Implementation method of systolic array structure for LU decomposition

Abstract

The invention discloses an implementation method of a systolic array structure for LU decomposition. The systolic array structure comprises an arithmetic unit array for calculating an upper triangularmatrix, an arithmetic unit array for calculating a lower triangular matrix, and a state controller module for controlling data input. Compared with an existing operation structure, the implementationmethod has the following innovations that (1) matrix data is input in parallel according to lines, and an input sequence does not need to be planned; (2) the dividers are independently extracted fromthe array processing unit, so that the number of the dividers is reduced, and the resource utilization rate is improved; (3) the pulsation array is partially parallelized, and the number of clock cycles required by operation is reduced while maintaining high pipelining; and (4) the high-dimensional systolic array structure designed by the invention can be compatible with lower-dimensional matrixLU decomposition, so that the same structure can be shared by matrixes with different dimensions, and the redesign of the structure is avoided. The implementation method can be applied to hardware implementation of matrix decomposition problems in the fields of signal processing, numerical analysis, artificial intelligence and the like.

Description

technical field [0001] The invention relates to the technical field of matrix calculation, in particular to a method for realizing a systolic array structure for LU decomposition. Background technique [0002] LU decomposition is a method of matrix decomposition. Its principle is to decompose a square matrix into an upper triangular matrix and a lower triangular matrix. Matrix factorization is commonly used in many scientific fields such as image processing and signal processing. [0003] At present, most algorithms such as image processing and signal processing are still running on the PC side based on software, which contains a large number of matrix decompositions that take up most of the computing time of the overall algorithm. With the increase of algorithm complexity and matrix dimension, based on The execution speed of the algorithm running by the software is far from meeting the demand. [0004] At present, it is urgent to carry out research on the matrix operation...

AI Technical Summary

Problems solved by technology

[0003] At present, most of the image processing, signal processing and other algorithms are still running on the PC side based on software, which contains a large number of matrix decompositions that take up most of the computing time of the overall algorithm , and as the complexity of the algorithm and the dimension of the matrix increase, the execution speed of the algorithm based on software operation is far from meeting the demand

Images