Selective Sampling of Nonvolatile Memory Blocks for Error Rate Estimation
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Nonvolatile memory systems face challenges in efficiently identifying and correcting data with elevated error rates, particularly as write-erase cycle counts increase, leading to potential uncorrectable errors that can degrade data retention and storage reliability.
Innovation Solution
A method involving sampling blocks with the lowest and highest write-erase cycle counts to estimate error rates, expanding the sample population as needed, and performing data recovery operations on blocks with error rates exceeding predetermined limits, utilizing Error Correction Codes to correct and relocate data.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Measurement precision
If all blocks are sampled to estimate error rates, then measurement precision is improved, but device complexity and time consumption increase
Solution Approach 1:
The patent applies local quality by focusing sampling efforts on specific subsets of blocks rather than uniformly sampling all blocks. It identifies and samples blocks with extreme write-erase cycle counts (lowest and highest) as these are most likely to contain degraded data, thereby achieving accurate error rate estimation with reduced sampling complexity
Solution Approach 2:
The patent segments the block population into different groups based on write-erase cycle counts. It divides blocks into subsets: those with lowest cycle counts, those with highest cycle counts, and optionally intermediate groups. This segmentation allows targeted sampling of the most critical blocks for error rate estimation while avoiding unnecessary sampling of all blocks
2Reliability
If write-erase cycle count monitoring is implemented, then reliability is improved, but device complexity increases
Solution Approach 1:
The memory system performs self-diagnosis by automatically monitoring write-erase cycle counts and identifying blocks at risk of data degradation. The system uses its own operational data (cycle counts) to assess its own reliability state and trigger appropriate maintenance operations without external intervention
Solution Approach 2:
The patent implements preliminary action by proactively identifying blocks with high error rates before they become uncorrectable. By monitoring cycle counts and sampling blocks at extreme points, the system detects degraded data early and initiates recovery operations before complete failure occurs
3Reliability
If data recovery operations are performed frequently, then reliability is improved, but use of energy and time increase
Solution Approach 1:
The system performs preliminary sampling and error rate estimation on selected blocks before initiating full data recovery operations. By first identifying which blocks actually have elevated error rates through targeted sampling, the system avoids unnecessary recovery operations on healthy blocks, thereby reducing time and energy consumption while maintaining reliability
Data Source
AI summary
Data stored in a nonvolatile memory is selectively sampled based on write-erase cycle counts of blocks. Blocks with the lowest write-erase cycle counts are sampled to determine an error rate which is compared with a limit. If the error rate exceeds the limit then the sample is expanded to include blocks with the next lowest write-erase cycle counts.