91results about How to "Make the most of your bandwidth" patented technology

The present invention provides a testing circuit and a testability design method thereof for an on-chip multinuclear processor; wherein, the testing circuit comprises a testing shell register chain, a chip core connecting circuit waiting to be tested, an on-chip data path connecting circuit and a control logic circuit. The chip core connecting circuit waiting to be tested is an interconnection circuit, which is connected between the testing shell register chain and the chip core waiting to be tested. The on-chip data path connecting circuit is the interconnection circuit which is connected between the testing shell register chain and the on-chip data path. The control logic circuit controls the data flow direction of the chip core connecting circuit waiting to be tested and the on-chip data path connecting circuit. The present invention conducts an optimum design according to the characteristics of the on-chip multinuclear processor. The bandwidth of the on-chip data path is fully used. The testing cost is reduced and the amount of a transmission data packet in the on-chip data path is reduced. So an extra power spending caused by mass active data packet is greatly reduced and the testing time is greatly shortened.

The invention discloses a PCI interface protocol based array expandable data collection system realized by adopting an FPGA (field programmable gate array). The system comprises a plurality of identical analog signal collection boards. Each of the boards comprises a controller module, a multipath ADC module, a power supply module and a PCI bridging chip, wherein the controller module is composed of an FPGA chip and an SRAM chip, and used for controlling the sampling process, generating between-board bus signals and controlling caching and transmission of data; the multipath ADC module is composed of 64 paths of single-path ADC modules with the same structure, and used for converting analog signals into digital signals and transmitting the data to the controller module; the power supply module is composed of two identical power supply sub-modules, and used for providing stable and low-noise power for the chips; and the PCI bridging chip is used for realizing communication between the analog signal collection boards and an upper computer through a PCI bus. The PCI interface protocol based array expandable data collection system realizes sampling control of a multipath ADC and control of data flows by using the FPGA, and greatly increases the flexibility and the reliability of the design.

The invention discloses an automatic wavelength tuning method and an automatic wavelength tuning system based on a TWDM-PON (time wavelength division multiplexing-passive optical network). The method includes: adding a multi-wave MAC (media access control) control sublayer on a multipoint MAC control sublayer of an EPON (Ethernet passive optical network) protocol stack to coordinate load balance of multiple wavelength pairs, and the multi-wave MAC control sublayer works in TDM (time division multiplexing) domains of all wavelengths. The multi-wave MAC control sublayer is specifically used for assigning at least one logical link identifier for optical network units when the optical network units are registered, binding one of the logical link identifiers with MAC addresses of the optical network units, and scheduling the registered optical network units on the wavelength pairs with the least number of the optical network units. By the aid of the automatic wavelength tuning method and the automatic wavelength tuning system, mutual coordination among the wavelength pairs can be achieved, the bandwidth of the whole system is fully used, and load balance among the wavelength pairs can be realized.

The invention provides a page downloading control method and a page downloading control system for an IE (Internet Explorer) core browser. The method provided by the invention comprises the following steps of: starting an IE core browser process and starting a preset downloading process; registering a communication protocol in the IE core browser process and waiting a page downloading request based on a corresponding communication protocol; when the IE core browser process receives the page downloading request, transmitting the page downloading request to the downloading process; acquiring, by the downloading process, file size information corresponding to the page downloading request; when the file size information exceeds a preset file size threshold value, executing downloading operation of a corresponding page by using a multi-thread downloading mode; and returning, by the downloading process, downloading state information to the IE core browser process in a page downloading operation process. Through the method and the system, a page downloading process of the IE core browser can be effectively controlled, so that the efficiency and the stability of page downloading are improved.

The invention discloses a link load balancing method and a link load balancing device. The method comprises the following steps: receiving a DNS (domain name server) request message by the link load balancing device; requesting a first class IP address of an external network server to a DNS; requesting a second class IP address of the external network server to the DNS; recording a corresponding relation between the first class IP address of the external network server and the second class IP address of the external network server in an equivalent service table by the link load balancing device; receiving a business request message by the link load balancing device, wherein the destination IP address is the first class IP address of the external network server; and when the second class IP address corresponding to the first class IP address of the external network server exists in the equivalent service table, selecting an ISP (internet service provider) link from the ISP link based on the first class IP address and the ISP link based on the second class IP address by the link load balancing device. With the adoption of the link load balancing method and the link load balancing device provided by the embodiment of the invention, the load balancing between the ISP link based on an IPv4 address and the ISP link based on an IPv6 address is realized, and the bandwidth of the ISP link is fully utilized.

