Memory Chip ECS Feedback Loop for DRAM Error Control

Resolve Bottlenecks,
Find Innovative Solutions
Generate Solutions

Solution Overview

Problem

Existing storage systems, particularly dynamic random access memory (DRAM), face challenges in efficiently performing error check and scrub (ECS) operations, as current methods lack flexibility and real-time control based on actual ECS check results.

Innovation Solution

A storage system comprising a memory chip and a memory controller, where the memory chip performs ECS operations on its memory array, generates an ECS finish flag signal, and sends it to the memory controller. The memory controller then generates an ECS start flag signal to initiate a new ECS cycle, allowing for adjustable timing and processing based on check result information.

Engineering Contradictions & Design Principles

VSEngineering Contradiction Analysis

1Adaptability or versatility

If traditional ECS operations are performed in DRAM, then data integrity is maintained, but the system lacks flexibility and real-time control based on actual ECS check results

Engineering Contradiction:
Improveflexibility of ECS operationsVSAvoiddata integrity
Core Design Contradiction:
Adaptability or versatilityVSReliability

Solution Approach 1:

The patent implements a feedback mechanism where the memory chip sends ECS finish flag signals and check result information to the memory controller, which then adjusts subsequent ECS operations based on the actual check results. This closed-loop feedback system enables real-time control and flexibility in ECS operations while maintaining data integrity through adaptive error correction strategies.

Inventive Principle:
Principle #23Feedback

Solution Approach 2:

The patent introduces dynamic control of ECS operations by allowing the memory controller to adjust ECS timing and frequency based on actual error check results. The system transitions from static, fixed-interval ECS operations to dynamic, adaptive ECS scheduling, improving versatility while maintaining reliability through result-based adjustment.

Inventive Principle:
Principle #15Dynamics

2Reliability

If ECS operations are performed frequently to ensure data integrity, then error detection capability is improved, but system complexity and control difficulty increase

Engineering Contradiction:
Improveerror detection capabilityVSAvoidcontrol process complexity
Core Design Contradiction:
ReliabilityVSDevice complexity

Solution Approach 1:

The memory chip autonomously performs ECS operations and generates check result information, reducing the control burden on the memory controller. The self-service mechanism handles error detection and reporting internally, simplifying the overall control process while maintaining strong error detection capability.

Inventive Principle:
Principle #25Self-service

Solution Approach 2:

The patent segments the ECS control function into distinct components: the memory chip handles execution and result generation, while the memory controller handles scheduling and adjustment. This functional segmentation reduces control complexity by distributing responsibilities across system components.

Inventive Principle:
Principle #1Segmentation

3Reliability

If ECS operations are performed on all memory addresses, then comprehensive error coverage is achieved, but operation time and productivity are reduced

Engineering Contradiction:
Improveerror coverageVSAvoidECS operation speed
Core Design Contradiction:
ReliabilityVSProductivity

Solution Approach 1:

The patent implements targeted ECS operations by identifying and focusing error checking on specific memory regions or addresses that exhibit error patterns. Instead of uniformly checking all memory addresses, the system applies local quality control by concentrating ECS resources on problematic areas, achieving comprehensive error coverage where needed while improving overall operation speed.

Inventive Principle:
Principle #3Local quality

Solution Approach 2:

The patent employs partial ECS action by performing error checks on selected memory addresses rather than all addresses in every ECS cycle. This partial action approach maintains adequate error coverage for critical regions while reducing the total operation time and improving productivity.

Inventive Principle:
Principle #16Partial or excessive action

Data Source

PatentUS20250068508A1Storage system, memory chip, and error check and scrub method
Publication Date: 2025.02.27 RUILI INTEGRATED CIRCUIT CO LTD
  • US20250068508A1 patent drawing
  • US20250068508A1 patent drawing
  • US20250068508A1 patent drawing

AI summary

Provided are a storage system, a memory chip, and an error check and scrub method. The storage system includes a memory controller and a memory chip. The memory chip performs an error check and scrub ECS operation on a memory array; and sends a generated ECS finish flag signal to the memory controller after a current ECS operation is completed. The memory controller receives the ECS finish flag signal, and sends a generated ECS start flag signal to the memory chip based on the ECS finish flag signal, so that the memory chip enters a new ECS operation cycle.