Non-Volatile Memory Read Threshold Tracking for Lower BER
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face performance degradation due to stress conditions like Data Retention (DR) and Read Disturb (RD), leading to increased Bit Error Rate (BER) and decoding failures, which conventional methods struggle to address effectively.
Innovation Solution
Implementing a fast read threshold tracking system that utilizes Failed Bit Count (FBC) information to identify stress conditions and adjust read thresholds dynamically, reducing BER through hardware and firmware enhancements.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional read thresholds are used in non-volatile memory, then device complexity is low, but reliability deteriorates due to increased bit error rate under stress conditions
Solution Approach 1:
The patent implements dynamic read threshold adjustment by continuously monitoring failed bit counts and updating thresholds based on observed error patterns. The system transitions from static manufacturing thresholds to adaptive thresholds that evolve with data retention conditions, directly addressing the reliability degradation under stress.
Solution Approach 2:
The system establishes a feedback loop where read operations monitor the number of failed bits, and this information feeds back into threshold adjustment decisions. The controller uses this feedback to determine when to apply different read thresholds, creating a closed-loop system that automatically adapts to changing memory conditions.
2Reliability
If read thresholds are adjusted dynamically to reduce bit error rate, then reliability improves, but device complexity increases
Solution Approach 1:
The system performs self-diagnosis and self-adjustment by monitoring its own error rates and automatically modifying read thresholds without external intervention. The controller independently evaluates failed bit counts and determines appropriate threshold adjustments, enabling the memory system to service itself in maintaining optimal read performance.
3Productivity
If fast read threshold tracking is implemented, then productivity improves through reduced decoding failures, but measurement precision requirements increase
Solution Approach 1:
The system applies partial action by adjusting read thresholds based on aggregated error patterns rather than requiring perfect measurement precision. It uses failed bit count information to make probabilistic threshold adjustments, accepting that not all errors need to be precisely characterized to achieve meaningful productivity improvement.
Data Source
AI summary
The present disclosure relates to systems, apparatuses, methods, and non-transitory computer-readable media 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 a page for reading data stored in the page of the non-volatile memory, and the data is read using a first read threshold. The controller is to determine a second read threshold based at least in part on the first read threshold and the number of page errors for the page and apply the second read threshold for subsequently reading data stored on the page according to a decision rule.