中科微点-全球专利检索

  1. Login
  2. Sign Up

Search Results

7 records (took 0.028 seconds)

    INTEGRATED HETEROGENEOUS PROCESSING UNITS
    1.
    发明申请
    INTEGRATED HETEROGENEOUS PROCESSING UNITS 审中-公开
    综合异构加工单位

    公开(公告)号：WO2016068999A1

    公开(公告)日：2016-05-06

    申请号：PCT/US2014/063479

    申请日：2014-10-31

    Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

    Inventor： CHEN, Yuan ,  TALWAR, Vanish ,  FAROOQUI, Naila ,  ROY, Indrajit

    IPC: G06F13/40 ,  G06F9/46

    CPC classification number: G06F9/5044 ,  Y02D10/22

    Abstract: According to an example, an instruction to run a kernel of an application on an apparatus having a first processing unit integrated with a second processing unit may be received. In addition, an application profile for the application at a runtime of the application kernel on the second processing unit may be created, in which the application profile identifies an affinity of the application kernel to be run on either the first processing unit or the second processing unit, and identifies a characterization of an input data set of the application. The application profile may also be stored in a data store.

    Abstract translation: 根据示例，可以接收在具有与第二处理单元集成的第一处理单元的装置上运行应用的内核的指令。 此外，可以创建在第二处理单元上的应用程序内核的运行时间处的应用程序的应用程序配置文件，其中应用程序配置文件标识应用程序内核在第一处理单元或第二处理单元上运行的亲和度 单元，并识别应用程序的输入数据集的表征。 应用程序配置文件也可以存储在数据存储中。

    SCHEDULER-ASSIGNED PROCESSOR RESOURCE GROUPS
    2.
    发明申请
    SCHEDULER-ASSIGNED PROCESSOR RESOURCE GROUPS 审中-公开
    调度员分配的处理器资源组

    公开(公告)号：WO2016118164A1

    公开(公告)日：2016-07-28

    申请号：PCT/US2015/012730

    申请日：2015-01-23

    Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

    Inventor： GMACH, Daniel ,  TALWAR, Vanish

    IPC: G06F9/46 ,  G06F9/50

    CPC classification number: G06F9/5061 ,  G06F2209/5012

    Abstract: In one implementation, a scheduler system includes a plurality of processor resource, a processor resource assignment engine to maintain a plurality of processor resource groups based on scheduler activity information, and a process assignment engine to assign a processor resource request to one of the plurality of resource groups, identify a processor resource of the plurality of resources assigned to the one of the plurality of resource groups, and enqueue a process associated with the processor resource request on a run-queue of the processor resource based on a strategy of the scheduler policy.

    Abstract translation: 在一个实现中，调度器系统包括多个处理器资源，基于调度器活动信息维护多个处理器资源组的处理器资源分配引擎，以及处理器资源请求，以将处理器资源请求分配给多个 资源组，识别分配给所述多个资源组中的一个资源组的所述多个资源中的处理器资源，并且基于所述调度器策略的策略，在所述处理器资源的运行队列上排队与所述处理器资源请求相关联的进程 。

    SCHEDULING JOBS IN A COMPUTING CLUSTER
    3.
    发明申请
    SCHEDULING JOBS IN A COMPUTING CLUSTER 审中-公开
    在计算机中排队

    公开(公告)号：WO2017018978A1

    公开(公告)日：2017-02-02

    申请号：PCT/US2015/041899

    申请日：2015-07-24

    Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

    Inventor： CHEN, Yuan ,  TALWAR, Vanish ,  MILOJICIC, Dejan S.

    IPC: G06F9/46 ,  G06F9/50

    CPC classification number: G06F9/46 ,  G06F9/50

    Abstract: In example implementations, a method is provided. The method includes receiving a job request at a scheduler of a plurality of schedulers based upon a quality of service (QoS) level associated with the job request and the scheduler. The job request is scheduled to a computing node based upon locally stored resource information of a selected number of computing nodes within a computing cluster. A shared memory is accessed via a memory fabric to obtain updated resource information of the selected number of computing nodes. The job request may then be re-scheduled to a different computing node based upon the updated resource information.

    Abstract translation: 在示例实现中，提供了一种方法。 该方法包括：基于与作业请求和调度器相关联的服务质量（QoS）级别在多个调度器的调度器处接收作业请求。 基于计算集群内选定数量的计算节点的本地存储的资源信息，将作业请求调度到计算节点。 通过存储器结构访问共享存储器以获得所选数量的计算节点的更新的资源信息。 然后可以基于更新的资源信息将作业请求重新调度到不同的计算节点。

    MEMORY NETWORK TO PRIORITIZE PROCESSING OF A MEMORY ACCESS REQUEST
    4.
    发明申请
    MEMORY NETWORK TO PRIORITIZE PROCESSING OF A MEMORY ACCESS REQUEST 审中-公开
    存储器访问存储器优先处理存储器网络

    公开(公告)号：WO2016122662A1

    公开(公告)日：2016-08-04

    申请号：PCT/US2015/013969

    申请日：2015-01-30

    Applicant: HEWLETT PACKARD ENTERPRISE DEVELOPMENT LP

    Inventor： TALWAR, Vanish ,  FARABOSCHI, Paolo ,  GMACH, Daniel Juergen ,  CHEN, Yuan ,  DAVIS, Alan Lynn ,  MADAN, Adit

    IPC: G06F15/173

    CPC classification number: G06F3/0659 ,  G06F3/0611 ,  G06F3/067 ,  G06F15/17331

    Abstract: In one example, a memory network may control access to a shared memory that is by multiple compute nodes. The memory network may control the access to the shared memory by receiving a memory access request originating from an application executing on the multiple compute nodes and determining a priority for processing the memory access request. The priority determined by the memory network may correspond to a memory address range in the memory that is specifically used by the application.

    Abstract translation: 在一个示例中，存储器网络可以控制对由多个计算节点进行的共享存储器的访问。 存储器网络可以通过接收从在多个计算节点上执行的应用程序产生的存储器访问请求来控制对共享存储器的访问，并且确定处理存储器访问请求的优先级。 由存储器网络确定的优先级可以对应于由应用专门使用的存储器中的存储器地址范围。

Patent Agency Ranking