-
21.发明授权Independently sizable memory pages for a plurality of connection ID types in a network switch 失效用于网络交换机中的多个连接ID类型的独立大小的存储器页面
公开(公告)号：US5991297A
公开(公告)日：1999-11-23
申请号：US919824
申请日：1997-08-28
CPC分类号： H04L49/552 , H04L49/201 , H04L49/203 , H04L49/3009 , H04L49/3081 , H04L49/309 , H04Q11/0478 , H04L49/253 , H04L49/30
摘要： A method and apparatus are disclosed for selectively accessing and independently sizing connection identification tables within a network switch. Upon receipt of a data unit, such as an asynchronous transfer mode cell at an input port of an Input Output Module, a plurality of selection bits are inserted into the cell header which are used to select one of a plurality of connection identifiers. The VPI/VCI addresses are mapped into a connection identifier and the connection identifier is also inserted within the respective cell header. The connection identifier may comprise an unicast connection identifier, a multicast connection identifier, or a redundant unicast identifier. The unicast, multicast and redundant identifiers are either stored in separate tables at call setup and the tables are independently selectable via use of the selection bits stored within the cell header. Alternatively, the selection bits are employed to specify a register which points to the first address for the respective type of identifiers. Thus, identifiers of a particular connection type are accessible via a base address plus an offset address. In the described manner, tables or portions of tables containing connection identifiers may be flexibly and independently sized.
摘要翻译： 公开了用于选择性地访问和独立地调整网络交换机内的连接识别表的方法和装置。 在输入输出模块的输入端口接收到诸如异步传送模式单元之类的数据单元时，将多个选择位插入到用于选择多个连接标识符之一的单元首标中。 VPI / VCI地址被映射到连接标识符中，并且连接标识符也被插入到相应的信元头部内。 连接标识符可以包括单播连接标识符，多播连接标识符或冗余单播标识符。 单播，多播和冗余标识符在呼叫建立时存储在单独的表中，并且可以通过使用存储在信元头部内的选择位来独立地选择表。 或者，选择位用于指定对于相应类型的标识符指向第一地址的寄存器。 因此，特定连接类型的标识符可通过基地址加偏移地址来访问。 以描述的方式，包含连接标识符的表或表的部分可以灵活地且独立地定尺寸。
-
公开(公告)号：US5872987A
公开(公告)日：1999-02-16
申请号：US714635
申请日：1996-09-16
申请人： Jon P. Wade , Daniel R. Cassiday , Robert D. Lordi , Guy Lewis Steele, Jr. , Margaret A. St. Pierre , Monica C. Wong-Chan , Zahi S. Abuhamdeh , David C. Douglas , Mahesh N. Ganmukhi , Jeffrey V. Hill , W. Daniel Hillis , Scott J. Smith , Shaw-Wen Yang , Robert C. Zak, Jr.
发明人： Jon P. Wade , Daniel R. Cassiday , Robert D. Lordi , Guy Lewis Steele, Jr. , Margaret A. St. Pierre , Monica C. Wong-Chan , Zahi S. Abuhamdeh , David C. Douglas , Mahesh N. Ganmukhi , Jeffrey V. Hill , W. Daniel Hillis , Scott J. Smith , Shaw-Wen Yang , Robert C. Zak, Jr.
IPC分类号： G06F15/173 , G06F15/78 , G06F15/80 , G06F7/02
CPC分类号： G06F15/8092 , G06F15/17381 , G06F15/8084 , G06F21/52
摘要： A massively-parallel computer includes a plurality of processing nodes and at least one control node interconnected by a network. The network faciliates the transfer of data among the processing nodes and of commands from the control node to the processing nodes. Each each processing node includes an interface for transmitting data over, and receiving data and commands from, the network, at least one memory module for storing data, a node processor and an auxiliary processor. The node processor receives commands received by the interface and processes data in response thereto, in the process generating memory access requests for facilitating the retrieval of data from or storage of data in the memory module. The node processor further controlling the transfer of data over the network by the interface. The auxiliary processor is connected to the memory module and the node processor. In response to memory access requests from the node processor, the auxiliary processor performs a memory access operation to store data received from the node processor in the memory module, or to retrieve data from the memory module for transfer to the node processor. In response to auxiliary processing instructions from the node processor, the auxiliary processor performs data processing operations in connection with data in the memory module.
