NAND Memory Interface Parity Feedback for On-Demand Re-Training
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Communication between non-volatile memory devices and controllers occurs at low operating frequencies, necessitating methods to align signals and compensate for delay variations due to temperature and voltage changes, which can lead to performance degradation and resource overhead.
Innovation Solution
The storage controller generates transmission parity data for each data line, enabling non-volatile memories to perform transmission error detection and determine re-training conditions, allowing real-time error detection and notification to the controller without periodic monitoring, thus optimizing re-training operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If periodic monitoring is used to detect transmission errors, then transmission errors can be detected, but communication efficiency deteriorates due to performance degradation and resource overhead
Solution Approach 1:
The non-volatile memory device autonomously performs transmission error detection on received data using parity data, and self-determines re-training execution conditions based on error detection results. This self-service mechanism eliminates the need for periodic monitoring by the controller, thereby maintaining communication efficiency while ensuring reliable error detection.
2Reliability
If re-training operations are performed frequently to maintain signal alignment, then communication reliability is improved, but resource overhead increases
Solution Approach 1:
The system implements feedback-based re-training control where the non-volatile memory device reports transmission error states and error detection results to the controller. The controller performs re-training operations only when re-training execution conditions are satisfied, optimizing the balance between signal alignment accuracy and resource consumption.
Solution Approach 2:
The non-volatile memory device performs transmission error detection and determines re-training execution conditions in advance before actual re-training is needed. This preliminary action allows the system to prepare for re-training operations only when necessary, reducing unnecessary resource overhead while maintaining communication reliability.
3Reliability
If transmission error detection is performed continuously, then transmission errors are detected in real-time, but device complexity increases
Solution Approach 1:
The transmission error detection function is extracted from the controller and implemented within the non-volatile memory device itself. This extraction simplifies the controller's complexity while enabling real-time error detection at the memory device level, where the detection logic operates independently on received data using parity information.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
An operation method of a storage device that includes a storage controller and a non-volatile memory device comprises generating a plurality of pieces of transmission parity data respectively corresponding to a plurality of data lines, transmitting, a write command, data, and the plurality of pieces of transmission parity data to a first non-volatile memory through the plurality of data lines, performing a transmission error detection operation with respect to each of the plurality of data lines, based on each of the plurality of pieces of transmission parity data, determining that re-training execution conditions are satisfied, based on an error detection result generated in the transmission error detection operation, and, in response to a state read command, when the re-training execution conditions are satisfied, transmitting state information indicating a transmission error state to the storage controller.