Non-Volatile Memory Error Correction Using Guided Simulated Annealing
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
Non-volatile memory systems face challenges in reliably reading data due to noise and charge neutrality issues, leading to erroneous data bits, which traditional error correction methods may struggle to correct, especially in multi-state memory devices.
Innovation Solution
The implementation of iterative probabilistic decoding with simulated annealing, guided by device characteristics, is used to adjust reliability metrics and introduce randomness to facilitate faster convergence and error correction in non-volatile memory systems, potentially obviating the need for absolute randomness.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Reliability
If traditional error correction methods are used, then the system is simple to implement, but the reliability of data reading deteriorates due to noise and charge neutrality issues in multi-state memory devices
Solution Approach 1:
The patent applies simulated annealing by dynamically changing the temperature parameter to control the probability of accepting worse solutions during decoding. The temperature starts high to allow extensive exploration of the solution space and gradually decreases to converge to an optimal solution, enabling the system to overcome local minima caused by noise in multi-state memory reading
Solution Approach 2:
The error correction system transitions from static traditional methods to dynamic simulated annealing decoding. The algorithm adaptively adjusts its behavior based on the current temperature state, allowing it to dynamically explore different decoding paths and converge to correct data even in the presence of charge neutrality issues and noise
2Productivity
If iterative probabilistic decoding with simulated annealing is used, then the convergence speed and error correction capability improve, but the computational complexity increases
Solution Approach 1:
The simulated annealing process employs periodic temperature reduction schedules where the temperature is systematically lowered after certain numbers of iterations or based on convergence criteria. This periodic cooling structure allows the algorithm to maintain high exploration capability initially while ensuring eventual convergence, balancing computational effort with decoding performance
Solution Approach 2:
The decoding algorithm incorporates feedback mechanisms where the current decoding state and error metrics influence the temperature schedule and acceptance probability. The system continuously monitors decoding progress and adjusts parameters accordingly, enabling faster convergence while managing computational complexity through adaptive control
Data Source
AI summary
Data in non-volatile storage is decoded using iterative probabilistic decoding. An error correcting code such as a low density parity check code may be used. In one approach, initial reliability metrics, such as logarithmic likelihood ratios, are used in decoding sensed states of a set of non-volatile storage elements. The decoding attempts to converge by adjusting the reliability metrics for bits in code words which represent the sensed state. Simulated annealing using an adjustable temperature parameter based on a level of error in the data can be performed to. The simulated annealing can introduce randomness, as noise for example, into the decoding process. Moreover, knowledge of the device characteristics can be used to guide the simulated annealing process rather than introducing absolute randomness. The introduction of a degree of randomness adds flexibility that permits possible faster convergence times and convergence in situations where data may otherwise be uncorrectable.