57 results about "Processor node" patented technology

The invention discloses a cache consistency state maintenance method and device, a multi-core processor and a server, and relates to the field of multi-core processors, the method is applied to the multi-core processor, and the method comprises the following steps: a local processor node obtains a local cache consistency maintenance message; wherein the local processor node is any processor node in the multi-core processor; determining a target directory from an exclusive directory and a shared directory according to a cache consistency state of a target cache line corresponding to the local cache consistency maintenance message; wherein the target directory is an exclusive directory or a shared directory; searching a target directory entry from the target directory, and adjusting the target directory entry; according to the method, the cache consistency catalog is divided into the exclusive catalog and the shared catalog, the exclusive catalog is used for recording the exclusive node information of the exclusive data, and the shared catalog is used for recording the shared node information of the shared data, so that the scale and resource occupation of the cache consistency catalog are reduced, and the query speed and efficiency of the catalog are improved.

The embodiment of the invention provides a server, a computer system and a multi-node management method, the server comprises a processor node and a connection node, the processor node comprises a plurality of processors and a first controller, and the connection node comprises a plurality of cable groups; the connection node is used for connecting reference equipment and providing multiple groups of data links for performing data transmission with the reference equipment for the multiple processors through the multiple cable groups; the first controller is used for establishing a corresponding relationship between the plurality of groups of data links and the plurality of cable groups; and in the process of data transmission between the plurality of processors and the reference equipment, detecting a target cable group with a fault from the plurality of cable groups according to the corresponding relationship and the fault state of each data link in the plurality of groups of data links. According to the method and the device, the problem that the efficiency of positioning the faulted cable group is low is solved, and the effect of improving the efficiency of positioning the faulted cable group is further achieved.

The invention discloses an NUMA scheduling method and device in a large model training scene, equipment and a medium, and relates to the technical field of artificial intelligence, and the method comprises the steps: collecting a target cluster topological relation configuration file; obtaining a target affinity strategy corresponding to the graphics processor demand of the current large model training task, and if the target affinity strategy is a first affinity strategy, screening out candidate processor nodes including candidate NUMA nodes from the processor nodes based on the topological relation configuration file, the candidate NUMA nodes are the NUMA nodes of which the idle number of the graphics processor meets the requirements of the graphics processor under a single NUMA node, and determining a target NUMA node from the candidate NUMA nodes according to the performance communication score of each candidate NUMA node; and when the training container is started, scheduling each graphics processor under the target NUMA node to complete a current large model training task. The efficiency of large model training is improved, and the cost is reduced.

The invention discloses a server, a plurality of graphics processor nodes are arranged in a first cabinet, the plurality of graphics processor nodes are vertically stacked in sequence, a plurality of switching nodes are arranged in a second cabinet, the plurality of switching nodes are horizontally stacked in sequence, and the graphics processor nodes are connected with the switching nodes. The technical problem that the reliability of the server is poor can be solved, the difficulty of installation and maintenance is reduced, the integrity of signal transmission is improved, and the reliability of the server is improved.

The invention relates to a modeling and formalized verification method for cache consistency protocol verification, and the method comprises the steps: building a protocol model which comprises a plurality of processor nodes, directory nodes and a communication mechanism through a structured modeling mode, and constructing an asynchronous message mechanism to simulate disordered concurrent communication; protocol behavior rules such as processor requests, directory responses and network receiving are defined, protocol property invariants are set, semantic constraints such as data consistency, confirmation before writing and sharing state legality are covered, model verification is carried out in a state space traversal mode, breadth-first search and a symmetry recognition mechanism are supported, and the method is suitable for the protocol behavior rules. A protocol error or deadlock state is effectively found, a traceable error path is generated, a verifier can automatically generate source codes through a compiler and operate on a host platform, and rapid verification and result output of a protocol model are achieved. The method has good protocol adaptability and model reusability, and is suitable for formalized verification of various cache consistency protocols.

