Storage Controller Reset Logic for Latch Soft Error Recovery
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory devices face reliability issues due to soft errors in latch circuits causing incorrect setting data, leading to reduced performance in read and write operations.
Innovation Solution
A storage controller with an error manager and setting data table detects and corrects soft errors in latch units by comparing fetched setting data with reference data, initiating a reset operation when mismatches are found, thereby maintaining operation reliability without powering off the device.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If the latch circuit stores setting data for memory cell operations, then the memory device can operate with configured DC levels and verification voltages, but soft errors in the latch circuit can cause incorrect setting data to be stored, reducing read and write operation reliability
Solution Approach 1:
The patent applies preliminary action by storing reference setting data in advance in a specific memory block during the design process. This pre-stored reference data is then used for comparison with setting data read from the latch circuit during operation, enabling detection of soft errors before they cause operational failures. The error detection and correction mechanism is prepared beforehand rather than reacting after errors occur.
Solution Approach 2:
The patent implements feedback by continuously comparing setting data read from the latch circuit with reference setting data stored in the memory block. When a mismatch is detected indicating a soft error, the system provides feedback by resetting the latch circuit to restore correct setting data. This closed-loop feedback mechanism ensures ongoing reliability by detecting and correcting errors in real-time during device operation.
2Reliability
If the device is restarted to correct soft errors in the latch unit, then setting data can be reset to reference values, but device restart causes loss of time and operational interruption
Solution Approach 1:
The patent applies self-service by enabling the storage device to automatically detect and correct soft errors in the latch unit without requiring external intervention or device restart. The controller reads setting data, compares it with reference data, and resets the latch unit when errors are detected, all while the device remains operational. This self-correcting mechanism eliminates the need for manual intervention or system shutdown.
Solution Approach 2:
The patent uses preliminary action by having reference setting data pre-stored in a memory block during device design. This pre-prepared reference data enables the controller to immediately compare and identify soft errors without needing to restart the device or externally provision correction data. The correction mechanism is ready to operate continuously, preventing time loss associated with device restarts.
3Reliability
If error detection and correction mechanisms are implemented in the storage controller, then soft errors can be detected and corrected, but the device complexity increases
Solution Approach 1:
The patent applies universality by utilizing existing storage memory blocks and controller resources to store and process reference setting data, rather than requiring dedicated error correction hardware. The same memory blocks used for data storage are leveraged to hold reference setting data, and the controller's existing data processing capabilities are used for comparison and error detection. This multi-functional use of existing components adds error correction capability without proportionally increasing device complexity.
Solution Approach 2:
The patent uses copying by creating a copy of the reference setting data and storing it in a specific memory block during the design process. This copied reference data serves as a template for continuous comparison with setting data from the latch circuit. Rather than implementing complex real-time generation of reference data, the system simply copies and stores the reference values, enabling efficient error detection through straightforward data comparison without excessive complexity.
Data Source
Figure 1
Figure 2
Figure 3
AI summary
Disclosed are an operating method of a storage controller which is configured to communicate with a host and with a non-volatile memory device and a storage controller. The method may include: generating an error count by counting a number of first-type error bits of a target super block of the non-volatile memory device, determining whether the error count exceeds a first reference value, fetching setting data from a latch unit of the non-volatile memory device, based on determining that the error count exceeds the first reference value, determining whether reference setting data of a setting table matches the fetched setting data, the reference setting data indicating information about a designed operating environment of the non-volatile memory device, and providing a reset request to the latch unit, based on determining that the reference setting data does not match the fetched setting data.