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

US5949789A Arbitration ring for accessing a limited bandwidth switching network 失效
标题翻译：用于访问有限带宽交换网络的仲裁环
公开(公告)号：US5949789A
公开(公告)日：1999-09-07
申请号：US754734
申请日：1996-11-21
申请人： Helen M. Davis , Bryan T. Preas , Alan G. Bell , Joseph B. Lyles , Daniel H. Greene
发明人： Helen M. Davis , Bryan T. Preas , Alan G. Bell , Joseph B. Lyles , Daniel H. Greene
IPC分类号： H04Q3/00 , H04L12/56 , H04J3/02
CPC分类号： H04L49/201 , H04L49/102 , H04L49/107 , H04L49/255 , H04L49/30 , H04L49/3081 , H04L49/508 , H04L2012/5651 , H04L2012/5679 , H04L49/103 , H04L49/25
摘要： Access to a limited bandwidth switching network of an ATM (Asynchronous Transfer Mode) switch is scheduled using a reservation ring. In general, a limited bandwidth switching network is unable to generate all possible one-to-one input to output channel mappings in a single switch cycle. The limited bandwidth switching network includes one or more routing channels for routing at most B data packets each switch cycle between the input channels and output channels, where the number of data packets B is less than the aggregate output bandwidth that can be directed at the routing channels. Arbitration requests make two passes around the reservation ring each arbitration cycle. Output channel contention is settled during the first pass around the reservation ring. Contention for limited switching network bandwidth is settled during the second pass around the reservation ring. Arbitration requests granted a reservation at the end of an arbitration cycle are issued into the limited bandwidth switching network during a subsequent switch cycle.
摘要翻译：使用预留环调度访问ATM（异步传输模式）交换机的有限带宽交换网络。通常，有限带宽交换网络不能在单个交换周期中产生所有可能的一对一输入以输出信道映射。有限带宽交换网络包括一个或多个路由信道，用于在输入信道和输出信道之间的每个交换周期中路由最多的B个数据分组，其中数据分组B的数量小于可以针对路由的聚合输出带宽频道仲裁请求每个仲裁周期在保留环周围进行两次通过。输出频道争用在预订环首次通过期间结算。有限切换网络带宽的争夺在保留环周围的第二次通过期间得到解决。在仲裁周期结束时授予的仲裁请求在随后的切换周期内发布到有限带宽交换网络中。

2. 发明授权

US5883895A Arbitration ring with automatic sizing for a partially populated switching network 失效
标题翻译：具有部分填充交换网络的自动调整大小的仲裁环
公开(公告)号：US5883895A
公开(公告)日：1999-03-16
申请号：US754688
申请日：1996-11-21
申请人： Helen M. Davis , Daniel H. Greene , Alan G. Bell
发明人： Helen M. Davis , Daniel H. Greene , Alan G. Bell
IPC分类号： H04L12/56 , H04L12/403 , H04J3/02
CPC分类号： H04L49/508 , H04L49/102 , H04L49/1553 , H04L49/201 , H04L49/25 , H04L49/30 , H04L49/3081 , H04L2012/5679 , H04L2012/5681 , H04L49/103 , H04L49/15 , H04L49/20
摘要： Access to a switching network of an ATM (Asynchronous Transfer Mode) switch is scheduled with a reservation ring that automatically determines the number of channels populating the switching network during a switch cycle. The reservation ring is a distributed arbiter that resolves conflicts arising among a plurality of input channels for access to a plurality of output channels of the switching network. Each input channel populating the switching network is coupled to an arbitration unit of the reservation ring. The arbitration units on the ring determine when an arbitration cycle is complete for each of the arbitration units populating the ring. This enables the number of channels populating the switching network to increase or decrease without having to reconfigure the reservation ring.
摘要翻译： ATM（异步传输模式）交换机的交换网络的访问通过预留环进行调度，自动确定在切换周期期间填充交换网络的信道数量。预留环是分布式仲裁器，其解决在用于访问交换网络的多个输出信道的多个输入信道之间产生的冲突。填充交换网络的每个输入信道被耦合到预留环的仲裁单元。环上的仲裁单元确定每个填充环的仲裁单元何时完成仲裁周期。这使得填充交换网络的信道的数量增加或减少，而不必重新配置保留环。

3. 发明授权

US5835491A Method for supporting multicast capabilities in switching networks with a reservation ring 失效
标题翻译：用于在具有预留环的交换网络中支持组播能力的方法
公开(公告)号：US5835491A
公开(公告)日：1998-11-10
申请号：US754726
申请日：1996-11-21
申请人： Helen M. Davis , Bryan T. Preas , Alan G. Bell , Joseph B. Lyles , Daniel H. Greene
发明人： Helen M. Davis , Bryan T. Preas , Alan G. Bell , Joseph B. Lyles , Daniel H. Greene
IPC分类号： H04Q3/00 , H04L12/56 , H04Q11/04
CPC分类号： H04L49/508 , H04L49/102 , H04L49/201 , H04L49/203 , H04L49/30 , H04L49/3081 , H04Q11/0478 , H04L2012/5679 , H04L2012/5681 , H04L49/103 , H04L49/25
摘要： A method controls multicast cell access to a switching network with a reservation ring in an ATM (Asynchronous Transfer Mode) switch. The switching network distributes the multicast cell in one or more passes from an input channel to one or more output channels of the switch during a switch cycle. An arbitration session for a multicast cell begins by submitting an arbitration request identifying a set of destination output channels to the reservation ring. During an arbitration cycle, the output channels in the set of destination output channels are arbitrated for over the reservation ring. The arbitration request is reissued during later arbitration cycles until access to each of the destination output channels in the set of output channels is granted.
摘要翻译：一种方法通过ATM（异步传输模式）交换机来控制具有预留环的交换网络的多播小区接入。在切换周期期间，交换网络将多播信元从输入信道一次或多次传送到交换机的一个或多个输出信道。多播小区的仲裁会话通过向保留环提交标识一组目的地输出信道的仲裁请求开始。在仲裁周期中，目的地输出通道组中的输出通道被仲裁用于保留环。在稍后的仲裁周期期间重新发布仲裁请求，直到授予在该组输出通道中的每个目的地输出通道的访问。

