-
公开(公告)号：US20120151307A1
公开(公告)日：2012-06-14
申请号：US13302688
申请日：2011-11-22
申请人： Francois Abel , Claude Basso , Jean L. Calvignac , Natarajan Vaidhyanathan , Fabrice Verplanken
发明人： Francois Abel , Claude Basso , Jean L. Calvignac , Natarajan Vaidhyanathan , Fabrice Verplanken
IPC分类号： G06F11/00
CPC分类号： H04L1/0079 , H04L1/0061 , H04L1/0072
摘要： Disclosed is a method and system for validating a data packet by a network processor supporting a first network protocol and a second network protocol and utilizing shared hardware. The network processor receives a data packet; identifies a network packet protocol for the data packet; and processes the data packet according to the network packet protocol comprising: updating a first register with a first partial packet length specific to the first network protocol; updating a second register with a second partial packet length specific to the second network protocol; and updating a third register with a first checksum computed from fields independent of the network protocol. The system produces a second checksum utilizing a function that combines values from the first register, the second register, and the third register. The system validates the data packet by comparing the data packet checksum to the second checksum.
摘要翻译： 公开了一种用于通过支持第一网络协议和第二网络协议的网络处理器来验证数据分组并利用共享硬件的方法和系统。 网络处理器接收数据包; 识别数据包的网络包协议; 并根据网络分组协议对数据分组进行处理，包括：以第一网络协议特有的第一部分分组长度更新第一寄存器; 用第二网络协议特有的第二部分分组长度更新第二寄存器; 以及用独立于网络协议的字段计算的具有第一校验和的更新第三寄存器。 该系统利用组合来自第一寄存器，第二寄存器和第三寄存器的值的函数产生第二校验和。 系统通过将数据包校验和与第二个校验和进行比较来验证数据包。
-
42.发明申请DUAL SCHEDULING OF WORK FROM MULTIPLE SOURCES TO MULTIPLE SINKS USING SOURCE AND SINK ATTRIBUTES TO ACHIEVE FAIRNESS AND PROCESSING EFFICIENCY 失效使用源和SINK属性从多个来源将多个工作阶段的工作重新排列成多个，以实现公平和处理效率公开(公告)号：US20110158254A1
公开(公告)日：2011-06-30
申请号：US12650174
申请日：2009-12-30
IPC分类号： H04J3/22
CPC分类号： H04L47/522 , H04L47/6215
摘要： A method and apparatus for assigning work, such as data packets, from a plurality of sources, such as data queues in a network processing device, to a plurality of sinks, such as processor threads in the network processing device. In a given processing period, a source is selected in a manner that maintains fairness in the selection process. A corresponding sink is selected for the selected source based on processing efficiency. If, due to assignment constraints, no sink is available for the selected source, the selected source is retained for selection in the next scheduling period, to maintain fairness. In this case, to optimize efficiency, a most efficient currently available sink is identified and a source for providing work to that sink is selected.
摘要翻译： 一种用于从多个源（例如网络处理设备中的数据队列）将诸如数据分组的工作分配给诸如网络处理设备中的处理器线程的多个接收器的方法和装置。 在给定的处理期间，以选择过程中保持公平的方式选择源。 基于处理效率为所选择的源选择相应的接收器。 如果由于分配限制，所选择的源没有可用的接收器，所选择的源被保留用于在下一个调度周期中进行选择，以保持公平性。 在这种情况下，为了优化效率，识别出最有效的当前可用的接收器，并且选择用于向该接收器提供工作的源。
-
43.发明申请Assigning Work From Multiple Sources to Multiple Sinks Given Assignment Constraints 失效将工作从多个源分配给多个接收器给定分配约束公开(公告)号：US20110158250A1
公开(公告)日：2011-06-30
申请号：US12650120
申请日：2009-12-30
申请人： Claude Basso , Jean L. Calvignac , Chih-Jen Chang , Hubertus Franke , Terry L. Nelms, II , Fabrice Jean Verplanken
发明人： Claude Basso , Jean L. Calvignac , Chih-Jen Chang , Hubertus Franke , Terry L. Nelms, II , Fabrice Jean Verplanken
IPC分类号： H04L12/56
CPC分类号： H04L49/9047
摘要： A method and apparatus for assigning work, such as data packets, from a plurality of sources, such as data queues in a network processing device, to a plurality of sinks, such as processor threads in the network processing device. In a given processing period, sinks that are available to receive work are identified and sources qualified to send work to the available sinks are determined taking into account any assignment constraints. A single source is selected from an overlap of the qualified sources and sources having work available. This selection may be made using a hierarchical source scheduler for processing subsets of supported sources simultaneously in parallel. A sink to which work from the selected source may be assigned is selected from available sinks qualified to receive work from the selected source.
