利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

8 条记录 (耗时 0.018 秒)

    Cooperative Reduced Power Mode Suspension For High Input/Output ('I/O') Workloads
    1.
    发明申请
    Cooperative Reduced Power Mode Suspension For High Input/Output ('I/O') Workloads 审中-公开
    用于高输入/输出（“I / O”）工作负载的合作低功耗模式暂停

    公开(公告)号：US20150121107A1

    公开(公告)日：2015-04-30

    申请号：US14068342

    申请日：2013-10-31

    申请人： International Business Machines Corporation

    发明人： Shareef F. Alshinnawi ,  Gary D. Cudak ,  Jarrod B. Johnson ,  Bryan M. Reese

    IPC分类号： G06F1/32

    CPC分类号： G06F1/3234 ,  G06F1/26 ,  G06F1/32 ,  G06F1/3203 ,  G06F1/3206 ,  G06F1/3209 ,  G06F1/3243 ,  G06F1/3246 ,  G06F1/3287 ,  G06F1/329 ,  H04L67/06

    摘要： Method of cooperative reduced power mode suspension for high input/output (‘I/O’) workloads, including: determining, by a transfer monitoring module, a size of a file to be transferred to a recipient, wherein the recipient includes a central processing unit (CPU) operating in a reduced power mode; determining, by the transfer monitoring module, a desired transfer rate for transferring the file to the recipient; calculating, by the transfer monitoring module, an expected transfer completion time in dependence upon the size of the file and the desired transfer rate; and sending, by the transfer monitoring module, a message to the recipient requesting that the CPU suspend the reduced power mode in dependence upon the expected transfer completion time.

    摘要翻译： 一种用于高输入/输出（I / O））工作负载的协同降低功率模式暂停的方法，包括：由传送监视模块确定要传送到接收者的文件的大小，其中接收方包括中央处理 单元（CPU）以降低功率模式运行; 由传送监控模块确定用于将文件传送到接收者的期望传送速率; 根据文件的大小和期望的传送速率，通过传送监视模块计算期望的传送完成时间; 以及由所述转移监视模块向所述接收者发送请求所述CPU根据所述预期转移完成时间暂停所述降低功率模式的消息。

    COLLABORATIVE ROUTE RESERVATION AND RANKING IN HIGH PERFORMANCE COMPUTING FABRICS
    2.
    发明申请
    COLLABORATIVE ROUTE RESERVATION AND RANKING IN HIGH PERFORMANCE COMPUTING FABRICS 有权
    高性能计算机织物的合作路线预留和排名

    公开(公告)号：US20150195215A1

    公开(公告)日：2015-07-09

    申请号：US14149202

    申请日：2014-01-07

    申请人： International Business Machines Corporation

    发明人： Gary D. Cudak ,  Christopher J. Hardee ,  Jarrod B. Johnson ,  Bryan M. Reese

    IPC分类号： H04L12/911 ,  H04L12/761 ,  H04L12/721

    CPC分类号： H04L47/72 ,  H04L45/16 ,  H04L45/44 ,  H04L47/826

    摘要： Embodiments of the present invention provide a method, system and computer program product for collaborative route reservation in an HPC fabric. A method for collaborative route reservation in an HPC fabric includes selecting a target node in a cluster of nodes to receive a payload from a source node of the cluster over an HPC fabric and computing a route over the HPC fabric for transferring the payload from the source node to the target node, and also a duration of time requisite to transferring the payload. The method also includes notifying other nodes in the cluster of a reservation of the computed route for the duration of time and utilizing the computed route during the duration of time to transfer the payload. Finally, the method includes responding to completing transfer of the payload by notifying the other nodes that the computed path is no longer reserved.

