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

US06418505B1 Accessing beyond memory address range of commodity operating system using enhanced operating system adjunct processor interfaced to appear as RAM disk 有权
标题翻译：使用增强型操作系统辅助处理器访问超出内存地址范围的商品操作系统，显示为RAM磁盘
公开(公告)号：US06418505B1
公开(公告)日：2002-07-09
申请号：US09215629
申请日：1998-12-17
申请人： Richard R. Barton , Peter Washington , John H. Waters
发明人： Richard R. Barton , Peter Washington , John H. Waters
IPC分类号： G06F1200
CPC分类号： G06F3/0613 , G06F3/064 , G06F3/0679 , G06F12/0292 , G06F12/0623
摘要： A multi-processor computer system that includes at least one “regular” processor and one “enhanced mode” processor. The enhanced mode processor is preferably not turned over to the regular processor, but is initialized to look like an internal or external device, such as a disk drive or the like. In a preferred embodiment, fast access memory that is outside the addressable range of the regular processor is coupled to the enhanced mode processor and accessed through a RAM-disk device driver. In this manner, the amount of fast access memory available to the regular processor is increased.
摘要翻译：包括至少一个“常规”处理器和一个“增强模式”处理器的多处理器计算机系统。增强型处理器优选地不转换到常规处理器，而是被初始化为看起来像内部或外部设备，例如磁盘驱动器等。在优选实施例中，在常规处理器的可寻址范围之外的快速存取存储器耦合到增强模式处理器并通过RAM盘驱动器访问。以这种方式，普通处理器可用的快速存取存储器的数量增加。

2. 发明授权

US6047316A Multiprocessor computing apparatus having spin lock fairness 失效
标题翻译：具有自旋锁公平性的多处理器计算设备
公开(公告)号：US6047316A
公开(公告)日：2000-04-04
申请号：US989617
申请日：1997-12-12
申请人： Richard R. Barton , Arthur F. Cochcroft, Jr. , Edward A. McDonald , Robert J. Miller , Byron L. Reams , Roy M. Stevens , Billy K. Taylor
发明人： Richard R. Barton , Arthur F. Cochcroft, Jr. , Edward A. McDonald , Robert J. Miller , Byron L. Reams , Roy M. Stevens , Billy K. Taylor
IPC分类号： G06F9/46 , G06F12/00
CPC分类号： G06F9/52 , G06F12/0817
摘要： A multiprocessor computing apparatus that includes a mechanism for favoring at least one processor over another processor to achieve more equitable access to cached data. Logic for detecting when, for example, a remote and a local processor are attempting to access data from the cache of another local processor is disclosed. Logic that provides an advantage to the remote processor in a manner that achieves fairer access among the various processors is also disclosed.
摘要翻译：一种多处理器计算装置，其包括用于在另一处理器上有利于至少一个处理器以实现对缓存数据的更公平访问的机制。公开了用于检测例如远程和本地处理器何时尝试从另一本地处理器的高速缓存访问数据的逻辑。还公开了以在各种处理器之间实现更公平的访问的方式为远程处理器提供优势的逻辑。

3. 发明授权

US5502840A Method and apparatus for advising a requesting process of a contention scheme to employ to access a shared resource 失效
标题翻译：用于建议竞争方案的请求过程用于访问共享资源的方法和装置
公开(公告)号：US5502840A
公开(公告)日：1996-03-26
申请号：US497961
申请日：1995-07-03
申请人： Richard R. Barton
发明人： Richard R. Barton
IPC分类号： G06F9/46 , G06F9/52 , G06F12/00 , G06F15/16 , G06F15/177 , G06F13/14
CPC分类号： G06F9/52
摘要： A method and apparatus in a multiprocessor computer system which advises a requesting process of how it should wait for a system process having shared data and/or shared resources that is currently occupied by another process. The method begins by storing data representing the state of the synchronization lock of the requested process in a memory within the computer system. A first processor acquires exclusive access to the data. The first processor reads the data. The first processor determines from a synchronization lock owner portion of the data if the synchronization lock of the requested process is currently owned by either the requesting process or another process executing on a second processor within the computer system, and if it is owned determines if the contention process indicated in an advice portion of the data is appropriate for the requesting process. If the contention process is appropriate, the first processor releases the exclusive access to the data and performs the contention process indicated by the advice portion of the data. If the contention process is not appropriate, the first processor releases the exclusive access to the data and performs a default contention process predetermined by the requesting process.
摘要翻译：多处理器计算机系统中的方法和装置，其建议请求过程如何等待具有当前被另一进程占用的共享数据和/或共享资源的系统进程。该方法开始于将表示所请求进程的同步锁定状态的数据存储在计算机系统内的存储器中。第一处理器获取对数据的独占访问。第一个处理器读取数据。如果请求的进程的同步锁当前由请求进程或在计算机系统内的第二处理器上执行的另一进程所拥有，则第一处理器从数据的同步锁所有者部分确定，并且如果其拥有则确定是否在数据的建议部分中指示的争用过程适用于请求过程。如果竞争过程是适当的，则第一处理器释放对数据的独占访问，并执行由数据的建议部分指示的争用过程。如果竞争过程不合适，则第一处理器释放对数据的独占访问，并执行由请求处理预定的默认争用处理。

