Memory Controller Read Voltage Optimization via Threshold Tracking
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in accurately reading data from memory cells due to shifts in threshold distributions caused by interference effects, leading to increased error bits and reduced data reliability.
Innovation Solution
The memory system employs a controller that issues instructions to determine threshold distributions and read data using adjusted read voltages based on shift tables and history tables, optimizing read operations by grouping word lines and updating indices accordingly.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If read operations are performed on memory cells, then data can be read from the memory system, but threshold distribution shifts occur due to interference effects causing increased error bits
Solution Approach 1:
The system performs a tracking operation before the actual read operation to determine the current threshold distribution characteristics. By conducting this preliminary characterization and storing it in a history table, the system prepares advance information about threshold shifts, enabling the controller to select appropriate read voltages that compensate for interference effects before data reading begins.
Solution Approach 2:
The system implements a feedback mechanism where the results of tracking operations are stored in a history table and used to determine read voltages for subsequent operations. The controller references historical threshold distribution data to adjust read voltage selections, creating a closed-loop system that continuously adapts to threshold shifts and interference effects.
2Reliability
If multiple read operations are performed to handle threshold shifts, then data reliability can be maintained, but the number of operations increases reducing productivity
Solution Approach 1:
By performing a tracking operation beforehand to characterize threshold distributions and storing results in a history table, the system eliminates the need for multiple retry read operations. The preliminary characterization allows the controller to select optimal read voltages in advance, reducing operational overhead while maintaining reliability.
Solution Approach 2:
The feedback mechanism through the history table enables the controller to learn from previous tracking operations and make informed voltage selections without requiring multiple read attempts. This feedback loop optimizes the read operation parameters once, eliminating repetitive operations and improving productivity.
3Reliability
If tracking operations are performed to determine threshold distributions, then read voltage optimization is achieved, but operation time increases
Solution Approach 1:
The tracking operation is performed as a preliminary action that characterizes threshold distributions once and stores the results. By conducting this characterization advance and caching the results in the history table, the system avoids repeated time-consuming tracking operations during subsequent read operations, thereby minimizing time loss while maintaining reliability.
Solution Approach 2:
The feedback mechanism stores tracking operation results in the history table for future reference. This allows the controller to retrieve pre-determined threshold distribution information without repeating the time-consuming tracking process, reducing operational time while preserving the reliability benefits of optimized read voltages.
Data Source
AI summary
According to one embodiment, a memory system includes a semiconductor memory and a controller. The semiconductor memory includes first to fourth word lines and first to fourth memory cells. The controller is configured to issue first and second instructions. The controller is further configured to execute a first operation to obtain a first read voltage based on a threshold distribution of the first memory cell, and a second operation to read data from the second memory cell.