Prediction method and system for vector multiplication operation time of sparse matrix

Abstract

The invention relates to a prediction method and system for vector multiplication operation time of a sparse matrix, and the method comprises the following steps: constructing a convolutional neural network which comprises an input layer, a feature processing layer, a data splicing layer and an output layer, wherein the input layer is used for inputting the characteristics of a row characteristicmatrix, the characteristics of a column characteristic matrix and the characteristics of an architecture parameter extension matrix in a sparse matrix; the feature processing layer is used for extracting features in the previous layer; the data splicing layer is used for splicing the extracted features of the row feature matrix, the extracted features of the column feature matrix and the extractedfeatures of the architecture parameter extension matrix; the output layer is used for outputting a prediction result and obtaining a plurality of groups of sparse matrixes with known sparse matrix vector multiplication operation time as sample data, and inputting the sample data into the convolutional neural network to realize training of the convolutional neural network; and inputting a sparse matrix to be classified into the trained convolutional neural network to realize prediction of sparse matrix vector multiplication operation time.

Description

technical field [0001] The present invention relates to the technical field of machine learning (Machine Learning), in particular to a method for predicting operation time of sparse matrix-vector multiplication based on deep learning. Background technique [0002] Sparse matrix-vector multiplication is an important operation in scientific computing and engineering fields, and its performance directly determines its performance in practical applications. Due to the irregularity of memory access in the process of sparse matrix-vector multiplication, the performance of sparse matrix-vector multiplication is relatively low, which needs to be optimized. At present, the optimization of sparse matrix-vector multiplication generally focuses on the optimization of specific storage formats or platforms. There is a lack of a method that can efficiently predict the operation time of sparse matrix-vector multiplication to provide guidance for performance optimization. Therefore, the opti...

AI Technical Summary

Problems solved by technology

[0003] The purpose of the present invention is to solve the problem of low performance of sparse matrix-vector multiplication in the prior art

Images