Abstract: The disclosure relates to a method and a system for predicting the operation time of sparse matrix vector multiplication. The method comprises constructing a convolutional neural network comprising an input layer, a feature processing layer, a data splicing layer and an output layer for outputting prediction results. The method further comprises acquiring a plurality of groups of sparse matrices with known sparse matrix vector multiplication operation time as sample data, inputting the sample data into the convolutional neural network to train the convolutional neural network, and inputting the sparse matrix to be classified into the trained convolutional neural network to realize the prediction of the operation time of sparse matrix vector multiplication.

Abstract: The disclosure relates to a method and a system for predicting the operation time of sparse matrix vector multiplication. The method comprises constructing a convolutional neural network comprising an input layer, a feature processing layer, a data splicing layer and an output layer for outputting prediction results. The method further comprises acquiring a plurality of groups of sparse matrices with known sparse matrix vector multiplication operation time as sample data, inputting the sample data into the convolutional neural network to train the convolutional neural network, and inputting the sparse matrix to be classified into the trained convolutional neural network to realize the prediction of the operation time of sparse matrix vector multiplication.

Abstract: SOAP client protocol encapsulation Based on TCP , based on the short TCP connection, SOAP client protocol encapsulation method, the client package for SOAP protocol, that is Web Services Description Language WSDL file into xml file, put to the client application's configuration file which, variable part of the SOAP protocol allows all the code from the configuration file object after conversion, and then generated after the body of SOAP protocol: 1) client load WSDL converted xml file; 2) the client application to read out the configuration file, the xml with the application to transfer data into a SOAP message body; 3) in the generated SOAP message body together with SOAP message header, turned into a complete SOAP request; 4) We will be based on TCP short connection to the complete SOAP request sent to the web services server, then receive and process about the content of web services to return, to complete a full SOAP interface calls; All the web Services client: a client using the same source, and adopt a

Abstract: As for the data transfer method based on MAP, adopts a MAP data structure during the data transferring process and configures it using SOID (Standard of Interface Department) syntax after encapsulation; the definition of MAP data structure; one system consists of many matching and individual source ends and target ends, one source end just accesses to its matching target end, and vice versa, all member methods of source and target end adopt MAP structure to transfer data, logic implementation steps are shown as below: data processing of database is the most basic and most featured part of BRS system which adopts SOID syntax, if a table is not simply imported into another Oracle database, it should be treated by another process, that is, generate a derived class directly, and then rewrite “Key process”; data transfer method based on MAP bring excellent compatibility. It nearly supports all kinds of existing platforms, protocols, businesses and manufacturers.