The embodiment of the invention provides a file uploading method and device and a file recombination method and device. The file uploading method comprises the following steps: sending a file uploading request to a service server, receiving object information which is sent by the service server and respectively corresponds to each cloud server, fragmenting a target file, obtaining fragmented files, distributing fragmentation identifiers to the fragmentation files; for each cloud server, sending at least one fragmented file, object information corresponding to the cloud server and the fragmentation identifier of the at least one fragmented file to each cloud server in parallel through an uploading channel corresponding to the cloud server, one object identifier corresponds to one uploadingchannel, and when the number of the cloud server is one, a plurality of fragmented files are sent to the cloud server in parallel; and when the number of the cloud servers is more than one, at least one fragmented file is sent to the cloud servers in parallel. Therefore, the bandwidth of a client is fully utilized to a certain extent, and the file uploading speed of the client is increased.

The invention discloses a file distribution system and a file distribution method based on IPFS, wherein a console is used to be provided to file distribution user for file distribution, a schedule system manages a plurality of area management nodes, and controls the scheduling of file distribution tasks, selectively deliveries the file distribution tasks to the zone management node managed by theschedule system, an area management node is responsible for downloading the files that need to be distributed, uploading to IPFS, addressing of file resources, and distribution of file distribution tasks to some edge nodes in the region. The edge nodes are used for receiving the file distribution tasks from the area management node where the edge nodes are located, downloading files, providing CDN services, and continuing to distribute file distribution tasks in a point-to-point manner. The file distribution system and the file distribution method of the invention combine the comprehensive advantages of the cloud and the edge equipment, and improve the file distribution efficiency through a point-to-point transmission protocol.

The present invention provides a method for adjusting modulating/coding mode based on CINR with a self-adapting mode. The method comprises the following steps: computing multi-frame average value of CINR measured value, eliminating the abnormal value of CINR measured value according to the multi-frame average value, and using the average value of residual frames which are eliminated with abnormal values as CINR statistic; preventing the fluctuation of chosen modulating/coding mode between the CINR threshold junctions corresponding to two adjacent grade modulating coding modes when the modulating/coding mode of each grade is respectively provided with an exit threshold CINR_THfloor which is switched to low stage, a least entering threshold CINR_THin and an exit threshold CINR_THceiling that is switched to high stage and the switching area between the modulating/coding modes of adjacent grades; and dynamically adjusting the CINR threshold corresponding with each modulating/coding mode according to the block-error rate BLER. Thereby the system stability and communication quality are ensured when the bandwidth is fully used and the spectrum efficiency is increased.

The embodiment of the invention discloses a load sharing balance method and device for physical ports, and a link aggregation system. The load sharing balance method comprises the following steps: determining that load sharing among physical ports on other positions is uniform through a position of the physical port affecting load sharing in a forwarding table in a link aggregation group through first Hash calculation; then determining the specific position and range of the physical port for forwarding data through secondary Hash calculation, so as to ensure that the physical port which is selected from the determined physical ports in the forwarding table is used for forwarding data in the data forwarding process, thus ensuring load share balance of the flow of each physical port in the link aggregation group added in the data forwarding process. The purposes of data forwarding balance and sufficient utilization of bandwidth of the physical ports are achieved.

The invention relates to a logging method used in a distributed environment, and the method comprises the following steps: configuring a log server and a log strategy of a client; sending logs of the client to the log server in real time; and storing the logs received by the log server according to the log strategy. According to the logging method disclosed by the invention, high-concurrency and high-capacity log services can be provided. Simultaneously, a system is easy to expand and can meet various different requirements. The logging method disclosed by the invention has no limitations on language of the client and can meet the requirements of various environments. In addition, the bandwidth can be fully utilized by using the logging method.