4. 发明授权

US5912889A ATM switch with output port clustering for dynamically allocating bandwidth between ports 失效
标题翻译：具有输出端口集群的ATM交换机，用于在端口之间动态分配带宽
公开(公告)号：US5912889A
公开(公告)日：1999-06-15
申请号：US754727
申请日：1996-11-21
申请人： Bryan T. Preas , Helen M. Davis , Alan G. Bell , Joseph B. Lyles
发明人： Bryan T. Preas , Helen M. Davis , Alan G. Bell , Joseph B. Lyles
IPC分类号： H04L12/56 , H04Q11/04
CPC分类号： H04L49/30 , H04L49/201 , H04L49/25 , H04L49/255 , H04L49/258 , H04L49/3081 , H04L49/508 , H04Q11/0478 , H04L2012/5672 , H04L2012/5679 , H04L2012/5681 , H04L2012/5683 , H04L2012/5686 , H04L49/102 , H04L49/103 , H04L49/15 , H04L49/20
摘要： Ports of an ATM (Asynchronous Transfer Mode) switch are consolidated into cluster modules to increase the aggregate throughput of the switch. Packets are routed between cluster modules using an intercluster switching network. The intercluster switching network includes a plurality of input channels and output channels. During a switch cycle, a maximum of "K" packets are delivered to each of the output channels of the intercluster switching network. This maximum of "K" packets is a speedup per cluster module that is shared between ports of each cluster module. Consequently, each output port of a cluster module operates with a peak speedup of up to "K" packets per switch cycle thereby increasing the aggregate throughput of the switch.
摘要翻译： ATM（异步传输模式）交换机的端口被整合到集群模块中，以增加交换机的总吞吐量。分组在集群模块之间使用集群间交换网络进行路由。集群间交换网络包括多个输入通道和输出通道。在切换周期期间，最大的“K”个分组被传送到集群间交换网络的每个输出信道。这个最大“K”数据包是每个集群模块的端口之间共享的每个集群模块的加速。因此，集群模块的每个输出端口以每个交换周期的高达“K”个分组的峰值加速度运行，从而增加交换机的总吞吐量。

5. 发明授权

US06486861B1 Method and apparatus for a display producing a fixed set of images 失效
标题翻译：用于产生固定图像组的显示器的方法和装置
公开(公告)号：US06486861B1
公开(公告)日：2002-11-26
申请号：US09306752
申请日：1999-05-07
申请人： Bryan T. Preas , Helen M. Davis
发明人： Bryan T. Preas , Helen M. Davis
IPC分类号： G09G336
CPC分类号： G09G3/04 , Y10T428/24802
摘要： A method to greatly simplify and reduce the cost of displays when all of the images that need to be displayed are known beforehand. By precomputing the intersections of the images and addressing the intersections of the images, the number of drivers that are required becomes a function of the number of images rather than a function of the resolution. For example, four arbitrarily complex, overlapping images require, at most, 16 drivers. In general, n arbitrarily complex, overlapping images require, at most, 2n drivers. This result holds irrespective of the size of the display or the complexity resolution, or amount of overlap of the images. Further reduction of the number of drivers is possible if some of the images do not overlap some of the other images. For example, two images overlap each other in one area and two other images may overlap each other in a separate area while the two sets of images do not themselves overlap. In this case, at most eight drivers are needed instead of the 16 drivers that would be required if all four of the images overlapped each other. In general, if you consider N separate, distinct areas, each with a set of overlapping images where ni images overlap in area i (ie, n1 images that overlap in area 1, n2 images that overlap in area 2, etc.). Then the maximum number of drivers that are required will be summation for i from 1 to N of 2 raised to the power of ni.
摘要翻译：当预先知道需要显示的所有图像时，大大简化和降低显示器成本的方法。通过预先计算图像的交点和寻址图像的交点，所需的驱动器数量成为图像数量的函数，而不是分辨率的函数。例如，四个任意复杂的重叠图像最多需要16个驱动程序。一般来说，n个任意复杂的重叠图像最多需要2n个驱动程序。无论显示器的尺寸或复杂性分辨率或图像的重叠量如何，该结果都将成立。如果某些图像不与其他图像重叠，则可以进一步减少驱动器的数量。例如，两个图像在一个区域中彼此重叠，并且另外两个图像可以在单独的区域中彼此重叠，而两组图像本身不重叠。在这种情况下，最多需要8个驱动程序，而不是所有4个映像重叠的16个驱动程序。一般来说，如果您考虑N个独立的不同区域，每个区域具有一组重叠图像，其中ni图像在区域i中重叠（即，区域1中重叠的n1个图像，区域2中重叠的n2个图像等）。那么所需的最大驱动程序数将是i从1到N的2的总和提高到ni的幂。

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