会员体验
专利管家(专利管理)
工作空间(专利管理)
风险监控(情报监控)
数据分析(专利分析)
侵权分析(诉讼无效)
联系我们
交流群
官方交流:
QQ群: 891211   
微信请扫码    >>>
现在联系顾问~
热词
    • 4. 发明授权
    • Method, system, and storage medium for searching multiple queues for prioritized work elements
    • 用于搜索多个队列以确定优先工作元素的方法,系统和存储介质
    • US07657889B2
    • 2010-02-02
    • US10820176
    • 2004-04-06
    • Bernard R. PierceRobert R. Rogers
    • Bernard R. PierceRobert R. Rogers
    • G06F9/46
    • G06F9/4881
    • A method of searching for work elements for processing in a computing system having a primary queue of work elements and at least one secondary queue of work elements. A numerical priority value is associated with each of the work elements. The method includes setting an initial priority bar and processing work elements from the primary queue until reaching a work element having a priority less than the initial priority bar. A priority bar is set equal to a minimum of a priority limit and a priority on the at least one secondary queue. If the primary queue contains a work element having a priority greater than or equal to the priority bar, then the work element is processed. If the primary queue contains a work element having a priority less than the priority bar, then a work element from the at least one secondary queue is processed.
    • 一种在具有工作元素的主队列和至少一个工作元素的次要队列的计算系统中搜索工作元素以进行处理的方法。 数值优先级值与每个工作元素相关联。 该方法包括设置初始优先级条并从主队列处理工作元素,直到到达优先级小于初始优先级条的工作元素。 将优先级条设置为等于所述至少一个次要队列的优先级限制和优先级的最小值。 如果主队列包含优先级大于或等于优先级的工作元素,则处理工作元素。 如果主队列包含具有优先级小于优先级条的工作元素,则处理来自至少一个辅助队列的工作元素。
    • 5. 发明申请
    • AFFINITY DISPATCHING LOAD BALANCER WITH PRECISE CPU CONSUMPTION DATA
    • 具有精确CPU消耗数据的AFFINITY DISPATCHING LOAD BALANCER
    • US20080178192A1
    • 2008-07-24
    • US12051295
    • 2008-03-19
    • Donna N. DillenbergerGreg A. DyckStephen J. HeisigBernard R. PierceDonald W. SchmidtGong Su
    • Donna N. DillenbergerGreg A. DyckStephen J. HeisigBernard R. PierceDonald W. SchmidtGong Su
    • G06F9/46
    • G06F9/505G06F2209/5022
    • A computer-implemented method for distributing a plurality of tasks over a plurality of processing nodes in a processor network includes the following steps: calculating a task process consumption value for the tasks; calculating a measured node processor consumption value for the nodes; calculating a target node processor consumption value for the nodes, the target node processor consumption value indicating optimal node processor consumption; calculating a load index value as a difference between the calculated node processor consumption value for a node i and the target node processor consumption value for node i; and distributing the tasks among the nodes to balance a processor workload among the nodes, according to the calculated load index value, such that the calculated load index value of each node is substantially zero. The method further embodies a multi-dimensional balancing matrix, each dimension of the matrix representing a node corresponding to a different processor type and each cell representing tasks assigned to multiple nodes.
