专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

101. 发明授权

US08909698B2 Grid-enabled, service-oriented architecture for enabling high-speed computing applications 有权
标题翻译：具有网格功能，面向服务的架构，实现高速计算应用
公开(公告)号：US08909698B2
公开(公告)日：2014-12-09
申请号：US13441233
申请日：2012-04-06
申请人： Onkar S. Parmar , Yonggang Hu
发明人： Onkar S. Parmar , Yonggang Hu
IPC分类号： G06F15/16 , G06F15/173 , H04L12/28 , H04L29/08 , G06F9/50 , H04L29/14
CPC分类号： G06F9/5038 , G06F9/505 , G06F9/5055 , G06F2209/5016 , G06F2209/508 , H04L67/1002 , H04L67/1012 , H04L67/1034 , H04L67/14 , H04L67/16 , H04L67/28 , H04L67/2809 , H04L67/325 , H04L69/40
摘要： According to one aspect of the present disclosure, a method and technique for data processing in a distributed computing system having a service-oriented architecture is disclosed. The method includes: receiving, by a workload input interface, workloads associated with an application from one or more clients for execution on the distributed computing system; identifying, by a resource management interface, available service hosts or service instances for computing the workloads received from the one or more clients; responsive to receiving an allocation request for the one or more hosts or service instances by the workload input interface, providing, by the resource management interface, address information of one or more workload output interfaces; and sending, by the one or more workload output interfaces, workloads received from the workload input interface to the one or more service instances.
摘要翻译：根据本公开的一个方面，公开了一种具有面向服务架构的分布式计算系统中的数据处理方法和技术。该方法包括：由工作负载输入接口接收与来自一个或多个客户端的应用程序相关联的工作负载以在分布式计算系统上执行; 通过资源管理界面识别可用的服务主机或服务实例，用于计算从所述一个或多个客户端接收的工作负载; 响应于所述工作负载输入接口接收到所述一个或多个主机或服务实例的分配请求，由所述资源管理接口提供一个或多个工作负荷输出接口的地址信息; 并且由一个或多个工作负载输出接口将从工作负载输入接口接收的工作负载发送到一个或多个服务实例。

102. 发明授权

US08875150B2 Monitoring real-time computing resources for predicted resource deficiency 有权
标题翻译：监控实时计算资源以预测资源缺乏
公开(公告)号：US08875150B2
公开(公告)日：2014-10-28
申请号：US13452662
申请日：2012-04-20
申请人： Rashed Ferdous , Arthur J Meyer, III , Carlos P Sosa
发明人： Rashed Ferdous , Arthur J Meyer, III , Carlos P Sosa
IPC分类号： G06F9/50 , G06F11/30 , G06F11/34 , G06F11/00
CPC分类号： G06F11/3442 , G06F9/5044 , G06F9/505 , G06F11/004 , G06F11/3409 , G06F11/3452 , G06F2209/503 , G06F2209/508
摘要： Techniques used to enhance the execution of long-running or complex software application instances and jobs on computing systems. In one embodiment, inadequate system resources and failure of a job execution on the computing system may be predicted. A determination may be made as to whether inadequate resources exist prior to execution of the job, and resource requirements may be monitored to detect in real time if inadequate resources will be encountered during the job execution for cases where, for example, resource availability has unexpectedly decreased. If a resource deficiency is predicted on the executing computer system, the job may be paused and corrective action may be taken or a user may be alerted. The job may resume after the resource deficiency is met. Additional embodiments may integrate resource monitoring with the adaptive selection of a computer system or application execution environment based on resource capability predictions and benchmarks.
摘要翻译：用于增强计算系统上长时间运行或复杂的软件应用程序实例和作业执行的技术。在一个实施例中，可以预测系统资源不足和计算系统上的作业执行失败。可以确定在执行作业之前是否存在不充足的资源，并且如果在例如资源可用性意外地出现的情况下，在作业执行期间将遇到不足的资源时，可以监视资源需求以便实时检测减少。如果在执行的计算机系统上预测资源不足，则该作业可以被暂停，并且可以采取纠正措施或者可以警告用户。资源不足之后，工作可能会恢复。另外的实施例可以基于资源能力预测和基准将资源监视与计算机系统或应用执行环境的自适应选择相结合。

