Memory Control With Local RAID Encoding for Weak Strings
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing RAID configurations face challenges in correcting uncorrectable errors in multiple physical programming cells, particularly in weak strings, leading to difficulties in data recovery and affecting memory device operation.
Innovation Solution
A memory control method that divides storage groups into first and second storage groups, performs different encoding processes based on group quality, using SLC programming mode for weak strings and MLC/TLC modes for normal strings, and stores parity data with enhanced reliability to correct errors.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional RAID encoding is used for all storage groups, then device complexity is reduced and operation is simplified, but error correction capability deteriorates for weak strings with uncorrectable errors
Solution Approach 1:
The patent applies different encoding strategies to different storage groups based on their quality characteristics. Weak strings (first storage groups) receive enhanced encoding with additional parity bits and multiple programming modes, while normal strings (second storage groups) use standard RAID encoding. This local differentiation resolves the contradiction by improving error correction for problematic areas without unnecessarily complicating the entire system.
Solution Approach 2:
The patent segments storage groups into first storage groups (weak strings) and second storage groups (normal strings) based on error correction capability assessment. This segmentation allows the system to apply targeted encoding strategies - complex enhanced encoding for weak strings and simple standard encoding for normal strings - thereby improving overall reliability without uniformly increasing device complexity.
2Reliability
If enhanced encoding is applied to all storage groups, then error correction capability is improved, but programming time and operation efficiency deteriorate
Solution Approach 1:
The patent divides storage groups into first storage groups requiring enhanced encoding and second storage groups using standard encoding. By segmenting based on actual string quality rather than applying enhanced encoding universally, the system achieves high data protection for weak strings while maintaining fast programming speeds for normal strings, thus resolving the contradiction between reliability and productivity.
Solution Approach 2:
The patent applies enhanced encoding procedures locally only to weak strings identified as first storage groups, while normal strings (second storage groups) use efficient standard encoding. This localized approach ensures high data protection where needed without sacrificing overall programming throughput, resolving the contradiction between data protection capability and programming speed.
3Reliability
If multiple programming modes are used for different storage groups, then error correction for weak strings is improved, but device complexity and control overhead increase
Solution Approach 1:
The patent segments storage groups into first and second groups based on error characteristics, enabling the use of different programming modes (first and second programming modes) for each segment. The memory controller includes logic to identify which segment a physical programming cell belongs to and apply the appropriate mode, resolving the contradiction by managing complexity through structured segmentation rather than ad-hoc control.
Solution Approach 2:
The patent performs preliminary classification of storage groups into first and second groups before data programming, based on error correction capability assessment. This preliminary action allows the memory controller to pre-determine which programming mode to use for each storage group, simplifying the control logic during actual programming operations and reducing real-time decision complexity while maintaining high error correction capability.
Data Source
AI summary
A memory control method and a memory storage device, and the method includes: dividing each of the storage groups into a first or second storage group; receiving a first write command from a host system, in which the first write command includes first data and a first address; performing a first encoding process on the first data to obtain first parity data; storing the first data and the first parity data in a first physical programming cell indicated by the first address; determining whether a current storage group to which the first physical programming cell belongs is the first or second storage group; and in response to the current storage group being the first storage group, performing a second encoding process on the first physical programming cell to obtain second parity data of the first physical programming cell, and storing the second parity data of the first physical programming cell.