Storage Controller Read Training Using User Data Alignment
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face issues with distorted electrical signals during operation, leading to impaired data transmission and reception, which affects the normal functioning of flash memory devices in computing systems.
Innovation Solution
A storage controller with training circuitry performs a read training operation based on user data to compensate for signal distortions, using a pattern generator, pattern buffer, and comparator to ensure data alignment and reliability.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If read training operation is performed using separately generated training data, then signal alignment can be achieved, but additional time is required for separate data-in operation
Solution Approach 1:
The patent combines the training data-in operation with the normal data-in operation by using user data itself as training data. The storage controller performs read training using user data that is already being transferred, merging two separate operations into one, thereby eliminating the need for separate training data transmission while achieving signal alignment.
Solution Approach 2:
The patent makes user data serve dual purposes: both as actual data to be stored and as training data for read training operations. This multi-functionality allows the same data transmission to accomplish both data storage and signal calibration, reducing overall operation time while maintaining training effectiveness.
2Speed
If electrical signals are transmitted without compensation, then data transmission speed is maintained, but signal distortion occurs affecting data integrity
Solution Approach 1:
The patent implements a feedback mechanism where the storage controller compares the received user data with the originally transmitted user data to detect signal distortion. Based on this comparison feedback, the controller adjusts timing parameters to compensate for distortion, thereby maintaining both transmission speed and data integrity through continuous optimization.
Solution Approach 2:
The patent performs read training operations during runtime using user data before actual data storage operations. By conducting training in advance using available user data, the system prepares optimal timing parameters that will be applied during subsequent data operations, ensuring both speed and reliability without adding delays to critical path operations.
Data Source
AI summary
A storage device includes a storage controller that includes training circuitry and that transmits a data signal including a command and user data, and a non-volatile memory device that receives the data signal from the storage controller. The training circuitry performs a read training operation based on at least a part of the user data.