专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

1. 发明授权

US06792445B1 Providing predictable scheduling of programs using a repeating precomputed schedule 有权
公开(公告)号：US06792445B1
公开(公告)日：2004-09-14
申请号：US09564822
申请日：2000-05-04
申请人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
发明人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
IPC分类号： G06F900
CPC分类号： G06F9/4887
摘要： The present invention provides predictable scheduling of programs using a repeating precomputed schedule. In a preferred embodiment, a scheduler accesses an activity scheduling graph. The activity scheduling graph is comprised of nodes each representing a recurring execution interval, and has one root, one or more leaves, and at least one path from the root to each leaf. Each node is on at least one path from the root to a leaf, and the number of times the execution interval represented by each node occurs during the traversal of the graph is equal to the number of paths from the root to a leaf that the node is on. Each node has associated with it an execution interval length, and is adapted to being dedicated to executing the threads of a single activity. The scheduler first selects a current node within the accessed scheduling graph. When the processor becomes available to execute threads, the scheduler advances from the current node to a new current node in accordance with a root-to-leaf traversal of the scheduling graph. After advancing to the new current node, the scheduler executes one or more threads of the activity to which the new current node is dedicated for the execution interval length associated with the new current node. In a further preferred embodiment, the scheduler allocates specific iterations through specific nodes to satisfy the constraints submitted by threads.

2. 发明授权

US06317774B1 Providing predictable scheduling of programs using a repeating precomputed schedule 失效
标题翻译：使用重复的预先计算的计划提供可预测的程序调度
公开(公告)号：US06317774B1
公开(公告)日：2001-11-13
申请号：US08781106
申请日：1997-01-09
申请人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
发明人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
IPC分类号： G06F900
CPC分类号： G06F9/4887
摘要： The present invention provides predictable scheduling of programs using a repeating precomputed schedule. In a preferred embodiment, a scheduler accesses an activity scheduling graph. The activity scheduling graph is comprised of nodes each representing a recurring execution interval, and has one root, one or more leaves, and at least one path from the root to each leaf. Each node is on at least one path from the root to a leaf, and the number of times the execution interval represented by each node occurs during the traversal of the graph is equal to the number of paths from the root to a leaf that the node is on. Each node has associated with it an execution interval length, and is adapted to being dedicated to executing the threads of a single activity. The scheduler first selects a current node within the accessed scheduling graph. When the processor becomes available to execute threads, the scheduler advances from the current node to a new current node in accordance with a root-to-leaf traversal of the scheduling graph. After advancing to the new current node, the scheduler executes one or more threads of the activity to which the new current node is dedicated for the execution interval length associated with the new current node. In a further preferred embodiment, the scheduler allocates specific iterations through specific nodes to satisfy the constraints submitted by threads.
摘要翻译：本发明使用重复的预先计算的进度来提供程序的可预测的调度。在优选实施例中，调度器访问活动调度图。活动调度图由每个表示循环执行间隔的节点组成，并且具有一个根，一个或多个叶以及从根到每个叶的至少一个路径。每个节点在从根到叶的至少一个路径上，并且在图的遍历期间发生由每个节点表示的执行间隔的次数等于从根到叶的路径的数量，该节点是在。每个节点与其相关联的执行间隔长度，并且适于专用于执行单个活动的线程。调度器首先选择所访问的调度图中的当前节点。当处理器可用于执行线程时，调度器将根据调度图的根到叶遍历从当前节点前进到新的当前节点。在进入新的当前节点之后，调度器执行新的当前节点专用于与新的当前节点相关联的执行间隔长度的活动的一个或多个线程。在另一优选实施例中，调度器通过特定节点分配特定迭代以满足线程提交的约束。