The embodiment of the invention provides a server. Relates to the technical field of computers. Comprising a first cabinet, a second cabinet, a plurality of graphics processor nodes, a power supply node, a plurality of switching nodes and a plurality of central processing unit nodes, the plurality of graphics processor nodes and the power supply node are arranged in the first cabinet, and the plurality of graphics processor nodes and the power supply node are arranged in the first cabinet in a stacked mode; the plurality of switching nodes and the plurality of central processing unit nodes are arranged in the second cabinet, and the plurality of switching nodes and the plurality of central processing unit nodes are vertically arranged in the second cabinet; the power supply node is connected with each graphics processor node, each switching node and each central processor node; for any one graphics processor node, the graphics processor node is connected with each switching node and the central processing unit node. According to the method provided by the embodiment of the invention, the computing power density of the server can be increased under the condition of the same computing power.

The subject matter of this specification can be embodied in, among other things, a method that includes receiving, by a first memory switch of a first processor node, data from a first on-chip memory of the first processor node, wherein the first processor node comprises a first processor circuit, receiving, by a first photonic transceiver, the data from the first memory switch, transmitting, by the first photonic transceiver, the data over a photonic link, receiving, by a second photonic transceiver, the data from the photonic link, transmitting, by the second photonic transceiver, the data to a second memory switch of a second processor node comprising a second processor circuit, wherein the second photonic transceiver is in electrical communication with the second memory switch in parallel with the second processor circuit, and storing, by the second memory switch, the data in a second on-chip memory of the second processor node.

Examples described herein relate to multiple processor nodes which are physically separate with interfaces to a common network interface. A local processor can run a timing recovery algorithm, and tune the master timer to align with the network domain to cause the master timer and network timing domains to be in the same domain. A common master timer can be used to align time stamps of independent processor nodes. A processor node can use the common master timer as a reference and the processor does not need to communicate with another processor to synchronize its timer.

Methods and systems are described herein for adaptive beamforming and interference mitigation using a time synchronized scalable cohered on-array processing system (“system”). The system may be a phased array implementing a software-defined radio using multi-input-multi-output antenna elements. The system includes multiple subarray elements which are configured into a tiered array of scalable subarrays that performs intermediary collation, coherence, noise reduction, and adaptive beamforming operations through processor nodes disposed between tiers. The intermediary collation operations process discrete portions of node excitation data to enable the phased array to generate an adaptive beam profile that directs high-directionality beams toward desired targets while adaptively partitioning interference sources between subarray elements. Further, the system makes use of a scalable multidimensional array to provide telecommunication and electromagnetic wave manipulation operations for applications of varying scale.

The invention provides an orthopedic surgery robot remote surgery control method, system and device and a computer readable storage medium. The method comprises the following steps: a local master control end receives a feedback data packet sent by a remote master control end through a wireless communication network, and records a data packet receiving timestamp and a data packet receiving duration; calculating a data packet transmission delay duration according to the data packet sending timestamp and the data packet receiving timestamp; if the data packet transmission delay duration is less than the data packet receiving duration, the local master control terminal dynamically allocates processor nodes with idle resources to receive and process the data packet; and in response to the operation of the local user, the local master control terminal sends a control instruction to the remote master control terminal through the wireless communication network so as to control the orthopedic surgery robot to perform surgery. According to the embodiment of the invention, the orthopedic surgical robot can be remotely controlled with lower delay.

The invention discloses a double-target cloud workflow scheduling method under an edge heterogeneous cluster, which constructs a double-target optimization model aiming at an edge heterogeneous cluster application scene, and maximizes the service quality while satisfying the energy consumption constraint. A scheduling algorithm based on distributed mixed integer programming is designed on the basis of decomposition of an original problem, energy consumption and service quality are optimized according to processor node characteristics and load conditions, and scheduling of an edge heterogeneous cluster is achieved. The edge heterogeneous computing cluster scheduling can be effectively balanced in the aspects of multi-objective optimization, heterogeneous resource adaptation, real-time performance, dynamic performance and the like, so that an efficient computing solution is provided for the fields.

The invention discloses an interconnection network independent set construction method and device, equipment and a readable storage medium, and relates to the technical field of computers. The construction method of the interconnection network independent set comprises the steps that the network dimension n of an initial folding segmentation and exchange cube network (FDSCn) is obtained, the node mark number of each processor node in the initial folding segmentation and exchange cube network (FDSCn) is created, n = 2d, and d is larger than or equal to 1; dividing the initial folding segmentation and exchange cube network (FDSCn) into a plurality of target folding segmentation and exchange cube networks (FDSC2) according to the network dimension n and the node label; a processor node is extracted from each target folding segmentation and exchange cube network (FDSC2) to form an independent set of an initial folding segmentation and exchange cube network (FDSCn), and the processor nodes in the independent set are not adjacent to each other. According to the scheme, communication conflicts between processor nodes are reduced, and the overall stability and reliability of an interconnection network are improved.

