Patents
Literature
Patsnap Eureka AI that helps you search prior art, draft patents, and assess FTO risks, powered by patent and scientific literature data.

85results about How to "Reduce visits" patented technology

Data caching method and device, computer equipment and storage medium

The invention relates to a data caching method and device, computer equipment, a storage medium and a computer program product. The method comprises the steps that after an access request for a target page sent by a terminal is received, a target cache timestamp corresponding to target cache data is acquired, and the cache duration of the target cache data is determined based on the target cache timestamp; when a preset condition is met between the cache duration and a preset data expiration duration, returning target cache data to the terminal, querying a current cache timestamp corresponding to the target data object, and comparing the target cache timestamp with the current cache timestamp; under the condition that the update timestamp is consistent with the current cache timestamp, taking the update timestamp as the current cache timestamp corresponding to the target data object, acquiring update data corresponding to the target data object from the remote database, and replacing the target cache data in the data cache with the update data; and taking the update timestamp as a target cache timestamp corresponding to the update data. And the response speed of the page access request is improved.
Owner:TENCENT TECHNOLOGY (SHENZHEN) CO LTD

Target detection system based on ARM + FPGA heterogeneous platform and hardware acceleration method thereof

The invention discloses a target detection system based on an ARM + FPGA heterogeneous platform and a hardware acceleration method thereof. The original 32-bit floating-point neural network model is quantized into an 8-bit fixed-point neural network model by quantizing neural network weight data and feature map data. And meanwhile, a configurable neural network hardware accelerator is designed, and the same hardware accelerator can be suitable for calculating different convolutional layers in the neural network by configuring parameters of each module, so that the acceleration operation of the whole neural network is completed. In the process of performing convolution calculation on the convolution layer, frequent access to an external DDR3 memory is reduced by designing a weight and reusing resources of a feature map cache module. A control process is designed at a PS end to complete the scheduling of the whole convolution calculation process and the post-processing step of target detection, the whole process design of image acquisition, target detection algorithm calculation and detection result output and display is realized, and finally the whole target detection system is built through soft and hard collaborative design.
Owner:DALIAN UNIV OF TECH

Accelerator for accelerating reasoning process of unstructured sparse large language model

The invention discloses an accelerator for accelerating the reasoning process of an unstructured sparse large language model and an operation method of the accelerator. The accelerator comprises a processor module, a direct memory access module, a memory controller module, a DDR memory module, an interconnection bus module, a calculation core module and a router module. The interconnection bus module is connected with the direct memory access module, the memory controller module and the computing core module; the processor module is connected with the direct memory access module; the DDR memory module is connected with the memory controller module; the router module is connected with the computing core module and the adjacent router module; and the calculation core module obtains to-be-calculated data from the off-chip DDR memory module through the interconnection bus module. According to the method, the limit that data reuse is carried out only along a single row or a single column on a traditional systolic array is broken through, cross-row and cross-column data reuse is achieved, the pressure of hardware equipment is relieved, the positions of non-zero elements are coded through bit masks, and the calculation efficiency is improved.
Owner:NINGBO ORIENTAL UNIV OF TECH (TEMPORARY NAME)

Enhanced GPGPU (General Purpose Graphics Processing Unit) thread bundle cache prefetching method and device

The invention relates to the technical field of GPGPU internal computing processing, and discloses an enhanced GPGPU thread beam cache prefetching method and device, and the method comprises the steps: carrying out the core initialization, and initializing a stride prefetcher for each processor core; configuring an independent training prefetcher for each thread bundle; each thread bundle stride table is used for recording stride information of each thread bundle, and the thread bundle stride table stores stride size, access frequency and other related parameters and provides guidance for prefetching operation; when it is monitored that the multiple thread bundles have the same stride for the same program counter, stride information is sent to a global stride table; untrained thread bundles are allowed to issue prefetch requests using entries in the global stride table. By analyzing the memory access address and stride of each thread bundle, the regular access mode can be identified, the prefetching request is generated accordingly, and the response speed of the prefetching operation is increased.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Artificial intelligence chip integrated with on-chip memory array, computing task processing method and electronic equipment