3. 发明授权

US06490612B1 Providing predictable scheduling of programs using a repeating precomputed schedule 有权
标题翻译：使用重复的预先计算的计划提供可预测的程序调度
公开(公告)号：US06490612B1
公开(公告)日：2002-12-03
申请号：US09564564
申请日：2000-05-04
申请人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
发明人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
IPC分类号： G06F15173
CPC分类号： G06F9/4887
摘要： The present invention provides predictable scheduling of programs using a repeating precomputed schedule. In a preferred embodiment, a scheduler accesses an activity scheduling graph. The activity scheduling graph is comprised of nodes each representing a recurring execution interval, and has one root, one or more leaves, and at least one path from the root to each leaf. Each node is on at least one path from the root to a leaf, and the number of times the execution interval represented by each node occurs during the traversal of the graph is equal to the number of paths from the root to a leaf that the node is on. Each node has associated with it an execution interval length, and is adapted to being dedicated to executing the threads of a single activity. The scheduler first selects a current node within the accessed scheduling graph. When the processor becomes available to execute threads, the scheduler advances from the current node to a new current node in accordance with a root-to-leaf traversal of the scheduling graph. After advancing to the new current node, the scheduler executes one or more threads of the activity to which the new current node is dedicated for the execution interval length associated with the new current node. In a further preferred embodiment, the scheduler allocates specific iterations through specific nodes to satisfy the constraints submitted by threads.
摘要翻译：本发明使用重复的预先计算的进度来提供程序的可预测的调度。在优选实施例中，调度器访问活动调度图。活动调度图由每个表示循环执行间隔的节点组成，并且具有一个根，一个或多个叶以及从根到每个叶的至少一个路径。每个节点在从根到叶的至少一个路径上，并且在图的遍历期间发生由每个节点表示的执行间隔的次数等于从根到叶的路径的数量，该节点是在。每个节点与其相关联的执行间隔长度，并且适于专用于执行单个活动的线程。调度器首先选择所访问的调度图中的当前节点。当处理器可用于执行线程时，调度器将根据调度图的根到叶遍历从当前节点前进到新的当前节点。在进入新的当前节点之后，调度器执行新的当前节点专用于与新的当前节点相关联的执行间隔长度的活动的一个或多个线程。在另一优选实施例中，调度器通过特定节点分配特定迭代以满足线程提交的约束。

4. 发明授权

US07117501B2 Application-level access to kernel input/output state 失效
标题翻译：应用程序级访问内核输入/输出状态
公开(公告)号：US07117501B2
公开(公告)日：2006-10-03
申请号：US10301468
申请日：2002-11-21
申请人： Daniela Rosu , Marcel-Catalin Rosu
发明人： Daniela Rosu , Marcel-Catalin Rosu
IPC分类号： G06F15/163
CPC分类号： G06F9/544 , G06F9/545
摘要： A technique for tracking a state of one or more input/output (I/O) channels associated with an application, by the application itself, comprises the steps of: (i) storing, by an operating system kernel, one or more selected elements of the state of at least a portion of the one or more I/O channels associated with the application in a memory which is shared by the application and the operating system kernel, when the one or more elements are available to the operating system kernel; (ii) acquiring, by the application, at least a portion of the stored elements through one or more memory read operations of the shared memory; and (iii) assessing, by the application, one or more of the acquired elements to determine the state of the one or more I/O channels corresponding thereto. In this manner, a need for context switching to track the state of the one or more I/O channels is thereby eliminated.
摘要翻译：用于跟踪由应用程序本身与应用相关联的一个或多个输入/输出（I / O）信道的状态的技术包括以下步骤：（i）由操作系统内核存储一个或多个所选元素当所述一个或多个元件对于所述操作系统内核可用时，所述至少一部分所述一个或多个I / O通道的状态与所述应用程序相关联的所述应用程序和所述操作系统内核共享的存储器中的状态; （ii）通过所述共享存储器的一个或多个存储器读取操作，通过所述应用获取所存储的元件的至少一部分; 以及（iii）由应用程序评估所获取的元素中的一个或多个以确定与其对应的一个或多个I / O信道的状态。以这种方式，由此消除了用于跟踪一个或多个I / O信道的状态的上下文切换的需要。

5. 发明授权

US06718360B1 Providing predictable scheduling of programs using a repeating precomputed schedule 有权
标题翻译：使用重复的预先计算的计划提供可预测的程序调度
公开(公告)号：US06718360B1
公开(公告)日：2004-04-06
申请号：US09564881
申请日：2000-05-04
申请人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
发明人： Michael B. Jones , Richard P. Draves, Jr. , Daniela Rosu , Marcel-Catalin Rosu
IPC分类号： G06F900
CPC分类号： G06F9/4887
摘要： The present invention provides predictable scheduling of programs using a repeating precomputed schedule. In a preferred embodiment, a scheduler accesses an activity scheduling graph. The activity scheduling graph is comprised of nodes each representing a recurring execution interval, and has one root, one or more leaves, and at least one path from the root to each leaf. Each node is on at least one path from the root to a leaf, and the number of times the execution interval represented by each node occurs during the traversal of the graph is equal to the number of paths from the root to a leaf that the node is on. Each node has associated with it an execution interval length, and is adapted to being dedicated to executing the threads of a single activity. The scheduler first selects a current node within the accessed scheduling graph. When the processor becomes available to execute threads, the scheduler advances from the current node to a new current node in accordance with a root-to-leaf traversal of the scheduling graph. After advancing to the new current node, the scheduler executes one or more threads of the activity to which the new current node is dedicated for the execution interval length associated with the new current node. In a further preferred embodiment, the scheduler allocates specific iterations through specific nodes to satisfy the constraints submitted by threads.
摘要翻译：本发明使用重复的预先计算的进度来提供程序的可预测的调度。在优选实施例中，调度器访问活动调度图。活动调度图由每个表示循环执行间隔的节点组成，并且具有一个根，一个或多个叶以及从根到每个叶的至少一个路径。每个节点在从根到叶的至少一个路径上，并且在图的遍历期间发生由每个节点表示的执行间隔的次数等于从根到叶的路径的数量，该节点是在。每个节点与其相关联的执行间隔长度，并且适于专用于执行单个活动的线程。调度器首先选择所访问的调度图中的当前节点。当处理器可用于执行线程时，调度器将根据调度图的根到叶遍历从当前节点前进到新的当前节点。在进入新的当前节点之后，调度器执行新的当前节点专用于与新的当前节点相关联的执行间隔长度的活动的一个或多个线程。在另一优选实施例中，调度器通过特定节点分配特定迭代以满足线程提交的约束。