The invention provides a page downloading control method and system for an IE (Internet Explore) kernel browser. The method comprises the following steps of: starting an IE kernel browser process and a preset downloading process; registering communication protocols in the IE kernel browser process, and waiting for page downloading requests based on corresponding communication protocols; when the IE kernel browser process receives the page downloading requests, transmitting the requests to the downloading process; adding the page downloading requests to a pre-generated downloading task list byusing the downloading process; acquiring page resource types corresponding to the page downloading requests, and sequencing the page downloading requests according to the page resource types in the downloading task list; and sequentially processing the page downloading lists in the downloading task list, executing corresponding page downloading operations and returning downloading state information to the IE kernel browser process. By the method and the system, the page downloading process of the IE kernel browser can be effectively controlled, and page downloading efficiency and stability can be improved.

The invention provides a page downloading control method and a page downloading control system for an IE (Internet Explorer) core browser. The method provided by the invention comprises the following steps of: S1, starting an IE core browser process and starting a preset downloading process; S2, registering a communication protocol in the IE core browser process and waiting a page downloading request based on a corresponding communication protocol; S3, when the IE core browser process receives the page downloading request, transmitting the page downloading request to the downloading process; S4, judging, by the downloading process, whether a requested file is previously written into a cache according to the page downloading request; if so, executing an S5; otherwise, executing S6, S7 and S8; S5, extracting the file from the cache; S6, downloading the corresponding file from the server according to the page downloading request; S7, returning downloading state information to the IE core browser process in a downloading process; and S8, writing the downloaded file into the cache. Through the method and the system, a page downloading process of the IE core browser can be effectively controlled, so that the efficiency and the stability of page downloading are improved.

The invention provides a page downloading control method and system of an IE (Internet Explorer) kernel browser, wherein the method comprises the following steps of: starting an IE kernel browser process, and starting a preset downloading process; registering a communication protocol in the IE kernel browser process, and waiting for a page downloading request which is based on corresponding communication protocol; when the IE kernel browser process receives the page downloading request, triggering the downloading process to control the page downloading procedure according to the preset downloading rule, and returning back downloading state information to the IE kernel browser in the page downloading procedure. With the method and the system provided by the invention, the page downloading procedure of the IE kernel browser can be controlled effectively, and the efficiency and the stability of page downloading are improved.

The invention comprises: at least one test enclosure register chain used for testing the core to be tested; an interconnection circuit for connecting said test enclosure register chain to the core to be tested; an interconnection circuit for connecting said test enclosure register chain to the external data channel. The invention also reveals a method for designing the test enclosure circuit.

The invention discloses a multi-core DSP (digital signal processor) motion estimation-oriented data prefetching method. According to the method, data of a coding block and a reference block are prefetched to a local storage according to the space relevancy of data in motion estimation and the data of a prediction motion vector prefetching coding bock and the reference block, so the parallel performing between the motion estimation operation of the current coding block and the data loading operation of the next code block and the reference block are realized, the influence of the storage to the speed of a multi-core processor in the motion estimation is reduced, and tests prove that the data prefetching method enables the motion estimation processing speed in the multi-core DSP parallel video coding to be obviously improved.

The invention discloses a negotiation coding resolution method used for video communication and a system thereof. The negotiation coding resolution method used for the video communication is characterized in that a calling terminal carries out pre-negotiation with a called terminal; when the calling terminal and the called terminal support the coding resolution negotiation, the calling terminal and the called terminal carry out the negotiation by using a maximum coding and decoding resolution which can be supported by a side; if a maximum coding resolution of the calling terminal is not greater than a maximum decoding resolution of the called terminal, the calling terminal uses the coding resolution corresponding to sending data to carry out coding processing on the sending data so as to generate a media stream and the media stream is sent to the called terminal, and the called terminal uses coding resolution information specifically adopted by the calling terminal to carry out decoding on the media stream. Therefore, two parties of communication can establish video communication with different resolutions according to a specific condition of a network side, and service quality of the video communication and a communication experience of a user can be increased.

The invention relates to a the field of automatic optical detection technology of TFT-LCD panels, and particularly relates to a method and a device for carrying out two-dimensional Fourier transform and inverse transform on an image. The method comprises the following steps: extracting a row of picture data from an A area of an external memory at one time, carrying out one-dimensional Fourier transform and inverse transform, and storing operation results in a B area of the external memory in sequence, until the one-dimensional Fourier transform and inverse transform of the entire picture is finished; partitioning the image data in the B area of the external memory, extracting an image from the B area of the external memory according to a row direction at each time, storing the image in a random memory, overturning the interiors of the image blocks, and writing the image blocks in the A area of the external memory according to a column direction in sequence; and repeating the process until the two-dimensional Fourier transform and inverse transform of the entire picture is finished. The image blocks are overturned and are the interiors of the image blocks overturned, so FPGA resource consumption is few, and image data reading and writing efficiency is high.

