SYSTEM AND METHOD FOR AUTOMATICALLY SEGMENTING AND POPULATING A DISTRIBUTED COMPUTING PROBLEM
    2.
    发明申请
    SYSTEM AND METHOD FOR AUTOMATICALLY SEGMENTING AND POPULATING A DISTRIBUTED COMPUTING PROBLEM 失效
    自动分类和分配分布式计算问题的系统和方法

    公开(公告)号:US20080301405A1

    公开(公告)日:2008-12-04

    申请号:US12191483

    申请日:2008-08-14

    IPC分类号: G06F15/76 G06F9/30

    CPC分类号: G06F17/5018

    摘要: The initial partitioning of a distributed computing problem can be critical, and is often a source of tedium for the user. A method is provided that automatically segments the problem into fixed sized collections of original program cells (OPCs) based on the complexity of the problem specified, and the combination of computing agents of various caliber available for the overall job. The OPCs that are on the edge of a collection can communicate with OPCs on the edges of neighboring collections, and are indexed separately from OPCs that are within the ‘core’ or inner non-edge portion of a collection. Consequently, core OPCs can iterate independently of whether any communication occurs between collections and groups of collections (VPPs). All OPCs on an edge have common dependencies on remote information (i.e., their neighbors are all on the same edge of a neighboring collection).

    摘要翻译: 分布式计算问题的初始划分可能是至关重要的,并且通常是用户的烦恼的来源。 提供了一种基于所指定的问题的复杂性以及可用于整个作业的各种口径的计算代理的组合,将问题自动地将问题分解成原始程序单元(OPC)的固定大小的集合。 位于集合边缘的OPC可与相邻集合边缘的OPC通信,并与集合“核心”或内部非边缘部分内的OPC分开索引。 因此,核心OPC可以独立于迭代集合和集合集(VPP)之间的任何通信。 边缘上的所有OPC都具有与远程信息(即它们的邻居都在相邻集合的相同边缘上)的公共依赖关系。

    System and method for automatically segmenting and populating a distributed computing problem
    3.
    发明授权
    System and method for automatically segmenting and populating a distributed computing problem 失效
    用于自动分段和填充分布式计算问题的系统和方法

    公开(公告)号:US08606844B2

    公开(公告)日:2013-12-10

    申请号:US12191483

    申请日:2008-08-14

    IPC分类号: G06F15/16 G06T15/00

    CPC分类号: G06F17/5018

    摘要: The initial partitioning of a distributed computing problem can be critical, and is often a source of tedium for the user. A method is provided that automatically segments the problem into fixed sized collections of original program cells (OPCs) based on the complexity of the problem specified, and the combination of computing agents of various caliber available for the overall job. The OPCs that are on the edge of a collection can communicate with OPCs on the edges of neighboring collections, and are indexed separately from OPCs that are within the ‘core’ or inner non-edge portion of a collection. Consequently, core OPCs can iterate independently of whether any communication occurs between collections and groups of collections (VPPs). All OPCs on an edge have common dependencies on remote information (i.e., their neighbors are all on the same edge of a neighboring collection).

    摘要翻译: 分布式计算问题的初始划分可能是至关重要的,并且通常是用户的烦恼的来源。 提供了一种基于所指定的问题的复杂性以及可用于整个作业的各种口径的计算代理的组合,将问题自动地将问题分解成原始程序单元(OPC)的固定大小的集合。 位于集合边缘的OPC可与相邻集合边缘的OPC通信,并与集合“核心”或内部非边缘部分内的OPC分开索引。 因此,核心OPC可以独立于迭代集合和集合集(VPP)之间的任何通信。 边缘上的所有OPC都具有与远程信息(即它们的邻居都在相邻集合的相同边缘上)的公共依赖关系。

    System and method for balancing a computing load among computing resources in a distributed computing problem
    4.
    发明授权
    System and method for balancing a computing load among computing resources in a distributed computing problem 失效
    用于在分布式计算问题中平衡计算资源之间的计算负载的系统和方法

