知搜-全球专利检索

  1. Login
  2. Sign Up

Search Results

400 records (took 0.031 seconds)

    Distributed Artifical Intelligence Workload Optimizer
    2.
    发明公开
    Distributed Artifical Intelligence Workload Optimizer 审中-公开

    公开(公告)号：US20240345885A1

    公开(公告)日：2024-10-17

    申请号：US18133849

    申请日：2023-04-12

    Applicant: Bank of America Corporation

    Inventor： Steven Sinks ,  Joshua Abraham

    IPC: G06F9/50

    CPC classification number: G06F9/5038 ,  G06F9/5083 ,  G06F2209/501 ,  G06F2209/503 ,  G06F2209/506

    Abstract: Arrangements for a distributed artificial intelligence workload optimizer are provided. In some aspects, a workload that identifies a number of computer processing cycles required to complete a task may be received. Processing constraints may be received from a user computing device. Contextual parameters associated with the workload may be received. Availability data for a plurality of resources in a distributed computing environment, each capable of performing at least part of the workload, may be acquired. Using an artificial intelligence algorithm, an optimization model for distributing the workload may be built based on the processing constraints, the contextual parameters, and the availability data. The optimization model may optimize the distribution of available resources allocated to executing the workload. Based on the optimization model, resource distribution options including an optimal distribution of the available resources for executing the workload may be identified, and the workload may be executed accordingly.

    Scheduling heterogeneous computation on multithreaded processors
    3.
    发明授权
    Scheduling heterogeneous computation on multithreaded processors 有权

    公开(公告)号：US12118398B2

    公开(公告)日：2024-10-15

    申请号：US16041066

    申请日：2018-07-20

    Applicant: Imagination Technologies Limited

    Inventor： Luke Tilman Peterson ,  James Alexander McCombe

    IPC: G06F9/50 ,  G06F9/38

    CPC classification number: G06F9/5038 ,  G06F9/3828 ,  G06F9/3851 ,  G06F9/3891 ,  G06F2209/506

    Abstract: Aspects include computation systems that can identify computation instances that are not capable of being reentrant, or are not reentrant capable on a target architecture, or are non-reentrant as a result of having a memory conflict in a particular execution situation. For example, a system can have a plurality of computation units, each with an independently schedulable SIMD vector. Computation instances can be defined by a program module, and a data element(s) that may be stored in a local cache for a particular computation unit of the plurality. Each local cache does not maintain coherency controls for such data elements. During scheduling, a scheduler can maintain a list of running (or runnable) instances, and attempt to schedule new computation instances by determining whether any new computation instance conflicts with a running instance and responsively defer scheduling. Such memory conflict checks can be conditioned on a flag or other indication of the potential for non-reentrancy.

    SERVICE DELIVERY WITH JOINT NETWORK AND CLOUD RESOURCE MANAGEMENT
    5.
    发明公开
    SERVICE DELIVERY WITH JOINT NETWORK AND CLOUD RESOURCE MANAGEMENT 审中-公开

    公开(公告)号：US20240323265A1

    公开(公告)日：2024-09-26

    申请号：US18680616

    申请日：2024-05-31

    Applicant: Telefonaktiebolaget LM Ericsson (publ)

    Inventor： Stefano SORRENTINO ,  Massimo CONDOLUCI ,  Björn SKUBIC ,  Wanlu SUN

    IPC: H04L67/62 ,  G06F9/50 ,  H04W28/16

    CPC classification number: H04L67/62 ,  G06F9/5044 ,  G06F9/5072 ,  H04W28/16 ,  G06F2209/506

    Abstract: Methods and apparatus are disclosed, including in one example a method for scheduling resources, associated with a plurality of components of a communication network, for providing a network service to a user equipment (UE). The method comprises receiving a service request for providing the network service, wherein the service request includes one or more service constraints. The method also comprises, for each of the plurality of network components, determining component resources that are needed to fulfill the service request according to the service constraints, sending, to a manager function associated with the particular component, a resource request that includes identification of the determined component resources and information related to the service constraints, and receiving, from the manager function, service information associated with the particular component. The method also includes, based on the service information and a cost function, determining a resource schedule for the plurality of network components that fulfils the service request.

    Method for task planning of space information network based resource interchange
    7.
    发明授权
    Method for task planning of space information network based resource interchange 有权

    公开(公告)号：US11884423B2

    公开(公告)日：2024-01-30

    申请号：US17489812

    申请日：2021-09-30

    Applicant: Xi'an University of Architecture and Technology

    Inventor： Runzi Liu ,  Xiang Ji ,  Wenzhu Zhang

    IPC: B64G1/10 ,  H04W28/16 ,  G06F9/50 ,  G06F9/48

    CPC classification number: B64G1/1021 ,  B64G1/1007 ,  G06F9/4881 ,  G06F9/5061 ,  H04W28/16 ,  G06F2209/506

    Abstract: Disclosed is a method for task planning of a space information network based on resource interchange. The method includes: initializing basic parameters of the space information network; dividing a planning horizon into K time slots of equal length, and constructing a resource time-varying graph for the space information network; sampling a feasible resource combination space of each task, and obtaining a candidate resource combination set comprised of the resource combinations with independence greater than or equal to a threshold n; calculating a conflict relation between resource combinations, and constructing a resource combination conflict graph; obtaining a maximum independent set of the resource combination conflict graph to obtain a global planning result; and searching a neighborhood of the global planning result, and completing a local adjustment of a task planning scheme through the resource interchange, to complete the task planning based on characteristics of the resource interchange.

    SELECTING BEST CLOUD COMPUTING ENVIRONMENT IN A HYBRID CLOUD SCENARIO
    9.
    发明公开
    SELECTING BEST CLOUD COMPUTING ENVIRONMENT IN A HYBRID CLOUD SCENARIO 审中-公开

    公开(公告)号：US20230259401A1

    公开(公告)日：2023-08-17

    申请号：US17651186

    申请日：2022-02-15

    Applicant: International Business Machines Corporation

    Inventor： Anton Zorin ,  Manish Kesarwani ,  Niels Dominic Pardon ,  Ritesh Kumar Gupta ,  Sameep Mehta

    IPC: G06F9/50 ,  G06F9/48 ,  G06F11/30 ,  G06F11/34

    CPC classification number: G06F9/5044 ,  G06F9/4881 ,  G06F11/3006 ,  G06F11/3409 ,  G06F2209/506 ,  H04L67/10

    Abstract: Embodiments for identifying an optimal cloud computing environment for a computing task is disclosed. Embodiments comprises receiving a computing task to be executed in a cloud computing environment, wherein the computing task requires a set of cloud computing environment parameter values of the cloud computing environment, pre-selecting a set of candidate cloud computing environments, each of which meets the set of cloud computing environment parameter values, ranking the candidate cloud computing environments using reward-based ranking parameter values of the candidate cloud computing environments as an additional selection constraint, and selecting the highest ranking cloud computing environment as the optimal cloud computing environment for the computing task. Furthermore, embodiments comprise executing the computing task in the optimal cloud computing environment, monitoring execution when executing the computing task, and updating parameter values of the reward-based ranking for the selected optimal cloud computing environment.

Patent Agency Ranking