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

US09063826B2 Process mapping in parallel computing 有权
标题翻译：并行计算过程映射
公开(公告)号：US09063826B2
公开(公告)日：2015-06-23
申请号：US13304799
申请日：2011-11-28
申请人： Dibyendu Das , Nagarajan Kathiresan , Rajan Ravindran , Bhaskaran Venkatsubramaniam
发明人： Dibyendu Das , Nagarajan Kathiresan , Rajan Ravindran , Bhaskaran Venkatsubramaniam
IPC分类号： G06F9/45 , G06F12/00 , G06F9/50
CPC分类号： G06F12/00 , G06F9/5066
摘要： A method of mapping processes to processors in a parallel computing environment where a parallel application is to be run on a cluster of nodes wherein at least one of the nodes has multiple processors sharing a common memory, the method comprising using compiler based communication analysis to map Message Passing Interface processes to processors on the nodes, whereby at least some more heavily communicating processes are mapped to processors within nodes. Other methods, apparatus, and computer readable media are also provided.
摘要翻译：将流程映射到并行计算环境中的处理器的方法，其中并行应用将在节点簇上运行，其中至少一个节点具有共享公共存储器的多个处理器，所述方法包括使用基于编译器的通信分析来映射消息传递接口进程到节点上的处理器，由此将至少一些更重的通信过程映射到节点内的处理器。还提供了其他方法，装置和计算机可读介质。

2. 发明申请

US20130139170A1 JOB SCHEDULING TO BALANCE ENERGY CONSUMPTION AND SCHEDULE PERFORMANCE 有权
标题翻译：工作计划平衡能源消耗和时间表性能
公开(公告)号：US20130139170A1
公开(公告)日：2013-05-30
申请号：US13541459
申请日：2012-07-03
申请人： Giridhar M. Prabhakar , Rajan Ravindran , Chiranjib Sur
发明人： Giridhar M. Prabhakar , Rajan Ravindran , Chiranjib Sur
IPC分类号： G06F9/46
CPC分类号： G06F9/4893 , Y02D10/24
摘要： An energy-aware backfill scheduling method combines overestimation of job run-times and processor adjustments, such as dynamic voltage and frequency scaling, to balance overall schedule performance and energy consumption. Accordingly, some scheduled jobs are executed in a manner reducing energy consumption. A computer-implemented method comprises identifying job performance data for a plurality of representative jobs and running a simulation of backfill-based job scheduling of the jobs at various combinations of run-time over-estimation values and processor adjustment values. The simulation generates data including energy consumption and job delay. The method further identifies one of the combinations of values that optimizes the mathematical product of an energy consumption parameter and a job delay parameter using the simulation generated data for the plurality of jobs. Jobs submitted to a processor are then scheduled using the identified combination of a run-time over-estimation value and a processor adjustment value.
摘要翻译：能量回收调度方法结合了作业运行时间的过高估计和处理器调整，如动态电压和频率缩放，以平衡总体进度表现和能耗。因此，以减少能量消耗的方式执行一些调度作业。计算机实现的方法包括识别多个代表作业的作业性能数据，并且以运行时过度估计值和处理器调整值的各种组合运行作业的基于回填作业调度的模拟。模拟产生包括能量消耗和作业延迟的数据。该方法进一步标识使用多个作业的模拟生成数据优化能量消耗参数和作业延迟参数的数学乘积的值的组合之一。然后使用识别的运行时过度估计值和处理器调整值的组合来调度提交给处理器的作业。

