Flash Memory Data Randomization for Program Disturb Suppression
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Flash memory devices face reliability issues due to data-dependent errors, particularly the Program Disturb (PD) effect, which causes unintended state changes in memory cells, leading to bit errors, especially in Multi-Bit Cells (MBC) where the difference between threshold voltage ranges is smaller, making them more prone to errors compared to Single Bit Cells (SBC).
Innovation Solution
The implementation of a data randomization method that transforms user data into pseudorandom bit sequences before storage, ensuring that all memory cell states occur with approximately equal probability, reducing the likelihood of problematic bit patterns that cause high error rates, thereby enhancing the reliability of flash memory devices.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Quantity of substance
If Multi-Bit Cells (MBC) are used to store multiple bits per cell, then storage capacity is improved, but reliability deteriorates due to smaller threshold voltage range differences making cells more prone to Program Disturb errors
Solution Approach 1:
The patent applies preliminary randomization to the data before it is written to the flash memory. A randomizer transforms the original data into a pseudorandom bit sequence, ensuring that all memory cell states occur with approximately equal probability. This preliminary action prevents problematic bit patterns that would otherwise cause high error rates in MBC cells, thereby improving reliability while maintaining the high storage capacity of MBC technology.
2Productivity
If data is stored in non-random patterns, then storage speed is improved, but error rates increase due to Program Disturb effects on specific bit patterns
Solution Approach 1:
The patent changes the statistical parameters of the stored data by applying randomization. The randomizer transforms data with potentially problematic patterns into a pseudorandom sequence where all cell states occur with equal probability. This parameter change in the data distribution eliminates the dependency on worst-case patterns, reducing error rates without impacting storage speed since the randomization is performed as a preprocessing step.
3Reliability
If Error Correction Code (ECC) redundancy is increased to handle worst-case error rates, then reliability is improved, but device complexity and cost increase
Solution Approach 1:
By applying randomization as a preliminary action before data storage, the patent transforms the error profile from being dependent on specific bit patterns to having a uniform, predictable error distribution. This eliminates worst-case scenarios, allowing the use of simpler and less redundant ECC schemes while maintaining high reliability. The randomizer effectively pre-processes the data to prevent the formation of error-prone patterns, reducing the burden on ECC mechanisms.
Data Source
AI summary
A device for storing data includes a nonvolatile memory and a controller and/or circuitry that randomize original data to be stored in the memory while preserving the size of the original data, that store the original data in the memory, and that, in response to a request for the original data, retrieve, derandomize and export the original data without authenticating the requesting entity. A system for storing data includes a first nonvolatile memory and a processor that similarly stores data in the first nonvolatile memory by executing driver code stored in a second nonvolatile memory. ECC encoding is applied either before or after randomizing; correspondingly, ECC decoding is applied either after or before derandomizing.