The invention provides a cluster computing resource isolation method and device, electronic equipment and a storage medium, and relates to the technical field of cluster computing resource management. And scheduling the containerized task to an adaptive physical graphics processor node based on the information, intercepting a resource access request during task operation, allocating an isolated video memory space and a computing context according to an allocated virtual graphics processor resource limit, and dynamically maintaining an isolated state of multiple tasks, so that the task access efficiency is improved. The problems of inter-task interference, limited hardware compatibility, insufficient resource allocation flexibility and low utilization rate caused by lack of a flexible virtualization scheme for decoupling from hardware and imperfect resource scheduling and isolation mechanisms in the prior art can be solved.

The present application discloses a server. A plurality of graphics processing nodes are arranged in a first cabinet and are vertically stacked in sequence. A plurality of switching nodes are arranged in a second cabinet and are horizontally stacked in sequence. Among them, the graphics processing nodes are connected to the switching nodes. Therefore, the technical problem of poor reliability of the server can be solved, the difficulty of installation and maintenance can be reduced, and the integrity of signal transmission can be improved, thereby improving the reliability of the server.

The invention discloses a client design method for a large-capacity new energy station monitoring system, and the method comprises the steps: obtaining an analysis result of the features of a new energy station, and storing the analysis result; performing multi-thread design according to the analysis result, and monitoring a data state in multiple threads by utilizing a channel management mode based on a shared memory; performing first judgment on the parameters for counting the channel state to obtain the channel state, and if the channel cannot reestablish the connection, transferring the front node to which the channel belongs; and carrying out second judgment on the to-be-associated device and the front-end processor node to which the to-be-associated device belongs to obtain a second judgment result, and carrying out dynamic load distribution according to the second judgment result, thereby providing a new solution thought for improving the load capacity and realizing transplantable and cross-platform application information interaction in the field of grid-connected control of the new energy station.

Methods and systems are described herein for adaptive beamforming and interference mitigation using a time synchronized scalable cohered on-array processing system (“system”). The system may be a phased array implementing a software-defined radio using multi-input-multi-output antenna elements. The system includes multiple subarray elements which are configured into a tiered array of scalable subarrays that performs intermediary collation, coherence, noise reduction, and adaptive beamforming operations through processor nodes disposed between tiers. The intermediary collation operations process discrete portions of node excitation data to enable the phased array to generate an adaptive beam profile that directs high-directionality beams toward desired targets while adaptively partitioning interference sources between subarray elements. Further, the system makes use of a scalable multidimensional array to provide telecommunication and electromagnetic wave manipulation operations for applications of varying scale.

The present application discloses a processor system, which relates to the field of computer technology. The system includes a processor node, a scheduler, and a system storage space with a third task set constructed. The processor node includes: a processor and a node storage space; a scheduler for screening a reference processor from the processor; screening a target task set from a candidate task set based on the task volume information of the reference task set, wherein the reference task set is a first task set in the processor storage space possessed by the reference processor, and the candidate task set includes: a reference task set, a second task set in the processor node where the reference processor is located, and a third task set; distributing the reference task to the target task set; and a reference processor for executing the tasks stored in the candidate task set. Through the present application, the technical problem of low processing efficiency of read and write requests in the related art is solved, and the technical effect of improving the processing efficiency of read and write requests is achieved.

The application discloses a network topology acquisition method and device, equipment and medium, and relates to the field of distributed heterogeneous computing systems. The dynamic host configuration protocol client integrated in the network communication module of each graphics processor node obtains the internet protocol address of the corresponding graphics processor node from the pre-stored multiple internet protocol addresses of the host node, and sends information containing the obtained internet protocol address to the host node, thereby realizing the automatic registration of each graphics processor node in the network of the distributed computing system, and establishing a node table according to the information sent by each dynamic host configuration protocol client through the host node, so that each graphics processor node can determine the network topology in the distributed computing system according to the node table, and the registration of the graphics processor on the network can be realized without relying on the central processor connected with the graphics processor, thereby improving the flexibility and scalability of the network topology.

