Lower Triangular Partial Storage Device and Parallel Reading Method of Self-Conjugate Matrix

Abstract

The embodiment of the invention provides a lower triangular part storage device of a self-conjugate matrix and a parallel reading method, and the device comprises a storage module selection circuit which is used for selecting a storage module corresponding to each element of the lower triangular part of the self-conjugate matrix to be accessed; an address generation circuit used for calculating the logic address of each element of the triangular part under the self-conjugate matrix to be accessed in the corresponding storage module; m parallel storage modules used for storing data corresponding to each element of the triangular part under the self-conjugate matrix to be accessed; a data shuffling module used for performing shuffling operation on the data read from the storage module; and aconjugate taking module used for carrying out bypass operation and conjugate taking operation on the shuffled data. According to the embodiment of the invention, only the lower triangular part of theself-conjugate matrix needs to be stored, any row vector and any column vector of the self-conjugate matrix are supported to be read and recovered in parallel, a parallel computing unit of hardware can be fully utilized, and the efficiency of a matrix computing algorithm is improved.

Description

technical field [0001] The embodiments of the present invention relate to the technical field of matrix operation, and more specifically, to a lower triangular part storage device and a parallel reading method of a self-conjugate matrix. Background technique [0002] Self-conjugate matrix (Hermitian Matrix) is a conjugate symmetrical square matrix, which is widely used in the field of digital signal processing. For example, many signal detection algorithms need to use the real autocorrelation matrix to obtain the second-order statistical characteristics of the signal. The complexity of solving the self-conjugate matrix increases quadratically with the increase of the matrix order. In order to reduce the computational complexity, according to the complex conjugate symmetry property of the self-conjugate matrix, only the lower triangular part of the self-conjugate matrix is ​​calculated. The upper triangular part of the conjugate matrix can be obtained from the lower triangul...

AI Technical Summary

Problems solved by technology

[0005] In order to solve the problems existing in the prior art that are limited by the low parallelism of the row and column vector data access of the triangular matrix, resulting in low hardware utilization and matrix operation algorithm efficiency, the embodiment of the present invention provides the following self-conjugate matrix Triangular Partial Storage Device and Parallel Read Method

Images