Memory Controller Cell State Randomization for Uniform Distribution
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Existing memory systems face challenges in uniformly distributing cell states across multi-level cells, which can lead to inefficiencies and reduced reliability in data storage and retrieval.
Innovation Solution
A memory controller is designed with a cell state generator, pseudo-random number generator, and operator that uses a hash function to change cell states, ensuring uniform distribution of cell states across multi-level cells in non-volatile memory devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If data is programmed directly into multi-level cells without randomization, then the programming process is simple and fast, but the cell states become non-uniformly distributed leading to reduced reliability
Solution Approach 1:
A pseudo-random number generator is introduced as an intermediary component between the data input and the multi-level cells. This generator produces pseudo-random numbers that are combined with the input data through a hash function to randomize the cell states, ensuring uniform distribution while maintaining a relatively simple overall system architecture.
Solution Approach 2:
The system changes the parameter of cell state distribution from non-uniform to uniform by applying a randomization process. A hash function is used to transform the input data into randomized cell states, where the output distribution parameters are controlled to achieve uniformity across all cell states, thereby improving reliability.
2Reliability
If pseudo-random number generation and hash function operations are added to randomize cell states, then uniform distribution of cell states is achieved improving reliability, but the processing time and computational complexity increase
Solution Approach 1:
The patent uses a pseudo-random number generator that produces short sequences of pseudo-random numbers for each data programming operation. These pseudo-random numbers are used once to randomize the cell states and are then discarded, allowing the system to achieve uniform distribution without maintaining complex long-term randomization state, thus reducing processing overhead.
Data Source
AI summary
A memory controller may include a cell state generator that is configured to generate a cell state for each of a plurality of multi-level cells included in a non-volatile memory device, using data of pages. The memory controller may also include a pseudo-random number generator that is configured to generate a pseudo-random number. The memory controller may further include an operator that is configured to change the cell state of each multi-level cell using the pseudo-random number, and that is configured to output a changed cell state for each multi-level cell.