63results about How to "Avoid caching" patented technology

A method for caching specified data in an n-way set associative memory with a copy-back update policy consists of the following steps. First, a row of the associative memory, organized as a plurality of rows and having n ways per row, is selected according to the main memory address of the specified data. The main memory provides primary storage for the data being cached. If one of the ways of the selected row holds invalid data, the specified data is cached in the way holding the invalid data and the data caching process is discontinued. If all n ways of the selected row hold valid data, the following steps are performed. First, a replacement strategy is used to select a way from the selected row. If the way selected in accordance with the replacement strategy holds unmodified data, the specified data is cached in the way selected by the replacement strategy and the data caching process is discontinued. However, if the way selected by the replacement strategy holds modified data, the ways of the selected row are examined again to find a way that holds data from the currently open page of the main memory. If such at least one such way is found, the specified data is cached in one of the ways holding data from the open page, and the data caching process is discontinued. Finally, if none of the ways in the selected row meet the above criteria, the specified data is cached in the way previously selected by the replacement algorithm, and the method terminates.

A PCI Express (PCIe) computer system utilizes address translation services to translate virtual addresses from I/O device adaptors to physical addresses of system memory. A combined memory controller and host bridge uses a translation agent to convert the I/O addresses via translation control entries (TCEs) in a TCE table (also known as an address translation and protection table). Some of the I/O device adaptors have address translation caches for local storage of TCEs. The TCE definition includes a new non-cacheable control bit which is set active in the TCE table when the TCE is in the process of being invalidated. The memory controller prevents further caching of the TCE while the non-cacheable control bit is active. A further implementation utilizes a change-in-progress control bit of the TCE to indicate that the TCE is in the process of being changed to allow simultaneous invalidation of the previously TCE information.

The invention concerns a method of displaying data on a client computer as well as a client computer and computer executable software code for data display on the client computer. The client computer retrieves a web page containing statical data of a graphical user interface and at least one inclusion for including the dynamic data of the web page, wherein said inclusion points to a program located at a network server and adapted to output a script. The client computer stores the web page in a cache memory. The script that contains dynamic data generated by the program is transferred from the network server to the client computer. A browser of the client computer includes the dynamic part into the static part of the web page by means of the dynamic data included in the retrieved script.

The present invention provides a decoding method for an enhanced uplink physical channel of a time division synchronous code division multiple access system. The method includes the following steps: when an enhanced uplink transmission time interval arrives, the user equipment determines the data type and resources transmitted in the current transmission time interval Multiplexing mode: the user equipment determines the transmission block length and modulation mode of the enhanced uplink service data according to the resource multiplexing situation and authorized power; the user equipment determines the physical layer control channel for this transmission according to the determined service data and resource multiplexing mode parameters; and the base station determines the total number of resources used by the user equipment according to the multiplexing indication in the physical layer control parameters, and combines the enhanced transmission format combination indication to obtain the modulation mode and transmission block length information of the service data part, and then demodulates and decodes . Therefore, without increasing the channel load, the buffering of channel data is avoided, the synchronous demodulation of the channel is realized, and the receiving efficiency of the channel is improved.

The invention relates to a streaming media transmission method on the basis of a UDP data transfer protocol. The method comprises the following steps: establishing a video file at a server side, wherein the video file comprises a plurality of data frames, and each data frame corresponds to a frame serial number and a frame timestamp; segmenting each data frame into a plurality of data packets or combining a plurality of the data frames into one data packet, wherein each data packet corresponds to a packet serial number and a packet timestamp; sending the data packets to a client side and recording the packet serial number and the packet timestamp of each data packet into a queue in an internal storage via the server side; detecting whether the data packets are lost via the client side, if yes, feeding back the serial numbers of the lost packets to the server side, and then finding out the corresponding packet timestamps via the server side according to the packet serial numbers in the queue; and according to the relation between the packet timestamps and the frame timestamps, finding out the corresponding data frames of the lost data packets, segmenting one data frame into a plurality of the data packets or combining a plurality of the data frames into one data packet and then sending the lost data packets to the client side.

