利索-全球专利检索

  1. 登录
  2. 注册

搜索结果

7 条记录 (耗时 0.02 秒)

    Remote translation mechanism for a multinode system
    1.
    发明授权
    Remote translation mechanism for a multinode system 有权
    多节点系统的远程翻译机制

    公开(公告)号：US07577816B2

    公开(公告)日：2009-08-18

    申请号：US10643758

    申请日：2003-08-18

    申请人： Kitrick Sheets ,  Andrew B. Hastings

    发明人： Kitrick Sheets ,  Andrew B. Hastings

    IPC分类号： G06F12/08

    CPC分类号： G06F12/1036 ,  G06F12/1072

    摘要： The present invention provides a method of initializing shared memory in a multinode system. The method includes building a local address space in each of a plurality of nodes and exporting the local address space from each of the plurality of nodes to a Remote Translation Table (RTT) in each of the plurality of nodes. The present invention further provides system including a plurality of nodes, each node having one or more processors and a memory controller operatively coupled to the one or more processors, wherein the memory controller includes a RTT for holding translation information for an entire virtual memory address space for the node, further wherein the RTT is initialized upon the start of a process by building a local address space in the node, and exporting the local address space from the node to a RTT in each of the plurality of other nodes.

    摘要翻译： 本发明提供了一种在多节点系统中初始化共享存储器的方法。 该方法包括在多个节点的每一个中构建本地地址空间，并将多个节点中的每一个节点的本地地址空间导出到多个节点中的每个节点中的远程转换表（RTT）。 本发明还提供了包括多个节点的系统，每个节点具有一个或多个处理器和可操作地耦合到一个或多个处理器的存储器控​​制器，其中存储器控制器包括用于保持整个虚拟存储器地址空间的翻译信息的RTT 对于所述节点，进一步其中，通过在所述节点中构建本地地址空间，并且在所述多个其他节点中的每一个中将所述本地地址空间从所述节点导出到RTT，在所述进程开始时初始化所述RTT。

    Sharing memory within an application using scalable hardware resources
    3.
    发明申请
    Sharing memory within an application using scalable hardware resources 有权
    使用可扩展硬件资源在应用程序内共享内存

    公开(公告)号：US20050044339A1

    公开(公告)日：2005-02-24

    申请号：US10643588

    申请日：2003-08-18

    申请人： Kitrick Sheets

    发明人： Kitrick Sheets

    IPC分类号： G06F12/08

    CPC分类号： G06F9/3834 ,  G06F9/3836 ,  G06F9/384

    摘要： Systems and methods include translating a virtual memory address into a physical memory address in a multi-node system that is initiated by providing the virtual memory address at a source node. A determination is made that a translation for the virtual memory address does not exist. A physical node to query is determined based on the virtual memory address. An emulated remote translation table (ERTT) segment is queried on the determined physical node to see if the ERTT segment may provide a translation. If the translation is received then the translation may be loaded into a TLB on the source node. Otherwise a memory reference error may be generated for the entity or application referencing the invalid virtual memory address.

    摘要翻译： 系统和方法包括将虚拟存储器地址转换成通过在源节点处提供虚拟存储器地址而启动的多节点系统中的物理存储器地址。 确定虚拟存储器地址的翻译不存在。 基于虚拟内存地址确定要查询的物理节点。 在确定的物理节点上查询仿真的远程转换表（ERTT）段，以查看ERTT段是否可以提供翻译。 如果接收到翻译，则可以将翻译加载到源节点上的TLB中。 否则可能为引用无效虚拟内存地址的实体或应用程序生成内存引用错误。

    Sharing memory within an application using scalable hardware resources
    4.
    发明授权
    Sharing memory within an application using scalable hardware resources 有权
    使用可扩展硬件资源在应用程序内共享内存

    公开(公告)号：US07529906B2

    公开(公告)日：2009-05-05

    申请号：US10643588

    申请日：2003-08-18

    申请人： Kitrick Sheets

    发明人： Kitrick Sheets

    IPC分类号： G06F12/00

    CPC分类号： G06F9/3834 ,  G06F9/3836 ,  G06F9/384

    摘要： Systems and methods include translating a virtual memory address into a physical memory address in a multi-node system that is initiated by providing the virtual memory address at a source node. A determination is made that a translation for the virtual memory address does not exist. A physical node to query is determined based on the virtual memory address. An emulated remote translation table (ERTT) segment is queried on the determined physical node to see if the ERTT segment may provide a translation. If the translation is received then the translation may be loaded into a TLB on the source node. Otherwise a memory reference error may be generated for the entity or application referencing the invalid virtual memory address.