3. 发明申请

US20130074084A1 DYNAMIC OPERATING SYSTEM OPTIMIZATION IN PARALLEL COMPUTING 有权
公开(公告)号：US20130074084A1
公开(公告)日：2013-03-21
申请号：US13524889
申请日：2012-06-15
申请人： Prathiba Kumar , Varun MALLIKARJUNAN , Rajan RAVINDRAN , Satish Kumar SADASIVAM
发明人： Prathiba Kumar , Varun MALLIKARJUNAN , Rajan RAVINDRAN , Satish Kumar SADASIVAM
IPC分类号： G06F9/46
CPC分类号： G06F9/505
摘要： A method for dynamic optimization of thread assignments for application workloads in an simultaneous multi-threading (SMT) computing environment includes monitoring and periodically recording an operational status of different processor cores each supporting a number of threads of the thread pool of the SMT computing environment and also operational characteristics of different workloads of a computing application executing in the SMT computing environment. The method further can include identifying by way of the recorded operational characteristics a particular one of the workloads demonstrating a threshold level of activity. Finally, the method can include matching a recorded operational characteristic of the particular one of the workloads to a recorded status of a processor core best able amongst the different processor cores to host execution in one or more threads of the particular one of the workloads and directing the matched processor core to host execution of the particular one of the workloads.

4. 发明授权

US08161127B2 Process mapping in parallel computing 失效
标题翻译：并行计算过程映射
公开(公告)号：US08161127B2
公开(公告)日：2012-04-17
申请号：US12390614
申请日：2009-02-23
申请人： Dibyendu Das , Nagarajan Kathiresan , Rajan Ravindran , Bhaskaran Venkatsubramaniam
发明人： Dibyendu Das , Nagarajan Kathiresan , Rajan Ravindran , Bhaskaran Venkatsubramaniam
IPC分类号： G06F15/16
CPC分类号： G06F9/5066 , G06F9/54 , G06F17/30
摘要： A method of mapping processes to processors in a parallel computing environment where a parallel application is to be run on a cluster of nodes wherein at least one of the nodes has multiple processors sharing a common memory, the method comprising using compiler based communication analysis to map Message Passing Interface processes to processors on the nodes, whereby at least some more heavily communicating processes are mapped to processors within nodes. Other methods, apparatus, and computer readable media are also provided.
摘要翻译：将流程映射到并行计算环境中的处理器的方法，其中并行应用将在节点簇上运行，其中至少一个节点具有共享公共存储器的多个处理器，所述方法包括使用基于编译器的通信分析来映射消息传递接口进程到节点上的处理器，由此将至少一些更重的通信过程映射到节点内的处理器。还提供了其他方法，装置和计算机可读介质。

5. 发明授权

US08104029B2 Method for computation-communication overlap in MPI applications 失效
标题翻译： MPI应用中计算通信重叠的方法
公开(公告)号：US08104029B2
公开(公告)日：2012-01-24
申请号：US12103705
申请日：2008-04-15
申请人： Dibyendu Das , Manish Gupta , Rajan Ravindran , Bhaskaran Venkatsubramaniam
发明人： Dibyendu Das , Manish Gupta , Rajan Ravindran , Bhaskaran Venkatsubramaniam
IPC分类号： G06F9/45 , G06F15/16 , G06F3/00 , G06F9/44 , G06F9/46 , G06F13/00
CPC分类号： G06F8/456
摘要： A computer implemented method is provided for optimizing at the time of compiling a program that employs a message-passing interface (MPI). The method includes: detecting an MPI application source file; identifying a non-blocking communication within the MPI application source file; and overlapping independent computation concurrently with the non-blocking communication. A system is also provided.
摘要翻译：提供了一种计算机实现的方法，用于在编译使用消息传递接口（MPI）的程序时进行优化。该方法包括：检测MPI应用源文件; 识别MPI应用源文件内的非阻塞通信; 并且与非阻塞通信同时重叠独立计算。还提供了一个系统。