6. 发明授权

US08321704B2 Managing electric power consumption by configuring elements of a distributed computing system 有权
标题翻译：通过配置分布式计算系统的元素来管理电力消耗
公开(公告)号：US08321704B2
公开(公告)日：2012-11-27
申请号：US12727950
申请日：2010-03-19
申请人： Edward P. Clarke, Jr. , Lorraine M. Herger , Marcel-Catalin Rosu , Frank A. Schaffa , Edith H. Stern
发明人： Edward P. Clarke, Jr. , Lorraine M. Herger , Marcel-Catalin Rosu , Frank A. Schaffa , Edith H. Stern
IPC分类号： G06F1/32 , G06F1/00 , G06F15/173
CPC分类号： G06F9/5072 , H04L41/0816 , H04L41/0853 , H04L41/5003 , H04L41/5019 , H04L41/5067 , H04L43/00 , H04L43/06 , H04L43/0817 , H04L43/0852 , H04L43/0882 , H04L43/0888 , H04L43/10 , H04L43/12 , H04L67/10 , H04L67/125 , H04L67/20 , H04L67/22 , H04L67/32 , H04L69/329 , Y02D10/22 , Y02D10/36
摘要： A method and system for managing electric power consumption by elements of a distributed computing system comprises: determining one or more system metrics that relate to electric power usage as consumed by elements of a configured distributed environment; determining a system value in response to the one or more system metrics, the value determined according to one or more value criteria; and, while in-progress applications are being run in the computing environment, evaluating one or more potential changes in the distributed computing environment and determining an alternate system value based on the changes; and, re-configuring elements of the distributed computing environment dynamically while the computing environment is operating, in accordance with a determined alternate system value. The re-configuring elements step is in accordance with a potential change operative to alter electric power consumption.
摘要翻译：一种用于通过分布式计算系统的元件管理电力消耗的方法和系统包括：确定与配置的分布式环境的元件消耗的与电力使用相关的一个或多个系统度量; 响应于所述一个或多个系统度量来确定系统值，所述值根据一个或多个价值标准确定; 并且当在计算环境中运行正在进行的应用程序时，评估分布式计算环境中的一个或多个潜在变化并且基于所述变化来确定替代系统值; 以及根据所确定的备选系统值，在所述计算环境正在运行时，重新配置所述分布式计算环境的元件。重新配置元件步骤符合可改变电力消耗的潜在变化。

7. 发明授权

US07752330B2 System for low power operation of wireless LAN interfaces 失效
标题翻译：无线LAN接口的低功耗操作系统
公开(公告)号：US07752330B2
公开(公告)日：2010-07-06
申请号：US11927572
申请日：2007-10-29
申请人： Claus Michael Olsen , Jeffrey W. Clark , Chandrasekhar Narayanaswami , Marcel-Catalin Rosu
发明人： Claus Michael Olsen , Jeffrey W. Clark , Chandrasekhar Narayanaswami , Marcel-Catalin Rosu
IPC分类号： G06F13/00
CPC分类号： H04W52/0216 , G06F1/3209 , H04L29/08846 , H04L67/02 , H04L67/2847 , H04L67/2852 , H04L67/2861 , H04L67/325 , H04L69/16 , H04L69/163 , H04L69/165 , H04W84/12 , Y02D30/30 , Y02D30/40 , Y02D70/142
摘要： A computer program product includes instructions for causing a processor to: alert a client of the configuration of said computer program product; use a memory space for buffering the network application data destined for the client; release the network application data to the client, based on at least one occurrence of a specified condition that promotes energy savings; and purposely delay at least some of said data with an amount of time greater than zero to promote energy savings.
摘要翻译：计算机程序产品包括用于使处理器：向客户端通知所述计算机程序产品的配置的指令; 使用内存空间来缓冲发往客户端的网络应用程序数据; 基于促进节能的指定条件的至少一个出现，将网络应用数据发布给客户端; 并且有意地将所述数据中的至少一些以大于零的时间量推迟以促进节能。