    摘要翻译： 本发明的实施例提供了一种用于HPC结构中的协作路由预留的方法，系统和计算机程序产品。 在HPC架构中协同路由预留的方法包括：选择节点簇中的目标节点，以通过HPC架构从群集的源节点接收有效载荷，并计算HPC架构上的路由，以从源传输有效载荷 节点到目标节点，以及传送有效载荷所需的时间持续时间。 该方法还包括在时间段内通知该计算出的路由的预留中的其他节点，并且在持续时间内利用计算的路由来传送有效载荷。 最后，该方法包括通过通知其他节点计算出的路径不再保留来响应完成有效载荷的传送。

    ROLE ASSIGNMENT FOR SERVERS IN A HIGH PERFORMANCE COMPUTING SYSTEM BASED ON MEASURED PERFORMANCE CHARACTERISTICS
    7.
    发明申请
    ROLE ASSIGNMENT FOR SERVERS IN A HIGH PERFORMANCE COMPUTING SYSTEM BASED ON MEASURED PERFORMANCE CHARACTERISTICS 有权
    基于测量性能特征的高性能计算系统中服务器的角色分配

    公开(公告)号：US20150244581A1

    公开(公告)日：2015-08-27

    申请号：US14190833

    申请日：2014-02-26

    申请人： INTERNATIONAL BUSINESS MACHINES CORPORATION

    发明人： Srihari V. Angaluri ,  Gary D. Cudak ,  Christopher J. Hardee ,  Bryan M. Reese ,  Junjiro Sumikawa

    IPC分类号： H04L12/24 ,  G06N5/04 ,  H04L12/26

    CPC分类号： H04L41/0823 ,  H04L41/0883 ,  H04L43/065

    摘要： Embodiments of the present invention disclose a method, computer program product, and for determining a recommendation relating to a configuration of a plurality of server nodes of a computing system. In one embodiment, in accordance with the present invention, the computer implemented method includes the steps of, for each server node, storing a first performance parameter value, wherein each first performance parameter value is a benchmarked value that corresponds to a measured actual performance parameter of its associated server node, and applying a first configuration rule based, at least in part, on the first performance parameter values of the plurality of server nodes to obtain a first configuration recommendation. In another embodiment, the method further includes the step of presenting the first recommendation to a human user.

    摘要翻译： 本发明的实施例公开了一种方法，计算机程序产品，并且用于确定与计算系统的多个服务器节点的配置有关的建议。 在一个实施例中，根据本发明，计算机实现的方法包括以下步骤：对于每个服务器节点，存储第一性能参数值，其中每个第一性能参数值是与所测量的实际性能参数相对应的基准值 并且至少部分地基于多个服务器节点的第一性能参数值应用第一配置规则以获得第一配置推荐。 在另一个实施例中，该方法还包括向人类用户呈现第一推荐的步骤。

    Keyboard, video and mouse switch identifying and displaying nodes experiencing a problem
    8.
    发明授权
    Keyboard, video and mouse switch identifying and displaying nodes experiencing a problem 有权
    键盘，视频和鼠标开关识别和显示遇到问题的节点

    公开(公告)号：US08943373B1

    公开(公告)日：2015-01-27

    申请号：US14036187

    申请日：2013-09-25

    申请人： International Business Machines Corporation

    发明人： Srihari V. Angaluri ,  Gary D. Cudak ,  Christopher J. Hardee ,  Bryan M. Reese ,  Junjiro Sumikawa

    IPC分类号： G06F3/00 ,  G06F11/00 ,  G06F11/07

    CPC分类号： G06F11/162 ,  G06F3/038 ,  G06F11/0709 ,  G06F11/0769 ,  G06F13/385

    摘要： A computer program product includes computer readable program code causing a keyboard, video and mouse (KVM) switch to communicate over a network with service processors of a plurality of compute nodes, computer readable program code for causing the KVM switch to identify a compute node from among the plurality of compute nodes that is experiencing one or more predetermined problems, and computer readable program code for causing the KVM switch to automatically generate a graphical user interface including the identity of the identified compute node for display on a display device that is connected to the KVM switch.

    摘要翻译： 计算机程序产品包括使键盘，视频和鼠标（KVM）切换器通过网络与多个计算节点的服务处理器通信的计算机可读程序代码，用于使KVM切换器从KVM切换器识别计算节点的计算机可读程序代码 在经历一个或多个预定问题的多个计算节点中的计算机可读程序代码以及用于使KVM切换器自动生成图形用户界面的计算机可读程序代码，所述图形用户界面包括所识别的计算节点的标识，以便在连接到 KVM切换器。