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

US08468539B2 Tracking and detecting thread dependencies using speculative versioning cache 有权
标题翻译：使用推测版本缓存来跟踪和检测线程依赖关系
公开(公告)号：US08468539B2
公开(公告)日：2013-06-18
申请号：US12553314
申请日：2009-09-03
申请人： Alexandre E. Eichenberger , John K. P. O'Brien , Kathryn M. O'Brien , Lakshminarayanan Renganarayana , Xiaotong Zhuang
发明人： Alexandre E. Eichenberger , John K. P. O'Brien , Kathryn M. O'Brien , Lakshminarayanan Renganarayana , Xiaotong Zhuang
IPC分类号： G06F9/46
CPC分类号： G06F9/3814 , G06F9/3834 , G06F9/3838 , G06F9/3842 , G06F9/3851 , G06F9/3857 , G06F9/3859
摘要： Mechanisms are provided for tracking dependencies of threads in a multi-threaded computer program execution. The mechanisms detect a dependency of a first thread's execution on results of a second thread's execution in an execution flow of the multi-threaded computer program. The mechanisms further store, in a hardware thread dependency vector storage associated with the first thread's execution, an identifier of the dependency by setting at least one bit in the hardware thread dependency vector storage corresponding to the second thread. Moreover, the mechanisms schedule tasks performed by the multi-threaded computer program based on the hardware thread dependency vector storage to minimize squashing of threads.
摘要翻译：提供了用于跟踪多线程计算机程序执行中线程依赖性的机制。该机制检测第一个线程执行对多线程计算机程序执行流程中第二个线程执行结果的依赖性。这些机制通过在与第二线程相对应的硬件线程相关性向量存储中设置至少一个比特来进一步存储与第一线程的执行相关联的硬件线程依赖向量存储中的依赖关系的标识符。此外，该机制基于硬件线程依赖向量存储来调度由多线程计算机程序执行的任务以最小化线程的挤压。

2. 发明申请

US20110055484A1 Detecting Task Complete Dependencies Using Underlying Speculative Multi-Threading Hardware 有权
标题翻译：使用基础投机多线程硬件检测任务完成依赖关系
公开(公告)号：US20110055484A1
公开(公告)日：2011-03-03
申请号：US12553314
申请日：2009-09-03
申请人： Alexandre E. Eichenberger , John K.P. O'Brien , Kathryn M. O'Brien , Lakshminarayanan Renganarayana , Xiaotong Zhuang
发明人： Alexandre E. Eichenberger , John K.P. O'Brien , Kathryn M. O'Brien , Lakshminarayanan Renganarayana , Xiaotong Zhuang
IPC分类号： G06F9/30 , G06F12/08
CPC分类号： G06F9/3814 , G06F9/3834 , G06F9/3838 , G06F9/3842 , G06F9/3851 , G06F9/3857 , G06F9/3859
摘要： Mechanisms are provided for tracking dependencies of threads in a multi-threaded computer program execution. The mechanisms detect a dependency of a first thread's execution on results of a second thread's execution in an execution flow of the multi-threaded computer program. The mechanisms further store, in a hardware thread dependency vector storage associated with the first thread's execution, an identifier of the dependency by setting at least one bit in the hardware thread dependency vector storage corresponding to the second thread. Moreover, the mechanisms schedule tasks performed by the multi-threaded computer program based on the hardware thread dependency vector storage to minimize squashing of threads.
摘要翻译：提供了用于跟踪多线程计算机程序执行中线程依赖性的机制。该机制检测第一个线程执行对多线程计算机程序执行流程中第二个线程执行结果的依赖性。这些机制通过在与第二线程相对应的硬件线程相关性向量存储中设置至少一个比特来进一步存储与第一线程的执行相关联的硬件线程依赖向量存储中的依赖关系的标识符。此外，该机制基于硬件线程依赖向量存储来调度由多线程计算机程序执行的任务以最小化线程的挤压。

