Adaptive Error Correction for Memory Devices
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory systems face challenges in efficiently managing error detection and correction, particularly in identifying and handling defective memory cells, which affects yield and power consumption, and often require pessimistic ECC designs to account for worst-case scenarios.
Innovation Solution
An adaptive ECC technique that initially sets a high scrub rate and designates defective memory cells as 'burned' cells, allowing them to be used for storage while adjusting the ECC to correct more errors, thereby reducing power consumption and improving system performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional error detection and correction techniques are used to handle defective memory cells, then memory reliability is improved, but power consumption increases and yield decreases
Solution Approach 1:
The ECC system dynamically adapts its error correction capability based on the actual number of defective cells detected during manufacturing. Instead of using a fixed pessimistic design, the system adjusts the scrub rate and ECC parameters to match the actual defect count, reducing unnecessary power consumption while maintaining adequate reliability
Solution Approach 2:
The patent changes key parameters including the scrub rate (from fixed high value to adaptive value based on burned bit count), ECC code rate, and error correction depth. These parameter adjustments allow the system to optimize the balance between reliability and power consumption based on actual manufacturing yield
2Reliability
If pessimistic ECC designs are used to account for worst-case scenarios, then memory reliability is improved, but device complexity and size increase
Solution Approach 1:
The ECC design transitions from a static pessimistic configuration to a dynamic adaptive system that adjusts its complexity based on actual defect measurements. The system determines the appropriate ECC strength and scrub frequency based on the measured number of burned bits, avoiding unnecessary complexity while maintaining reliability
Solution Approach 2:
The patent performs preliminary characterization of defective cells during manufacturing before the memory is deployed. By identifying and marking burned cells early, the system can configure the ECC parameters in advance based on actual conditions rather than worst-case assumptions, simplifying the overall design
3Reliability
If high scrub rates are used to correct errors in defective memory cells, then memory reliability is improved, but power consumption increases
Solution Approach 1:
The scrub rate is changed from a fixed high value to a dynamic value that adapts based on the actual number of burned bits detected. The system performs initial characterization, counts the defective cells, and then configures an optimal scrub rate that provides adequate error correction while minimizing power consumption
Solution Approach 2:
The memory system performs self-characterization during manufacturing by detecting and counting its own defective cells. Based on this self-assessment, the system automatically configures its ECC parameters and scrub rate, eliminating the need for external pessimistic design assumptions and reducing unnecessary power consumption
Data Source
AI summary
Some embodiments include apparatuses and methods having an interface to receive information from memory cells, the memory cells configured to have a plurality of states to indicate values of information stored in the memory cells, and a control unit to monitor errors in information retrieved from the memory cells. Based on the errors in the information, the control unit generates control information to cause the memory cell to change to from a state among the plurality of states to an additional state. The additional state is different from the plurality of states.