Flash Memory Data Storage Using Multi-Phase Decoding
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Flash memory devices face challenges in maintaining uniform reliability across pages, leading to unequal error rates and inefficient data storage due to varying transition probabilities between states, which affects access performance and data integrity.
Innovation Solution
Implementing a multi-phase decoding concatenated code construction that splits encoded data into sub-codes and joint parity, allowing for efficient access and error correction by distributing data and redundancy across multiple pages based on page reliability, and using different error correction coding schemes for Single-Level Cell (SLC) and Multi-Level Cell (MLC) partitions.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If multiple bits are stored in each flash memory cell to increase storage density, then storage capacity is improved, but reliability of individual bits deteriorates due to unequal error rates across pages
Solution Approach 1:
The patent segments the flash memory into multiple pages with different reliability characteristics (first page with higher reliability, second page with lower reliability). By dividing the storage into distinct segments with different error rates, the system can apply different error correction strategies to each segment, thereby maintaining high storage density while managing reliability through targeted protection mechanisms.
2Quantity of substance
If data is stored in pages with lower reliability, then storage capacity is utilized more fully, but error rates increase requiring additional redundant information
Solution Approach 1:
The patent applies local quality by providing enhanced error correction protection specifically for data stored in the second page (lower reliability region). The system uses a concatenated code construction where the first code protects against typical errors and the second code provides additional protection for the more vulnerable second page. This localized enhancement of protection quality allows full utilization of storage capacity while compensating for the higher error rates in specific regions.
3Reliability
If additional redundant information is added to protect data in low-reliability pages, then reliability is improved, but codeword length exceeds single page capacity
Solution Approach 1:
The patent resolves the codeword length issue by transitioning from a single-page storage model to a multi-page distributed storage model. The concatenated codeword is split across multiple pages (first page and second page), with different portions stored in different reliability zones. This dimensional change from one-page to multi-page storage allows the system to accommodate longer protected codewords while utilizing the full storage capacity of the flash memory device.
4Quantity of substance
If encoded data is split across multiple physical pages, then storage efficiency is optimized, but access complexity increases due to multi-phase decoding
Solution Approach 1:
The patent segments the decoding process into multiple phases corresponding to the segmented storage structure. The first decoding phase processes data from the first page using the first error correction code, while the second decoding phase processes data from the second page using the second error correction code. This segmented approach to decoding, while necessarily more complex than single-page decoding, is made manageable through systematic organization and allows the system to achieve high storage efficiency by fully utilizing available memory capacity.
Data Source
AI summary
A method includes, when using a binary cache in an multi-level cell (MLC) flash memory splitting a codeword corresponding to a data page into multiple data pages and storing the multiple data pages into multiple single level cell (SLC) pages of the binary cache for subsequent storage into a single wordline of the MLC flash memory.