6. 发明申请

US20110131425A1 SYSTEMS AND METHODS FOR POWER MANAGEMENT IN A HIGH PERFORMANCE COMPUTING (HPC) CLUSTER 有权
标题翻译：高性能计算（HPC）集群中的电源管理系统和方法
公开(公告)号：US20110131425A1
公开(公告)日：2011-06-02
申请号：US12627589
申请日：2009-11-30
申请人： Pradipta K. Banerjee , Anbazhagan Mani , Rajan Ravindran , Vaidyanathan Srinivasan
发明人： Pradipta K. Banerjee , Anbazhagan Mani , Rajan Ravindran , Vaidyanathan Srinivasan
IPC分类号： G06F1/26 , G06F9/44
CPC分类号： G06F1/3209 , G06F9/5094 , G06F11/3006 , G06F11/3055 , G06F11/3404 , G06F2201/81 , Y02D10/22 , Y02D10/34
摘要： Embodiments of the invention broadly contemplate systems, methods, apparatuses and program products providing a power management technique for an HPC cluster with performance improvements for parallel applications. According to various embodiments of the invention, power usage of an HPC cluster is reduced by boosting the performance of one or more select nodes within the cluster so that the one or more nodes take less time to complete. Embodiments of the invention accomplish this by selectively identifying the appropriate node(s) (or core(s) within the appropriate node(s)) in the cluster and increasing the computing capacity of the selected node(s) (or core(s) within the appropriate node(s)).
摘要翻译：本发明的实施例广泛地考虑了为HPC集群提供用于并行应用的性能改进的电源管理技术的系统，方法，装置和程序产品。根据本发明的各种实施例，通过提高集群内的一个或多个选择节点的性能来降低HPC集群的功率使用，使得一个或多个节点花费更少的时间来完成。本发明的实施例通过选择性地识别群集中的适当节点（或适当节点内的核心）来实现这一点，并且增加所选择的节点（或核心）的计算能力，在适当的节点内）。

7. 发明授权

US07512788B2 Method and apparatus for anonymous group messaging in a distributed messaging system 失效
标题翻译：分布式消息系统中匿名组消息传递的方法和装置
公开(公告)号：US07512788B2
公开(公告)日：2009-03-31
申请号：US10316247
申请日：2002-12-10
申请人： Jong Hyuk Choi , Hubertus Franke , Shailabh Nagar , Rajan Ravindran
发明人： Jong Hyuk Choi , Hubertus Franke , Shailabh Nagar , Rajan Ravindran
IPC分类号： H04L9/00 , H04K1/00
CPC分类号： H04L63/0421 , H04L63/08 , H04L63/10
摘要： A group messaging system enabling anonymous collective communications in a group which is locally defined in association with a group owner's messaging account, wherein messaging software at the group owner converts a group message into multiple one-to-one group messages destined to each group member in collaboration with the said group membership resolution process. The invention further includes a group message reply process wherein the messaging software at a recipient's side composes a reply message and transmits it to the group owner messaging software which then forwards it to the group members in collaboration with said group membership resolution process, thereby providing a means of designating the identity of a group in the group owner messaging account, sending a group message, and hiding the identities of individual recipients during the lifetime of the group message. The group owner side can additionally perform access control for group communications.
摘要翻译：组消息传递系统，使组中的匿名集体通信能够与组所有者的消息收发帐户相关联地定义，其中组所有者的消息传递软件将组消息转换为多个一对一的组消息，该消息指定给每个组成员与所述组成员解析过程进行协作。本发明还包括组消息回复过程，其中，接收者侧的消息收发软件组成一个回复消息，并将其发送给组所有者消息传递软件，然后与组所有者消息传递软件协作转发给组成员，从而提供一个指定组所有者消息帐户中的组的身份的指示，发送组消息以及在组消息的生存期间隐藏各个接收者的身份的装置。集团所有者方面可以另外执行组通信的访问控制。

8. 发明授权

US08972940B2 Systems and methods for identifying software performance influencers 有权
公开(公告)号：US08972940B2
公开(公告)日：2015-03-03
申请号：US12888680
申请日：2010-09-23
申请人： Ramakrishnan Kannan , Anbazhagan Mani , Rajan Ravindran , Karthik Subbian
发明人： Ramakrishnan Kannan , Anbazhagan Mani , Rajan Ravindran , Karthik Subbian
IPC分类号： G06F9/44 , G06F11/34 , G06F11/36
CPC分类号： G06F8/77 , G06F8/71 , G06F11/3419 , G06F11/3452 , G06F11/3466 , G06F11/368 , G06F2201/865
摘要： Described are a system and method for identifying variables which impact performance of software under development. Data is collected that is related to performance characteristics of the software under development. Performance change gradients are determined between previous builds of the software under development. A set of performance change factors are generated from the collected data that corresponds to each performance change gradient. Performance characteristic data corresponding to a current build of the software under development are compared to the performance change gradients. At least one fault component from the set of performance change factors that influences performance of the current build is output in response to the comparison between the performance characteristic data corresponding to the current build and the plurality of performance change gradients.

