公开(公告)号：US08108877B2

公开(公告)日：2012-01-31

申请号：US12051611

申请日：2008-03-19

申请人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

发明人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

IPC分类号： G06F9/46 ,  G06F15/173

CPC分类号： G06F9/505 ,  G06F2209/5022

摘要： A system for distributing a plurality of tasks over a plurality of nodes in a network includes: a plurality of processors for executing tasks; a plurality of nodes comprising processors; a task dispatcher; and a load balancer. The task dispatcher receives as input the plurality of tasks; calculates a task processor consumption value for the tasks; calculates a node processor consumption value for the nodes; calculates a target node processor consumption value for the nodes; and then calculates a load index value as a difference between the calculated node processor consumption for a node i and the target node processor consumption value for the node i. The balancer distributes the tasks among the nodes to balance the processor workload among the nodes according to the calculated load index value of each node, such that the calculated load index value of each node is substantially zero.

摘要翻译： 用于在网络中的多个节点上分布多个任务的系统包括：用于执行任务的多个处理器; 包括处理器的多个节点; 任务调度员 和负载平衡器。 任务调度员作为输入接收多个任务; 计算任务的任务处理器消耗值; 计算节点的节点处理器消耗值; 计算节点的目标节点处理器消耗值; 然后计算负载指标值作为节点i的计算的节点处理器消耗与节点i的目标节点处理器消耗值之间的差值。 平衡器根据每个节点的计算负载指数值，在节点之间分配任务以平衡节点之间的处理器工作负荷，使得每个节点的计算负载指数值基本为零。

公开(公告)号：US20080178192A1

公开(公告)日：2008-07-24

申请号：US12051295

申请日：2008-03-19

申请人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

发明人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

IPC分类号： G06F9/46

CPC分类号： G06F9/505 ,  G06F2209/5022

摘要： 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.

摘要翻译： 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。

公开(公告)号：US07941805B2

公开(公告)日：2011-05-10

申请号：US11504155

申请日：2006-08-15

申请人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

发明人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

IPC分类号： G06F9/46 ,  G06F15/173

CPC分类号： G06F9/505 ,  G06F2209/5022

摘要： 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.

摘要翻译： 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。

公开(公告)号：US08108875B2

公开(公告)日：2012-01-31

申请号：US12051295

申请日：2008-03-19

申请人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

发明人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

IPC分类号： G06F9/46 ,  G06F15/173

CPC分类号： G06F9/505 ,  G06F2209/5022

摘要： 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.

摘要翻译： 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。

公开(公告)号：US20080216087A1

公开(公告)日：2008-09-04

申请号：US12051611

申请日：2008-03-19

申请人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

发明人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

IPC分类号： G06F9/46

CPC分类号： G06F9/505 ,  G06F2209/5022

摘要： A system for distributing a plurality of tasks over a plurality of nodes in a network includes: a plurality of processors for executing tasks; a plurality of nodes comprising processors; a task dispatcher; and a load balancer. The task dispatcher receives as input the plurality of tasks; calculates a task processor consumption value for the tasks; calculates a node processor consumption value for the nodes; calculates a target node processor consumption value for the nodes; and then calculates a load index value as a difference between the calculated node processor consumption for a node i and the target node processor consumption value for the node i. The balancer distributes the tasks among the nodes to balance the processor workload among the nodes according to the calculated load index value of each node, such that the calculated load index value of each node is substantially zero.

摘要翻译： 用于在网络中的多个节点上分布多个任务的系统包括：用于执行任务的多个处理器; 包括处理器的多个节点; 任务调度员 和负载平衡器。 任务调度员作为输入接收多个任务; 计算任务的任务处理器消耗值; 计算节点的节点处理器消耗值; 计算节点的目标节点处理器消耗值; 然后计算负载指标值作为节点i的计算的节点处理器消耗与节点i的目标节点处理器消耗值之间的差值。 平衡器根据每个节点的计算负载指数值，在节点之间分配任务以平衡节点之间的处理器工作负荷，使得每个节点的计算负载指数值基本为零。

公开(公告)号：US20080046895A1

公开(公告)日：2008-02-21

申请号：US11504155

申请日：2006-08-15

申请人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

发明人： Donna N. Dillenberger ,  Greg A. Dyck ,  Stephen J. Heisig ,  Bernard R. Pierce ,  Donald W. Schmidt ,  Gong Su

IPC分类号： G06F9/46

CPC分类号： G06F9/505 ,  G06F2209/5022

摘要： 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.

摘要翻译： 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。

公开(公告)号：US20090055636A1

公开(公告)日：2009-02-26

申请号：US11843386

申请日：2007-08-22

申请人： Stephen J. Heisig ,  Joshua W. Knight ,  Rui Zhang

发明人： Stephen J. Heisig ,  Joshua W. Knight ,  Rui Zhang

IPC分类号： G06F9/30

CPC分类号： G06F11/3447 ,  G06F11/3409

摘要： A computer implemented method, data processing system, and computer program product for generating and applying a model to predict hardware performance hazards in a machine instruction sequence. The illustrative embodiments generate rules which specify relationships between a first instruction code sequence and hardware performance hazards. This rule generation is performed as a machine task rather than a human task (e.g., traditional hand coding tools). When a second instruction code sequence is received, the rules are applied to the second instruction code sequence. Responsive to a prediction that execution of the second instruction code sequence will cause the hardware performance hazards, instructions in the second instruction code sequence that cause the hardware performance hazards are identified.

摘要翻译： 一种用于生成和应用模型以预测机器指令序列中的硬件性能危害的计算机实现的方法，数据处理系统和计算机程序产品。 说明性实施例产生规定第一指令代码序列与硬件性能危害之间的关系的规则。 该规则生成作为机器任务而不是人的任务来执行（例如，传统的手写编码工具）。 当接收到第二指令代码序列时，将规则应用于第二指令代码序列。 响应于第二指令代码序列的执行将导致硬件性能危害的预测，识别导致硬件性能危害的第二指令代码序列中的指令。