The invention relates to the field of artificial intelligence chips, in particular to an artificial intelligence chip integrated with an on-chip memory array, a computing task processing method and electronic device.The chip comprises a controller and a plurality of processor-memory modules, obtaining a plurality of sub-calculation tasks; the processor-memory module comprises a processing unit group, a memory and a scheduler, the processing unit group comprises a plurality of processing units, and the processing units process the sub-calculation tasks; the memory stores data related to the plurality of processing units in the processing unit group when executing the corresponding sub-calculation tasks; the scheduler is connected to the plurality of processing units and the memory and is used for scheduling access operation of the plurality of processing units to the memory, the processing unit group is arranged in a processing layer of the artificial intelligence chip, the memory is arranged in a storage layer of the artificial intelligence chip, and the processing unit group is used for processing the processing units. The processing layer and the storage layer are arranged in a stacked mode.
Owner:BEIJING SMARTCHIP MICROELECTRONICS TECHNOLOGY CO LTD

Code automatic vectorization optimization method and device and medium

The invention discloses an automatic code vectorization optimization method and device and a medium, belongs to the technical field of high-performance computing, and aims at solving the problems that existing automatic code vectorization is inconvenient, the manual operation proportion is large, vectorization of irregular codes or codes with a load dependency relationship is difficult to support, and the vectorization efficiency is high. And improvement of calculation performance and reduction of energy consumption are not facilitated. The method comprises the steps of obtaining a scalar instruction diagram of a calculation task according to a calculation kernel of parallel calculation; performing protocol conversion processing on the scalar instruction diagram to obtain a protocol instruction diagram; according to the high-level organization structure of the instruction, grouping processing related to mapping vectors is carried out on the protocol instruction graph, and a grouping graph is obtained; based on the limited vector length of hardware, performing splitting matching processing on instruction vectors in the grouping graph to obtain a vector matching grouping graph; and executing configuration on each group of elements in the vector matching grouping graph to obtain a vector operation graph.
Owner:SHANDONG INSPUR SCI RES INST CO LTD

Neural network forward prediction hardware accelerator based on programmable logic device

The neural network forward prediction hardware accelerator based on the programmable logic device can be applied to the technical field of neural network hardware acceleration. The accelerator comprises a multi-layer hardware accelerator module unit, and the hardware accelerator module unit comprises an input feature map cache module and a data processing module; the accelerator module units are connected in an assembly line structure mode; multi-channel feature maps can be processed in parallel; and the output data of the hardware accelerator module unit of each layer is stored in the input feature map cache module of the hardware accelerator module unit of the next layer for the operation of the next layer. By adopting an assembly line structure, the throughput rate of the hardware accelerator is improved; a multi-channel parallel processing mode is adopted, and the running speed of a hardware accelerator is increased; and on-chip storage is adopted, so that the off-chip access times are reduced, and the power consumption of the hardware accelerator is reduced.
Owner:INST OF SEMICONDUCTORS - CHINESE ACAD OF SCI

Inference calculation method and device, electronic equipment and storage medium

The invention provides a reasoning calculation method and device, electronic equipment and a storage medium, and the method comprises the steps: obtaining a target text to be reasoned through a large language model; the target text is preprocessed, and all first tokens in the target text are obtained; through a target data loading strategy obtained by limiting parameters of each second token in N second tokens which need to be loaded and are processed recently and uniformly storing row and column data of a feedforward neural network layer of the large language model, target parameters used for reasoning are loaded from a persistent storage medium storing the large language model; wherein the second token comprises the first token and / or a token obtained by reasoning based on the first token; and performing reasoning calculation on the integer ID through the target parameter to complete reasoning of the new second token. According to the invention, the problems of high data transmission cost and low reasoning speed in the prior art are solved.
Owner:BEIJING KINGSOFT CLOUD NETWORK TECH CO LTD