9. 发明授权

US08607243B2 Dynamic operating system optimization in parallel computing 有权
标题翻译：并行计算中的动态操作系统优化
公开(公告)号：US08607243B2
公开(公告)日：2013-12-10
申请号：US13237035
申请日：2011-09-20
申请人： Prathiba Kumar , Varun Mallikarjunan , Rajan Ravindran , Satish Kumar Sadasivam
发明人： Prathiba Kumar , Varun Mallikarjunan , Rajan Ravindran , Satish Kumar Sadasivam
IPC分类号： G06F9/46
CPC分类号： G06F9/505
摘要： A method for dynamic optimization of thread assignments for application workloads in an simultaneous multi-threading (SMT) computing environment includes monitoring and periodically recording an operational status of different processor cores each supporting a number of threads of the thread pool of the SMT computing environment and also operational characteristics of different workloads of a computing application executing in the SMT computing environment. The method further can include identifying by way of the recorded operational characteristics a particular one of the workloads demonstrating a threshold level of activity. Finally, the method can include matching a recorded operational characteristic of the particular one of the workloads to a recorded status of a processor core best able amongst the different processor cores to host execution in one or more threads of the particular one of the workloads and directing the matched processor core to host execution of the particular one of the workloads.
摘要翻译：用于在同时多线程（SMT）计算环境中的应用工作负载的线程分配的动态优化的方法包括监视和周期性地记录不同处理器核心的操作状态，每个处理器核心支持SMT计算环境的线程池的数量的线程，也是在SMT计算环境中执行的计算应用程序的不同工作负载的操作特性。该方法还可以包括通过记录的操作特征识别表明阈值活动水平的特定一个工作负载。最后，该方法可以包括将所述特定工作负载的所记录的操作特征与处理器核心的记录状态相匹配，所述处理器核心在所述不同处理器核心之间最好地承载所述特定工作负载的一个或多个线程中的执行，并且引导匹配的处理器核心来托管特定工作负载的执行。

10. 发明申请

US20130138929A1 PROCESS MAPPING IN PARALLEL COMPUTING 审中-公开
标题翻译：并行计算中的过程映射
公开(公告)号：US20130138929A1
公开(公告)日：2013-05-30
申请号：US13304799
申请日：2011-11-28
申请人： DIBYENDU DAS , Nagarajan Kathiresan , Rajan Ravindran , Bhaskaran Venkatsubramaniam
发明人： DIBYENDU DAS , Nagarajan Kathiresan , Rajan Ravindran , Bhaskaran Venkatsubramaniam
IPC分类号： G06F9/312 , G06F12/00
CPC分类号： G06F12/00 , G06F9/5066
摘要： A method of mapping processes to processors in a parallel computing environment where a parallel application is to be run on a cluster of nodes wherein at least one of the nodes has multiple processors sharing a common memory, the method comprising using compiler based communication analysis to map Message Passing Interface processes to processors on the nodes, whereby at least some more heavily communicating processes are mapped to processors within nodes. Other methods, apparatus, and computer readable media are also provided.
摘要翻译：将流程映射到并行计算环境中的处理器的方法，其中并行应用将在节点簇上运行，其中至少一个节点具有共享公共存储器的多个处理器，所述方法包括使用基于编译器的通信分析来映射消息传递接口进程到节点上的处理器，由此将至少一些更重的通信过程映射到节点内的处理器。还提供了其他方法，装置和计算机可读介质。

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