利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

10 条记录 (耗时 0.02 秒)

    HYBRID MEMORY CUBE SYSTEM INTERCONNECT DIRECTORY-BASED CACHE COHERENCE METHODOLOGY
    1.
    发明申请
    HYBRID MEMORY CUBE SYSTEM INTERCONNECT DIRECTORY-BASED CACHE COHERENCE METHODOLOGY 审中-公开
    混合存储器系统基于连接的基于目录的缓存相关方法

    公开(公告)号：US20150324290A1

    公开(公告)日：2015-11-12

    申请号：US14706516

    申请日：2015-05-07

    申请人： John Leidel ,  Richard C. Murphy

    发明人： John Leidel ,  Richard C. Murphy

    IPC分类号： G06F12/08 ,  G06F13/16 ,  G06F13/40

    CPC分类号： G06F12/0817 ,  G06F12/0828 ,  G06F13/16 ,  G06F13/1663 ,  G06F13/40 ,  G06F13/4022 ,  G06F2212/622 ,  G11C5/025 ,  G11C8/12 ,  H01L25/105 ,  H01L2924/0002 ,  H01L2924/00

    摘要： A system includes a plurality of host processors and a plurality of hybrid memory cube (HMC) devices configured as a distributed shared memory for the host processors. An HMC device includes a plurality of integrated circuit memory die including at least a first memory die arranged on top of a second memory die, and at least a portion of the memory of the memory die is mapped to include at least a portion of a memory coherence directory; and a logic base die including at least one memory controller configured to manage three-dimensional (3D) access to memory of the plurality of memory die by at least one second device, and logic circuitry configured to implement a memory coherence protocol for data stored in the memory of the plurality of memory die.

    摘要翻译： 系统包括多个主机处理器和被配置为用于主处理器的分布式共享存储器的多个混合存储器立方体（HMC）设备。 HMC装置包括多个集成电路存储器管芯，其包括布置在第二存储器管芯的顶部上的至少第一存储器管芯，并且存储器管芯的存储器的至少一部分被映射以包括存储器的至少一部分 连贯目录 以及包括至少一个存储器控制器的逻辑基准管芯，所述至少一个存储器控制器被配置为通过至少一个第二器件来管理对所述多个存储器管芯的存储器的三维（3D）访问;以及逻辑电路，被配置为实现存储在 多个存储器管芯的存储器。

    IN-MEMORY LIGHTWEIGHT COHERENCY
    2.
    发明申请
    IN-MEMORY LIGHTWEIGHT COHERENCY 审中-公开
    内存轻量级密码

    公开(公告)号：US20150325272A1

    公开(公告)日：2015-11-12

    申请号：US14706490

    申请日：2015-05-07

    申请人： Richard C. Murphy

    发明人： Richard C. Murphy

    IPC分类号： G11C5/02 ,  G06F12/02

    CPC分类号： G11C8/12 ,  G06F12/0284 ,  G06F12/0815 ,  G06F12/0817 ,  G06F12/0824 ,  G06F12/084 ,  G06F12/1072 ,  G06F2212/1032 ,  G06F2212/1048 ,  G06F2212/251 ,  G06F2212/3042 ,  G11C5/02 ,  G11C5/025

    摘要： A system includes a plurality of host processors and a plurality of HMC devices configured as a distributed shared memory for the host processors. An HMC device includes a plurality of integrated circuit memory die including at least a first memory die arranged on top of a second memory die and at least a portion of the memory of the memory die is mapped to include at least a portion of a memory coherence directory; and a logic base die including at least one memory controller configured to manage three-dimensional (3D) access to memory of the plurality of memory die by at least one second device, and logic circuitry configured to determine memory coherence state information for data stored in the memory of the plurality of memory die, communicate information regarding the access to memory, and include the memory coherence information in the communicated information.