The invention discloses a method and system for data communication between cluster system devices. The number of GPUs in each node is obtained, all the GPUs in each node are numbered, the calculation results of the GPUs are partitioned, all result data blocks are numbered according to the GPUs, each GPU sends the corresponding result data blocks to other GPUs according to the serial number of the data blocks, each GPU renews data in the nodes through a first preset rule according to the corresponding result data blocks at the moment and the result data blocks sent by other GPUs, the target GPU in each node conducts agreement stipulation operation on the GPUs, corresponding to the target GPU, in other nodes, data between the nodes are renewed according to a second preset rule, each GPU distributes the corresponding renewed result data blocks to other GPUs in the corresponding node, and each GPU processes one data block. The system network bandwidth is fully used, the loads of the GPUs are balanced, and the data communication between the GPUs can be efficiently achieved.

The invention provides an Er-Tm-Nd co-doped fiber ultra wideband light source which comprises a pump laser, a pump coupler and an Er-Tm-Nd co-doped fiber. The Er-Tm-Nd co-doped fiber is the fiber mixed with three rare earth ions of Er, Tm and Nd. The pump laser, the pump coupler and the Er-Tm-Nd co-doped fiber are successively connected. Pump light sent from the pump laser enters the Er-Tm-Nd co-doped fiber through the pump coupler, and broadband light is emitted from an output end. The invention has beneficial effects as follows: the structure is simple and easy to realize; and through appropriate selection of copping concentration of the three rare earth ions of Er, Tm and Nd and fiber length, broadband optical fiber covering all wave optical fiber low-loss window can be obtained so as to bandwidth of all wave optical fiber.

The invention discloses a picture storage method and device, a query method and device and an access system. the picture storage method comprises: using a Hash transformation method, generating a KEYvalue according to the spatial position and the generation time of the picture; integrally storing the picture data of the picture in a cache queue corresponding to the KEY value; the same or different KEY values can be generated according to the picture data of other pictures received in the timing period of the timer; and storing each picture data into a cache queue corresponding to the KEY value, writing the cache queue into a storage device group with a serial number of KEY value in a form of a drop disk file after the timing period is finished, and generating an index file convenient forquerying the picture. The bandwidth utilization rate of the storage device group can be effectively improved.

The invention discloses a method for processing virtual concatenation group (VCG) overtime delay, which comprises the following steps of: obtaining a multiple frame indication (MFI) and a multiple frame relay (PTR) of each member in the VCG getting to a destination end according to a multiple frame header of a virtual container (VC) in a synchronous digital hierarchy (SDH); and comparing the obtained MFI and PTR of each member, obtaining a time delay comparison result, feeding a member state territory (MST) back to a source end by each member in the VCG taking the serial-number identifier (SQ) thereof as a symbol according to the time delay comparison result, temporarily deleting a member having overtime delay by the source end, and restoring a complete data stream by the destination end. The invention also discloses a device for processing the virtual concatenation group overtime delay, which comprises a multiple frame header extracting unit, a latch unit, a time delay comparing unit, an MST feedback unit and an overtime delay processing unit. The method and the device can guarantee that the destination end can restore the complete data stream when an overtime delay member exists in the VCG.

The invention discloses an access control method and an access control device. The method comprises the following steps of: calculating the average physical bandwidth used for new traffic stream in each frame; determining whether the calculated physical bandwidth meets the requirement of the physical bandwidth required by QoS minimum preset speed of the new traffic stream or not; accessing the new traffic stream when the new traffic stream belongs to real-time service, the calculated physical bandwidth meets the requirement of the physical bandwidth required by QoS minimum preset speed of thenew traffic stream, and the requirements of the new traffic stream and QoS maximum time delay of the connected real-time traffic stream are met; otherwise, rejecting accessing the new traffic stream.The access control method and the access control device meet the requirement of the QoS minimum preset speed of the traffic stream accepted by the system, and meet the requirement of the QoS maximum time delay of the real-time service accepted by the system on the premise of fully utilizing the system bandwidth resources.