摘要翻译： 一种用于从多个源（例如网络处理设备中的数据队列）将诸如数据分组的工作分配给诸如网络处理设备中的处理器线程的多个接收器的方法和装置。 在给定的处理期间，确定可用于接收工作的接收器，并且考虑到任何分配约束来确定用于将工作发送到可用接收器的资源。 从具有可用工作的合格来源和源的重叠中选择单个来源。 可以使用用于并行同时处理所支持的源的子集的分级源调度器来进行该选择。 从可选择的来源可以分配工作的接收端从有资格从所选源接收工作的可用接收器中选择。
-
44.发明申请TECHNIQUES FOR DYNAMICALLY ASSIGNING JOBS TO PROCESSORS IN A CLUSTER USING LOCAL JOB TABLES 有权使用本地工作表动态地组织处理器的工作的技术公开(公告)号：US20100153966A1
公开(公告)日：2010-06-17
申请号：US12336329
申请日：2008-12-16
IPC分类号： G06F9/46
CPC分类号： G06F9/4856 , G06F9/5066 , G06F9/5088
摘要： A technique for operating a high performance computing cluster includes monitoring workloads of multiple processors. The high performance computing cluster includes multiple nodes that each include two or more of the multiple processors. Workload information for the multiple processors is periodically updated in respective local job tables maintained in each of the multiple nodes. Based on the workload information in the respective local job tables, one or more threads are periodically moved to a different one of the multiple processors.
摘要翻译： 用于操作高性能计算集群的技术包括监视多个处理器的工作负载。 高性能计算集群包括多个节点，每个节点包括多个处理器中的两个或多个。 多个处理器的工作量信息在维护在多个节点中的每个节点的相应本地作业表中周期性地更新。 基于各个本地作业表中的工作负载信息，将一个或多个线程周期性地移动到多个处理器中的不同的一个。
-
45.发明申请TECHNIQUES FOR DYNAMICALLY ASSIGNING JOBS TO PROCESSORS IN A CLUSTER BASED ON BROADCAST INFORMATION 有权基于广播信息的群集中的处理者动态地组织作业的技术公开(公告)号：US20100153542A1
公开(公告)日：2010-06-17
申请号：US12336312
申请日：2008-12-16
IPC分类号： G06F15/173
CPC分类号： G06F9/5088
摘要： A technique for operating a high performance computing cluster (HPC) having multiple nodes (each of which include multiple processors) includes periodically broadcasting information, related to processor utilization and network utilization at each of the multiple nodes, from each of the multiple nodes to remaining ones of the multiple nodes. Respective local job tables maintained in each of the multiple nodes are updated based on the broadcast information. One or more threads are then moved from one or more of the multiple processors to a different one of the multiple processors (based on the broadcast information in the respective local job tables).
摘要翻译： 用于操作具有多个节点（每个包括多个处理器）的高性能计算群集（HPC）的技术包括：从多个节点中的每个节点到多个节点周期性地广播与多个节点中的每个节点处的处理器利用和网络利用相关的信息 多个节点中的一个。 基于广播信息来更新维护在多个节点中的每个节点的相应的本地作业表。 然后，一个或多个线程从多个处理器中的一个或多个移动到多个处理器中的不同处理器（基于相应的本地作业表中的广播信息）。
-
公开(公告)号：US07715428B2
公开(公告)日：2010-05-11
申请号：US11669419
申请日：2007-01-31
申请人： Claude Basso , Jean L. Calvignac , Chih-jen Chang , Philippe Damon , Herman D. Dierks, Jr. , Christoph Raisch , Jan-Bernd Themann , Natarajan Vaidhyanathan , Fabrice J. Verplanken , Colin B. Verrilli
发明人： Claude Basso , Jean L. Calvignac , Chih-jen Chang , Philippe Damon , Herman D. Dierks, Jr. , Christoph Raisch , Jan-Bernd Themann , Natarajan Vaidhyanathan , Fabrice J. Verplanken , Colin B. Verrilli
CPC分类号： H04L47/50
摘要： Mechanisms for processing of communications between data processing devices are provided. With the mechanisms of the illustrative embodiments, a set of techniques that enables sustaining media speed by distributing transmit and receive-side processing over multiple processing cores is provided. In addition, these techniques also enable designing multi-threaded network interface controller (NIC) hardware that efficiently hides the latency of direct memory access (DMA) operations associated with data packet transfers over an input/output (I/O) bus. Multiple processing cores may operate concurrently using separate instances of a communication protocol stack and device drivers to process data packets for transmission with separate hardware implemented send queue managers in a network adapter processing these data packets for transmission. Multiple hardware receive packet processors in the network adapter may be used, along with a flow classification engine, to route received data packets to appropriate receive queues and processing cores for processing.
