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

US07290105B1 Zero overhead resource locks with attributes 有权
标题翻译：具有属性的零开销资源锁
公开(公告)号：US07290105B1
公开(公告)日：2007-10-30
申请号：US10320120
申请日：2002-12-16
申请人： Robert E. Jeter, Jr. , Kenneth H. Potter , Darren Kerr , John W. Marshall , Manish Changela
发明人： Robert E. Jeter, Jr. , Kenneth H. Potter , Darren Kerr , John W. Marshall , Manish Changela
IPC分类号： G06F12/00
CPC分类号： G06F9/526 , G06F2209/522 , G06F2209/523
摘要： A technique efficiently accesses locks associated with resources in a computer system. A processor accesses (e.g., acquires or releases) a lock by specifying and issuing a request to a resource controller, the request containing attribute and resource location information associated with the lock. In response, the resource controller applies the information contained in the request to an outstanding lock data structure to determine if the request should be blocked, blocked as a pending writer, allowed or an error condition. If the request is blocked, it remains blocked until the outstanding lock blocking the request is released. If the request is allowed, operations associated with the request are performed.
摘要翻译：技术有效地访问与计算机系统中的资源相关联的锁。处理器通过向资源控制器指定和发出请求来访问（例如，获取或释放）锁定，该请求包含与该锁相关联的属性和资源位置信息。作为响应，资源控制器将包含在请求中的信息应用于未完成的锁定数据结构，以确定请求是否应被阻止，被阻塞作为待决作者，允许或错误状况。如果请求被阻止，它将被阻止，直到释放阻塞请求的未锁定的锁。如果请求被允许，则执行与该请求相关联的操作。

2. 发明授权

US07254687B1 Memory controller that tracks queue operations to detect race conditions 有权
标题翻译：跟踪队列操作以检测竞争条件的内存控制器
公开(公告)号：US07254687B1
公开(公告)日：2007-08-07
申请号：US10320162
申请日：2002-12-16
申请人： Robert E. Jeter, Jr. , Kenneth H. Potter
发明人： Robert E. Jeter, Jr. , Kenneth H. Potter
IPC分类号： G06F12/00
CPC分类号： G06F9/526
摘要： A technique for controlling access to resources that may be accessed by one or more entities in a system. According to the technique, an entity accesses a shared resource by issuing a request containing an identifier that identifies the resource and an operation that specifies an operation to be performed on the resource. The operation is compared with one or more outstanding operations associated with the shared resource to determine if the operation conflicts with one or more of the outstanding operations. If a conflict is detected, a guard value is applied to determine if a race condition could occur. If a race condition is detected, the operation is blocked; otherwise, the operation is allowed.
摘要翻译：用于控制对可由系统中的一个或多个实体访问的资源的访问的技术。根据该技术，实体通过发出包含标识资源的标识符的请求和指定要在资源上执行的操作的操作来访问共享资源。将该操作与与共享资源相关联的一个或多个未完成的操作进行比较，以确定操作是否与一个或多个未完成操作冲突。如果检测到冲突，则应用保护值来确定是否可能发生竞争条件。如果检测到竞争条件，则操作被阻止; 否则，允许操作。