摘要翻译： 大型并行计算机包括多个处理节点和由网络互连的至少一个控制节点。 该网络便于处理节点之间的数据传输和从控制节点到处理节点的命令。 每个处理节点包括用于从网络传输数据并从其接收数据和命令的接口，用于存储数据的至少一个存储器模块，节点处理器和辅助处理器。 节点处理器在产生存储器访问请求的过程中接收由接口接收的命令并响应于此处理数据，以便于从存储器模块中的数据检索或存储数据。 节点处理器进一步通过接口控制网络上的数据传输。 辅助处理器连接到存储器模块和节点处理器。 响应于来自节点处理器的存储器访问请求，辅助处理器执行存储器访问操作以将从节点处理器接收的数据存储在存储器模块中，或者从存储器模块检索数据以传送到节点处理器。 响应于来自节点处理器的辅助处理指令，辅助处理器结合存储器模块中的数据执行数据处理操作。
-
23.发明授权公开(公告)号：US08553866B2
公开(公告)日：2013-10-08
申请号：US13226737
申请日：2011-09-07
CPC分类号： H04L65/1006 , H04L65/1016 , H04L67/14 , H04L67/142
摘要： A system and method provisions dynamic call models within a network having a serving node for providing session control for user endpoint (UE) devices. A user endpoint device (UE) with agent logic, expresses dynamic context of the UE in a message and sends said dynamic context message to a serving node. The dynamic context includes a subset of devices that could be used as UEs or associated devices, network connections that terminate or emanate from said devices that could be used as UEs or associated devices, and capabilities of said devices that could be used as UEs or associated devices. The serving node logic receives said context message from the UE and constructs a dynamic call model in response. The dynamic call model having filter codes to associate service codes with application servers (ASs) in communication with the network, and each AS having service logic to provide a service.
摘要翻译： 一种系统和方法提供具有用于为用户端点（UE）设备提供会话控制的服务节点的网络内的动态呼叫模型。 具有代理逻辑的用户端点设备（UE）在消息中表达UE的动态上下文，并将所述动态上下文消息发送到服务节点。 动态上下文包括可用作UE或相关设备的设备的子集，从可用作UE或相关设备的所述设备终止或发出的网络连接以及可用作UE或相关联的所述设备的能力 设备。 服务节点逻辑从UE接收所述上下文消息并且响应地构造动态呼叫模型。 具有将服务代码与与网络通信的应用服务器（AS）相关联的过滤代码的动态呼叫模型，并且每个AS具有服务逻辑以提供服务。
-
24.发明申请公开(公告)号：US20120063582A1
公开(公告)日：2012-03-15
申请号：US13226737
申请日：2011-09-07
IPC分类号： H04M3/42
CPC分类号： H04L65/1006 , H04L65/1016 , H04L67/14 , H04L67/142
摘要： A system and method provisions dynamic call models within a network having a serving node for providing session control for user endpoint (UE) devices. A user endpoint device (UE) with agent logic, expresses dynamic context of the UE in a message and sends said dynamic context message to a serving node. The dynamic context includes a subset of devices that could be used as UEs or associated devices, network connections that terminate or emanate from said devices that could be used as UEs or associated devices, and capabilities of said devices that could be used as UEs or associated devices. The serving node logic receives said context message from the UE and constructs a dynamic call model in response. The dynamic call model having filter codes to associate service codes with application servers (ASs) in communication with the network, and each AS having service logic to provide a service.