The present disclosure relates to a method, device, equipment and storage medium for scheduling a container set, the method comprising: obtaining the update time of a first data processor node; judging whether the time difference between the current time and the update time is greater than a first preset time; if the time difference is greater than the first preset time, determining a second host node from host nodes other than the first host node, the first host node being the host node corresponding to the first data processor node; and scheduling the container set in the first host node to the second host node. The present disclosure judges whether the first data processor node is working normally by comparing the update time of the first processor node with the current time, and then when it is not working normally, schedules the container set on the first host node corresponding to it to other host nodes, so that the container set on the first host node that cannot work normally can work normally on other nodes, thereby ensuring normal communication of the cluster.

This invention provides a multi-node dynamic management method and system based on a PCIe switch. The system includes a PCIe switch and a multi-processor node connected to the PCIe switch. Each multi-processor node includes one upstream port node and multiple downstream port nodes. The upstream port node is used for PCIe switch link configuration, data processing, data distribution, and data management. The downstream port nodes are used to receive and process data allocated by the upstream port node and output the processed data. The method includes defining the upstream and downstream port nodes within the multi-processor node; the upstream port node performs link configuration, data processing, data distribution, and data management on the PCIe switch; and the downstream port nodes receive and process the distributed data. The method and system of this invention can increase the rate of product data exchange and processing, and provide fault-tolerant backup capabilities and health monitoring capabilities to improve reliability.

The invention provides an online dynamic adjustment method, system and device for control parameters and a medium, and the method comprises the steps: collecting storage use data from each processor node, processing state fluctuation in a multi-node environment through employing a distributed collection protocol, and obtaining the current storage occupation proportion of each node; determining high-load state nodes by adopting a threshold comparison method according to the current storage occupation proportion of each node; analyzing a storage state of a processor node adjacent to the high-load state node, and determining a target node of the migration task; and sending a part of data packets of the high-load node to a target node through a transmission path based on an encrypted transmission protocol to complete online dynamic adjustment. According to the method, real-time monitoring of the storage state is realized in a multiprocessor environment, and storage resources are dynamically balanced through a collaboration mechanism among nodes.

The present invention provides a rapidIO network management method, aiming to provide a method for reducing software operation anomalies caused by network congestion. This solution is achieved through the following technical solutions: Each processor node on the signal processing module is interconnected through a rapidIO network switch to form a rapidIO sub-network, and the rapidIO sub-networks on each module are interconnected to form a rapidIO backbone network. The master node in the sub-network maintains the status of each node in the sub-network, executes fault handling measures when an anomaly occurs, and periodically sends the sub-network status to the master node of the main module. The master node of the main module maintains the status of each sub-network. When the master node of the main module fails, the master node of the backup module maintains the status of the backbone network.

A cloud-based virtualized data storage system includes cloud computing infrastructure executing instances of virtual storage appliance (VSA) software to realize respective VSAs which have virtualized network interfaces to a cloud network and to cloud storage. Each VSA has storage processor (SP) nodes each having (1) an inter-node (IN) network interface for communicating with the other SP node of the VSA and an intra-cluster (IC) network interface for communicating with other VSAs of a cluster, the IN and IC network interfaces using private network addresses not routable in the cloud network, and (2) a network virtualization layer connecting the IN and IC network interfaces to an IN tunnel and an IC tunnel, respectively, carried in the cloud network using cloud network addresses routable in the cloud network, with the IN tunnel providing communications between the SP nodes of a VSA, and the IC tunnel providing communications among VSAs of a cluster.

The invention belongs to the technical field of computers, and particularly relates to a highly programmable processor array network which comprises a processor array, the processor array is provided with a plurality of processor units distributed in an array, each processor unit is provided with a processor node and a register group, and adjacent processor nodes perform data interaction through the register group; and the dynamic random access memory layer is provided with one or more layers of dynamic random access memories, the dynamic random access memory layer is stacked on the upper layer of the processor array, and each dynamic random access memory is connected with each processor node. The chip is designed into a processor array form, the size of the processor array can be customized at will during packaging, cutting is carried out according to requirements, and the purpose of a single-wafer large chip can be achieved.

