-
公开(公告)号：US08024365B2
公开(公告)日：2011-09-20
申请号：US11782354
申请日：2007-07-24
IPC分类号： G06F17/30
CPC分类号： G06Q10/06 , Y10S707/99944
摘要： A dynamic status tree facility for providing status information about one or more systems. The facility includes a tree data structure and methods for manipulating the data structure. The facility is accessible to provider processes using a set of provider interface methods. The facility is accessible to consumer processes using a set of consumer interface methods. The tree data structure is defined by nodes stored in shared memory and attached to by way of a defined data structure made available to the provider and consumer interface methods. The nodes in the tree data structure are defined to have a control block and a variable set of export data. The export data for any one node is specified by a variable in the control block. Certain of the exported data in the tree is representable in a format selected to have one of four defined properties.
摘要翻译： 用于提供关于一个或多个系统的状态信息的动态状态树设施。 该设施包括树状数据结构和操纵数据结构的方法。 使用一组提供程序接口方法，提供程序进程可以访问该设施。 消费者流程使用一组消费者接口方法可以访问该设施。 树数据结构由存储在共享存储器中的节点定义，并通过定义的数据结构附加到提供商和消费者接口方法。 树数据结构中的节点被定义为具有控制块和导出数据的变量集合。 任何一个节点的导出数据由控制块中的变量指定。 树中某些导出的数据可以以选定为具有四个定义属性之一的格式表示。
-
2.发明申请METHODS, APPARATUS AND ARTICLES OF MANUFACTURE FOR REGAINING MEMORY CONSISTENCY AFTER A TRAP VIA TRANSACTIONAL MEMORY 失效方法，装置和制造商在通过交易记录进行跟踪之后记录一致性的制造公开(公告)号：US20090217018A1
公开(公告)日：2009-08-27
申请号：US12037888
申请日：2008-02-26
申请人： ALEXANDER ABRASHKEVICH , Dmitri Abrashkevich , Robert J. Blainey , Thomas J. Heller, JR. , Matthew A. Huras , Sridhar Munireddy , Yogendra K. Srivastava , Mark F. Wilding
发明人： ALEXANDER ABRASHKEVICH , Dmitri Abrashkevich , Robert J. Blainey , Thomas J. Heller, JR. , Matthew A. Huras , Sridhar Munireddy , Yogendra K. Srivastava , Mark F. Wilding
IPC分类号： G06F9/44
CPC分类号： G06F9/467 , G06F11/1474
摘要： Embodiments of the invention provide a method for regaining memory consistency after a trap via transactional memory. Transactional memory and a transactional memory log are used to undo changes made to memory from a transaction start point up to the point of a trap event. After the trap event is processed, and the changes are rolled back, the program can resume execution at the beginning of the transaction.
摘要翻译： 本发明的实施例提供一种通过事务存储器在陷阱之后恢复存储器一致性的方法。 事务内存和事务性内存日志用于撤消从事务起始点到陷阱事件点对内存所做的更改。 处理陷阱事件后，回滚更改，程序可以在事务开始时恢复执行。
-
公开(公告)号：US07827375B2
公开(公告)日：2010-11-02
申请号：US11626691
申请日：2007-01-24
CPC分类号： G06F11/366 , G06F12/023
摘要： A data structure, method and system are provided incorporating a general purpose memory allocator and defensive heap memory manager. This provides an ability to reliably detect various types of memory errors, dynamically enable or disable memory debugging, enhance success of read and write operations using various memory verification techniques. Further, through separation of control information associated with allocated and free chunks of memory from the chunks themselves (separation of metadata from actual data), enhanced protection of vital information about the heap memory layout in general is provided. The heap memory manager uses read, write, and execute protected heap header walls and pool header walls and may, for each pool and memory block, separately use hidden front and back Memory Debug Information Areas (MDIAs) with checksums and well-known signature fields thereby enhancing overall memory management.
摘要翻译： 提供了包含通用存储器分配器和防御堆存储器管理器的数据结构，方法和系统。 这提供了可靠地检测各种类型的存储器错误，动态地启用或禁用存储器调试的能力，使用各种存储器验证技术增强了读取和写入操作的成功。 此外，通过分离与分组本身的分配的和自由的存储块相关联的控制信息（元数据与实际数据的分离），提供了关于堆存储器布局的重要信息的增强保护。 堆内存管理器使用读，写和执行保护的堆标头墙和池标题墙，并且对于每个池和内存块，可以分别使用具有校验和和公知签名字段的隐藏的前端和后端内存调试信息区域（MDI） 从而增强整体内存管理。
-
公开(公告)号：US07181585B2
公开(公告)日：2007-02-20
申请号：US10427085
申请日：2003-04-30
CPC分类号： G06F12/023
摘要： A data structure, method and system are provided incorporating a general purpose memory allocator and defensive heap memory manager. This provides an ability to reliably detect various types of memory errors, dynamically enable or disable memory debugging, enhance success of read and write operations using various memory verification techniques. Further, through separation of control information associated with allocated and free chunks of memory from the chunks themselves (separation of metadata from actual data), enhanced protection of vital information about the heap memory layout in general is provided. The heap memory manager uses read, write, and execute protected heap header walls and pool header walls and may, for each pool and memory block, separately use hidden front and back Memory Debug Information Areas (MDIAs) with checksums and well-known signature fields thereby enhancing overall memory management.
