7results about How to "Reduce copy" patented technology

The invention provides a service grid message acceleration processing method, device and system and a DPU (Data Processing Unit), and the method comprises the steps: determining that an application layer message type to which a target application layer message currently received in a protocol stack of the DPU belongs is marked as acceleration processing; if yes, performing service processing on the target application layer message in a protocol stack based on service configuration information corresponding to the application layer message type to which the target application layer message belongs; and sending the target application layer message to a target application layer message buffer area which is preset in a protocol stack and corresponds to the sending end buffer area, so as to forward the target application layer message in the target application layer message buffer area based on a network communication protocol. According to the method and the device, the service of the service grid Sidecar agent module can be sunk to the protocol stack, the interaction overhead between the protocol stack and the service grid Sidecar agent module can be effectively reduced, and the forwarding efficiency of the service grid message can be improved.

This disclosure provides a data transmission method, apparatus, device, and medium. The method includes: acquiring data to be transmitted from a first application; transmitting the data to be transmitted to a second application of a display device via a target server in a remote procedure call (RPC); wherein the target server is one of the servers in the RPC.

The invention provides a memory use method and device, equipment and a medium, relates to the technical field of storage systems, and is applied to a distributed storage system.The method comprises the steps that after business processing services are started, a corresponding shared memory object is created for each business processing service; when data interaction needs to be carried out, establishing a link between the business processing service and the business request service; based on first network card information of a first physical node where the business processing service is located and second network card information of a second physical node where the business request service is located, whether the first physical node and the second physical node are the same physical node or not is judged; and when the nodes are the same physical node, performing data interaction by using the shared memory object. The copying of data interaction between the business request service and the business processing service deployed in the same physical node is reduced, and the copying by using a memory of a network card is not needed, so that the performance of the distributed storage system is improved.

The invention relates to the technical field of VR screen projection, and provides a VR display method of a 2D application and VR equipment, which are used for realizing immersive viewing of the 2D application. According to the method, the left eye image and the right eye image are respectively created according to the width and the height of the eye buffer area, and data sharing is performed on the image buffer data of the to-be-displayed 2D application, so that the left eye image and the right eye image are rendered by a synthesizer in a cross-process mode, the data copying process is reduced, the rendering display efficiency is improved, and the display effect is improved. Meanwhile, the left eye image and the right eye image are ensured to be complete 2D application images; moreover, the display positions of the left-eye image and the right-eye image relative to the viewer are respectively calculated through the six-degree-of-freedom head pose and the eye interpupillary distance, so that the left-eye screen and the right-eye screen are rendered and displayed by using a single buffer area according to the corresponding display positions, and compared with double buffer areas, the rendering display efficiency is further improved, and the rendering display time delay is reduced.

The invention provides a method for reducing driver memory copy in a data transmission process and a device driver, the method is applied to a Ubuntu platform, and relates to the technical field of software storage, the method comprises the following steps: creating a memory pool used for carrying out data transmission with a video device driver on an application layer of the video device driver, and arranging a plurality of memory blocks in the memory pool; initializing a video equipment driver, acquiring a plurality of memory blocks from the memory pool, respectively serving as a plurality of buffer areas to be listed in a buffer area queue of the video equipment driver, acquiring a target buffer area from the buffer area queue by the video equipment driver, acquiring a physical address of the buffer area, and storing corresponding image data to the buffer area according to the physical address; obtaining a buffer area in which data storage is completed through an application layer driven by the video equipment, and transmitting the buffer area to an application process; and after the application process is used, returning the buffer area to the memory pool. According to the invention, unnecessary drive memory copying is reduced, and the data transmission efficiency and the system performance are improved.

The present invention provides a document generation method, device and electronic device, wherein a preset development tool obtains template configuration data of each original file from a cloud server based on RDMA technology; generates a document template corresponding to each original file based on the template configuration data; obtains the first key content data corresponding to each original file, and generates a file conversion task corresponding to each original file based on the original file type and converted file type corresponding to each original file and the obtained first key content data and document template; and a distributed platform executes the obtained file conversion tasks in parallel to convert each original file into a corresponding document with a converted file type. The present invention can alleviate the problems of low efficiency and poor precision of file format conversion in related technologies.

This invention relates to the field of data processing technology, providing a log processing method and system. The method includes: recording the location information of sub-variables that need to be compressed in a log block as key positions and corresponding metadata of the encoded stream into a preset data structure based on a preset template; compressing the log block into different storage units based on the preset data structure; locating the storage unit corresponding to the search keyword based on the distribution of the location vectors corresponding to each log block on the location matrix, and completing the retrieval of log entries based on the matching result of the search keyword and the storage unit, where the location vector is the matching result of the search keyword and the decompressed preset template. This invention efficiently extracts dynamic patterns from logs through preset templates and stores log data as fine-grained units, thereby improving log compression bandwidth; it uses vectorization technology to achieve low-latency retrieval of fine-grained units, thus providing effective support for log analysis and system modeling.