Some embodiments provide an optimized multi-hit caching technique that minimizes the performance impact associated with caching of long-tail content while retaining much of the efficiency and minimal overhead associated with first hit caching in determining when to cache content. The optimized multi-hit caching utilizes a modified bloom filter implementation that performs flushing and state rolling to delete indices representing stale content from a bit array used to track hit counts without affecting identification of other content that may be represented with indices overlapping with those representing the stale content. Specifically, a copy of the bit array is stored prior to flushing the bit array so as to avoid losing track of previously requested and cached content when flushing the bit arrays and the flushing is performed to remove the bit indices representing stale content from the bit array and to minimize the possibility of a false positive.

The invention relates to a method realized by a parallel pipeline for performing real-time marking and identification on connected domains of a plurality of point targets, which comprises the following steps of: adopting a Gauss filter to carry out noise smoothing on images; providing an adaptive threshold calculation method so that a system can work in different light environments and under different target luminous intensities; aiming at the characteristics of the connected domains formed from the point targets, providing a scanning window for marking the connected domains; and establishing equivalence marks for mark conflict areas in the same connected domain, and performing weighted accumulation and accumulation again on gray scales of pixel positions to realize identification of centre-of-gravity positions of the targets when solving a mark conflict. The method realizes real-time marking and identification of the connected domains of the point targets in parallel by adopting a multi-level pipeline logical algorithm. The method has the advantages that: the method can perform real-time marking on the plurality of point targets in different light environments and identify two-dimensional positions of the targets in the images; only seven pixel clock delay is reserved between original image data and processing results; and identification precision is correct to sub-pixel level.

The embodiment of the invention provides a pupil positioning device and method, and a display driver of a virtual reality device. The pupil positioning device comprises a preprocessing circuit and a coordinate processing circuit, wherein the preprocessing circuit is used for preprocessing an eye image during an eye image transmission process, obtaining all boundary points of the eye image, and thecoordinate processing circuit is used for performing communication area processing on all boundary points, and determining the pupil center coordinates according to the maximum communication area. Aneye image is preprocessed in the data transmission process, the pupil center coordinates are determined by adopting a hardware communication region processing mode, and the large-data-quantity operation caused by delay is avoided. The processing speed is increased, the processing time is shortened, and the storage resources and the logic resources are saved. Hardware implementation is convenient,and the pupil positioning device is integrated in a display driver of a head-mounted virtual reality device.

The invention discloses a method and a device for mapping resource in a downlink control channel. The method comprises the following steps: sorting REG (Resource Element Group) in the downlink control channel; using the mapping address of PCFICH (Physical Control Format Indicator Channel) data in the downlink control channel and the mapping address of PHICH (Physical Hybrid Automatic Repeat Indicator Channel) data in the downlink control channel; endowing a sorted serial number to the PDCCH (Physical Download Control Channel) data in the downlink control channel; and according to the sequence of the serial number, obtaining the data in the downlink control channel corresponding to the serial number so as to map the resource in the downlink control channel. According to the method disclosed by the invention, the PDCCH data is cached, storage and time delay pressure are lowered.

The invention discloses a method and a device for transmitting message, and belongs to the communication field. The method comprises the following steps: tunnel bidirectional detecting message is utilized to acquire the minimum MTU of a GRE tunnel; the message is transmitted to the GRE tunnel according the MTU, or the message is transmitted to the GRE tunnel after being sliced. The device comprises an acquisition module and a transmission module. The invention utilizes the tunnel bidirectional detecting message to acquire the minimum MTU of the GRE tunnel, and determines whether to transmit the message directly or transmit the message to the GRE tunnel after being sliced according to the MTU, thereby guaranteeing the transmitted message in the GRE tunnel without the need to be sliced anymore and the exit edge node of the GRE tunnel without the need to reorganize the message, preventing the exit edge node from caching the un-complete slicing message, saving the resources of the exit edge node equipment and reducing the burden of the equipment. Besides, the forwarding node in the GRE tunnel is also not required to be sliced, thereby reducing the burden of the intermediate forwarding node.