103. 发明授权

US08874893B2 Effect translation and assessment among microarchitecture components 有权
标题翻译：微架构组件之间的效果翻译和评估
公开(公告)号：US08874893B2
公开(公告)日：2014-10-28
申请号：US13429587
申请日：2012-03-26
申请人： Bulent Abali , Michael S. Floyd , Eren Kursun
发明人： Bulent Abali , Michael S. Floyd , Eren Kursun
IPC分类号： G06F9/00 , G06F1/00 , G06F1/32 , G06F15/00 , G06F3/00
CPC分类号： G06F11/3024 , G06F11/3058 , G06F11/3062 , G06F11/3409 , G06F11/3433 , G06F11/348 , G06F2209/501 , G06F2209/508
摘要： Awareness of the relationships among the operating parameters for an individual core and among cores allows dynamic and intelligent management of the multi-core system. The relationships among operating parameters and cores, which can be somewhat opaque, are established with design-time simulations, and adapted with run time data collected from operation of the multi-core system. The relationships are expressed with functions that translate between operating parameters, between different cores, and between operating parameters of different cores. These functions are embodied in circuitry built into the multi-core system. The circuitry will be referred to hereinafter as a translator unit. The translator unit traverses the complex relational dependencies among multiple operating parameters and multiple cores, and determines an outcome with respect to one or more constraints corresponding to those operating parameters and cores.
摘要翻译：意识到单个核心和核心的运行参数之间的关系允许多核系统的动态和智能管理。可以通过设计时模拟建立操作参数和核心之间的关系，这些关系可能有些不透明，并且适用于从多核系统运行收集的运行时数据。这些关系用转换操作参数，不同内核之间以及不同内核的操作参数之间的函数表示。这些功能体现在内置于多核系统中的电路中。电路在下文中将被称为翻译单元。翻译器单元遍历多个操作参数和多个核心之间的复杂关系依赖关系，并且确定与这些操作参数和核心相对应的一个或多个约束的结果。

104. 发明授权

US08856196B2 System and method for transferring tasks in a multi-core processor based on trial execution and core node 有权
标题翻译：基于试运行和核心节点在多核处理器中传输任务的系统和方法
公开(公告)号：US08856196B2
公开(公告)日：2014-10-07
申请号：US12742854
申请日：2009-02-23
申请人： Kazumi Yamada
发明人： Kazumi Yamada
IPC分类号： G06F15/16 , G06F11/16 , G06F9/50 , G06F11/00
CPC分类号： G06F9/505 , G06F11/004 , G06F11/1641 , G06F2209/508 , Y02D10/22
摘要： A multi core system for allocating a task generated from a control system program to an appropriate CPU core and executing the task includes a trial-execution instructing part configured to cause a second CPU core to trial-execute a task which a first CPU core executes before the multi core system transfers the task from the first CPU core to the second CPU core and causes the second CPU core to execute the task, a determining part configured to determine whether an execution result by the first CPU core matches an execution result by the second CPU core, and an allocation fixing part configured to fix the second CPU core as the appropriate CPU core to which the task is allocated if the determining part determines that the execution result by the first CPU core matches the execution result by the second CPU core.
摘要翻译：一种用于将从控制系统程序生成的任务分配给适当的CPU核并执行该任务的多核系统包括一个试用执行指令部分，被配置为使第二CPU核心试图执行第一CPU内核执行的任务所述多核系统将所述任务从所述第一CPU内核传送到所述第二CPU内核，并且使所述第二CPU内核执行所述任务，所述确定部件被配置为确定所述第一CPU核心的执行结果是否与执行结果匹配第二CPU核心 CPU核心和分配固定部件，其被配置为如果所述确定部件确定所述第一CPU核心的执行结果与所述第二CPU核心的执行结果相匹配，则将所述第二CPU核心固定为所述任务分配到的适当CPU核心。

