Emc IP Holding Company LLC

Dell Products Inc.

Zhi Ying

Kun Wang

Junping Zhao

Pengfei Wu

Jinpeng Liu

Layne Lin Peng

Kenneth Durazzo

Ming Zhang

Tianxiang Chen

Min Chao Zhao

A method comprises obtaining an intermediate representation of the machine learning model written in a source language. The intermediate representation is independent of the source language and a target language and comprises a structured text. The method also comprises generating a computation graph based on the intermediate representation. Nodes in the computation graph represent functions related to the machine learning model and a directed edge in the computation graph represents a dependency between functions. The method further comprises partitioning the computation graph into sequential parts in sequence such that the parts are executed sequentially, and functions corresponding to nodes in each part are executed in parallel.

Method, electronic device and computer program product for processing machine learning model

Embodiments of the present disclosure provide a method, electronic device and computer-readable medium for processing data generated by a service. The method disclosed herein comprises: obtaining a data packet generated by a service; identifying whether the service generating the data packet is a predetermined service for which a routing path is to be set; in response to identifying that the service is the predetermined service, attaching an indication of the routing path to the data packet. In this way, the embodiments of the present disclosure can provide different routing paths for data packets generated by services, thereby increasing transfer efficiency of data packets.

Method, electronic device and computer-readable medium for processing data generated by service

In a multi-cloud computing environment comprising a plurality of cloud platforms with each cloud platform comprising one or more nodes, a method maintains at a given one of the nodes in the multi-cloud computing environment a blockchain instance in accordance with a decentralized blockchain network comprised of at least a subset of the nodes in the multi-cloud computing environment wherein each of the subset of nodes locally maintain a blockchain instance. Further, the method maintains at the given one of the nodes a global state database which is locally synchronized with the locally maintained blockchain instance and stores identifying information about nodes in the multi-cloud computing environment, wherein the identifying information comprises information on how to find one or more of the nodes.

Decentralized node finder in multi-cloud computing environment

Techniques for generating a network topology are provided. For example, a method comprises: sending, at an edge node of a network, first exploration data to a first node of the network. The method also comprises receiving from the first node first feedback information for the first exploration data. The first feedback information includes identity information of the first node and first associated node list information, and the first associated node list information includes identity information of nodes associated with the first node in the network. In addition, the method comprises: determining latency between the first node and the second node based on the first latency information and the second latency information. Then, the method further comprises updating the network topology based on the latency between the first node and the second node. Through the method, the present disclosure can provide accurate data support for path optimization.

Method, electronic device and computer program product for generating network topology

Embodiments of the present disclosure provide methods, apparatuses and computer program products for transmitting data. A method comprises determining, at a source node, a traffic type of a packet to be sent to a destination node, the source node and the destination node having therebetween a plurality of network paths for different traffic types. The method further comprises including a mark indicating the traffic type in the packet. In addition, the method further comprises sending the packet including the mark to the destination node such that the packet is forwarded along one of the plurality of network paths specific to the traffic type. Embodiments of the present disclosure can transmit data using different network paths based on different traffic types of data so as to optimize network performance for different network requirements.

Methods, apparatuses and computer program products for transmitting data

Implementations of the present disclosure relate to a method, apparatus and computer program product for processing a computing task. The method comprises: obtaining status information of multiple computing resources; in response to receiving a neural network model-based computing task, determining configuration information of multiple layers associated with the neural network model; obtaining parameter data associated with at least one part of the multiple layers on the basis of the configuration information; and based on the status information and the parameter data, selecting from the multiple computing resources a group of computing resources for processing the computing task. According to the example implementations of the present disclosure, multiple computing resources may be utilized sufficiently, and it may be guaranteed that a load balance may be stricken between the multiple computing resources.

Method, apparatus, and computer program product for processing computing task

A method for processing a computing task comprises: determining parameter data of multiple layers associated with a neural network model in response to receiving a computing task based on the neural network model; ranking at least one part of the multiple layers on the basis of the parameter data so as to obtain a layer list; ranking multiple computing resources on the basis of status information of the multiple computing resources so as to obtain a resource list; and determining a mapping between a corresponding layer among the multiple layers and a corresponding computing resource among the multiple computing resources on the basis of the layer list and the resource list, where the mapping indicates one computing resource among the multiple computing resources is to process parameters associated with one layer among the multiple layers.

