Data Encoding for Crossbar Memory Arrays
Find Innovative SolutionsGenerate Solutions
Solution Overview
Problem
High parasitic current draw from half-selected resistive switching devices in crossbar memory arrays leads to wasted power and reduced longevity, impacting read sensitivity and circuit longevity.
Innovation Solution
Implementing a data encoding method that applies a Hamming-weight constraint to limit the number of memory devices in the ON state on each conductor, using bit-flipping operations to ensure no more than half of the devices on each row or column are in the ON state, thereby controlling current draw during write and read operations.
Engineering Contradictions & Design Principles
Engineering Contradiction Analysis
1Manufacturing precision
If a crossbar array structure is used to achieve high cell density, then manufacturing precision and device integration are improved, but parasitic current draw from half-selected devices increases
Solution Approach 1:
The patent applies preliminary action by pre-processing the data before storage through encoding schemes that constrain the Hamming weight of stored words. This preliminary encoding ensures that when data is later read or written, the number of simultaneously active devices is limited, thereby preventing excessive parasitic current draw while maintaining the high-density crossbar structure
2Productivity
If more devices are activated during read/write operations to increase storage capacity utilization, then productivity is improved, but power consumption increases
Solution Approach 1:
The patent applies parameter changes by modifying the data representation parameters through encoding schemes. By transforming the data into encoded forms with constrained Hamming weights, the system changes the activation pattern parameters during read/write operations, thereby reducing the number of simultaneously active devices and lowering power consumption while maintaining effective storage capacity utilization
3Measurement precision
If high current is drawn during operations to improve read sensitivity, then measurement precision is improved, but device longevity deteriorates
Solution Approach 1:
The patent applies preliminary action by pre-encoding data to control the number of active devices during operations. This preliminary constraint on Hamming weight ensures that read operations can be performed with sufficient sensitivity while limiting the cumulative stress on devices, thereby extending device longevity without sacrificing measurement precision
Data Source
AI summary
A method of storing data into a memory array converts an input string into a first binary array with (m−1) rows and (n−1) columns. A second binary array with m rows and n columns in an encoded bit pattern is then generated from the first binary array. The second binary array in the encoded bit pattern has at most n/2 1's in each row and at most m/2 1's in each column, and the m-th row and an n-th column contain information for decoding other entries of the second binary array. The encoded bit pattern of the second binary array is then stored into corresponding memory devices of the memory array.