Neural network accelerator based on eDRAM in-memory calculation and control method thereof

The invention discloses a neural network accelerator based on eDRAM in-memory calculation and a control method thereof, the neural network accelerator comprises a top layer controller and an extensible and reconfigurable SR-CIM macro array, and the extensible and reconfigurable SR-CIM macro array is operated in a global system mode. The method comprises the following steps: acquiring weight data and input activation data; setting a working mode of the extensible and reconfigurable SR-CIM macro array; and according to the working mode of the extensible and reconfigurable SR-CIM macro array, performing operation on the weight data and the input activation data, and transmitting an operation result to the off-chip neural network. According to the embodiment of the invention, the computing efficiency of the neural network can be improved by improving the reuse rate of the data and reducing the access times of the off-chip data in different data flow modes. The method can be widely applied to the technical field of neural network accelerators.
Owner:UNIV OF MACAU

Neural network data operation acceleration device and method, equipment and medium

The invention relates to a neural network data operation acceleration device and method, equipment and a medium, and the method comprises the steps: firstly obtaining the input data of neural network operation and Cin convolution kernel data, dividing a feature matrix SMF into N feature sub-matrixes MF in a C direction, generating an index table of img2col operation after pad for each feature sub-matrix MF, and carrying out the calculation of the img2col operation according to the index table. According to the method, firstly, an index table generating img2col operation is mapped back to an index table of an original feature matrix SMF, finally, localization of data of neural network operation is achieved, operation processing is carried out, multiple sliding windows can be calculated at a time, in other words, multiple pieces of data can be read at a time, and therefore the number of times of data access is greatly reduced, and the operation efficiency is greatly improved. Compared with the prior art, localization operation of the neural network is achieved, cache occupation of a computer is effectively reduced, the number of times of access to the feature data is reduced, and the method can be universally used for operation acceleration of various neural networks.
Owner:HUNAN GREAT WALL GALAXY TECH CO LTD

Direct memory access device and method, electronic equipment and readable storage medium

The embodiment of the invention provides a direct memory access device and method, electronic equipment and a readable storage medium. The method comprises the steps of performing high-speed connection with a system-on-chip and an accelerator consistency port through a data interface; the buffer area temporarily stores data in a data transmission process; the command receiving area is responsible for receiving a command sent by the central processing unit; the result temporary storage area is used for storing a result after the direct memory access controller executes the command; the direct memory access controller parses the command and performs a data migration operation, and processes data transmissions associated with an accelerator coherency port interface. According to the direct memory access device integrated with the consistent port interface of the accelerator, under the condition that resources of a central processing unit are not occupied, rapid read-write operation of data between the memory and the cache is achieved, and therefore the overall performance and the data processing capacity of a system-level chip are remarkably improved.
Owner:SHANDONG YUNHAI GUOCHUANG CLOUD COMPUTING EQUIP IND INNOVATION CENT CO LTD

Data hybrid storage method and device and computer equipment

The invention relates to the technical field of power acquisition terminal data storage, and discloses a data hybrid storage method and device and computer equipment, which are applied to a memory database, and the method comprises the following steps: when electric energy meter reading data is written into a main database of a power acquisition terminal, receiving a data change notification sent by the main database; recording the meter reading data into a data cache by adopting a key value mode based on the data change notification; and preferentially querying the corresponding meter reading data in the data cache based on a preset data retrieval requirement, and if the corresponding meter reading data is not queried, switching to the main database to continue data retrieval. According to the method, a large amount of data is prevented from simultaneously accessing the main database at the same moment, so that the load of the main database is reduced, load balancing is realized, the memory database is preferentially queried during data retrieval, and the main database is switched to retrieve when the memory database cannot be queried, so that the access frequency of the main database is greatly reduced, and the data retrieval efficiency is improved. And the performance bottleneck during batch data query of the relational database is solved.
Owner:ZHEJIANG CHINT INSTR & METER

Black box attack detection method, device and system based on multi-feature fusion

