ensuring adequate retention when needed.

Inventive Principle:

Principle #35Parameter changes

4Productivity

If erase operations are selected based on workload and policy, then system performance is optimized, but device complexity increases

Engineering Contradiction:

Improvesystem performanceVSAvoiderase operation selection logic

Core Design Contradiction:

ProductivityVSDevice complexity

Solution Approach 1:

The memory subsystem performs self-service by automatically analyzing its own workload characteristics and evaluating erase policy requirements without external intervention. This self-analysis capability enables the system to autonomously select optimal erase operations, optimizing performance while containing complexity within the subsystem itself.

Inventive Principle:

Principle #25Self-service

Solution Approach 2:

The memory subsystem integrates multiple functions into a single unified mechanism: workload analysis, erase policy evaluation, and erase operation selection. By combining these functions into one multi-functional component, the system optimizes performance without proportionally increasing complexity, as the same infrastructure serves multiple purposes.

Inventive Principle:

Principle #6Universality (Multi-functionality)

Data Source

PatentUS20250370925A1Dynamic erase operation selection using erase policy

Publication Date: 2025.12.04 MICRON TECHNOLOGY INC

AI summary

Methods, systems, and apparatuses include determining a workload for a memory device. An erase operation is selected based on the determined workload, where the erase operations include an alternating erase operation and a uniform erase operation. The erase operation is executed on a portion of memory.