    公开(公告)号:US07590984B2

    公开(公告)日:2009-09-15

    申请号:US10448625

    申请日:2003-05-29

    IPC分类号: G06F9/46

    CPC分类号: G06F9/5066

    摘要: A distributed parallel computing system actively takes advantage of problem partitioning to balance the computing load among computing resources continually during processing. Variable problem partitions (VPPs) are initially defined as groups of original problem cells (OPCs). VPPs may be redefined and redistributed during execution, if necessary, to optimize performance based on the actual computing agent parameters and costs observed or reported through self-tests. For example, a good rule for efficient execution of a computing problem may be that the time required to perform a computation sequence (iteration) of all OPCs in a VPP should be comparable to the time required to share results via edge OPCs at the VPP collection perimeters. The rules that yield cost-efficient execution may be saved and re-used to generate initial partitionings for subsequent computing problem execution runs.

    摘要翻译: 分布式并行计算系统积极利用问题划分,在处理过程中不断平衡计算资源之间的计算负担。 可变问题分区(VPPs)最初被定义为原始问题单元(OPC)的组。 如果需要,可以在执行期间重新定义和重新分配VPP,以根据实际的计算代理参数和通过自检来观察或报告的成本优化性能。 例如,有效执行计算问题的一个好的规则可能是执行VPP中所有OPC的计算序列(迭代)所需的时间应该与VPP集合上的边缘OPC共享结果所需的时间相当 周长 可以保存产生成本效益的执行的规则,并重新使用这些规则来生成用于后续计算问题执行运行的初始分区。

    Automatically segmenting and populating a distributed computing problem
    5.
    发明授权
    Automatically segmenting and populating a distributed computing problem 失效
    自动分割和填充分布式计算问题

    公开(公告)号:US07467180B2

    公开(公告)日:2008-12-16

    申请号:US10448949

    申请日:2003-05-29

    IPC分类号: G06F15/16

    CPC分类号: G06F17/5018

    摘要: A method is described for automatically segmenting and populating a distributed problem, including determining a bounding space that is at least equal in size to a problem space volume, partitioning the bounding space into a plurality of sub-spaces capable of holding collections of original problem cells, mapping the distributed problem into the partitioned bounding space to populate the sub-spaces with data from the problem, and determining boundaries between the sub-spaces. The method further includes determining coupling interdependencies between sub-spaces, determining complexities associated with boundaries, calculating densities of the data from the problem, and if the densities of two or more contiguous collections fall below a lower level threshold, dynamically joining the two or more contiguous collections, if a particular collection density exceeds an upper threshold, dynamically subdividing the particular collection into a finer granularity, and processing the problem based on the boundaries, the coupling interdependencies, the complexities, and the densities.

    摘要翻译: 描述了一种用于自动分割和填充分布式问题的方法,包括确定与问题空间体积大小至少相等的边界空间,将边界空间划分成能够保存原始问题单元的集合的多个子空间 将分布式问题映射到分区边界空间中,以便从问题的数据中填充子空间,并确定子空间之间的边界。 该方法还包括确定子空间之间的耦合相互依赖性,确定与边界相关联的复杂性,计算来自问题的数据的密度,以及如果两个或更多个连续集合的密度落入低于下限阈值,则动态地连接两个或多个 连续集合,如果特定集合密度超过上限阈值,则将特定集合动态细分为更精细的粒度,并且基于边界,耦合相互依赖性,复杂性和密度来处理该问题。

    System and method for data space management using buddy system space
allocation
    6.
    发明授权
    System and method for data space management using buddy system space allocation 失效
    使用好友系统空间分配进行数据空间管理的系统和方法