摘要翻译： 提供了用于处理数据处理设备之间的通信的机制。 利用说明性实施例的机制，提供了一组通过在多个处理核上分发发送和接收侧处理来维持媒体速度的技术。 此外，这些技术还可以设计出多线程网络接口控制器（NIC）硬件，可有效地隐藏通过输入/输出（I / O）总线传输数据分组的直接存储器访问（DMA）操作的延迟。 多个处理核心可以使用通信协议栈和设备驱动程序的单独实例同时运行，以处理用于传输的数据分组，其中单独的硬件实现了处理这些数据分组以进行传输的网络适配器中的发送队列管理器。 可以使用网络适配器中的多个硬件接收分组处理器以及流分类引擎将接收到的数据分组路由到适当的接收队列和处理核心进行处理。
-
公开(公告)号：US07466715B2
公开(公告)日：2008-12-16
申请号：US11091245
申请日：2005-03-28
申请人： Claude Basso , Jean L. Calvignac , Chih-jen Chang , Philippe Damon , Joseph F. Logan , Fabrice J. Verplanken
发明人： Claude Basso , Jean L. Calvignac , Chih-jen Chang , Philippe Damon , Joseph F. Logan , Fabrice J. Verplanken
IPC分类号： H04L12/28
CPC分类号： H04L12/5601 , H04L49/90 , H04L2012/5642 , H04L2012/5652 , H04L2012/5658 , H04L2012/5681
摘要： A communication network used to link information handling systems together utilizes a switching network to transmit data among senders and receivers. Each individual packet of data is described and controlled by an FCB. The bandwidth associated with the storing and distribution of data is optimized by chaining the data packets in different types of queues, or operating without chaining outside a queue. When a frame is in an output queue, the third word contains an RFCBA for egress of the frame to a line port, and an MCID for ingress from an output queue to a switch port. The RFCBA and the MCID have multicast capabilities. The format does not require a third word when a frame is in an input queue.
摘要翻译： 用于将信息处理系统链接在一起的通信网络利用交换网络在发送者和接收者之间传送数据。 每个单独的数据包由FCB描述和控制。 与存储和分发数据相关联的带宽通过将数据分组链接在不同类型的队列中进行优化，或者在不在队列外链接的情况下运行。 当帧位于输出队列中时，第三个字包含用于将帧从线路端口排出的RFCBA，以及用于从输出队列进入交换机端口的MCID。 RFCBA和MCID具有多播功能。 当帧在输入队列中时，格式不需要第三个字。
-
公开(公告)号：US07333493B2
公开(公告)日：2008-02-19
申请号：US10850296
申请日：2004-05-20
IPC分类号： H04L12/28
CPC分类号： H04L69/166 , H04L29/06 , H04L69/16
摘要： A method for sequencing delivery of information packets from a router having several processing elements to a receiving processing installation, wherein delivery of the packets must be completed in the order the packets arrive at the router. A linked list of packets is formed in the order they are received at the router, and each packet fragmented into successive fragments. Each fragment is processed at the router. The last fragment of each packet in each linked list is labeled with the sequence in which the packet was received, and enqueued in the order labeled for each last fragment on each linked list. Each fragment of each packet is delivered as processed, except the last fragment of each packet on its linked list to the receiving processor installation, and thereafter, transmitting the final fragment of each packet after processing only if that fragment is at the head of the queue.