105. 发明申请

US20140289733A1 SYSTEM AND METHOD FOR EFFICIENT TASK SCHEDULING IN HETEROGENEOUS, DISTRIBUTED COMPUTE INFRASTRUCTURES VIA PERVASIVE DIAGNOSIS 有权
标题翻译：通过全面诊断在异质性，分布式计算机基础结构中有效的任务调度的系统和方法
公开(公告)号：US20140289733A1
公开(公告)日：2014-09-25
申请号：US13848934
申请日：2013-03-22
申请人： PALO ALTO RESEARCH CENTER INCORPORATED
发明人： Christian Fritz , Shekhar Gupta , Johan de Kleer , Robert R. Price
IPC分类号： G06F9/48
CPC分类号： G06F9/5066 , G06F2209/508
摘要： A system and method schedules jobs in a cluster of compute nodes. A job with an unknown resource requirement profile is received. The job includes a plurality of tasks. Execution of some of the plurality of tasks is scheduled on compute nodes of the cluster with differing capability profiles. Timing information regarding execution time of the scheduled tasks is received. A resource requirement profile for the job is inferred based on the received timing information and the differing capability profiles. Execution of remaining tasks of the job is scheduled on the compute nodes of the cluster using the resource requirement profile.
摘要翻译：系统和方法调度计算节点集群中的作业。收到资源需求不明确的作业。该工作包括多个任务。在具有不同能力简档的集群的计算节点上调度执行多个任务中的一些。接收有关计划任务的执行时间的定时信息。基于所接收的定时信息和不同的能力简档来推断作业的资源需求简档。使用资源需求配置文件在集群的计算节点上调度作业的剩余任务的执行。

106. 发明申请

US20140282588A1 SYSTEM AND SCHEDULING METHOD 有权
标题翻译：系统和调度方法
公开(公告)号：US20140282588A1
公开(公告)日：2014-09-18
申请号：US14027712
申请日：2013-09-16
申请人： FUJITSU LIMITED
发明人： Takahisa SUZUKI , Koichiro YAMASHITA , Hiromasa YAMAUCHI , Koji KURIHARA , Fumihiko HAYAKAWA , Naoki ODATE , Tetsuo HIRAKI , Toshiya OTOMO
IPC分类号： G06F9/50
CPC分类号： G06F9/5094 , G06F1/3293 , G06F9/5044 , G06F9/505 , G06F2209/508 , Y02D10/122 , Y02D10/22
摘要： A system includes a CPU; an accelerator; a comparing unit that compares a first value that is based on a first processing time period elapsing until the CPU completes a first process and a second processing time period elapsing until the accelerator completes the first process, and a second value that is based on a state of use of a battery driving the CPU and the accelerator; and a selecting unit that selects any one among the CPU and the accelerator, based on a result of comparison by the comparing unit.
摘要翻译：一个系统包括一个CPU; 加速器比较单元，其比较基于经过的第一处理时间段直到CPU完成第一处理的第一值和经过所述加速器完成第一处理的第二处理时间段，以及基于状态的第二值使用驱动CPU和加速器的电池; 以及选择单元，其基于比较单元的比较结果来选择CPU和加速器中的任一个。

107. 发明授权

US08826287B1 System for adjusting computer resources allocated for executing an application using a control plug-in 有权
标题翻译：用于调整分配用于使用控制插件执行应用程序的计算机资源的系统
公开(公告)号：US08826287B1
公开(公告)日：2014-09-02
申请号：US11046333
申请日：2005-01-28
申请人： Sven Graupner , Nigel Cook , Jean-Marc Chevrot
发明人： Sven Graupner , Nigel Cook , Jean-Marc Chevrot
IPC分类号： G06F9/46 , G06F15/173
CPC分类号： G06F9/5061 , G06F2209/5011 , G06F2209/508
摘要： A resource manager computer system allocates computer resources from a pool of computer resources for executing an application. A data monitoring system monitors metrics for the allocated computer resources, and a resource assessment computer system executes a control plug-in specifying a policy for determining whether to adjust the allocated computer resources based on the metrics.
摘要翻译：资源管理器计算机系统从用于执行应用程序的计算机资源池分配计算机资源。数据监视系统监视分配的计算机资源的度量，资源评估计算机系统执行指定用于基于度量来确定是否调整分配的计算机资源的策略的控制插件。