    公开(公告)号:US5732402A

    公开(公告)日:1998-03-24

    申请号:US387052

    申请日:1995-02-10

    申请人: Tobin Jon Lehman

    发明人: Tobin Jon Lehman

    IPC分类号: G06F12/02 G06F17/30

    摘要: A relational data base management system that stores and retrieves large data objects (LOBs) from data base storage includes a data manager that maintains LOB data space allocation according to the buddy system with two types of allocation pages, called regular buddy space (RBS) pages and super buddy space (SBS) pages. The RBS pages control buddy spaces comprising equal-size areas of the LOB data space in which LOB buddy segments are stored. The SBS pages control the RBS pages. The RBS pages include a pointer array that contains the forward-most location of where searching for a free storage space should begin and a counter array that indicates the number of free buddy segments in a buddy space for a particular buddy segment size. The SBS pages include analogous pointer and counter arrays that refer to the RBS pages and indicate the location and extent of free storage space, and also include a divided-space array and an SBS page directory.

    摘要翻译: 从数据库存储中存储和检索大型数据对象(LOB)的关系数据库管理系统包括一个数据管理器,该数据管理器根据好友系统维护两种类型的分配页面(称为常规伙伴空间(RBS)页面)的LOB数据空间分配 和超级伙伴空间(SBS)页面。 RBS页面控制伙伴空间,其包括存储LOB好友段的LOB数据空间的相等大小的区域。 SBS页面控制RBS页面。 RBS页面包括一个指针数组,其中包含最开始搜索空闲存储空间的位置的最前面的位置,以及指示特定好友段大小的好友空间中的空闲好友段的数量的计数器数组。 SBS页面包括引用RBS页面并指示空闲存储空间的位置和范围的类似的指针和计数器阵列,并且还包括分空间阵列和SBS页目录。

    Active calendar system
    7.
    发明授权
    Active calendar system 失效
    活动日历系统

    公开(公告)号:US06480830B1

    公开(公告)日:2002-11-12

    申请号:US09049661

    申请日:1998-03-27

    IPC分类号: G06F1700

    CPC分类号: G06Q10/109 G06Q10/1095

    摘要: An “active” calendar automatically analyzes a user's calendar entries and sends machine-readable messages to destinations appropriate to content of the calendar entry. A group of event categories is established, each category specifying one class of anticipated calendar entry. An action rule database pre-associates each event category with one or more message formats each having a content and a destination. The action rule database also contains data identifying sources containing the content and destination for each message format. These sources include records of the action rule database itself, subparts of calendar entries of the pre-associated event category, one or more other databases, or a combination of the foregoing. After the calendar receives a user-submitted computer calendar entry describing a planned event, it identifies one of the event categories of the established group that classifies the planned event. For each message format pre-associated with the identified event category, the calendar determines the content and destination for the message as specified by the action rule database, and transmits the message to the destination.

    摘要翻译: “活动”日历自动分析用户的日历条目,并将机器可读消息发送到适合日历条目内容的目的地。 建立一组事件类别,每个类别指定一类预期的日历项。 动作规则数据库将每个事件类别与每个具有内容和目的地的一个或多个消息格式相关联。 动作规则数据库还包含标识每个消息格式的内容和目标的源的数据。 这些来源包括动作规则数据库本身的记录,预关联事件类别的日历条目的子部分,一个或多个其他数据库或前述的组合。 在日历接收到描述计划事件的用户提交的计算机日历条目之后,它识别为计划事件分类的已建立组的事件类别之一。 对于与识别的事件类别预先关联的每个消息格式,日历确定由动作规则数据库指定的消息的内容和目的地,并将该消息发送到目的地。

    Information exchange operator for a tuplespace
    8.
    发明授权
    Information exchange operator for a tuplespace 失效
    用于元组空间的信息交换运算符

    公开(公告)号:US5974420A

    公开(公告)日:1999-10-26

    申请号:US13505

    申请日:1998-01-27

    IPC分类号: G06F9/46 G06F17/30

    摘要: A method, apparatus, and article of manufacture for exchanging information in a computer-implemented database system. The present invention implements this exchange using a new operator known as a Rhonda operator. A Rhonda operator includes a tuple and template as arguments and, when performed, atomically swaps its tuple with a tuple from another Rhonda operator when both their templates match. More specifically, if two processes perform Rhonda operations, and each process' template argument matches the other process' tuple argument, then each process receives the other process' tuple as a result. This atomic synchronization can be performed for two or more Rhonda operators at a time.