摘要翻译： 提供了包含通用存储器分配器和防御堆存储器管理器的数据结构，方法和系统。 这提供了可靠地检测各种类型的存储器错误，动态地启用或禁用存储器调试的能力，使用各种存储器验证技术增强了读取和写入操作的成功。 此外，通过分离与分组本身的分配的和空闲的存储块相关联的控制信息（元数据与实际数据的分离），提供了关于堆存储器布局的重要信息的增强保护。 堆内存管理器使用读，写和执行保护的堆标头墙和池标题墙，并且对于每个池和内存块，可以分别使用具有校验和和公知签名字段的隐藏的前端和后端内存调试信息区域（MDI） 从而增强整体内存管理。
-
5.发明授权Methods, apparatus and articles of manufacture for regaining memory consistency after a trap via transactional memory 失效用于通过事务记忆在陷阱之后恢复记忆一致性的方法，装置和制品公开(公告)号：US08032736B2
公开(公告)日：2011-10-04
申请号：US12037888
申请日：2008-02-26
申请人： Alexander Abrashkevich , Dmitri Abrashkevich , Robert J. Blainey , Thomas J. Heller, Jr. , Matthew A. Huras , Sridhar Munireddy , Yogendra K. Srivastava , Mark F. Wilding
发明人： Alexander Abrashkevich , Dmitri Abrashkevich , Robert J. Blainey , Thomas J. Heller, Jr. , Matthew A. Huras , Sridhar Munireddy , Yogendra K. Srivastava , Mark F. Wilding
CPC分类号： G06F9/467 , G06F11/1474
摘要： Embodiments of the invention provide a method for regaining memory consistency after a trap via transactional memory. Transactional memory and a transactional memory log are used to undo changes made to memory from a transaction start point up to the point of a trap event. After the trap event is processed, and the changes are rolled back, the program can resume execution at the beginning of the transaction.
摘要翻译： 本发明的实施例提供一种通过事务存储器在陷阱之后恢复存储器一致性的方法。 事务内存和事务性内存日志用于撤消从事务起始点到陷阱事件点对内存所做的更改。 处理陷阱事件后，回滚更改，程序可以在事务开始时恢复执行。
-
公开(公告)号：US07533098B2
公开(公告)日：2009-05-12
申请号：US10196024
申请日：2002-07-15
IPC分类号： G06F17/30
CPC分类号： G06Q10/06 , Y10S707/99944
摘要： A dynamic status tree facility for providing status information about one or more systems. The facility includes a tree data structure and methods for manipulating the data structure. The facility is accessible to provider processes using a set of provider interface methods. The facility is accessible to consumer processes using a set of consumer interface methods. The tree data structure is defined by nodes stored in shared memory and attached to by way of a defined data structure made available to the provider and consumer interface methods. The nodes in the tree data structure are defined to have a control block and a variable set of export data. The export data for any one node is specified by a variable in the control block. Certain of the exported data in the tree is representable in a format selected to have one of four defined properties. A set of tags are defined for the identification of nodes and export information in the tree data structure.
摘要翻译： 用于提供关于一个或多个系统的状态信息的动态状态树设施。 该设施包括树状数据结构和操纵数据结构的方法。 使用一组提供程序接口方法，提供程序进程可以访问该设施。 消费者流程使用一组消费者接口方法可以访问该设施。 树数据结构由存储在共享存储器中的节点定义，并通过定义的数据结构附加到提供商和消费者接口方法。 树数据结构中的节点被定义为具有控制块和导出数据的变量集合。 任何一个节点的导出数据由控制块中的变量指定。 树中某些导出的数据可以以选定为具有四个定义属性之一的格式表示。 定义了一组标签，用于识别节点，并在树状数据结构中导出信息。
-
公开(公告)号：US07447693B2
公开(公告)日：2008-11-04
申请号：US10390812
申请日：2003-03-17
申请人： Mark F. Wilding , Matthew A. Huras
发明人： Mark F. Wilding , Matthew A. Huras
CPC分类号： G06F17/30575 , G06F17/30362 , Y10S707/99931 , Y10S707/99938 , Y10S707/99953
摘要： A distributed database management system implemented on a cluster of computers. The cluster including disks organized as data nodes. The data nodes being locally connected to one or more computers in the cluster. The distributed database management system includes a distributed database manager layer having a lock manager, a resource manager, and an architecture manager. The lock manager serializes access to the data nodes in the cluster. The resource manager maintains a data representation of the resources of each computer in the cluster and makes the data available to other computers in the cluster to facilitate access to the resources by the other computers. The architecture manager defines logical ownership relationships between data nodes and computers in the cluster to permit the architecture of the database to be dynamically reconfigured to provide improved performance.