The invention provides a multi-feature fusion-based black box attack detection method (MFBA), device and system, different features are extracted by using a multi-model fusion strategy, the effectiveness and quality of opposite samples are improved, and the MFBA comprises the following three key steps: firstly, obtaining an initial data set from a target model; a decision boundary is approached by using a multi-feature fusion model; secondly, the stability of the model is enhanced through multiple rounds of training application data expansion and incremental learning technologies; and finally, generating opposite examples by using the optimized fusion model. By constructing the comprehensive attack framework, how to combine various model features to improve the performance against the resistance attack is demonstrated; compared with a single substitution model, the antagonism examples generated by the MFBA have higher mobility under different disturbance levels and have better attack effects; according to the method, an effective solution is provided for black box antagonism attacks, and the model in the generation of the advantage opposite paradigm of multi-feature fusion is verified.
Owner:YANGZHOU UNIV

Method for transmitting and pushing alarm data to Web page

The invention discloses a method for transmitting and pushing alarm data to a Web page. The method comprises the following steps: generating alarm data to be pushed; bidirectional communication connection between the Web browser and the Web server is realized through a TCP socket; the received alarm data are analyzed through a gateway, and the analyzed data are written into a MySQL database and a Redis database; packaging the data; alarm data subscription and push judgment; and alarm data pushing and displaying: formatting the alarm data determined to be pushed through an XML conversion function built in the Web server, then directly pushing the alarm data to a corresponding Web browser by using a TCP socket, and after the Web browser receives the pushed data, updating and displaying a corresponding Web page so as to display alarm information. The XML is used as a data exchange format, so that the flexibility and compatibility of data among different systems, platforms and application programs are greatly enhanced. And the standardized data format enables different systems to quickly process data, so that the circulation and sharing of information are promoted.
Owner:HENAN ZHONGYUAN CONSUMER FINANCE CO LTD

Bezier curve calculation method and device, medium and program product

The invention relates to the technical field of algorithm calculation, in particular to a Bezier curve calculation method and device, a medium and a program product. The Bezier curve calculation method comprises the steps that an initial graph is provided, and a plurality of initial control points of a Bezier curve are obtained based on the outline of the initial graph; performing uniform processing on the initial control point to obtain a plurality of uniform target control points; performing recursive calculation on the target control point to obtain a new control point of the Bezier curve; and obtaining a target Bezier curve by taking the target control point and all new control points obtained in the recursive calculation process as final control points. The contour points of the Bezier curve are calculated through multi-thread cooperation, and the calculation efficiency is improved.
Owner:SHENZHEN JINGYUAN INFORMATION TECH CO LTD

Model reasoning method and device, electronic equipment and storage medium

The invention provides a model reasoning method and device, electronic equipment and a storage medium, and relates to the technical field of artificial intelligence. Inputting the input vector into a target model to obtain a model reasoning result corresponding to the input vector output by the target model; wherein the target model comprises at least one hybrid expert module; the hybrid expert module comprises a time sequence feature extraction layer, a routing selection layer, an expert model layer and a result output layer which are connected in sequence; the expert model layer comprises a plurality of state space models; the input vector is generated based on at least one of text, speech, image, or video. According to the method and the device provided by the invention, the storage consumption of the large model is reduced, the access frequency of the large model to the storage is reduced, and the reasoning efficiency of the large model is improved.
Owner:SHANGHAI BIREN TECH CO LTD

U8 quantization convolution acceleration device, method, equipment and medium

The invention relates to a U8 quantization convolution acceleration device, method and equipment and a medium, which effectively improve the convolution speed and realize operation localization by combining localization and quantization of matrix multiplication, reduce the cache occupation problem and reduce the access frequency of feature data, and are universal for various networks to realize conversion and calculation at the same time. A scheme for realizing floating point multiplication by integer multiplication and shift is provided, a result does not need to be inversely quantized firstly, then quantized into a U8 data type and then input into a next-layer network, but can be directly input into the next-layer network to participate in calculation, so that the calculation amount is greatly reduced. Compared with the prior art, a software and hardware collaborative optimization scheme is adopted, an online hardware compensation module is added in a U8 matrix multiplication acceleration hardware device, compensation value real-time calculation and convolution reasoning operation are synchronously completed, the calling frequency is reduced, and the calculation efficiency is greatly improved.
Owner:HUNAN GREAT WALL GALAXY TECH CO LTD