    摘要翻译： 系统包括多个主机处理器和被配置为用于主机处理器的分布式共享存储器的多个HMC设备。 HMC装置包括多个集成电路存储器管芯，其包括布置在第二存储管芯的顶部上的至少第一存储器管芯，并且映射存储器管芯的存储器的至少一部分以包括存储器连贯性的至少一部分 目录; 以及包括至少一个存储器控制器的逻辑基准管芯，所述至少一个存储器控制器被配置为通过至少一个第二器件来管理对所述多个存储器管芯的存储器的三维（3D）访问;以及逻辑电路，被配置为确定存储在 多个存储器管芯的存储器，传送关于对存储器的访问的信息，并且将所述存储器一致性信息包括在传送的信息中。

    Automated resource management using perceptron prediction
    6.
    发明授权
    Automated resource management using perceptron prediction 有权
    使用感知器预测的自动资源管理

    公开(公告)号：US07191329B2

    公开(公告)日：2007-03-13

    申请号：US10382723

    申请日：2003-03-05

    申请人： Richard C. Murphy

    发明人： Richard C. Murphy

    IPC分类号： G06F1/24

    CPC分类号： G06F9/44505

    摘要： A system and method for automatically identifying a desirable reconfiguration of computer system resources, using a perceptron to determine whether one resource configuration will likely be more efficient or more effective than a second configuration. An iterative solver identifies possible configurations or reconfigurations of the resources. A possible configuration is applied to the perceptron, which determines whether the new configuration is more attractive than an existing or baseline configuration, in terms of a predetermined objective function (e.g., cost, performance, resource utilization, throughput). If the new configuration improves the objective function, the new configuration may be automatically or manually applied through a dynamic reconfiguration operation.

    摘要翻译： 一种用于使用感知器来自动识别计算机系统资源的期望的重新配置以确定一个资源配置是否可能比第二配置更有效或更有效的系统和方法。 迭代求解器识别资源的可能配置或重新配置。 根据预定的目标函数（例如，成本，性能，资源利用率，吞吐量），可能的配置被应用于感知器，感知器确定新配置是否比现有或基线配置更具吸引力。 如果新配置改善了目标函数，则可以通过动态重新配置操作自动或手动应用新配置。

    System and method for dynamic resource configuration using a dependency graph
    7.
    发明授权
    System and method for dynamic resource configuration using a dependency graph 有权
    使用依赖图进行动态资源配置的系统和方法

    公开(公告)号：US07152157B2

    公开(公告)日：2006-12-19

    申请号：US10382427

    申请日：2003-03-05

    申请人： Richard C. Murphy ,  Scott M. Carter ,  Mario G. Ornelas ,  Shrikant Deshpande

    发明人： Richard C. Murphy ,  Scott M. Carter ,  Mario G. Ornelas ,  Shrikant Deshpande

    IPC分类号： G06F1/24

    CPC分类号： G06F9/5077

    摘要： A system and method for predicting whether a dynamic reconfiguration of a resource of a resource domain would be successful, prior to attempting the reconfiguration. A resource domain includes one or more computer resources (e.g., physical, logical and pseudo devices) and a graph management agent configured to maintain a graph representing the resources and dependencies between resources. Vertices of the graph represent resources; edges represent dependencies. A resource domain may also include a set of policies or constraints regarding resources and reconfigurations of resources. An illustrative constraint may specify that a particular resource (e.g., a multi-pathed logical device) must have a minimal number of paths (e.g., two). The graph agent identifies the effect the dynamic reconfiguration operation would have upon the resources and dependencies, and determines whether any constraints would be violated. If no constraints would be violated, the graph management agent may indicate that the reconfiguration would succeed.

    摘要翻译： 在尝试重新配置之前，用于预测资源域的资源的动态重新配置是否将成功的系统和方法。 资源域包括一个或多个计算机资源（例如，物理，逻辑和伪设备）以及图形管理代理，其被配置为维护表示资源的图表和资源之间的依赖关系。 图的顶点代表资源; 边缘表示依赖关系。 资源域还可以包括关于资源的资源和重新配置的一组策略或约束。 说明性的约束可以指定特定资源（例如，多播路逻辑设备）必须具有最小数量的路径（例如，两个）。 图形代理识别动态重新配置操作对资源和依赖关系的影响，并确定是否违反任何约束。 如果不违反任何限制，则图形管理代理可以指示重新配置将成功。