An autonomous repeater system includes a processor node, a storage device, and two or more nodes. The processor node includes a processor, software, and a processor communication device. The software autonomously and continuously queries latitude data, longitude data, and signal-to-noise ratio data from two or more nodes and calculates a target latitude and a target longitude for each node using the latitude data, the longitude data, and the signal-to-noise ratio data received from the two or more nodes. The processor communication device is operatively connected to the processor to transmit or receive the latitude data, longitude data, and signal-to-noise ratio data between the two or more nodes and the processor and transmitting the target latitude and the target longitude calculated for each node. Each node includes a node communication device that transmits and receives data between the two or more nodes and the computer processor.

The application discloses a data processing method and device based on a neural network model and electronic equipment, and relates to the technical field of data processing, and comprises the following steps: merging N network layers of a neural network model to obtain M network layer groups; the network layers in each network layer group are calculated in parallel on a same general processor node; target network layers corresponding to a plurality of first input data are determined, the first input data are expanded based on the dimension characteristics of the target network layer groups to which the target network layers belong, the expanded first input data are calculated through a target general processor node where the target network layer group is located, second input data are output, and the target network layers corresponding to the second input data are updated; and in response to the target network layer being the Nth network layer, third input data output by the Nth network layer are taken as output data of the neural network model. The application shortens the calculation time and reduces the time delay.

The present invention discloses a system and method for implementing distributed replication of local storage of multi-CPU architecture containers, belonging to the technical field of container local storage. The system for implementing distributed replication of local storage of multi-CPU architecture containers of the present invention includes a resource module, a working node and a master node. The resource module is used for storage volume declaration, Piraeus storage class, storage volume and volume loading. The working node includes a Linstor processor, a CSI node, a container group, a container manager, a Linstor processor, and the master node includes a database, a Linstor controller, a Linstr processor and a CSI controller. The system for implementing distributed replication of local storage of multi-CPU architecture containers of the present invention can ensure that Inspur Cloud supports the ability of containers to use local storage across nodes, improves local storage, and has a good value for promotion and application.

Disclosed herein is a system and method for a mesh wireless network, deployable via an aircraft, drone, or other airborne system. Wide area network (WAN) connectivity is provided via a backhaul interface selected from a modem, satellite transceiver, wired module, or other wireless interface. Nodes are powered internally by portable supplies such as batteries, solar, wind, or kinetic energy, enabling continuous operation. The system enables rapid deployment in conflict zones, disaster areas, maritime or remote searches, and mass casualty events, with uninterrupted connectivity even when nodes are damaged or lost. Each node is portable, durable, and water-resistant, with housing comprised of resilient materials to withstand explosions, ammunition, and extreme weather. Multiple nodes form a mesh Wi-Fi network, with traffic routable via any node connected to a backhaul channel. Each node includes a processor for routing and inter-node communication. Nodes may also implement encryption, anti-jamming, and overlapping densities to maintain connectivity.

The invention discloses a construction method, device and equipment of an interconnection network dominating set and a readable storage medium, and relates to the technical field of computers. The construction method of the interconnection network dominating set comprises the steps that an initial folding segmentation and exchange cube network (FDSC2) is constructed, the dimension n of a target folding segmentation and exchange cube network (FDSCn) is obtained, n = 2d, and d is larger than or equal to 1; according to the dimension n of the target folding segmentation and exchange cube network (FDSCn), constructing the target folding segmentation and exchange cube network (FDSCn) by using the plurality of initial folding segmentation and exchange cube networks (FDSC2); a first processor node is extracted from each initial folding partition and exchange cube network (FDSC2) included in a target folding partition and exchange cube network (FDSCn) to form a dominating set of the target folding partition and exchange cube network (FDSCn). According to the scheme, the resource utilization rate of the interconnection network is improved, and the overall stability of the interconnection network is also improved.

Methods and systems are described herein for adaptive beamforming and interference mitigation using a time synchronized scalable cohered on-array processing system (“system”). The system may be a phased array implementing a software-defined radio using multi-input-multi-output antenna elements. The system includes multiple subarray elements which are configured into a tiered array of scalable subarrays that performs intermediary collation, coherence, noise reduction, and adaptive beamforming operations through processor nodes disposed between tiers. The intermediary collation operations process discrete portions of node excitation data to enable the phased array to generate an adaptive beam profile that directs high-directionality beams toward desired targets while adaptively partitioning interference sources between subarray elements. Further, the system makes use of a scalable multidimensional array to provide telecommunication and electromagnetic wave manipulation operations for applications of varying scale.