108. 发明授权

US08825864B2 System and method for supporting a dynamic resource broker in a transactional middleware machine environment 有权
标题翻译：用于在事务中间件机器环境中支持动态资源代理的系统和方法
公开(公告)号：US08825864B2
公开(公告)日：2014-09-02
申请号：US13423024
申请日：2012-03-16
申请人： Zhenyu Li , Lidan Liu
发明人： Zhenyu Li , Lidan Liu
IPC分类号： G06F15/173 , G06F15/16
CPC分类号： H04L47/70 , G06F8/60 , G06F9/5072 , G06F2209/508
摘要： A system and method can support dynamically scaling up/down transactional resources in a transactional middleware machine environment. Transactional resources, such as groups and machines, can be by added or removed using a dynamic resource broker according to resource usage changes. The transactional middleware machine environment can comprise a deployment center in the transactional middleware machine environment, wherein the deployment center maintains one or more deployment policies for the transactional middleware machine environment and one or more deployment agents. Each of the one or more deployment agents is associated with a transactional middleware machine of a plurality of transactional middleware machines in a transactional domain in the transactional middleware machine environment. The deployment center operates to receive machine usage information from the one or more deployment agents, and dynamically scale up/down resources used in the transactional domain based on the resource usage information collected by the one or more deployment agents.
摘要翻译：系统和方法可以支持在事务性中间件机器环境中动态扩展上/下交易资源。根据资源使用情况的变化，可以使用动态资源代理来添加或删除事务资源（如组和机器）。交易中间件机器环境可以包括事务中间件机器环境中的部署中心，其中部署中心维护事务中间件机器环境和一个或多个部署代理的一个或多个部署策略。所述一个或多个部署代理中的每一个与交易中间件机器环境中的事务域中的多个事务中间件机器的事务性中间件机器相关联。所述部署中心用于从一个或多个部署代理接收机器使用信息，并且基于由所述一个或多个部署代理收集的资源使用信息来动态地扩展/减少事务域中使用的资源。

109. 发明申请

US20140237472A1 RESOURCE OPTIMIZATION RECOMMENDATIONS 审中-公开
标题翻译：资源优化建议
公开(公告)号：US20140237472A1
公开(公告)日：2014-08-21
申请号：US14137528
申请日：2013-12-20
申请人： Amazon Technologies, Inc.
发明人： Eden G. Adogla , Awo D. Ashiabor
IPC分类号： G06F9/455
CPC分类号： G06F9/45533 , G06F9/5077 , G06F11/3409 , G06F11/3442 , G06F11/3466 , G06F2201/815 , G06F2201/865 , G06F2209/508
摘要： A resource optimization manager monitors resource metrics of a set of virtual machine instance types and determines a set of applications associated with the virtual machine instance types and associates the resource metrics to the set of applications. Thereafter, the resource optimization manager can generate clusters of applications that share one or more similar attributes and store resource optimizations for the clustered applications. The resource optimization manager can obtain a designation of a target application run on a virtual machine instance or otherwise obtain a definition of an application. The resource optimization manager can then associate the target application with one or more of the clustered applications based on a comparison of similarities between the clustered applications and the target applications.
摘要翻译：资源优化管理器监视一组虚拟机实例类型的资源度量，并确定与虚拟机实例类型相关联的一组应用程序，并将资源度量与该组应用程序相关联。此后，资源优化管理器可以生成共享一个或多个相似属性的应用程序集群，并为集群应用程序存储资源优化。资源优化管理器可以获得在虚拟机实例上运行的目标应用的指定，或者获得应用的定义。然后，资源优化管理器可以基于群集应用程序和目标应用程序之间的相似性的比较，将目标应用程序与一个或多个群集应用程序相关联。

110. 发明申请

US20140229646A1 INFORMATION PROCESSING SYSTEM, METHOD AND COMPUTER-READABLE RECORDING MEDIUM 审中-公开
标题翻译：信息处理系统，方法和计算机可读记录介质
公开(公告)号：US20140229646A1
公开(公告)日：2014-08-14
申请号：US14255246
申请日：2014-04-17
申请人： FUJITSU LIMITED
发明人： Yoshiyuki OHHIRA
IPC分类号： G06F9/48
CPC分类号： G06F9/4812 , G06F9/4881 , G06F9/544 , G06F11/3612 , G06F2209/508
摘要： An information processing system includes a memory that stores a first program and a second program, a first processor coupled to the memory and configured to execute the first program, and a second processor coupled to the memory and configured to delay execution of the second program until the first processor starts executing the first program.
摘要翻译：信息处理系统包括存储第一程序和第二程序的存储器，耦合到存储器并被配置为执行第一程序的第一处理器，以及耦合到存储器并被配置为延迟执行第二程序的第二处理器，直到第一个处理器开始执行第一个程序。

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