摘要翻译： 在一组计算机上实现的分布式数据库管理系统。 集群包括组织为数据节点的磁盘。 数据节点本地连接到集群中的一台或多台计算机。 分布式数据库管理系统包括具有锁管理器，资源管理器和架构管理器的分布式数据库管理器层。 锁定管理器将访问集群中的数据节点序列化。 资源管理器维护集群中每台计算机的资源的数据表示，并使数据可用于集群中的其他计算机，以便其他计算机访问资源。 架构管理员定义集群中数据节点和计算机之间的逻辑所有权关系，以允许动态重新配置数据库的体系结构以提供改进的性能。
-
公开(公告)号：US20080162946A1
公开(公告)日：2008-07-03
申请号：US11617597
申请日：2006-12-28
申请人： Guy M. Lohman , Mark F. Wilding
发明人： Guy M. Lohman , Mark F. Wilding
IPC分类号： H04L9/32
CPC分类号： G06F21/6227
摘要： Some aspects of the invention provide methods, systems, and computer program products for inserting an encrypted problem signature into a symptom database. A problem signature is first provided, which is then used to derive a hash value. The problem signature is then encrypted using the hash value. The hash value is further used to indicate the location in the database to insert the problem signature. The problem signature is then inserted at the location in the database indicated by the location.
摘要翻译： 本发明的一些方面提供了用于将加密的问题签名插入症状数据库的方法，系统和计算机程序产品。 首先提供问题签名，然后将其用于导出哈希值。 然后使用哈希值对问题签名进行加密。 散列值进一步用于指示数据库中插入问题签名的位置。 然后将问题签名插入位置指示的数据库中的位置。
-
9.发明授权Method and system for generating executable code for formatting and printing complex data structures 失效用于生成用于格式化和打印复杂数据结构的可执行代码的方法和系统公开(公告)号：US07313785B2
公开(公告)日：2007-12-25
申请号：US10426384
申请日：2003-04-29
摘要： The present invention provides a complier and linker for analyzing the structures of complex data stored in memory when a print statement specified in source code refers to those complex data structures, and then generating executable code which will print the complex data when a data processing system executes the executable code.
摘要翻译： 本发明提供了一种编译器和链接器，用于在源代码中指定的打印语句涉及这些复杂数据结构时，分析存储在存储器中的复杂数据的结构，然后生成当数据处理系统执行时将打印复杂数据的可执行代码 可执行代码。
-
公开(公告)号：US06976107B2
公开(公告)日：2005-12-13
申请号：US10242524
申请日：2002-09-12
申请人： Joseph Serge Limoges , Dominique J. Evans , Dale J. Hagen , Matthew A. Huras , Stephen A. Schormann , Mark F. Wilding
发明人： Joseph Serge Limoges , Dominique J. Evans , Dale J. Hagen , Matthew A. Huras , Stephen A. Schormann , Mark F. Wilding
CPC分类号： G06F9/526
摘要： An adaptive spin latch system is provided for use in a multiprocessor computer system. The spin latch system includes a run queue, a spin latch module and a wait queue. The run queue is adapted to store agent index data correlated to at least one agent in run mode. The spin latch module is adapted to put the at least one agent into sleep mode for a period of time correlated to a number of agents awaiting access to a resource. The wait queue is adapted to store agent index data correlated to the at least one agent in sleep mode. A method of regulating access by agents to a resource in a multiprocessor computing system is also provided.
摘要翻译： 提供了一种在多处理器计算机系统中使用的自适应旋转锁存系统。 自旋锁存系统包括运行队列，自旋锁存模块和等待队列。 运行队列适于在运行模式下存储与至少一个代理相关的代理索引数据。 自旋锁存模块适于将至少一个代理进入休眠模式一段时间，其与等待访问资源的代理的数量相关。 等待队列适于在休眠模式下存储与至少一个代理相关的代理索引数据。 还提供了一种调节代理对多处理器计算系统中的资源的访问的方法。
-
-
-
-
-
-
-
-
-
搜索结果
24 条记录 (耗时 0.021 秒)