    • 用于在处理器网络中的多个处理节点上分布多个任务的计算机实现的方法包括以下步骤:计算任务的任务过程消耗值; 计算节点的测量节点处理器消耗值; 计算节点的目标节点处理器消耗值,目标节点处理器消耗值指示最佳节点处理器消耗; 计算负载指标值作为节点i的计算节点处理器消耗值与节点i的目标节点处理器消耗值之间的差值; 并且根据所计算的负载指数值,在所述节点之间分配所述任务以平衡所述节点之间的处理器工作负荷,使得所计算的每个节点的负载指数值基本为零。 该方法进一步体现了多维平衡矩阵,矩阵的每个维度表示对应于不同处理器类型的节点,每个小区表示分配给多个节点的任务。
    • 6. 发明申请
    • DETERMINATION OF THE FRAME AGE IN A LARGE REAL STORAGE ENVIRONMENT
    • 在大型实际存储环境中确定框架年龄
    • US20080077764A1
    • 2008-03-27
    • US11857513
    • 2007-09-19
    • Bernard R. PierceElpida TzortzatosDieter Wellerdiek
    • Bernard R. PierceElpida TzortzatosDieter Wellerdiek
    • G06F12/00
    • G06F12/123G06F11/3419G06F11/3433G06F2201/81G06F2201/835G06F2201/88
    • A method for automatically determining performance problems in a computer system due to a metric indicating a current memory peak load in the computer system is disclosed. In order to decrease CPU consumption in large memories it is proposed to perform the steps of: a) using a cyclic stealing algorithm used in prior art for stealing subunits, if the subunits were not referenced since the last cycle and writing the subunits to a secondary memory device, with an extension for determining the age of memory subunits, wherein the extension comprises the steps of: b) writing time stamps for a subselection of the memory subunits to a data storage always when the stealing routine has processed a subselection, wherein the current time of a current cycle and the preceding current time of a preceding cycle are stored in respective entries of the data storage, for generating age information for the memory subunits, c) calculating the metric based on average age calculations including differences between a respective one of the current time and a respective one of the preceding current time of one or more of the table entries, d) determining the occurrence of a peak load, when the metric is beyond a predetermined threshold level.
    • 公开了一种用于在计算机系统中自动确定由于指示计算机系统中的当前存储器峰值负载的度量的度量而导致的性能问题的方法。 为了降低大存储器中的CPU消耗,建议执行以下步骤:a)使用现有技术中用于窃取子单元的循环窃取算法,如果从上次循环以来未参考子单元并将子单元写入次级 存储器设备,具有用于确定存储器子单元的年龄的扩展,其中所述扩展包括以下步骤:b)当所述窃取程序已经处理子选择时,始终将所述存储器子单元的子选择的时间戳写入数据存储器,其中, 当前周期的当前时间和前一周期的先前当前时间被存储在数据存储器的相应条目中,用于生成存储器子单元的年龄信息,c)基于平均年龄计算来计算包括相应一个 以及当前时间的一个或多个的前一当前时间中的相应一个,d)确定峰值的出现 当度量超过预定阈值水平时。
    • 9. 发明授权
    • Affinity dispatching load balancer with precise CPU consumption data
    • 亲和调度负载平衡器,具有精确的CPU消耗数据
    • US07941805B2
    • 2011-05-10
    • US11504155
    • 2006-08-15
    • Donna N. DillenbergerGreg A. DyckStephen J. HeisigBernard R. PierceDonald W. SchmidtGong Su
    • Donna N. DillenbergerGreg A. DyckStephen J. HeisigBernard R. PierceDonald W. SchmidtGong Su
    • G06F9/46G06F15/173
    • G06F9/505G06F2209/5022
    • A computer-implemented method for distributing a plurality of tasks over a plurality of processing nodes in a processor network includes the following steps: calculating a task process consumption value for the tasks; calculating a measured node processor consumption value for the nodes; calculating a target node processor consumption value for the nodes, the target node processor consumption value indicating optimal node processor consumption; calculating a load index value as a difference between the calculated node processor consumption value for a node i and the target node processor consumption value for node i; and distributing the tasks among the nodes to balance a processor workload among the nodes, according to the calculated load index value, such that the calculated load index value of each node is substantially zero. The method further embodies a multi-dimensional balancing matrix, each dimension of the matrix representing a node corresponding to a different processor type and each cell representing tasks assigned to multiple nodes.
    • 用于在处理器网络中的多个处理节点上分布多个任务的计算机实现的方法包括以下步骤:计算任务的任务过程消耗值; 计算节点的测量节点处理器消耗值; 计算节点的目标节点处理器消耗值,目标节点处理器消耗值指示最佳节点处理器消耗; 计算负载指标值作为节点i的计算节点处理器消耗值与节点i的目标节点处理器消耗值之间的差值; 并且根据所计算的负载指数值,在所述节点之间分配所述任务以平衡所述节点之间的处理器工作负荷,使得所计算的每个节点的负载指数值基本为零。 该方法进一步体现了多维平衡矩阵,矩阵的每个维度表示对应于不同处理器类型的节点,每个小区表示分配给多个节点的任务。