摘要翻译： 一种用于将信息分组从具有多个处理元件的路由器传送到接收处理设备的方法，其中分组的传送必须按分组到达路由器的顺序完成。 分组的链表以它们在路由器处接收的顺序形成，并且每个分组被分段成连续的片段。 每个片段在路由器处理。 每个链表中每个数据包的最后一个片段都标有接收数据包的顺序，并按照每个链表上每个最后一个片段标记的顺序排队。 每个分组的每个片段被处理，除了其链接列表上的每个分组的最后片段到接收处理器安装，然后在处理之后仅在该片段位于队列的头部时发送每个分组的最后片段 。
-
公开(公告)号：US07149749B2
公开(公告)日：2006-12-12
申请号：US10453245
申请日：2003-06-03
申请人： Claude Basso , Jean L. Calvignac , Gordon T. Davis , Marco Heddes , Piyush C. Patel , Steven R. Perrin , Grayson W. Randall , Sonia K. Rovner
发明人： Claude Basso , Jean L. Calvignac , Gordon T. Davis , Marco Heddes , Piyush C. Patel , Steven R. Perrin , Grayson W. Randall , Sonia K. Rovner
IPC分类号： G06F17/30
CPC分类号： G06F17/30625 , Y10S707/99936 , Y10S707/99942 , Y10S707/99943
摘要： A technique is provided to either insert or delete a leaf in a Patricia tree having a direct table and a plurality of PSCB's which decode portions of the pattern of a leaf in the tree without shutting down the functioning of the tree. A leaf having a pattern is identified as either a leaf to be inserted or deleted. Using the pattern, the tree is walked once to identify the location of the leaf to be deleted or the location where the leaf is to be inserted. If it is a delete operation, the leaf to be deleted is identified and deleted, and any relevant PSCB modified, if necessary. If it is an insert operation, the tree is walked a second time to insert the leaf and reform or create any PSCB in the chain that needs to be reformed or created. The technique also is applicable to inserting or deleting a prefix of a prefix.
摘要翻译： 提供了一种技术来插入或删除具有直接表的Patricia树中的叶子，以及多个PSCB，其解码树中的叶子的图案的部分，而不关闭树的功能。 具有图案的叶被识别为要插入或删除的叶。 使用图案，树一次走一次，以确定要删除的叶的位置或叶被插入的位置。 如果是删除操作，则要删除的叶被识别和删除，并且必要时修改任何相关的PSCB。 如果是插入操作，则树第二次移动以插入叶，并在需要重新创建或创建的链中重新构建或创建任何PSCB。 该技术也适用于插入或删除前缀的前缀。
-
公开(公告)号：US06963868B2
公开(公告)日：2005-11-08
申请号：US10448528
申请日：2003-05-30
申请人： Claude Basso , Jean L. Calvignac , Gordon T. Davis , Marco Heddes , Piyush C. Patel , Steven R. Perrin , Grayson W. Randall
发明人： Claude Basso , Jean L. Calvignac , Gordon T. Davis , Marco Heddes , Piyush C. Patel , Steven R. Perrin , Grayson W. Randall
CPC分类号： H04L45/00 , H04L45/56 , H04L45/7457 , Y10S707/99933
摘要： A tree structure and method to organize routing information for processing messages within a network, each message being associated with a search key of “n” bits. The processing determines where to send the message next. The structure has a direct table (DT) of 2x entries for decoding the first “x” bits of the search key, and one or more pattern search control blocks (PSCB's), each having 2m entries for decoding subsequent groups of “m” bits. Each PSCB entry and DT entry includes a pointer to data associated with a specific route, if at this point a specific routing table entry is a potential match to the search key or a pointer to a subsequent PSCB if the end of a search trail is not identified. Each PSCB entry DT entry also indicates that the search has been resolved to the end of the search trail.
摘要翻译： 一种用于组织用于处理网络内的消息的路由信息的树结构和方法，每个消息与“n”比特的搜索关键字相关联。 该处理确定接下来发送消息的位置。 该结构具有用于对搜索关键字的第一个“x”比特进行解码的2个“<”条目的直接表（DT），以及一个或多个模式搜索控制块（PSCB），每个具有2个
-
-
-
-
-
-
-
-
-
搜索结果
253 条记录 (耗时 0.04 秒)