3. 发明申请

US20110314442A1 REDUCING PARALLELISM OF COMPUTER SOURCE CODE 有权
标题翻译：减少计算机源代码并行计算
公开(公告)号：US20110314442A1
公开(公告)日：2011-12-22
申请号：US12817999
申请日：2010-06-17
申请人： Uday Kumar Bondhugula , Alexandre E. Eichenberger , John Kevin P. O'Brien , Lakshminarayanan Renganarayana , Yuan Zhao
发明人： Uday Kumar Bondhugula , Alexandre E. Eichenberger , John Kevin P. O'Brien , Lakshminarayanan Renganarayana , Yuan Zhao
IPC分类号： G06F9/44
CPC分类号： G06F8/443 , G06F8/51
摘要： An example embodiment disclosed is a method for reducing parallelism of computer source code. The method includes receiving multi-threaded program source code and representing the multi-threaded program source code as a polyhedral framework stored in computer readable memory. The polyhedral framework is used to convert the polyhedral framework from the multi-threaded program source code representation to a single-threaded program source code representation.
摘要翻译：所公开的示例性实施例是用于减少计算机源代码的并行性的方法。该方法包括接收多线程程序源代码并将多线程程序源代码表示为存储在计算机可读存储器中的多面体框架。多面体框架用于将多面体框架从多线程程序源代码表示转换为单线程程序源代码表示。

4. 发明授权

US08584103B2 Reducing parallelism of computer source code 有权
标题翻译：减少计算机源代码的并行性
公开(公告)号：US08584103B2
公开(公告)日：2013-11-12
申请号：US12817999
申请日：2010-06-17
申请人： Uday Kumar Bondhugula , Alexandre E. Eichenberger , John Kevin P. O'Brien , Lakshminarayanan Renganarayana , Yuan Zhao
发明人： Uday Kumar Bondhugula , Alexandre E. Eichenberger , John Kevin P. O'Brien , Lakshminarayanan Renganarayana , Yuan Zhao
IPC分类号： G06F9/44 , G06F9/45 , G06F9/46
CPC分类号： G06F8/443 , G06F8/51
摘要： An example embodiment disclosed is a method for reducing parallelism of computer source code. The method includes receiving multi-threaded program source code and representing the multi-threaded program source code as a polyhedral framework stored in computer readable memory. The polyhedral framework is used to convert the polyhedral framework from the multi-threaded program source code representation to a single-threaded program source code representation.
摘要翻译：所公开的示例性实施例是用于减少计算机源代码的并行性的方法。该方法包括接收多线程程序源代码并将多线程程序源代码表示为存储在计算机可读存储器中的多面体框架。多面体框架用于将多面体框架从多线程程序源代码表示转换为单线程程序源代码表示。

5. 发明授权

US09038085B2 System, method and program product for cost-aware selection of stored virtual machine images for subsequent use 有权
公开(公告)号：US09038085B2
公开(公告)日：2015-05-19
申请号：US13615809
申请日：2012-09-14
申请人： Marcos Dias De Assuncao , Marco Aurelio Stelmar Netto , Lakshminarayanan Renganarayana , Christopher C. Young
发明人： Marcos Dias De Assuncao , Marco Aurelio Stelmar Netto , Lakshminarayanan Renganarayana , Christopher C. Young
IPC分类号： G06F9/455 , G06F9/50 , G06F15/16 , G06F9/445
CPC分类号： G06F9/455 , G06F8/63 , G06F9/45558 , G06F2009/45562
摘要： A system, method and computer program product for allocating shared resources. Upon receiving requests for resources, the cost of bundling software in a virtual machine (VM) image is automatically generated. Software is selected by the cost for each bundle according to the time required to install it where required, offset by the time to uninstall it where not required. A number of VM images having the highest software bundle value (i.e., highest cost bundled) is selected and stored, e.g., in a machine image store. With subsequent requests for resources, VMs may be instantiated from one or more stored VM images and, further, stored images may be updated selectively updated with new images.