4. 发明授权

US5835775A Method and apparatus for executing a family generic processor specific application 失效
标题翻译：用于执行家庭通用处理器特定应用的方法和装置
公开(公告)号：US5835775A
公开(公告)日：1998-11-10
申请号：US764146
申请日：1996-12-12
申请人： Peter Washington , Richard R. Barton
发明人： Peter Washington , Richard R. Barton
IPC分类号： G06F9/06 , G06F9/455 , G06F9/44
CPC分类号： G06F9/45504
摘要： A method and computer system are disclosed for executing family generic, processor specific files. In accordance with one embodiment of the present invention, there is provided a method of executing a file on a computer system. The method includes the computer implemented steps of determining the processor type of a processor; storing a processor type identifier that represents the determined processor type of the processor; executing a first plurality of instructions that includes instructions exclusively from a common set of instructions that are common to a plurality of processor types; executing a second plurality of instructions that is optimized for a first processor type, if the processor type identifier indicates that the processor is of the first processor type; and executing a third plurality of instructions that includes instructions exclusively from the common set of instructions, if the processor type identifier indicates the processor is of a type different than the first processor type.
摘要翻译：公开了一种用于执行家庭通用处理器特定文件的方法和计算机系统。根据本发明的一个实施例，提供了一种在计算机系统上执行文件的方法。该方法包括计算机实现的步骤：确定处理器的处理器类型; 存储表示所确定的处理器的处理器类型的处理器类型标识符; 执行第一多个指令，其包括专用于多个处理器类型共有的公共指令集的指令; 如果处理器类型标识符指示处理器是第一处理器类型，则执行针对第一处理器类型而被优化的第二多个指令; 以及如果所述处理器类型标识符指示所述处理器的类型与所述第一处理器类型不同，则执行包括来自所述公共指令集的指令的第三多个指令。

5. 发明授权

US5317737A Method and apparatus for controlling a re-entrant synchronization lock tenure in a multiprocessor system 失效
标题翻译：用于控制多处理器系统中的重入同步锁定权限的方法和装置
公开(公告)号：US5317737A
公开(公告)日：1994-05-31
申请号：US737115
申请日：1991-07-29
申请人： Richard R. Barton
发明人： Richard R. Barton
IPC分类号： G06F9/46 , G06F12/14
CPC分类号： G06F9/526 , G06F9/524
摘要： A method and apparatus for extending a tenure of a process that owns a system process that has shared data or resources and also is requesting the owned system process. The ability to extend the tenure of the owning process allows the nesting of requests to the system process. By properly ordering how the requests are nested, deadlocks may be avoided. Additionally, by extending the tenure of a current process, some unnecessary changes in processor instructions and data may be avoided and processing efficiency increased.
摘要翻译：一种用于扩展拥有具有共享数据或资源的系统过程并且还请求所属系统进程的进程的任期的方法和装置。扩展所有权流程的权限的能力允许将请求嵌套到系统进程。通过适当地排序请求如何嵌套，可能会避免死锁。此外，通过延长当前进程的使用权限，可以避免处理器指令和数据的一些不必要的变化，并且可以提高处理效率。

6. 发明授权

US5860141A Method and apparatus for enabling physical memory larger than corresponding virtual memory 失效
标题翻译：用于使物理存储器大于相应的虚拟存储器的方法和装置
公开(公告)号：US5860141A
公开(公告)日：1999-01-12
申请号：US763918
申请日：1996-12-11
申请人： Peter Washington , John H. Waters , Richard R. Barton , Vernon K. Boland
发明人： Peter Washington , John H. Waters , Richard R. Barton , Vernon K. Boland
IPC分类号： G06F12/02 , G06F12/06 , G06F12/10 , G06F12/00
CPC分类号： G06F12/0292 , G06F12/109 , G06F12/0623
摘要： A method and apparatus for enabling a physical memory larger than a corresponding virtual memory. An apparatus is disclosed that includes a processor having an address word of a predefined length, a main memory having a size larger than the addressable range of the predefined address word, and virtual memory logic for configuring the processor virtual memory to contain a subset of the main memory as resident memory and pointers to the remainder of main memory. Analogous method steps are disclosed as is dividing main memory into a plurality of buffer uniquely identifiable within the address range of the predefined address word.
摘要翻译：一种用于启用大于相应虚拟存储器的物理存储器的方法和装置。公开了一种装置，其包括具有预定长度的地址字的处理器，具有大于预定义地址字的可寻址范围的大小的主存储器，以及用于配置处理器虚拟存储器以包含主存储器作为驻留存储器，并指向主存储器的剩余部分。公开了类似的方法步骤是将主存储器划分为在预定义地址字的地址范围内唯一可识别的多个缓冲器。

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