摘要翻译： 一种系统和方法提供具有用于为用户端点（UE）设备提供会话控制的服务节点的网络内的动态呼叫模型。 具有代理逻辑的用户端点设备（UE）在消息中表达UE的动态上下文，并将所述动态上下文消息发送到服务节点。 动态上下文包括可用作UE或相关设备的设备的子集，从可用作UE或相关设备的所述设备终止或发出的网络连接以及可用作UE或相关联的所述设备的能力 设备。 服务节点逻辑从UE接收所述上下文消息并且响应地构造动态呼叫模型。 具有将服务代码与与网络通信的应用服务器（AS）相关联的过滤代码的动态呼叫模型，并且每个AS具有服务逻辑以提供服务。
-
公开(公告)号：US6008995A
公开(公告)日：1999-12-28
申请号：US924473
申请日：1997-08-19
申请人： Mark Pusateri , John P. Jones , Mahesh N. Ganmukhi
发明人： Mark Pusateri , John P. Jones , Mahesh N. Ganmukhi
CPC分类号： G06F1/185 , G06F1/184 , G06F1/186 , H05K7/1424
摘要： A card cage for mounting printed circuit cards of at least two sizes is disclosed. The card cage includes an insert removably mounted to a mounting bar position between first and second ends of the card cage. The insert extends along a portion of the width of the card cage. When the insert is mounted to the mounting bar, a printed circuit card of a first length may be disposed between the insert and one of the card cage ends. When the insert is removed, a printed circuit card of a second length greater than the first length may be mounted between the first and second ends of the card cage. Plural mounting bars may be located between the respective card cage ends to accommodate printed circuit cards of different lengths.
摘要翻译： 公开了一种用于安装至少两种尺寸的印刷电路卡的卡笼。 卡笼包括可移除地安装到卡笼的第一和第二端之间的安装杆位置的插入件。 插入件沿着卡笼的宽度的一部分延伸。 当插入件安装到安装杆上时，第一长度的印刷电路卡可以设置在插入件与卡盒端部中的一个之间。 当移除插入件时，大于第一长度的第二长度的印刷电路卡可以安装在卡盒的第一和第二端之间。 多个安装杆可以位于相应的卡笼端之间，以适应不同长度的印刷电路卡。
-
公开(公告)号：US5995511A
公开(公告)日：1999-11-30
申请号：US628206
申请日：1996-04-05
CPC分类号： H04L12/5601 , H04L49/107 , H04Q11/0478 , H04L2012/5679 , H04L2012/5681
摘要： A queue control system is disclosed for use in connection with the transfer of information, in the form of information transfer units, in a digital network. The network provides a plurality of service rate classes, based on, for example transmission rates for the various paths. The information buffer control subsystem includes a information transfer unit receiver, a information transfer unit buffer and a group controller. The information transfer unit receiver receives the information transfer units, and the buffer is provided to buffer the received information transfer units prior to transmission. The group controller controls the buffering of information transfer units received by the information transfer unit receiver in the buffer. In that operation, the group controller aggregates the information transfer units for each path in the buffer according to respective service rate classes, in particular aggregating the information transfer units for each path in a queue and further aggregating the queues for the paths associated with each service rate class in a queue. A transmission scheduler is also disclosed for use in transferring information, in the form of information transfer units, each associated with a path, in a digital network. The network provides a plurality of service rate classes, based on, for example, transmission rates for the various paths. The information transfer units for each path in a path queue, and the path queues for the paths associated with each service rate class are aggregated in a service rate queue. The transmission scheduler includes a information transfer unit selector for selecting from among the service rate queues, one path queue to provide a information transfer unit for transmission, and a information transfer unit transmitter for transmitting the information transfer unit provided by the selected path queue.
