A Novel Memristive-Based Data Reordering Scheme
Mojtaba Mahdavi
Abstract
A novel method is proposed for the implementation of arbitrary reordering schemes using a 2-dimensional array of memristive devices. The key idea is to convert the data reordering algorithm into a matrix-vector multiplication operation, which can be efficiently executed by memristors. Specifically, the process of generating a KxK reordering matrix based on the desired reordering algorithm is demonstrated. This matrix is then programmed into the array of memristive devices, which takes a sequence of <tex xmlns:mml="http://www.w3.org/1998/Math/MathML" xmlns:xlink="http://www.w3.org/1999/xlink">$K$</tex> input samples to be reordered. The resulting multiplication output corresponds to the reordered sequence of input samples. Importantly, the proposed approach enables the fully parallel reordering of large-scale data, which is crucial for various digital signal processing applications, including quantum computing and wireless communication systems.