Method for inversely sorting and assembling tree data

The invention discloses a method for inversely sorting and assembling tree data, which relates to the field of software background development and comprises the following steps: S1, preparing; s2, a sorting step; s3, a cache establishment step; and S4, traversing and assembling. Compared with a traditional assembling mode of arranging from root nodes in sequence and recurring layer by layer, the method for assembling the tree structure data in the inverted sorting mode has the remarkable beneficial effects that the basic data are traversed in the inverted sorting mode, calculation is started from the last-stage node, the lower-stage nodes are set, and the efficiency is improved. According to the method, the complete tree structure can be assembled only through one-time circulation, the number of times and depth of recursion calling are greatly reduced, the time complexity problem (O (1)-O (n2)) caused by too deep recursion hierarchy and uncertain tree branch is avoided, and therefore the response time of a tree interface is remarkably shortened, and the overall running smoothness of software is improved.
Owner:富盛科技股份有限公司

Transposition operation processing device, method and artificial intelligence chip

The present disclosure provides a processing device, method and artificial intelligence chip for transposition operation, which relates to the field of artificial intelligence technology. The processing device for transposition operation includes K groups of registers, the kth group of registers includes M registers, and each register includes N storage units. The i-th register in the kth group of registers is configured to receive the i-th row element of the kth matrix to be transposed, and store the j-th element in the i-th row element in the j-th storage unit of the i-th register in the kth group of registers, the kth matrix to be transposed is an M×N matrix, and the N elements in the i-th row element are arranged in sequence from 1 to N; the M registers in the kth group of registers are configured to output the N column elements of the kth matrix to be transposed in sequence from 1 to N or from N to 1, and the j-th column element includes the j-th element in the j-th storage unit of each register in the kth group of registers.
Owner:SHENZHEN CORERAIN TECH CO LTD

Image processing method and device based on element-by-element operation, equipment and medium

The invention provides an image processing method and device based on element-by-element operation, equipment and a medium, and relates to the technical field of GPUs (Graphics Processing Unit), and the method comprises the following steps: according to the number of a plurality of elements contained in a plurality of input tensors needing to participate in operation and hardware resource information of GPU equipment, determining the number of the plurality of elements contained in the plurality of input tensors needing to participate in operation; determining the number of thread blocks required to be used by the plurality of input tensors in the element-by-element operation process; according to the number of the thread blocks, the number of the elements and the memory layout of the multiple elements, kernel functions of element-by-element operation class operators corresponding to the multiple input tensors needing to participate in operation are determined on the basis of a predefined template structure body, and parameters of the template structure body comprise element types and the number of the elements; and based on the number of the thread blocks, initiating a plurality of threads to enable the plurality of threads to obtain the plurality of elements according to the kernel function, and executing an element-by-element operation process of the plurality of input tensors to obtain an image processing result.
Owner:INSPUR SUZHOU INTELLIGENT TECH CO LTD

Multi-version concurrent control method, device, equipment and medium for database

The present invention provides a multi-version concurrency control method for a database, which can be applied to the field of database technology. The multi-version concurrency control method for a database includes: determining the difference information of a target data row according to a first version and a second version of the target data row, wherein the second version of the target data row is obtained by modifying the first version through a first transaction; writing the difference information as the latest row version information into an uncommitted version data chain corresponding to the target data row, wherein the uncommitted version data chain includes at least one row version information, and the at least one row version information is obtained by executing a first transaction; upon receiving a feedback signal indicating that the first transaction is successfully committed, generating the committed row version information corresponding to the target data row according to the uncommitted version data chain, and writing the committed row version information into the committed row version chain corresponding to the target data row.
Owner:SUZHOU JIBEISI DATA TECHNOLOGY CO LTD +1