3. 发明授权

US07194568B2 System and method for dynamic mirror-bank addressing 有权
标题翻译：用于动态镜像组寻址的系统和方法
公开(公告)号：US07194568B2
公开(公告)日：2007-03-20
申请号：US10394984
申请日：2003-03-21
申请人： Robert E. Jeter, Jr. , Kenneth H. Potter, Jr.
发明人： Robert E. Jeter, Jr. , Kenneth H. Potter, Jr.
IPC分类号： G06F12/06 , G06F12/16
CPC分类号： G06F11/2087 , G06F11/1451 , G06F11/2069
摘要： A dynamic addressing technique mirrors data across multiple banks of a memory resource. Information stored in the memory banks is organized into separately addressable blocks, and memory addresses include a mirror flag. To write information mirrored across two memory banks, a processor issues a single write transaction with the mirror flag asserted. A memory controller detects that the mirror flag is asserted and, in response, waits for both memory banks to become available. At that point, the memory controller causes the write to be performed at both banks. To read data that has been mirrored across two memory banks, the processor issues a read with the mirror flag asserted. The memory controller checks the availability of both banks having the desired information. If either bank is available, the read request is accepted and the desired data is retrieved from the available bank and returned to the processor.
摘要翻译：动态寻址技术可以跨越存储器资源的多个组来镜像数据。存储在存储体中的信息被组织成单独可寻址的块，并且存储器地址包括镜像标志。要写入跨两个内存库镜像的信息，处理器会发出一个单独的写事务，并将镜像标志置为有效。存储器控制器检测到镜像标志被断言，并且作为响应，等待两个存储体变得可用。此时，存储器控制器使得在两个存储体上执行写入。要读取跨两个存储区镜像的数据，处理器发出读取，镜像标志置为有效。存储器控制器检查具有所需信息的两个存储体的可用性。如果任一银行可用，则接受读取请求，并从可用存储区检索所需的数据并将其返回到处理器。

4. 发明授权

US07290096B2 Full access to memory interfaces via remote request 有权
标题翻译：通过远程请求完全访问内存接口
公开(公告)号：US07290096B2
公开(公告)日：2007-10-30
申请号：US11403364
申请日：2006-04-13
申请人： Robert E. Jeter, Jr. , John W. Marshall , Jeffery B. Scott
发明人： Robert E. Jeter, Jr. , John W. Marshall , Jeffery B. Scott
IPC分类号： G06F13/00 , G06F12/00
CPC分类号： G06F12/0284 , G06F12/1072 , H04L29/08846 , H04L67/28
摘要： A system and method for enabling a processor to access a memory not directly coupled to the processor. A memory request, including a request identifier field, is issued by a processor to a local memory management unit (MMU). Using the request identifier field, the local MMU determines whether the memory request should be issued by the local memory management unit (MMU) to a local memory, or should be transferred by the local MMU to a remote MMU and issued by the remote MMU to a remote memory, the remote memory associated with a different processor. In this manner, the remote MMU issues certain memory requests on behalf of the local processor and returns any results back to the local processor.
摘要翻译：一种使处理器能够访问不直接耦合到处理器的存储器的系统和方法。包括请求标识符字段的存储器请求由处理器发布到本地存储器管理单元（MMU）。使用请求标识符字段，本地MMU确定存储器请求是否应由本地存储器管理单元（MMU）发布到本地存储器，或者应由本地MMU传送到远程MMU并由远程MMU发布到远程存储器，与不同处理器相关联的远程存储器。以这种方式，远程MMU代表本地处理器发出某些存储器请求并将任何结果返回到本地处理器。

5. 发明授权

US07047370B1 Full access to memory interfaces via remote request 有权
标题翻译：通过远程请求完全访问内存接口
公开(公告)号：US07047370B1
公开(公告)日：2006-05-16
申请号：US10342039
申请日：2003-01-14
申请人： Robert E. Jeter, Jr. , John W. Marshall , Jeffery B. Scott
发明人： Robert E. Jeter, Jr. , John W. Marshall , Jeffery B. Scott
IPC分类号： G06F13/00
CPC分类号： G06F12/0284 , G06F12/1072 , H04L29/08846 , H04L67/28
摘要： A technique for enabling a processor to access a memory not directly coupled to the processor. According to the technique, a local processor accesses a remote memory by issuing a memory request that contains an indicator that indicates the request is addressed to the remote memory. The request is then transferred to a remote memory management unit (MMU) coupled to the remote memory. The remote MMU acts as a proxy and issues the memory request to the remote memory on behalf of the local processor. The results of the request, if any, are returned to the local processor.
摘要翻译：一种使处理器能够访问不直接耦合到处理器的存储器的技术。根据该技术，本地处理器通过发出包含指示该请求的指示符到存储器的存储器请求来访问远程存储器。然后将该请求传送到耦合到远程存储器的远程存储器管理单元（MMU）。远程MMU充当代理，并代表本地处理器向远程内存发出内存请求。请求的结果（如果有的话）返回给本地处理器。