    摘要翻译: 一种用于在计算机实现的数据库系统中交换信息的方法,装置和制品。 本发明使用称为Rhonda运算符的新运算符来实现该交换。 Rhonda运算符包含一个元组和模板作为参数,当执行时,当它们的模板匹配时,用另一个Rhonda运算符与一个元组进行原子交换。 更具体地说,如果两个进程执行Rhonda操作,并且每个进程的'template参数与其他进程'tuple参数匹配,那么每个进程都会收到另一个进程'tuple作为结果。 一次可以为两个或更多Rhonda运算符执行此原子同步。

    Technique of dynamically adding functionality from a client to
manipulated data at a server
    9.
    发明授权
    Technique of dynamically adding functionality from a client to manipulated data at a server 失效
    从服务器动态添加功能到操纵数据的技术

    公开(公告)号:US5963947A

    公开(公告)日:1999-10-05

    申请号:US13768

    申请日:1998-01-27

    摘要: A method, apparatus, and article of manufacture for dynamically adding functionality to a server. A first operator is received at the server from an attached client, wherein the first operator indicates that new functionality is to be added to the server. A first handler is located for the first operator. The first handler is executed in the server, wherein the first handler registers a second operator associated with the new functionality and installs a second handler for the second operator to perform the new functionality.

    摘要翻译: 一种用于向服务器动态地添加功能的方法,装置和制品。 在服务器处从附加的客户端接收第一运营商,其中第一运营商指示将新的功能添加到服务器。 第一个操作符位于第一个处理程序。 第一处理程序在服务器中执行,其中第一处理程序注册与新功能相关联的第二操作符,并为第二操作者安装第二处理程序以执行新功能。

    System, method, and service for dynamically selecting an optimum message pathway
    10.
    发明授权
    System, method, and service for dynamically selecting an optimum message pathway 失效
    用于动态选择最佳消息路径的系统,方法和服务

    公开(公告)号:US07957363B2

    公开(公告)日:2011-06-07

    申请号:US11139799

    申请日:2005-05-26

    IPC分类号: H04L12/28

    摘要: A message pathway selection system dynamically selects an optimum message pathway for transmitting messages. The system dynamically optimizes a message pathway according to various criteria such as, for example, efficiency, economy, data requirements, auditing requirements, security, data size, etc. The system can direct a message to bypass an infrastructure messaging server, using a direct message pathway. The system can also switch from an infrastructure messaging server to a direct method. The system can also utilize an infrastructure messaging pathway either as an alternative or in parallel with the direct message pathway. The system allows an application to use a single communication system for both a direct mode and an infrastructure mode of data transfer. The present system can bypass the infrastructure message pathway, thus reducing message latency, number of messages sent, and improving overall bandwidth.

    摘要翻译: 消息路径选择系统动态地选择用于发送消息的最佳消息路径。 系统根据各种标准动态优化消息路径,例如效率,经济性,数据需求,审计要求,安全性,数据大小等。系统可以使用直接的方式指导消息绕过基础设施消息传递服务器 消息通路。 系统还可以从基础架构消息传递服务器切换到直接方法。 该系统还可以利用基础设施消息传递路径作为替代或与直接消息路径并行。 系统允许应用程序使用单个通信系统进行数据传输的直接模式和基础架构模式。 本系统可以绕过基础设施消息通道,从而减少消息延迟,发送消息数量,提高整体带宽。