Dynamic Read Voltage Adjustment for Memory Sub-Systems
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Conventional memory sub-systems face reliability issues due to threshold voltage drift over time, leading to increased bit error rates and reduced performance, particularly influenced by operating characteristics such as die temperature, write-to-write and write-to-read delay times, and cycling conditions, which existing scrub operations attempt to mitigate but degrade system quality and cause unnecessary read disturb errors.
Innovation Solution
A memory sub-system that identifies and applies an optimized read voltage level based on current operating characteristics, such as write-to-write and write-to-read delay times, die temperature, and cycling conditions, to minimize bit error rates and counteract threshold voltage drift, thereby reducing read-retry triggers and improving data integrity without degrading system performance.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If conventional scrub operations are performed to mitigate threshold voltage drift, then reliability is improved, but system quality degrades and read disturb errors increase
Solution Approach 1:
The patent dynamically adjusts the read voltage level based on operating characteristics (temperature, delay times, cycling conditions) to compensate for threshold voltage drift. This parameter change approach replaces the conventional scrub operation methodology, achieving drift mitigation without causing read disturb errors.
Solution Approach 2:
The system transitions from static scrub operations to dynamic read voltage adjustment that adapts in real-time to changing operating conditions. The read voltage level is continuously optimized based on current temperature, delay times, and cycling conditions, eliminating the need for periodic scrub operations that cause harm.
2Reliability
If read voltage level is adjusted to counteract threshold voltage drift, then bit error rate decreases, but system complexity increases
Solution Approach 1:
The system implements feedback by monitoring operating characteristics (temperature, delay times, cycling conditions) and using this information to dynamically adjust the read voltage level. This closed-loop approach automatically compensates for threshold voltage drift without requiring complex external intervention or sophisticated control mechanisms.
Solution Approach 2:
The memory sub-system performs self-adjustment of read voltage levels based on its own operating characteristics. The system monitors its own state (temperature, cycling conditions, delay times) and autonomously optimizes read voltage to maintain data integrity, eliminating the need for external scrub operations or complex error correction mechanisms.
3Reliability
If dynamic read voltage adjustment is implemented, then data integrity improves, but manufacturing complexity increases
Solution Approach 1:
The patent pre-establishes the relationship between operating characteristics and optimal read voltage levels through characterization data collected during manufacturing or initial operation. This preliminary action allows the system to implement dynamic adjustment using simple lookup tables or predefined models, avoiding the need for complex real-time calculations or sophisticated manufacturing processes.
Data Source
AI summary
A data structure including a target read voltage level corresponding to each set of values of a plurality of sets of values corresponding to a plurality of operating characteristics is stored. In response to a read command associated with a memory cell, a current set of measured values of the plurality of operating characteristics associated with the memory cell is measured. A match between a first set of values of the plurality of sets of values corresponding to the plurality of operating characteristics and the current set of measured values is identified. Using the data structure, a first stored target read voltage level corresponding to the match between the first set of values and the current set of measured values is identified. The read command is executed using the first stored target read voltage level.