Flash Memory Data Pseudo-Randomization for Coupling Control
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High-density flash memory arrays face issues with data patterns causing read and program disturbs, leading to reduced memory endurance and reliability due to cell coupling effects, such as floating gate to floating gate coupling and NAND string resistance.
Innovation Solution
Data is randomized within and across memory pages to avoid persistent patterns, using pseudo-randomization techniques such as independent starting addresses for each page and pseudo-random bit sequences to ensure an equal mix of erased and programmed states, reducing cell coupling effects.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Productivity
If data is stored repeatedly in the same blocks of flash memory, then storage capacity utilization is improved, but cell coupling effects and program disturb increase
Solution Approach 1:
The patent segments the data storage by dividing data into multiple pages and distributing them across different memory blocks. The pseudo-randomization further segments the data patterns within each page by applying bit-level transformations. This segmentation prevents concentration of identical data patterns in single blocks, reducing cell coupling effects while maintaining high storage utilization.
Solution Approach 2:
The patent applies preliminary pseudo-randomization transformation to data before it is stored in flash memory. This preliminary action modifies the data pattern in advance to avoid persistent identical patterns that would cause program disturb and cell coupling. The transformation is reversible, allowing original data recovery during read operations.
2Quantity of substance
If high-density memory arrays are used to increase capacity, then storage density is improved, but read and program disturb due to cell coupling increase
Solution Approach 1:
The patent applies local quality by making the data pattern different in each local region (memory block) through pseudo-randomization. Each block receives transformed data with unique patterns, preventing the uniform data distribution that causes cell coupling in high-density arrays. This local variation in data quality reduces interference between adjacent cells while maintaining high overall density.
Solution Approach 2:
The patent changes the parameter of data pattern distribution by applying pseudo-random transformation algorithms that alter the bit sequences stored in each block. This parameter change ensures that even in high-density arrays where physical proximity causes coupling, the logical data patterns remain sufficiently different to minimize interference effects.
3Productivity
If persistent data patterns are stored in flash memory, then programming efficiency is improved, but floating gate coupling and NAND string resistance effects increase
Solution Approach 1:
The patent converts the potential harm of persistent data patterns into a benefit by using pseudo-randomization to create controlled variation. Instead of allowing harmful persistent patterns to form naturally, the system intentionally introduces randomness that prevents coupling effects while still enabling efficient programming operations. The transformation turns what would be a harmful condition into a protective mechanism.
Data Source
AI summary
Features within an integrated-circuit memory chip enables scrambling or randomization of data stored in an array of nonvolatile memory cells. In one embodiment, randomization within each page helps to control source loading errors during sensing and floating gate to floating gate coupling among neighboring cells. Randomization from page to page helps to reduce program disturbs, user read disturbs, and floating gate to floating gate coupling that result from repeated and long term storage of specific data patterns. In another embodiment, randomization is implemented both within a page and between pages. The scrambling or randomization may be predetermined, or code generated pseudo randomization or user driven randomization in different embodiments. These features are accomplished within the limited resource and budget of the integrated-circuit memory chip.