A black-box neural network detection method using small amounts of data and adversarial attacks

The present invention discloses a method for detecting the type of a black box neural network using a small amount of data and adversarial attacks, and the implementation steps are: generating a training set, constructing an alternative network, arbitrarily selecting an untrained alternative network, training the selected alternative network, expanding the current data set until the updated alternative network meets the training termination condition, using the attack sample set generated by the trained alternative network to attack the black box neural network to be detected, and expanding the current training set again until all alternative networks generate attack sample sets to determine the type of the black box neural network to be detected. The present invention can use a small amount of data to detect the type of the black box neural network model of the cloud service platform that only has access rights, and has the advantages of using less data and consuming less resources.
Owner:XIDIAN UNIV

Real-time attendance checking method and system based on cache preheating and hotspot peak clipping

The invention provides a real-time attendance checking method and system based on cache preheating and hotspot peak clipping. The real-time attendance checking method based on cache preheating and hotspot peak clipping comprises the following steps: before a real-time attendance checking system is started or the concurrent access quantity exceeds a preset first concurrent access quantity threshold value, loading hotspot data into a cache region in advance; monitoring the concurrent access quantity of the attendance system in real time, when the concurrent access quantity exceeds a preset second concurrent access quantity threshold value, setting a target concurrent access processing quantity, and performing asynchronous processing on the access request by utilizing the target concurrent access processing quantity; and according to the data processing response duration offset coefficient corresponding to the employee card punching data processing response duration, determining whether data processing abnormity exists, and when the data processing abnormity exists, carrying out abnormity alarm. The system comprises modules corresponding to the steps of the method.
Owner:COFCO INFORMATION TECH CO LTD

Control method and device, equipment and storage medium executed by neural network

PendingCN122596110Areduce visitsSolve the technical problem of insufficient reasoning efficiency
The application discloses a control method and device of a neural network execution, equipment and a storage medium, relates to the technical field of neural network inference, and comprises the following steps: acquiring an activated neuron set of a current neural network layer and corresponding weight data of the activated neuron set; performing calculation of the current neural network layer based on the activated neuron set and the weight data; in the process of performing calculation, determining an activated neuron set of a next neural network layer based on an intermediate result of calculation, and accordingly, pre-fetching weight data corresponding to the activated neuron set of the next neural network layer. According to the application, the activated neuron set of the next layer is determined in advance and the corresponding weight data is pre-fetched based on the intermediate result in the calculation process of the current layer, so that only the weight data related to the activated neuron needs to be loaded, the data access amount is reduced, and efficient inference is realized under the condition of limited bandwidth.
Owner:YOUDI ROBOT (WUXI) CO LTD

A method, device, electronic device and medium for processing commodity inventory data

The present invention is applicable to the field of artificial intelligence technology, and provides a commodity inventory data processing method, device, electronic device and medium. The method obtains the inventory of commodities to be purchased stored in a cache database, and if the purchase quantity of the commodities to be purchased is greater than the inventory of the commodities to be purchased, matches the substitute commodities; obtains the matching degree of the commodities to be purchased and the substitute commodities, determines the target commodities according to the matching degree, and generates a target order; obtains the inventory of the target commodities stored in the cache database according to the target order, and locks the inventory of the target commodities; if the payment status of the target order is paid, deducts the inventory of the target commodities according to the purchase quantity of the target commodities, unlocks the inventory of the target commodities, performs anomaly detection on the newly added inventory change data, and returns the deducted inventory of the target commodities to the client according to the detection result; and solves the problems of system congestion and inventory deduction failure under high concurrency conditions.
Owner:PING AN TECH (SHENZHEN) CO LTD

