Bit Swap Encoding for Flash Memory Programming Optimization
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
The high programming costs associated with MultiLevel Cell (MLC) technology in flash memories, which store multiple bits per memory cell, necessitate a solution to manage these costs effectively.
Innovation Solution
Implementing a bit swap encoding method that identifies dominant bit pair combinations in memory regions and swaps them with the 'do-nothing' erased level, optimizing programming times and reducing system power consumption by minimizing the number of cells that need to be programmed.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If MLC technology is used to store multiple bits per memory cell, then storage density is improved, but programming cost and complexity increase
Solution Approach 1:
The patent applies parameter changes by transforming the bit representation from standard binary (0-3 for 2 bits per cell) to a modified encoding scheme where the most significant bit is inverted and mapped to a special erased state. This changes the parameter space from {0,1,2,3} to {E,0,1,2} where E represents the erased state, enabling the memory controller to distinguish between programmed and unprogrammed cells more efficiently, thereby reducing programming complexity while maintaining high storage density
2Productivity
If bit swap encoding is applied to optimize programming, then programming efficiency is improved, but encoding complexity increases
Solution Approach 1:
The patent implements preliminary action by having the memory controller pre-calculate and prepare the bit swap encoding mappings before actual programming operations occur. The controller maintains lookup tables that define the correspondence between original bit values and their swapped equivalents based on the dominant bit pattern analysis performed in advance. This preliminary preparation eliminates the need for complex real-time encoding calculations during programming, thereby improving productivity while keeping the actual encoding implementation simple
Solution Approach 2:
The patent employs feedback mechanisms where the memory controller continuously monitors the programming results and uses this information to determine the dominant bit pattern in each memory region. Based on this feedback, the controller dynamically adjusts the bit swap encoding strategy for different regions, optimizing programming efficiency for each specific case while maintaining a relatively simple overall encoding implementation through adaptive rather than predetermined complex rules
Data Source
AI summary
A wireless device incorporates a nonvolatile memory that dynamically controls a swapping or mapping of bit pairs for a selected memory region to optimize programming times.