8. 发明申请

US20080052548A1 SYSTEM FOR LOW POWER OPERATION OF WIRELESS LAN INTERFACES 审中-公开
标题翻译：无线局域网接口低功耗运行系统
公开(公告)号：US20080052548A1
公开(公告)日：2008-02-28
申请号：US11926977
申请日：2007-10-29
申请人： Claus Olsen , Jeffrey Clark , Chandrasekhar Narayanaswami , Marcel-Catalin Rosu
发明人： Claus Olsen , Jeffrey Clark , Chandrasekhar Narayanaswami , Marcel-Catalin Rosu
IPC分类号： G08C17/02
CPC分类号： H04W52/0216 , G06F1/3209 , H04L29/08846 , H04L67/02 , H04L67/2847 , H04L67/2852 , H04L67/2861 , H04L67/325 , H04L69/16 , H04L69/163 , H04L69/165 , H04W84/12 , Y02D30/30 , Y02D30/40 , Y02D70/142
摘要： In a network including a proxy server located between a wireless access point and an origin server; and a client module detecting the availability of the proxy server; a method for conserving power in the client module includes: configuring a wireless interface to promote energy savings when using a proxy server; buffering data destined for the wireless client unit at the proxy server; and releasing the data to the client module responsive to the occurrence of at least one specified condition that promotes energy savings.
摘要翻译：在包括位于无线接入点和原始服务器之间的代理服务器的网络中; 以及客户端模块，用于检测代理服务器的可用性; 一种用于在客户端模块中节省功率的方法包括：配置无线接口以在使用代理服务器时促进节能; 在代理服务器处缓存指定给无线客户端单元的数据; 以及响应于促进节能的至少一个指定条件的发生而将数据发布到客户端模块。

9. 发明申请

US20050071561A1 Apparatus for reducing accesses to levels of a storage hierarchy in a computing system 有权
标题翻译：用于减少对计算系统中的存储层级的访问的设备
公开(公告)号：US20050071561A1
公开(公告)日：2005-03-31
申请号：US10674926
申请日：2003-09-30
申请人： Claus Olsen , Frederick Douglis , Marcel-Catalin Rosu , Thomas Hildner
发明人： Claus Olsen , Frederick Douglis , Marcel-Catalin Rosu , Thomas Hildner
IPC分类号： G06F1/32 , G06F12/00
CPC分类号： G06F1/3268 , G06F1/3221 , G06F1/3275 , Y02D10/13 , Y02D10/14 , Y02D10/154
摘要： An information processing system comprises first and second levels of a storage hierarchy, wherein accessing information in the first level consumes more energy than accessing information in the second level; and a processor for writing information to the second level of storage based on energy-conserving criteria. The energy-conserving criteria comprise a set of heuristics, including system state information and user preferences.
摘要翻译：信息处理系统包括存储分级的第一级和第二级，其中访问第一级的信息比访问第二级的信息消耗更多的能量; 以及基于节能标准将信息写入第二级存储的处理器。节能标准包括一组启发式，包括系统状态信息和用户偏好。

10. 发明授权

US08713564B2 Method and apparatus for using virtual machine technology for managing parallel communicating applications 失效
标题翻译：用于使用虚拟机技术来管理并行通信应用的方法和装置
公开(公告)号：US08713564B2
公开(公告)日：2014-04-29
申请号：US12098219
申请日：2008-04-04
申请人： Marcel-Catalin Rosu , Dehanjan Saba , Sambit Sahu , Anees A. Shaikh
发明人： Marcel-Catalin Rosu , Dehanjan Saba , Sambit Sahu , Anees A. Shaikh
IPC分类号： G06F9/455 , G06F9/46
CPC分类号： G06F9/5088 , G06F9/45558 , G06F2009/4557
摘要： A method (and system) for managing a distributed-memory parallel application running on multiple servers, includes dynamically moving a plurality of executable program components, where each of the plurality of executable program components are running on one of a plurality of virtual machines, using migration of the virtual machines between physical servers. The load balancing is operated based on a workload of each of the virtual machines and servers, where a virtual machine, or a plurality of virtual machines, are transferred to balance the workload between each of the servers.
摘要翻译：一种用于管理在多个服务器上运行的分布式存储器并行应用的方法（和系统），包括动态移动多个可执行程序组件，其中所述多个可执行程序组件中的每一个在多个虚拟机之一上运行，使用在物理服务器之间迁移虚拟机。基于每个虚拟机和服务器的工作负载来操作负载平衡，其中虚拟机或多个虚拟机被传送以平衡每个服务器之间的工作负载。

你已经成功收藏专利！

检索式保存成功!

IPRDB

热门服务

关于我们

友情链接

联系方式