Abstract: A splitting circuit included in a floating-point number calculation circuit splits a mantissa part of a first floating-point number and a mantissa part of a second floating-point number. An exponential processing circuit obtains a second number of shifted bits of each mantissa part obtained after splitting. A calculation circuit calculates a product of the mantissa part of the first floating-point number and the mantissa part of the second floating-point number based on each mantissa part obtained after splitting and the second number of shifted bits of each mantissa part obtained after splitting. The floating-point number calculation circuit can split a large bit-width floating-point number into small bit-width floating-point numbers, so that a small bit-width multiplier is used to calculate the large bit-width floating-point number.

Abstract: A matrix processing method performed by a graphics processing unit (GPU) includes: determining a plurality of non-zero elements in a to-be-processed matrix at a processor in the GPU; generating a distribution matrix of the to-be-processed matrix at the processor, where the distribution matrix comprises identities for indicating positions of the plurality of non-zero elements in the to-be-processed matrix; obtaining a target matrix from another matrix by using the distribution matrix at a logic circuit in the processor, where the target matrix comprises a plurality of target elements from the another matrix; and performing matrix processing on the plurality of non-zero elements and the target matrix to obtain an operation result at the processor.

Abstract: A multiplier (500) configured to simultaneously implement a plurality of low bit width multiplication operations is provided. The multiplier (500) includes a multiplicator input end (550) for receiving two low bit width multiplicators, a multiplicand input end (560) for receiving two low bit width multiplicands, a mask circuit (540) for masking each low bit width multiplicator, and a multiplication operation circuit (502) for multiplying a mask result and a multiplicand. When a sum of bit widths of the multiplicators is smaller than the multiplicator input end (550) and a sum of bit widths of the multiplicands is smaller than the multiplicand input end (560), masking is performed on each of the low bit width multiplicators, so that the multiplier (500) may respectively implement two low bit width multiplication operations, which resolves a waste of hardware resources that occurs because the multiplier can only process multiplication operations in one data format.

Abstract: A matrix processing method performed by a graphics processing unit (GPU) includes: determining a plurality of non-zero elements in a to-be-processed matrix at a processor in the GPU; generating a distribution matrix of the to-be-processed matrix at the processor, where the distribution matrix comprises identities for indicating positions of the plurality of non-zero elements in the to-be-processed matrix; obtaining a target matrix from another matrix by using the distribution matrix at a logic circuit in the processor, where the target matrix comprises a plurality of target elements from the another matrix; and performing matrix processing on the plurality of non-zero elements and the target matrix to obtain an operation result at the processor.

Abstract: A matrix processing method includes: determining a quantity of non-zero elements in a to-be-processed matrix, where the to-be-processed matrix is a one-dimensional matrix; generating a distribution matrix of the to-be-processed matrix, where the distribution matrix is used to indicate a position of a non-zero element in the to-be-processed matrix; combining the quantity of non-zero elements, values of all non-zero elements in the to-be-processed matrix arranged sequentially, and the distribution matrix, to obtain a compressed matrix of the to-be-processed matrix.

Abstract: A matrix processing method includes: determining a quantity of non-zero elements in a to-be-processed matrix, where the to-be-processed matrix is a one-dimensional matrix; generating a distribution matrix of the to-be-processed matrix, where the distribution matrix is used to indicate a position of a non-zero element in the to-be-processed matrix; combining the quantity of non-zero elements, values of all non-zero elements in the to-be-processed matrix arranged sequentially, and the distribution matrix, to obtain a compressed matrix of the to-be-processed matrix.

Abstract: Disclosed are an authentication method and an authentication apparatus for reinforced software. The method includes: obtaining, after verification of a shell procedure of a reinforced software performed by a server succeeds, key data sent from the server, the key data including hidden data in a plain-text software code of the reinforced software and an entry address corresponding to the hidden data; and replacing, according to the hidden data and the entry address, corresponding data hidden in the plain-text software code of the reinforced software stored in a memory, and loading the plain-text software code.

Abstract: A protection method and device for application data are provided. The method includes: acquiring a data request sent by a monitored application, wherein the data request is used for requesting data in a first data source in which data needing protection is stored (S302); and redirecting the data request from the first data source to a second data source, wherein the second data source is used to store false data of the data needing protection (S304).

Abstract: A method for calculating the number and moving direction of pedestrians is provided. in which feature points of a current frame image are extracted; the feature points of the current frame image are compared with those of a selected historical frame image, to obtain moving feature points of the current frame image; directional weighted counting is performed on the moving feature points of the current frame image to obtain the moving direction of the pedestrians; and edge points of pedestrian images are extracted from a foreground image of the current frame image, and performing joint weighted counting on the edge points of the pedestrian images and the moving feature points of the current frame image according to correction coefficients of locations of the respective points, to obtain the number of the pedestrians. A device for calculating the number and moving direction of pedestrians is also provided.

Abstract: A method for calculating the number and moving direction of pedestrians is provided. in which feature points of a current frame image are extracted; the feature points of the current frame image are compared with those of a selected historical frame image, to obtain moving feature points of the current frame image; directional weighted counting is performed on the moving feature points of the current frame image to obtain the moving direction of the pedestrians; and edge points of pedestrian images are extracted from a foreground image of the current frame image, and performing joint weighted counting on the edge points of the pedestrian images and the moving feature points of the current frame image according to correction coefficients of locations of the respective points, to obtain the number of the pedestrians. A device for calculating the number and moving direction of pedestrians is also provided.

Abstract: The present invention discloses a P2P system and a resource query method for this system, wherein the P2P system includes: at least one content management servers, for managing the distribution of content resources in its domain and accepting a resource query request from P2P node in its domain; and at least one resource management servers, for managing the content resources of the P2P nodes in its domain, accepting a resource query request from P2P nodes in its domain and in domains of other resource management servers, and reporting to the at least one content management servers the statistic information of the content resources in its domain.

Abstract: The present invention discloses a P2P system and a resource query method for this system, wherein the P2P system includes: at least one content management servers, for managing the distribution of content resources in its domain and accepting a resource query request from P2P node in its domain; and at least one resource management servers, for managing the content resources of the P2P nodes in its domain, accepting a resource query request from P2P nodes in its domain and in domains of other resource management servers, and reporting to the at least one content management servers the statistic information of the content resources in its domain.