6. 发明授权

US08930541B2 System, method and program product for cost-aware selection of templates for provisioning shared resources 有权
标题翻译：用于提供共享资源的模板的成本感知选择的系统，方法和程序产品
公开(公告)号：US08930541B2
公开(公告)日：2015-01-06
申请号：US13304571
申请日：2011-11-25
申请人： Marcos Dias De Assuncao , Marco Aurelio Stelmar Netto , Brian L. Peterson , Lakshminarayanan Renganarayana , John J. Rofrano , Christopher C. Young
发明人： Marcos Dias De Assuncao , Marco Aurelio Stelmar Netto , Brian L. Peterson , Lakshminarayanan Renganarayana , John J. Rofrano , Christopher C. Young
IPC分类号： G06F15/173
CPC分类号： G06F9/50 , Y02D10/22
摘要： A template generator organizing templates in a cost-aware clustering, a method of allocating resources using cost-aware clustering and computer program products therefor. A resource provisioning unit generates, selects and maintains a selected number of resource templates. Each template specifies an allocable resource capacity configuration. Each requesting client device has resources allocated determined by one of the selected resource templates. A resource provisioning unit includes a configuration store with costs of allocable resources and associated attributes, a server request store with previously received requests, and an input parameter store with template list options. A template generator determines an optimum list of templates to satisfy previously received requests. A template store stores generated template lists.
摘要翻译：在成本感知型集群中组织模板的模板生成器，使用成本感知集群分配资源的方法及其计算机程序产品。资源供应单元生成，选择和维护所选数量的资源模板。每个模板指定可分配的资源容量配置。每个请求客户端设备具有由所选择的资源模板之一确定的资源。资源配置单元包括具有可分配资源和相关联属性的成本的配置存储，具有先前接收的请求的服务器请求存储以及具有模板列表选项的输入参数存储。模板生成器确定最佳的模板列表以满足先前接收到的请求。模板商店存储生成的模板列表。

7. 发明申请

US20130339787A1 SYSTEMATIC FAILURE REMEDIATION 审中-公开
公开(公告)号：US20130339787A1
公开(公告)日：2013-12-19
申请号：US13562913
申请日：2012-07-31
申请人： Vasanth Bala , Niyu Ge , Ea-Ee Jan , Darrell C. Reimer , Lakshminarayanan Renganarayana , Xiaolan Zhang
发明人： Vasanth Bala , Niyu Ge , Ea-Ee Jan , Darrell C. Reimer , Lakshminarayanan Renganarayana , Xiaolan Zhang
IPC分类号： G06F11/14
CPC分类号： G06F11/1433 , G06F2201/83
摘要： Aspects of the present invention provide a tool for analyzing and remediating an update-related failure. In an embodiment, a failure state of a computer system that has been arrived at as a result of an update is captured. A semantic diff that includes the difference between the failure state and at least one of an original state or a completion state is then computed. This semantic diff is transformed into a feature vector format. Then the transformed semantic diff is analyzed to determine a remediation for the update. Failure and/or resolution signatures can be constructed using the semantic diff and contextual data, and these signatures can be used in comparison and analysis of failures and resolutions.

8. 发明申请

US20130111018A1 PASSIVE MONITORING OF VIRTUAL SYSTEMS USING AGENT-LESS, OFFLINE INDEXING 审中-公开
标题翻译：使用代理商，离线索引对虚拟系统进行被动监控
公开(公告)号：US20130111018A1
公开(公告)日：2013-05-02
申请号：US13527948
申请日：2012-06-20
申请人： Glenn S. Ammons , Ahmed M. Azab , Vasanth Bala , Sastry S. Duri , Todd W. Mummert , Darrell C. Reimer , Lakshminarayanan Renganarayana , Xiaolan Zhang
发明人： Glenn S. Ammons , Ahmed M. Azab , Vasanth Bala , Sastry S. Duri , Todd W. Mummert , Darrell C. Reimer , Lakshminarayanan Renganarayana , Xiaolan Zhang
IPC分类号： G06F15/173
CPC分类号： G06F9/45558
摘要： Aspects of the present invention provide a solution for passively monitoring a computer system. In an embodiment, a virtual server is accessed by an indexing agent that is contained in an indexing appliance. The virtual server is located on a physical server and is one of a plurality of virtual system instances on a common physical server. The indexing appliance is separate from the virtual server and, as such, the indexing agent is not executed within the virtual server, itself. The indexing agent retrieves a virtual image of the virtual server and indexes the virtual image to extract features indicative of changes in the virtual server. These features are analyzed to perform passive monitoring of the virtual server. Since the indexing appliance is separate from the virtual server for which passive monitoring is being performed, the indexing agent can perform the retrieving and the indexing without utilizing agents executing within the virtual server.
摘要翻译：本发明的方面提供了一种被动监视计算机系统的解决方案。在一个实施例中，虚拟服务器被包含在索引设备中的索引代理访问。虚拟服务器位于物理服务器上，并且是公共物理服务器上的多个虚拟系统实例之一。索引设备与虚拟服务器分开，因此，索引代理本身不在虚拟服务器内执行。索引代理检索虚拟服务器的虚拟映像，并对虚拟映像进行索引以提取指示虚拟服务器中的更改的特征。分析这些功能以执行虚拟服务器的被动监控。由于索引设备与正在执行被动监视的虚拟服务器分离，因此索引代理可以在不使用在虚拟服务器内执行的代理的情况下执行检索和索引。