6. 发明授权

US07155588B1 Memory fence with background lock release 有权
标题翻译：内存围栏与背景锁释放
公开(公告)号：US07155588B1
公开(公告)日：2006-12-26
申请号：US10217023
申请日：2002-08-12
申请人： Robert E. Jeter, Jr.
发明人： Robert E. Jeter, Jr.
IPC分类号： G06F12/00
CPC分类号： G06F9/526 , G06F9/3004 , G06F9/30087 , G06F9/522 , G06F2209/521
摘要： A technique releases locks associated with particular memory locations. The technique uses a “background” approach to determining when the locks should be released in that memory operations associated with the memory locations are monitored while instructions continue to execute on a processor. The memory operations are monitored by generating a condition for each memory operation and clearing the condition when the operation completes. When all the conditions are cleared, the associated locks are released.
摘要翻译：技术释放与特定内存位置相关联的锁定。该技术使用“背景”方法来确定何时应该释放锁定，以在与存储器位置相关联的操作中监视指令，同时指令在处理器上继续执行。通过产生每个存储器操作的条件并且当操作完成时清除条件来监视存储器操作。当所有条件都被清除时，相关的锁将被释放。

7. 发明授权

US07434016B2 Memory fence with background lock release 有权
标题翻译：内存围栏与背景锁释放
公开(公告)号：US07434016B2
公开(公告)日：2008-10-07
申请号：US11601334
申请日：2006-11-17
申请人： Robert E. Jeter, Jr.
发明人： Robert E. Jeter, Jr.
IPC分类号： G06F12/00
CPC分类号： G06F9/526 , G06F9/3004 , G06F9/30087 , G06F9/522 , G06F2209/521
摘要： In one embodiment, a processor is operable to issue a first memory request to access a particular memory location, and, prior to completion of the first memory request, to issue a command to release a memory lock on the particular memory location when access to the particular memory location is complete. The processor is further operable to, prior to release of the memory lock, issue a second memory request to access a different memory location. Also a memory management unit is operable to receive the command to release the memory lock and to monitor for when access to the particular memory location is complete. The memory management unit releases the memory lock in response to completion.
摘要翻译：在一个实施例中，处理器可操作以发出访问特定存储器位置的第一存储器请求，并且在完成第一存储器请求之前，当访问特定存储器位置时发出命令来释放特定存储器位置上的存储器锁特定内存位置已完成。处理器还可操作以在释放存储器锁之前发出访问不同存储器位置的第二存储器请求。还有，存储器管理单元可操作以接收释放存储器锁的命令并监视对特定存储器位置的访问何时完成。内存管理单元响应完成释放内存锁。

8. 发明授权

US07257681B2 Maintaining entity order with gate managers 有权
标题翻译：维护实体订单与门经理
公开(公告)号：US07257681B2
公开(公告)日：2007-08-14
申请号：US10458869
申请日：2003-06-11
申请人： Robert E. Jeter, Jr. , John A. Chanak
发明人： Robert E. Jeter, Jr. , John A. Chanak
IPC分类号： G06F12/00
CPC分类号： H04L12/4604 , H04L49/90 , H04L49/901
摘要： A technique for maintaining order among a plurality of entities contained in an intermediate node by ensuring orderly access to a resource shared by the entities. A request is generated to access the resource. The request is placed on a queue associated with an entity. The request eventually reaches the head of the queue. An identifier generated by a gate manager is compared with an identifier associated with the queue to determine if they match. If so, the request is transferred to the resource, which processes the request. Results acquired from the resource (if any) are transferred to the entity.
摘要翻译：一种用于通过确保有序地访问由所述实体共享的资源来在包含在中间节点中的多个实体之间维持秩序的技术。生成访问资源的请求。请求被放置在与实体相关联的队列上。请求最终到达队列的头部。由门管理器生成的标识符与与队列相关联的标识符进行比较，以确定它们是否匹配。如果是这样，请求被转移到处理请求的资源。从资源获得的结果（如果有的话）被转移到实体。

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