DRAM Refresh Controller Segmentation for Data Reliability

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Current memory devices, particularly DRAM, face challenges in maintaining data reliability due to uniform refresh operations, which do not account for varying data characteristics, leading to inconsistent data retention across different storage regions.

Innovation Solution

A memory device and system that utilize a refresh controller to apply different refresh rates to distinct storage regions based on data characteristics, with a host system determining the refresh control values to prioritize high-reliability data by adjusting the refresh ratio between low- and high-reliability data storage regions.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Reliability

If uniform refresh operations are applied to all storage regions, then the refresh operation is simple to implement, but data reliability varies across different storage regions

Engineering Contradiction:
Improvedata reliabilityVSAvoidrefresh operation complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The memory device divides the storage regions into multiple segments based on data reliability requirements. The refresh controller applies different refresh rates to different segments, with high-reliability data regions receiving more frequent refresh operations than low-reliability data regions. This segmentation allows tailored refresh strategies for different data types while maintaining overall system reliability.

Inventive Principle:
Principle #1Segmentation

Solution Approach 2:

The patent implements local quality by assigning different refresh characteristics to different storage regions. High-reliability data regions are configured with higher refresh rates and priority, while low-reliability data regions use lower refresh rates. This localized differentiation ensures that critical data maintains higher reliability without uniformly increasing refresh operations across the entire memory device.

Inventive Principle:
Principle #3Local quality

2Reliability

If different refresh rates are applied to different storage regions, then data reliability is enhanced, but the refresh control complexity increases

Engineering Contradiction:
Improvedata retentionVSAvoidrefresh control structure
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The refresh controller dynamically adjusts refresh rates based on data characteristics and system conditions. It can change refresh parameters in real-time, allocating higher refresh rates to high-reliability data regions when needed and reducing refresh rates for low-reliability regions. This dynamic adaptation allows the system to optimize data retention while managing complexity through flexible, condition-based control.

Inventive Principle:
Principle #15Dynamics

Solution Approach 2:

The patent changes refresh parameters such as refresh rate, timing, and priority based on data reliability requirements. High-reliability data regions receive parameter configurations that ensure frequent refresh operations, while low-reliability regions use optimized parameters that reduce overhead. This parameter differentiation achieves enhanced data retention without requiring fundamentally complex control structures.

Inventive Principle:
Principle #35Parameter changes

3Reliability

If high-reliability data is refreshed more frequently, then data integrity is improved, but energy consumption increases

Engineering Contradiction:
Improvedata integrityVSAvoidrefresh energy consumption
Core Design Contradiction:
ReliabilityVSUse of energy by moving object

Solution Approach 1:

The memory device applies local quality by concentrating refresh energy on high-reliability data regions rather than uniformly refreshing all regions. High-reliability data receives frequent refresh operations to maintain integrity, while low-reliability data regions are refreshed less frequently. This localized energy allocation preserves data integrity for critical information while reducing overall energy consumption compared to uniform high-rate refreshing.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent applies partial action by providing excessive refresh operations only where necessary for high-reliability data, rather than applying uniform refresh rates across all regions. Low-reliability data regions receive minimal refresh operations sufficient for their requirements. This partial approach ensures data integrity for critical data while avoiding wasteful energy consumption on non-critical regions.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS11133050B2Memory device, memory system, and method for refreshing memory device
Publication Date: 2021.09.28 SK HYNIX INC
  • US11133050B2 patent drawing
  • US11133050B2 patent drawing
  • US11133050B2 patent drawing

AI summary

A memory device applies different refresh rates to target data (or objective data) according to data characteristics (i.e., required reliability levels). The memory device includes a memory cell array provided with a plurality of memory cells, a row decoder configured to selectively activate word lines of the memory cell array in response to a row address signal, and a refresh controller configured to output the row address signal in response to the row address signal. The refresh controller controls a refresh ratio of a first storage region and a second storage region contained in the memory cell array in response to a changeable refresh control value.