    摘要翻译： 系统和方法包括将虚拟存储器地址转换成通过在源节点处提供虚拟存储器地址而启动的多节点系统中的物理存储器地址。 确定虚拟存储器地址的翻译不存在。 基于虚拟内存地址确定要查询的物理节点。 在确定的物理节点上查询仿真的远程转换表（ERTT）段，以查看ERTT段是否可以提供翻译。 如果接收到翻译，则可以将翻译加载到源节点上的TLB中。 否则可能为引用无效虚拟内存地址的实体或应用程序生成内存引用错误。

    Information Processing Grid and Method for High Performance and Efficient Resource Utilization
    5.
    发明申请
    Information Processing Grid and Method for High Performance and Efficient Resource Utilization 审中-公开
    信息处理网格和高效能资源利用方法

    公开(公告)号：US20120005685A1

    公开(公告)日：2012-01-05

    申请号：US13170894

    申请日：2011-06-28

    申请人： Steve S. Chen ,  Kitrick Sheets ,  Peter Marosan

    发明人： Steve S. Chen ,  Kitrick Sheets ,  Peter Marosan

    IPC分类号： G06F9/46

    CPC分类号： G06F9/5072

    摘要： System and method are proposed for intelligent assignment of submitted information processing jobs to computing resources in an information processing grid based upon real-time measurements of job behavior and predictive analysis of job throughput and computing resource consumption of the correspondingly generated workloads. The job throughput and computing resource utilization are measured and analyzed in multiple parametric dimensions. The analyzed workload may work with a job scheduling system to provide optimized job dispatchment to computing resources across the grid. Application of a parametric weighting system to the parametric dimensions makes the optimization system dynamic and flexible. Through adjustment of these parametric weights, the focus of the optimization can be adjusted dynamically to support the immediate operational goals of the system as a whole.

    摘要翻译： 提出了系统和方法，用于基于作业行为的实时测量和对相应产生的工作负载的计算资源消耗的预测分析，将所提交的信息处理作业智能地分配给信息处理网格中的计算资源。 在多个参数维度中测量和分析作业吞吐量和计算资源利用率。 分析的工作负载可能与作业调度系统一起工作，以便为跨网格的计算资源提供优化的作业调度。 参数加权系统对参数尺寸的应用使得优化系统动态灵活。 通过调整这些参数权重，可以动态调整优化的重点，以支持整个系统的即时操作目标。

    Remote translation mechanism for a multinode system
    7.
    发明申请
    Remote translation mechanism for a multinode system 有权
    多节点系统的远程翻译机制

    公开(公告)号：US20050044340A1

    公开(公告)日：2005-02-24

    申请号：US10643758

    申请日：2003-08-18

    申请人： Kitrick Sheets ,  Andrew Hastings

    发明人： Kitrick Sheets ,  Andrew Hastings

    IPC分类号： G06F12/08

    CPC分类号： G06F12/1036 ,  G06F12/1072

    摘要： The present invention provides a method of initializing shared memory in a multinode system. The method includes building a local address space in each of a plurality of nodes and exporting the local address space from each of the plurality of nodes to a Remote Translation Table (RTT) in each of the plurality of nodes. The present invention further provides system including a plurality of nodes, each node having one or more processors and a memory controller operatively coupled to the one or more processors, wherein the memory controller includes a RTT for holding translation information for an entire virtual memory address space for the node, further wherein the RTT is initialized upon the start of a process by building a local address space in the node, and exporting the local address space from the node to a RTT in each of the plurality of other nodes.

    摘要翻译： 本发明提供了一种在多节点系统中初始化共享存储器的方法。 该方法包括在多个节点的每一个中构建本地地址空间，并将多个节点中的每一个节点的本地地址空间导出到多个节点中的每个节点中的远程转换表（RTT）。 本发明还提供了包括多个节点的系统，每个节点具有一个或多个处理器和可操作地耦合到一个或多个处理器的存储器控​​制器，其中存储器控制器包括用于保持整个虚拟存储器地址空间的翻译信息的RTT 对于所述节点，进一步其中，通过在所述节点中构建本地地址空间，并且在所述多个其他节点中的每一个中将所述本地地址空间从所述节点导出到RTT，在所述进程开始时初始化所述RTT。