专利快速检索-快速检索全球专利，免费商用专利数据库-IPRDB

11. 发明申请

US20060253655A1 Scalable rundown protection for object lifetime management 有权
公开(公告)号：US20060253655A1
公开(公告)日：2006-11-09
申请号：US11480799
申请日：2006-07-03
申请人： Ravisankar Pudipeddi , Neill Clift , Neal Christiansen
发明人： Ravisankar Pudipeddi , Neill Clift , Neal Christiansen
IPC分类号： G06F12/00 , G06F13/00
CPC分类号： G06F12/0261
摘要： Object rundown protection that scales with the number of processors in a shared-memory computer system is disclosed. Prior to object rundown, a cache-aware reference count data structure is used to prevent cache-pinging that would otherwise result from data sharing across processors in a multiprocessor computer system. In this data structure, a counter of positive references and negative dereferences, aligned on a particular cache line, is maintained for each processor. When an object is to be destroyed, a rundown wait process is begun, during which new references on the object are prohibited, and the total number of outstanding references is added to an on-stack global counter. Destruction is delayed until the global reference count is reduced to zero. In an implementation on non-uniform memory access multiprocessor machines, each processor's reference count is additionally allocated in a region of main memory that is physically close to that processor.

12. 发明授权

US07133977B2 Scalable rundown protection for object lifetime management 有权
公开(公告)号：US07133977B2
公开(公告)日：2006-11-07
申请号：US10461755
申请日：2003-06-13
申请人： Ravisankar Pudipeddi , Neill Clift , Neal R. Christiansen
发明人： Ravisankar Pudipeddi , Neill Clift , Neal R. Christiansen
IPC分类号： G06F12/16
CPC分类号： G06F12/0261
摘要： A system and method for object rundown protection that scales with the number of processors in a shared-memory computer system is disclosed. In an embodiment of the present invention, prior to object rundown, a cache-aware reference count data structure is used to prevent cache-pinging that would otherwise result from data sharing across processors in a multiprocessor computer system. In this data structure, a counter of positive references and negative dereferences, aligned on a particular cache line, is maintained for each processor. When an object is to be destroyed, a rundown wait process is begun, during which new references on the object are prohibited, and the total number of outstanding references is added to an on-stack global counter. Destruction is delayed until the global reference count is reduced to zero. In an embodiment of the invention suited to implementation on non-uniform memory access multiprocessor machines, each processor's reference count is additionally allocated in a region of main memory that is physically close to that processor.

13. 发明申请

US20060048149A1 Conditional variables without spinlocks 失效
标题翻译：没有自旋锁的条件变量
公开(公告)号：US20060048149A1
公开(公告)日：2006-03-02
申请号：US10932475
申请日：2004-09-01
申请人： Neill Clift
发明人： Neill Clift
IPC分类号： G06F9/46
CPC分类号： G06F9/52 , G06F9/526
摘要： The use of spinlocks is avoided in the combination of mutex and condition variables by using any suitable atomic compare and swap functionality to add a thread to a list of waiting threads that waits for a data event to occur. Various embodiments of the present invention also provide an organization scheme of data, which describes an access bit, an awaken count, and a pointer to the list of waiting threads. This organization scheme of data helps to optimize the list of waiting threads so as to better awaken a waiting thread or all waiting threads at once.
摘要翻译：通过使用任何合适的原子比较和交换功能将线程添加到等待数据事件发生的等待线程的列表中，在互斥体和条件变量的组合中避免使用自旋锁。本发明的各种实施例还提供数据的组织方案，其描述访问位，唤醒计数和指向等待线程列表的指针。这种数据组织方案有助于优化等待线程列表，以便一次更好地唤醒等待线程或所有等待线程。

14. 发明申请

US20050102578A1 System and method for capturing kernel-resident information 有权
标题翻译：捕获内核驻留信息的系统和方法
公开(公告)号：US20050102578A1
公开(公告)日：2005-05-12
申请号：US10712619
申请日：2003-11-12
申请人： Andrew Bliss , John Service , Narayanan Ganapathy , Neill Clift , Yi Meng
发明人： Andrew Bliss , John Service , Narayanan Ganapathy , Neill Clift , Yi Meng
IPC分类号： G06F11/00
CPC分类号： G06F11/3476
摘要： A system, method and interface for consistently capturing kernel resident information are provided. An operating system architecture includes user mode modules and kernel mode applications. A user mode module initiates a kernel mode information request through an application program interface identifying one or more process threads of interest. A kernel mode module captures information corresponding to standard kernel mode information and corresponding to the specifically identified process threads. The information is returned in a pre-allocated buffer.
摘要翻译：提供了一种用于始终捕获内核驻留信息的系统，方法和接口。操作系统架构包括用户模式模块和内核模式应用程序。用户模式模块通过识别感兴趣的一个或多个进程线程的应用程序接口来发起内核模式信息请求。内核模式模块捕获与标准内核模式信息相对应的信息，并对应于特定标识的进程线程。信息在预先分配的缓冲区中返回。

15. 发明授权

US06513100B1 System and method for fast referencing a reference counted item 有权
标题翻译：用于快速引用引用计数项目的系统和方法
公开(公告)号：US06513100B1
公开(公告)日：2003-01-28
申请号：US09738568
申请日：2000-12-15
申请人： Neill Clift
发明人： Neill Clift
IPC分类号： G06F1200
CPC分类号： G06F12/0261
摘要： A system and method for fast referencing a reference counted item is provided. The system provides for establishing a reference counted item, establishing a fast referencing item, setting a pointer to the reference counted item and storing a local copy of the reference counted item in the pointer to the reference counted item, the pointer being associated with the fast referencing item. The system and method thus allow items to obtain references to the reference counted item from the fast referencing item without employing a locking algorithm wherein the reference counted item is locked, accessed, and unlocked.
摘要翻译：提供了用于快速引用参考计数项目的系统和方法。系统提供建立参考计数项目，建立快速参考项目，设置指向参考计数项目的指针并将参考计数项目的本地副本存储在指向参考计数项目的指针中，该指针与快速引用项目。因此，系统和方法允许项目从快速参考项目获得对参考计数项目的引用，而不采用锁定算法，其中参考计数项目被锁定，访问和解锁。

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