-
公开(公告)号：US5953314A
公开(公告)日：1999-09-14
申请号：US919828
申请日：1997-08-28
CPC分类号： G06F11/2038 , H04Q3/5455 , G06F11/2017 , G06F11/2025 , H04J3/0697 , H04Q2213/1305 , H04Q2213/13104 , H04Q2213/13107 , H04Q2213/13162 , H04Q2213/13166 , H04Q2213/13167
摘要： First and second control processor cards are employed in conjunction with first and second switch fabric cards to interconnect Input/Output cards in a telecommunications switch. The control processor cards provide a portion of the functionality previously associated with switch fabric cards, such as exertion of control over allocation of bandwidth within the switch. The control processor cards also provide new functionality. In particular, each control processor card can configure both switch fabric cards. Redundant control processor cards and redundant switch fabric cards are employed to provide a switch that is less susceptible to failure than switches with only redundant switch fabric cards. Hence, failure of a control processor card and a switch fabric card can be sustained without resulting in switch failure. Timing control functions may also be provided by a separate timing module card.
摘要翻译： 第一和第二控制处理器卡与第一和第二交换结构卡结合使用以互连电信交换机中的输入/输出卡。 控制处理器卡提供先前与交换结构卡相关联的功能的一部分，例如对交换机内的带宽分配的控制。 控制处理器卡还提供新的功能。 特别地，每个控制处理器卡可以配置两个交换矩阵卡。 冗余控制处理器卡和冗余交换矩阵卡被用于提供一个不仅仅具有冗余交换矩阵卡的交换机的故障易受影响的交换机。 因此，可以维持控制处理器卡和交换矩阵卡的故障，而不会导致开关故障。 定时控制功能也可以由单独的定时模块卡提供。
-
公开(公告)号：US5905730A
公开(公告)日：1999-05-18
申请号：US49510
申请日：1998-03-27
申请人： Tao Yang , Mahesh N. Ganmukhi
发明人： Tao Yang , Mahesh N. Ganmukhi
IPC分类号： H04L12/54 , H04L12/70 , H04L12/851 , H04L12/863 , H04L12/869 , H04L12/873 , H04L12/875 , H04Q11/04
CPC分类号： H04L47/2408 , H04L12/5601 , H04L12/5602 , H04L12/5693 , H04L47/24 , H04L47/522 , H04L47/564 , H04L47/60 , H04L47/621 , H04L47/6215 , H04L47/623 , H04Q11/0478 , H04L2012/5649 , H04L2012/5651 , H04L2012/5679 , H04L2012/568 , H04L2012/5681
摘要： A packet scheduler is disclosed which provides a high degree of fairness in scheduling packets associated with different sessions. The scheduler also minimizes packet delay for packet transmission from a plurality of sessions which may have different requirements and may operate at different transfer rates. When a packet is received by the scheduler, the packet is assigned its own packet virtual start time based on whether the session has any pending packets and the values of the virtual finish time of the previous packet in the session and the packets arrival time. The scheduler then determines a virtual finish time of the packet by determining the transfer time required for the packet based upon its length and rate and by adding the transfer time to the packet virtual start time of the packet. The packet with the smallest virtual finish time is then scheduled for transfer. By selecting packets for transmission in the above described manner, the available bandwidth may be shared in pro-rata proportion to the guaranteed session rate, thereby providing a scheduler with a high degree of fairness while also minimizing the amount of time a packet waits in the scheduler before being served.