Mapping resources to each layer of a neural network model based computing task

A method for path optimization comprises: obtaining, at an edge node of a network including a plurality of nodes, locations and performances of one or more nodes from among the plurality of nodes in the network; determining performance indices associated with the one or more nodes based on the locations and the performances of the one or more nodes and a service level objective (SLO), a performance index indicating a difference between a performance of a respective node and the SLO; and determining, based on the locations of the one or more nodes and the performance indices, a target path for delivering a packet from the edge node to a destination node. Advantageously, the path for transmitting the packet flow is optimized in real time according to dynamic changes in the network environment, so that an end-to-end service level objective is met as much as possible.

Method, device and computer program product for path optimization

A data processing method comprises: receiving a data packet related to a service. The method also comprises determining whether predefined configuration information indicates a priority of the service. The method further comprises in response to the configuration information indicating the priority of the service, adding an indication of the priority into the data packet. The above method can enable the underlying network devices to adopt a suitable strategy to process data packets from services of different priorities, so as to improve the transmission efficiency of the data packets and enhance user experience of the services.

Method, device and computer program product for data processing

Embodiments of the present disclosure relate to a method, device and computer program product for protocol selection. According to embodiments of the present disclosure, a client may determine supported transmission protocols based on its own hardware information and transmit a connection request to a server using a protocol with a higher priority. The server may determine supported protocols based on its own hardware information and respond to the connection request according to the supported protocols. In this way, the establishment of the connection between the client and the server is transparent to users.

Method, device and computer program product for protocol selection

Embodiments of the present disclosure relate to a method, apparatus and computer program product for scheduling dedicated processing resources. The method comprises: in response to receiving a scheduling request for a plurality of dedicated processing resources, obtaining a topology of the plurality of dedicated processing resources, the topology being determined based on connection attributes related to connections among the plurality of dedicated processing resources; and determining, based on the topology, a target dedicated processing resource satisfying the scheduling request from the plurality of dedicated processing resources. In this manner, the performance and the resource utilization rate of scheduling the dedicated processing resources are improved.

Method, apparatus and computer program product for scheduling dedicated processing resources

Embodiments of the present disclosure provide a method, a device and a computer program product for controlling a game. The method comprises: in response to receiving an input of a user for a game at a terminal device, sending a message indicating the input to a network device; receiving a candidate game frame from a network device, where the candidate game frame is a game frame in the game that is possible to occur subsequent to a target game frame corresponding to the input, and the candidate game frame is determined by the network device based on a message indicating the input; and storing the candidate game frame in a game frame buffer. In such a manner, the embodiments of the present disclosure can reduce the delay of responding to an input of a user for a game.

Method, device and computer program product for controlling a game

Embodiments of the present disclosure provide a computer-implemented method, an electronic device and a computer program product. In this method, an attribute description of a node is determined at the node of a computer network based on a distributed hash table The attribute description comprises a plurality of attribute items and respective attribute values. A key-identifier pair of the node in the distributed hash table is generated where the key being obtained from the attribute description based on a predetermined mapping so that the node is searchable by the distributed hash table according to the attribute description. The key-identifier pair is transmitted to at least one node connected directly with the node. Embodiments of the present disclosure can improve searching of a node in a computer network.

Method, electronic device and computer program product for searching for node

Embodiments of the present disclosure relate to a method of tracing a computing system, a device for tracing a computing system, and a computer readable medium. According to some embodiments, tracing data is extracted from a request that requests a dedicated processing resource for a task, the request being initiated by an application executed on a client and the tracing data including a parameter for performing the task, an identifier of the application, and time elapsed from initiating the request. The tracing data is stored in a volatile memory to facilitate transmitting the tracing data to a database server. The request is caused to be processed by a computing server hosting the dedicated processing resource. In this way, the cloud computing system may be traced rather than tracing the stand-alone tasks only.

Method, device, and computer readable medium for tracing computing system

Techniques are provided for implementing a graphics processing unit (GPU) service platform that is configured to provide topology aware grouping and provisioning of GPU resources for GPU-as-a-Service. A GPU server node receives a service request from a client system for GPU processing services provided by the GPU server node, wherein the GPU server node comprises a plurality of GPU devices. The GPU server node accesses a performance metrics data structure which comprises performance metrics associated with an interconnect topology of the GPU devices and hardware components of the GPU sever node. The GPU server node dynamically forms a group of GPU devices of the GPU server node based on the performance metrics of the accessed data structure, and provisions the dynamically formed group of GPU devices to the client system to handle the service request.

Growing community of inventors

Shanghai, China

Zhi Ying