Memory Error Correction Using Content Addressable Memory Redundancy
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Current memory systems face challenges in handling recurring single bit errors, which can lead to uncorrectable double bit errors, especially in high temperature environments, causing disruptive system operations and increased costs due to the need for complex and costly error correction codes.
Innovation Solution
Implementing a content addressable memory (CAM) as a redundant system to replace defective memory locations, where a memory location is marked as defective after two failures, allowing the CAM to store corrected data and handle future accesses, thereby reducing the likelihood of double bit errors and minimizing disruptive system operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If ECC is used to correct single bit errors, then reliability is improved, but device complexity increases when two bit errors need correction
Solution Approach 1:
The patent segments the error correction approach into two levels: standard ECC for single bit errors and a redundant memory location system for recurring errors. This segmentation allows the system to use simple ECC most of the time while having a specialized fallback mechanism only when needed, avoiding the complexity of a fully robust ECC system.
Solution Approach 2:
The patent implements preliminary action by monitoring error occurrences and proactively replacing defective memory locations with redundant locations before they cause uncorrectable double bit errors. The system tracks which locations have recurring errors and pre-empts potential failures by switching to backup locations.
2Reliability
If data is rewritten and tested whenever an error is detected, then some bit errors are corrected, but system operation becomes disruptive and delayed failures are not caught in time
Solution Approach 1:
The system performs preliminary monitoring of error patterns and proactively replaces defective locations before they cause uncorrectable errors. By tracking which memory locations have recurring errors, the system can preemptively switch to redundant locations without waiting for error occurrence, thus avoiding disruption.
Solution Approach 2:
The memory system performs self-diagnosis and self-repair by automatically detecting error patterns, identifying defective locations, and replacing them with redundant locations without external intervention. This self-service capability eliminates the need for disruptive manual error correction operations.
3Reliability
If a memory location is replaced after two failures, then uncorrectable errors are reduced, but the system requires tracking and management of defective locations
Solution Approach 1:
The patent uses a content addressable memory (CAM) structure that serves multiple functions: it stores mapping information for redundant locations, tracks error patterns, and manages the replacement logic. This multi-functional approach consolidates what would otherwise require separate tracking mechanisms into a single integrated structure.
Solution Approach 2:
The system creates copies of defective memory locations in redundant locations and uses a CAM table to map the original defective addresses to their backup addresses. This copying approach allows the system to maintain functional redundancy without physically replacing the defective hardware, simplifying the tracking and management process.
Data Source
AI summary
A method is provided for error correction of a memory. The method includes: providing a first memory and a second memory; initiating a read operation of the first memory to retrieve data; performing an error correction code (ECC) processing on the data, wherein the ECC processing for determining that at least a portion of the data is erroneous and for providing corrected data; and determining if an address of the erroneous data is stored in the second memory, if the address of the erroneous data is stored in the second memory, storing the corrected data in the second memory, and if the address of the erroneous data is not stored in the second memory, storing the address in the second memory.