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. 发明申请

US20070110087A1 Method and system to reduce interconnect latency 有权
标题翻译：减少互连延迟的方法和系统
公开(公告)号：US20070110087A1
公开(公告)日：2007-05-17
申请号：US11402091
申请日：2006-04-10
申请人： Francois Abel , Alan Benner , Richard Grzybowski , Brewster Hemenway , Ilias Iliadis , Rajaram Krishnamurthy , Ronald Luijten , Cyriel Minkenberg
发明人： Francois Abel , Alan Benner , Richard Grzybowski , Brewster Hemenway , Ilias Iliadis , Rajaram Krishnamurthy , Ronald Luijten , Cyriel Minkenberg
IPC分类号： H04L12/56 , H04L12/43
CPC分类号： H04L45/00 , H04L12/417 , H04L43/087 , H04L45/62 , H04L47/50 , H04L47/58 , H04L49/254 , H04L49/3027 , H04L49/508
摘要： A method and system for reducing arbitration latency employs speculative transmission (STX) without prior arbitration in combination with routing fabric scheduled arbitration. Packets are sent from source locations to a routing fabric through scheduled arbitration, and also through speculative arbitration, to non-contentiously allocate outputs that were not previously reserved in the routing fabric to the speculatively transmitted packets.
摘要翻译：用于减少仲裁延迟的方法和系统使用推测传输（STX），而没有预先仲裁结合路由结构调度仲裁。数据包通过调度仲裁从源位置发送到路由结构，并通过推测性仲裁，将非先前在路由结构中保留的输出非争用地分配给推测性传输的数据包。

2. 发明授权

US08135024B2 Method and system to reduce interconnect latency 有权
标题翻译：减少互连延迟的方法和系统
公开(公告)号：US08135024B2
公开(公告)日：2012-03-13
申请号：US11402091
申请日：2006-04-10
申请人： Francois G Abel , Alan F Benner , Richard R Grzybowski , Brewster Roe Hemenway, Jr. , Ilias Iliadis , Rajaram Krishnamurthy , Ronald P Luijten , Cyriel Minkenberg
发明人： Francois G Abel , Alan F Benner , Richard R Grzybowski , Brewster Roe Hemenway, Jr. , Ilias Iliadis , Rajaram Krishnamurthy , Ronald P Luijten , Cyriel Minkenberg
IPC分类号： H04L12/56
CPC分类号： H04L45/00 , H04L12/417 , H04L43/087 , H04L45/62 , H04L47/50 , H04L47/58 , H04L49/254 , H04L49/3027 , H04L49/508
摘要： A method and system for reducing arbitration latency employs speculative transmission (STX) without prior arbitration in combination with routing fabric scheduled arbitration. Packets are sent from source locations to a routing fabric through scheduled arbitration, and also through speculative arbitration, to non-contentiously allocate outputs that were not previously reserved in the routing fabric to the speculatively transmitted packets.
摘要翻译：用于减少仲裁延迟的方法和系统使用推测传输（STX）而没有预先仲裁并结合路由结构调度仲裁。数据包通过调度仲裁从源位置发送到路由结构，并通过推测性仲裁，将非先前在路由结构中保留的输出非争用地分配给推测性传输的数据包。

3. 发明申请

US20070201497A1 Method and system for high-concurrency and reduced latency queue processing in networks 审中-公开
标题翻译：网络中高并发性和减少延迟队列处理的方法和系统
公开(公告)号：US20070201497A1
公开(公告)日：2007-08-30
申请号：US11362683
申请日：2006-02-27
申请人： Rajaram Krishnamurthy
发明人： Rajaram Krishnamurthy
IPC分类号： H04L12/56
CPC分类号： H04L47/6215 , H04L47/10 , H04L47/24 , H04L47/50 , H04L47/56 , H04L49/254 , H04L49/3018 , H04L49/3045
摘要： A method and a system for controlling a plurality of queues of an input port in a switching or routing system. The method supports the regular request-grant protocol along with speculative transmission requests in an integrated fashion. Each regular scheduling request or speculative transmission request is stored in request order using references to minimize memory usage and operation count. Data packet arrival and speculation event triggers can be processed concurrently to reduce operation count and latency. The method supports data packet priorities using a unified linked list for request storage. A descriptor cache is used to hide linked list processing latency and allow central scheduler response processing with reduced latency. The method further comprises processing a grant of a scheduling request, an acknowledgement of a speculation request or a negative acknowledgement of a speculation request. Grants and speculation responses can be processed concurrently to reduce operation count and latency. A queue controller allows request queues to be dequeued concurrently on central scheduler response arrival. Speculation requests are stored in a speculation request queue to maintain request queue consistency and allow scheduler response error recovery for the central scheduler.
摘要翻译：一种用于控制交换或路由系统中的输入端口的多个队列的方法和系统。该方法以集成方式支持常规请求授权协议以及推测传输请求。每个常规调度请求或推测传输请求使用引用以请求顺序存储以最小化存储器使用和操作计数。可以同时处理数据包到达和推测事件触发器，以减少操作数和延迟。该方法使用用于请求存储的统一链表支持数据包优先级。描述符缓存用于隐藏链接列表处理延迟并允许中央调度器响应处理以减少的延迟。该方法还包括处理调度请求的准许，投机请求的确认或投机请求的否定确认。可以同时处理赠款和投机回应，以减少运营数量和延迟。队列控制器允许请求队列在中央调度程序响应到达时同时出队。投机请求存储在推测请求队列中，以保持请求队列一致性，并允许中央调度程序的调度程序响应错误恢复。

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