The invention provides a decoding method of enhancing an uplink physical channel by a time division synchronous code division multiple access system. The decoding method includes the following steps: step S301, when an enhanced uplink transmission time interval comes, user equipment determines a data type and a resource multiplexing mode transmitted in the current transmission time interval; step S302, the user equipment determines the length of a transmission block and the modulation type of the enhanced uplink service data; step S303, the user equipment determines the physical layer control channel parameters of the current transmission; step S304, a base station determines the total number of resources used by the user equipment; and step S305, the base station combines enhanced transmission format combined indication to obtain part of the length of a transmission block and the modulation type of service data and then carries out demodulation and decoding; wherein, the data type includes a dispatching service data type and a non-dispatching service data type. In this way, under the condition of no increment of channel load, the invention can avoid the caching of channel data, realize the synchronous demodulation of the channel and improve the receiving efficiency of the channel.

The invention provides a method and a system for transmitting user data of a browser and the browser. The method for transmitting user data of the browser comprises the following steps of: acquiring request operation of transmitting the user data of the browser; generating a data request message according to the request operation and adding identification characters at a predetermined field in the data request message; and sending the data request message added with the identification characters to a server of the browser. According to the scheme adopted by the invention, when the user data is transmitted, the identification characters are added into the data generating message to distinguish the data generating message from other data requests, so that content corresponding to the user data request cannot be matched and obtained from a cache system, the buffer data cannot be returned, the finally obtained content is guaranteed to be data stored on the network, and inconvenience caused to the user due to stale data is avoided.

A web buffering method in a virtual machine environment is characterized by comprising the steps that the http connection of a virtual machine is intercepted through a virtual machine management program to obtain an http response data package of the http connection; a buffering identifier in the http response data package is obtained; whether the buffering identifier can be buffered or not is judged, if yes, the link address corresponding to the http response data package is obtained, data content of the http response data package is copied, and the extracted data content and the link address are correspondingly stored in a web buffering memory set by the virtual machine management program; the buffering identifier in the http response data package is set to be not capable of being buffered and is transmitted to a virtual machine corresponding to the http connection. In addition, the invention provides a web buffering device in the virtual machine environment. The web buffering method and device in the virtual machine environment can improve I/O efficiency.

The invention discloses a neural network accelerator. The neural network accelerator is used for being externally connected with a global control module, a first direct memory access module DMA and amemory. The neural network accelerator comprises a second direct memory access module DMA, a convolution module, a single data processing module, a plane data processing module, a channel data processing module and a probability calculation module which are connected in sequence in an assembly line mode; the convolution module performs multiply-add operation on the data; the single data processingmodule performs normalization, proportional operation and activation function processing; the plane data processing module performs maximum pooling, minimum pooling and average pooling processing; the channel data processing module performs channel splicing, surface rearrangement and matrix replacement processing; the probability calculation module finds out five maximum values in the data and completes probability operation of the five maximum values; the second DMA transmits the data to a convolution module; and the convolution module and the channel data processing module share one DMA control bus.

The invention discloses a method and a device of data obtaining. The method is applied to interconnection and interworking of a plurality of content distribution networks (CDNs). The method comprises that when a downstream CDN obtains content from at least one upstream CDN, a content identification list is inquired according to content identifications of the content, wherein the content identifications of all the content obtained by the downstream CDN are stored in the content identification list, and each piece of content only corresponds to one content identification; and when the content identifications of the content are not found in the content identification list of the downstream CDN, the content is obtained from the upstream CDNs. The method and the device of data obtaining can resolve the problem that downstream CDNs in correlation technique repeatedly obtain and cache the same content.

A client computer and a server computer communicate via HTTP. The client computer uses a standard HTTP-browser. Substantially simultaneously with establishing a session by allocating a resource at the server computer, the server computer sends a termination instruction to the browser. The instruction remains unexecuted in the browser during the whole session. In the event that the server computer terminates the session (such as upon unloading the instruction from the browser), the browser causes the server computer to de-allocate the resource.

