Sequential Read Tracking in Non-Volatile Memory for Adaptive Thresholds
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face challenges in maintaining optimal read thresholds due to physical phenomena like Data Retention and Read Disturb, leading to increased Bit Error Rate and decoding failures, which degrade system performance.
Innovation Solution
Implementing a sequential read tracking method that uses read and decoding results to estimate optimal read thresholds based on current block conditions, utilizing read histograms and directional error information to adjust read thresholds without additional read commands, thereby reducing decoding errors and improving system performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If fixed read thresholds are used for sequential read operations, then device complexity is reduced and ease of operation is improved, but decoding failures increase and reliability deteriorates due to Data Retention and Read Disturb effects
Solution Approach 1:
The patent applies preliminary action by performing a read histogram analysis on a portion of the page before completing the full sequential read operation. This preliminary analysis allows the system to predict and adjust read thresholds in advance, preventing decoding failures that would otherwise occur due to Data Retention and Read Disturb effects. The read histogram is computed on sampled data, and threshold adjustments are made proactively before the entire block is read, ensuring high reliability without requiring complex real-time threshold management throughout the operation.
2Reliability
If read thresholds are adjusted frequently to maintain optimal performance, then reliability improves, but productivity decreases due to additional read commands and processing overhead
Solution Approach 1:
The patent applies partial action by performing read histogram analysis and threshold adjustment on only a portion of the page (e.g., a subset of codewords or a sampled region) rather than analyzing the entire block. This partial analysis provides sufficient information to predict threshold drift and adjust read thresholds appropriately, while avoiding the productivity penalty of processing the full dataset. The system achieves reliable threshold adaptation with reduced processing overhead by applying the principle of partial action.
3Manufacturing precision
If read thresholds are adjusted based on comprehensive error analysis, then manufacturing precision of read operations improves, but loss of time increases due to additional processing during sequential read
Solution Approach 1:
The patent performs read histogram computation and error analysis on a portion of the page in advance, before the full sequential read operation completes. This preliminary action allows the system to determine accurate read thresholds proactively, so that when the actual read operation proceeds, the thresholds are already optimized. The time-consuming analysis is performed on sampled data rather than the full dataset, and the results are applied to the entire block, achieving high manufacturing precision with minimal time loss during the critical read path.
Data Source
AI summary
The arrangements disclosed herein relate to systems, methods, non-transitory computer-readable media, and apparatuses including a non-volatile memory and a controller operatively coupled to the non-volatile memory. The controller is to determine information on a number of errors for at least a portion of a page for performing a sequential read operation of a plurality of pages of a block of a plurality of blocks of the non-volatile memory, where the data is read using a first read threshold. The controller is to determine a second read threshold based at least in part on read histogram for the sequential read operation and the information on the number of the errors for at least the portion of the page and the first read threshold.