API request processing method, system and device and storage medium

The invention discloses an API (Application Program Interface) request processing method, system and device and a storage medium, which are applied to a cache management center and are used for reducing the dependence on a server, reducing the delay of the server and improving the user experience. The method comprises the following steps: acquiring an API request initiated by a micro-service application, wherein the micro-service application is formed by aggregating a plurality of single applications; judging whether target data requested by the API request is cached or not; if the target data is cached, sending the target data to the micro-service application; if the API request is not cached, sending the API request to a server; and caching the target data returned by the server in response to the API request.
Owner:JIALIAN PAYMENTS CO LTD

Time sequence database label management method

PendingCN119127886A
The invention discloses a time sequence database label management method which specifically comprises the following steps: S1, label definition: defining a plurality of labels for data in a time sequence database, each label comprising a label name and a label value; and S2, label storage: storing the defined labels in a label table of a time sequence database, wherein the label table comprises fields of label names, label values, data pointers, creation time and update time. According to the time sequence database label management method, labels are defined and updated according to actual requirements, service changes are adapted, a label table contains rich fields, the full life cycle of the labels is convenient to manage, data and label association modes are diversified, data classification is clearer, meanwhile, a flexible query interface is provided, a user can perform multi-dimensional query, and the user experience is improved. The data pointers are used for quickly positioning the data, the query efficiency is improved, the management strategy can be optimized through tag statistics, and the database performance is improved.
Owner:HEBEI NET NEW DIGITAL TECH CO LTD

Five-tuple matching method and device, computer equipment and readable storage medium

The invention relates to a quintuple matching method and device, computer equipment and a readable storage medium. The method comprises the steps that under the condition that a target quintuple of a to-be-processed message contains an internet protocol IP address, the IP address contained in the target quintuple is matched with a target IP filtering table to obtain an initial query address, the target IP filtering table stores the IP address associated with each IP matching rule table and the query address in a memory, and the initial query address is stored in the memory; the IP addresses of the quintuple matching rules associated with the same IP matching rule table are the same, determining a hierarchical query strategy of the target quintuple according to the quintuple information type contained in the target quintuple, and performing rule matching on the target quintuple by adopting the hierarchical query strategy and the initial query address. By adopting the method, the matching efficiency of the quintuple can be improved on the basis of reducing the access times of the memory.
Owner:DAWNING NETWORK TECH CO LTD

A multi-level flow table matching method and device based on Bloom filter

The present invention discloses a multi-level flow table matching method and device based on Bloom filter. The method comprises the following steps: obtaining a data frame of a computer network data flow to be matched, extracting key fields from the data frame to obtain the value of the key field; inputting the values ​​of matching keywords corresponding to each level of the flow table into a preset counting Bloom filter in order of priority from high to low for detection, until the detection is passed; matching the values ​​of matching keywords corresponding to the flow table that passes the detection with a preset multi-bucket hash table based on DDR, and outputting the matching result; the device comprises a frame processing module, a serial matching module, a counting Bloom filter and a DDR memory; the present invention adopts a DDR memory to store the multi-bucket hash table, thereby increasing the flow table scale supported by the matching circuit; adopting a Bloom filter when matching flow table items, thereby reducing the number of accesses to the off-chip DDR storage and improving the matching speed of the data frame.
Owner:ARMY ENG UNIV OF PLA

Buffer operation circuit for neural network, chip and computing device

The embodiment of the invention discloses a buffer operation circuit for a neural network, a chip and a computing device, and the circuit comprises a first preset number of operation units, a first preset number of buffer units, an input unit, an output unit and a memory. The input unit determines a window region to which each data included in the input tensor stored in the memory belongs; reading data in the input tensor from the memory and inputting the data into the corresponding arithmetic unit; the operation unit performs operation on the received data to obtain an operation result set, and inputs the operation result set into the corresponding buffer unit; and the output unit acquires the operation result set from the corresponding buffer unit when the operation of any operation unit is finished, and stores the operation result set as the data included in the output tensor into the memory. According to the embodiment of the invention, the storage efficiency of the buffer unit is improved, the access frequency of the memory is reduced, and the circuit can be suitable for tensors of various sizes, so that the universality of circuit application is improved.
Owner:NANJING HOUMO TECH CO LTD