The embodiment of the invention discloses a clearing method for mobile terminal cache, a device and a mobile terminal and relates to the technical field of a computer. The method is used for solving the problems that the cache clearing for the mobile terminal under a Windows Phone 8 operation system is uncontrollable, especially, the cache clearing cannot be performed when the storage space of the mobile terminal is not fully occupied. The method comprises the following steps: receiving a cache clearing instruction for the mobile terminal; acquiring the residual space capacity of the storage space of the mobile terminal; establishing a filling file in the storage space according to the residual space capacity; using the filling file for filling the residual space; clearing the cache file in the storage space by the system of the mobile terminal when the residual space capacity is less than a preset threshold value. The method provided by the invention is fit for the releasing of the storage space of the mobile terminal based on the Windows Phone 8 operation system.

The invention provides a decoder device of Time Division Synchronous Code Division Multiple Access system enhanced uplink physical channel. The device includes: a first determining unit used for determining a transmitted data type and a transmitted resource multiplex way in current transmission interval, a second determining unit used for determining a transport block length and a modulation way of a enhanced uplink business data according to a resource multiplex situation and a authorized power, a third determining unit used for determining a physical layer control channel parameter of current transmission according to the determined business data and resource multiplexing way, and a fourth determining unit used for determining a resource count used by the user device according to a multiplexing instruct of the physical layer control parameter, and obtaining a modulation way and a transmission block length information of the service data by combining with the enhanced transmission format assemble instruct and carrying out a decoder and a modulation. Therefore, the invention avoids a cache of the channel data without increase of channel burden, and realizes a synchronous decoder of the channel and enhances a receiving efficiency of the channel.

The present invention discloses a method and system for carrying out IO deduplication on non-homologous data of a storage system in the operation process, and relates to the field of data processing. The method comprises: S1, by a virtual machine, reading data and acquiring a characteristic code of the data; S2, determining whether the characteristic code of the data exists in a dedicated cache, proceeding to S3 if yes, and if not, proceeding to S4; S4, calling data which is stored in the dedicated cache and corresponds to the characteristic code of the data, and proceeding to S5; S4, calling data in an image file, which corresponds to the characteristic code of the data, and proceeding to S5; and S5, enabling the virtual machine to work by using the acquired data. The system comprises: a physical machine system module, a physical machine caching module, a virtual machine image file module and a virtual machine system module. The method and system provided by the present invention solve the problem that when a plurality of virtual machines simultaneously read respective image files, a server system cache is easy to reach a bottleneck.

Protected publication of sensitive documents with authentication and accountability enables storing and sharing confidential files, while reducing risk that a recipient will distribute and share the file information with unauthorized recipients. Every user request for an original file generates a unique provided file based on the original file, the user request, and configuration information. The provided file has characteristics that make the provided file based on a first user request unique from any other provided file based on any other user request. Unique characteristics include changing the format of the original file to another format for the provided file, altering file properties, altering file content, and watermarking.

The application provides a data transmission method and device. The method includes the following steps: determining a data stream mapped to a data radio bearer (DRB); and controlling the transmissionrate of the data stream based on a transmission rate of the data stream and a first rate threshold of the data stream. According to the data transmission method and device provided by the application, the transmission rate of the data stream mapped to the DRB can be controlled.

The invention discloses a real-time satellite-borne SAR processing device and method. The device comprises a first FPGA, second FPGA, an SOC, a first DDR2, a second DDR2, a third DDR2, a first SRAM and a second SRAM. An improved RD or CS imaging algorithm is selected as the real-time satellite-borne SAR processing method, and a data preprocessing and imaging algorithm is realized through two stages of processing. Through methods such as staged processing, FPGA synchronous pipeline computation and parallel transposition access, homemade and aerospace-level processing chips with relatively low performance can satisfy the performance requirements of real-time satellite-borne SAR processing.