Flash Memory Soft-Read Hamming Weights for Faster ECC
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing error correction techniques in flash memory devices face limitations in accurately reading data due to factors like ambient temperature and wear, leading to errors that are difficult to correct efficiently, especially when hardware restrictions limit the application of redundancy protocols.
Innovation Solution
The system generates Hamming weights from multiple soft reads of data bits, reducing the number of bits required for error correction and improving decoding efficiency by using a controller to perform logical operations on the bit sets, thereby reducing memory accesses and computation time.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If multiple soft reads are performed to improve error correction accuracy, then data reading reliability is improved, but memory access time and computation time increase
Solution Approach 1:
The patent extracts only the essential reliability information from multiple soft reads by generating Hamming weights that capture error probability without retaining all redundant soft read data. This extraction process reduces memory access requirements while preserving the critical information needed for error correction decisions.
Solution Approach 2:
Instead of using all soft read bits directly for error correction, the patent inverts the approach by deriving compressed Hamming weight representations that indicate error likelihood. This inversion transforms the problem from processing large volumes of soft data to processing compact weight indicators, significantly reducing computation time.
2Reliability
If redundancy protocols are applied to improve error correction capability, then error correction accuracy is improved, but device complexity increases due to hardware restrictions
Solution Approach 1:
The patent changes the parameter representation from full soft read bit sets to compressed Hamming weight values. This parameter transformation maintains error correction accuracy by preserving error probability information while reducing the data structure complexity and hardware requirements for implementation.
Solution Approach 2:
The patent introduces Hamming weights as an intermediary representation between soft reads and error correction decisions. This intermediary layer simplifies the interface between storage hardware and error correction logic, reducing device complexity while maintaining correction accuracy through the mediating weight calculations.
3Reliability
If full bit sets from soft reads are used for error correction, then correction accuracy is maintained, but memory occupancy increases
Solution Approach 1:
The patent extracts only the essential error probability information from complete bit sets by computing Hamming weights. This extraction reduces memory occupancy from storing all soft read bits to storing only the compressed weight representations, while preserving sufficient information for accurate error correction.
Solution Approach 2:
Instead of storing and processing complete bit sets, the patent inverts the approach by computing compact Hamming weight summaries that capture the essential correction information. This inversion dramatically reduces memory occupancy while maintaining correction accuracy through the condensed weight data.
Data Source
AI summary
Embodiments herein provide for a controller that is operable to soft read a data bit a plurality of times, to generate a bit set for the data bit from the soft reads, to logically operate on the bit set, and to generate a Hamming weight for the data bit based on the logical operation. The Hamming weight has fewer bits than the bit set and is operable to correct the data bit.