摘要翻译： 公开了一种在调度与不同会话相关联的分组中提供高度公平性的分组调度器。 调度器还使来自可能具有不同要求并且可以以不同传送速率操作的多个会话的分组传输的分组延迟最小化。 当调度器接收到分组时，基于会话是否具有任何未决分组以及会话中的先前分组的虚拟完成时间的值和分组到达时间，向分组分配其自己的分组虚拟开始时间。 调度器然后通过基于其长度和速率确定分组所需的传送时间，并通过将传送时间添加到分组的分组虚拟开始时间来确定分组的虚拟完成时间。 然后计划传输最小虚拟完成时间的数据包。 通过以上述方式选择用于传输的分组，可以按照保证会话速率的比例共享可用带宽，从而提供高度公平的调度器，同时最小化分组等待的时间量 服务前调度程序。
-
29.发明授权Parallel computer system with physically separate tree networks for data and control messages 失效并行计算机系统，具有用于数据和控制消息的物理分离的树形网络
公开(公告)号：US5590283A
公开(公告)日：1996-12-31
申请号：US380854
申请日：1995-01-27
申请人： W. Daniel Hillis , David C. Douglas , Charles E. Leiserson , Bradley C. Kuszmaul , Mahesh N. Ganmukhi , Jeffrey V. Hill , Monica C. Wong-Chan
发明人： W. Daniel Hillis , David C. Douglas , Charles E. Leiserson , Bradley C. Kuszmaul , Mahesh N. Ganmukhi , Jeffrey V. Hill , Monica C. Wong-Chan
IPC分类号： G06F15/16 , G06F11/00 , G06F11/08 , G06F11/22 , G06F15/173 , G06F15/80 , G06F15/163
CPC分类号： G06F15/17381 , G06F11/08 , G06F11/22 , G06F11/324 , G06F15/17343 , H04L45/48 , H04L49/35 , H04L49/555 , G06F2201/88
摘要： A digital computer comprises a plurality of processing elements, a communications router, and a control network. Each processing element performs data processing operations in connection with commands, at least some of the processing elements performing the data processing operations in connection with the commands in messages they receive over the control network. Each processing element also generates and receives data transfer messages, each including an address portion containing an address, for transfer to another processing element as identified by the address. At least one of the processing elements further generates the control network messages for transfer over the communications router. The communications router comprises router nodes interconnected in the form of a "fat-tree," and the control network comprises control network nodes interconnected in the form of a tree, with the processing elements being connected at the leaf nodes of the respective communications router and control network.
摘要翻译： 数字计算机包括多个处理元件，通信路由器和控制网络。 每个处理单元执行与命令有关的数据处理操作，至少一些处理单元通过控制网络接收的消息中的命令进行数据处理操作。 每个处理元件还产生和接收数据传送消息，每个数据传送消息包括包含地址的地址部分，用于传送到由该地址识别的另一个处理元件。 处理元件中的至少一个进一步生成用于通过通信路由器传送的控制网络消息。 通信路由器包括以“胖树”形式互连的路由器节点，并且控制网络包括以树形式互连的控制网络节点，处理元件连接在相应通信路由器的叶节点处， 控制网络。
-
公开(公告)号：US09468033B2
公开(公告)日：2016-10-11
申请号：US13276744
申请日：2011-10-19
IPC分类号： H04W4/00 , H04W76/02 , H04M7/12 , H04L29/08 , H04W48/16 , H04W8/26 , H04W48/18 , H04W80/10 , H04W88/18 , H04L29/06 , H04W84/04 , H04W84/18 , H04W88/06
CPC分类号： H04W76/15 , H04H20/38 , H04L65/1016 , H04L67/14 , H04L67/146 , H04L67/306 , H04M7/123 , H04W4/00 , H04W4/80 , H04W8/26 , H04W48/16 , H04W48/18 , H04W72/0493 , H04W80/10 , H04W84/045 , H04W84/18 , H04W88/04 , H04W88/06 , H04W88/18
摘要： A method of associating multiple user endpoints (UEs) with a single IMS session in an IMS network having a serving node for controlling at least one IMS session for a user and at least a first access network for providing access to UEs. The method involves associating a first UE with the user and with an IMS session; discovering a second UE in a proximity of the first UE; discovering information about the second UE; communicating the information about the second UE to the serving node; the serving node utilizing computer-implemented policy logic to determine whether to associate the second UE with the user and the IMS session; and if the policy logic determines that the second UE is to be associated, the serving node associating the second UE with the IMS session while retaining the association with the first UE.
-
-
-
-
-
-
-
-
-
搜索结果
37 条记录 (耗时 0.029 秒)