9. 发明授权

US09069545B2 Relaxation of synchronization for iterative convergent computations 有权
标题翻译：放松迭代收敛计算的同步
公开(公告)号：US09069545B2
公开(公告)日：2015-06-30
申请号：US13184718
申请日：2011-07-18
申请人： Lakshminarayanan Renganarayana , Vijayalakshmi Srinivasan
发明人： Lakshminarayanan Renganarayana , Vijayalakshmi Srinivasan
IPC分类号： G06F9/44 , G06F9/30 , G06F9/52 , G06F9/45
CPC分类号： G06F9/3004 , G06F8/458 , G06F9/30087 , G06F9/30185 , G06F9/52
摘要： Systems and methods are disclosed that allow atomic updates to global data to be at least partially eliminated to reduce synchronization overhead in parallel computing. A compiler analyzes the data to be processed to selectively permit unsynchronized data transfer for at least one type of data. A programmer may provide a hint to expressly identify the type of data that are candidates for unsynchronized data transfer. In one embodiment, the synchronization overhead is reducible by generating an application program that selectively substitutes codes for unsynchronized data transfer for a subset of codes for synchronized data transfer. In another embodiment, the synchronization overhead is reducible by employing a combination of software and hardware by using relaxation data registers and decoders that collectively convert a subset of commands for synchronized data transfer into commands for unsynchronized data transfer.
摘要翻译：公开了允许至少部分地消除全局数据的原子更新以减少并行计算中的同步开销的系统和方法。编译器分析要处理的数据，以选择性地允许至少一种类型的数据的不同步数据传输。程序员可以提供明确识别作为不同步数据传输候选的数据类型的提示。在一个实施例中，可以通过生成一个应用程序来减少同步开销，所述应用程序选择性地替代用于同步数据传输的代码子集的非同步数据传输的代码。在另一个实施例中，可以通过使用松弛数据寄存器和解码器来将软件和硬件的组合应用于将用于同步数据传输的命令的子集合转换成用于非同步数据传输的命令来减少同步开销。

10. 发明申请

US20130138812A1 SYSTEM, METHOD AND PROGRAM PRODUCT FOR COST-AWARE SELECTION OF TEMPLATES FOR PROVISIONING SHARED RESOURCES 有权
标题翻译：成本选择用于提供共享资源的模板的系统，方法和程序产品
公开(公告)号：US20130138812A1
公开(公告)日：2013-05-30
申请号：US13304571
申请日：2011-11-25
申请人： Marcos Dias De Assuncao , Marco Aurelio Stelmar Netto , Brian L. Peterson , Lakshminarayanan Renganarayana , John J. Rofrano , Christopher C. Young
发明人： Marcos Dias De Assuncao , Marco Aurelio Stelmar Netto , Brian L. Peterson , Lakshminarayanan Renganarayana , John J. Rofrano , Christopher C. Young
IPC分类号： G06F9/50
CPC分类号： G06F9/50 , Y02D10/22
摘要： A template generator organizing templates in a cost-aware clustering, a method of allocating resources using cost-aware clustering and computer program products therefor. A resource provisioning unit generates, selects and maintains a selected number of resource templates. Each template specifies an allocable resource capacity configuration. Each requesting client device has resources allocated determined by one of the selected resource templates. A resource provisioning unit includes a configuration store with costs of allocable resources and associated attributes, a server request store with previously received requests, and an input parameter store with template list options. A template generator determines an optimum list of templates to satisfy previously received requests. A template store stores generated template lists.
摘要翻译：在成本感知型集群中组织模板的模板生成器，使用成本感知集群分配资源的方法及其计算机程序产品。资源供应单元生成，选择和维护所选数量的资源模板。每个模板指定可分配的资源容量配置。每个请求客户端设备具有由所选择的资源模板之一确定的资源。资源配置单元包括具有可分配资源和相关联属性的成本的配置存储，具有先前接收的请求的服务器请求存储以及具有模板列表选项的输入参数存储。模板生成器确定最佳的模板列表以满足先前接收到的请求。模板商店存储生成的模板列表。

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