Abstract: A switch resource receives control plane packets and data packets. The control plane packets indicate how to configure the network in which the switch resource resides. The switch resource includes a classifier. The classifier classifies the control plane packets based on priority and stores the control plane packets into different packet priority queues. The switch resource also includes a flow controller. The forwarding manager selectively forwards the control plane packets stored in the control plane packet priority queues to a control plane packet processing environment depending on a completion status of processing previously forwarded control plane packets by a packet processing thread. The control plane packet processing environment includes a monitor resource that generates one or more interrupts to an operating system to ensure further forwarding of the packets downstream to the packet processing thread for timely processing.

Abstract: Embodiments herein include systems and methods for providing a mechanism for efficient data synchronization of ARP records between two peer nodes of an SMLT system. Such techniques include modifying control information of ARP packets transmitted between peer nodes of the SMLT system to indicate originating SMLT ports. Techniques also include disabling MAC synchronization control messaging across the IST link. These techniques enable real-time synchronization ARP records for MAC learning without needing dedicated control messaging over the IST, thereby providing nodal and SMLT port failover and recovery.

Abstract: A method and apparatus for efficient memory bank utilization in multi-threaded packet processors is presented. A plurality of memory access requests, are received and are buffered by a plurality of memory First In First Out (FIFO) buffers, each of the memory FIFO buffers in communication with a memory controller. The memory access requests are distributed evenly across said memory banks by way of the memory controller. This reduces and/or eliminates memory latency which can occur when sequential memory operations are performed on the same memory bank.

Abstract: A method and apparatus for providing TCAM functionality in a custom integrated circuit (IC) is presented. An incoming key is broken into a predefined number of sub-keys. Each sub-key is sued to address a Random Access Memory (RAM), one RAM for each sub-key. An output of the RAM is collected for each sub-key, each output comprising a Partial Match Vector (PMV). The PMVs are bitwise ANDed to obtain a value which is provided to a priority encoder to obtain an index. The index is used to access a result RAM to return a result value for the key.

Abstract: A method, apparatus and computer program product for maintaining port state tables in a forwarding plane of a network element are presented. The state of a first set of ports associated with a first Forwarding Data Unit (FDU) are periodically determined, the first FDU being one of a plurality of FDUs. The determined state is used to update a first port state table of the port state database associated with the first FDU. The determined state is transmitted to each other FDUs on the network element to enable each of the other FDUs to store the state of the first set of ports in a port state database local to each of the other FDUs. The port state database is used by the forwarding plane to perform fast reroute of packets.

Abstract: A method, apparatus and computer program product for implementing port selection via synchronized port state databases maintained by the forwarding plane of a network element is presented. Each Forwarding Data Unit (FDU) within the forwarding plane of the network element maintains a respective port state database, each port state database containing a synchronized view of the port state for all ports within the network element. A port selection process is performed by each port state database upon request of its associated FDU, to identify an available port in an UP state associated with a Multi-Link Trunk (MLT) to enable fast reroute between ports associated with the MLT in the event of port failure. The process returns an identified port to the FDU for use by the FDU to forward the packet.

Abstract: A method, apparatus and computer program product for providing a fast re-route of a multicast packet within a network element to an available port associated with a multi-link trunk is presented. A packet is received by a Forwarding Data Unit (FDU) in a data plane of a network element and a determination made that the packet is a multicast packet. The packet is forwarded to all egress FDUs having at least one port associated with at least one receiver of the multicast packet. A lookup is performed by each egress FDU in a synchronized local port state database to find a port for each receiver that is in an UP state. The packet is forwarded out the port to a receiver when the port is in the UP state and dropped when the port is in the DOWN state.

Abstract: A method, apparatus and computer program product for providing fast reroute of a packet that may be forwarded on one of a plurality of Equal Cost Multi Path (ECMP) routes through a network is presented. A packet is received by a Forwarding Data Unit (FDU) in a data plane of a network element. The unicast packet is routed at L3, and ECMP is enabled for a next hop for the unicast packet. An ECMP route is selected for forwarding the packet to a destination port. A lookup is performed in a port state table maintained by the FDU to determine an available local port for said ECMP route that is in an UP state for the destination, and if no local port is UP, then a lookup is performed in the port state table to determine an available remote port that is in an UP state for the selected ECMP route.

Abstract: A method, apparatus and computer program product for providing fast reroute of a packet is presented. A unicast packet is received by an FDU in a data plane of a network element and a destination is determined for the packet. A lookup is performed in a port state table maintained by the FDU to determine an available local port that is in an UP state for the destination, and if no local port is UP, then a lookup is performed in the port state table to determine an available remote port that is in an UP state for the destination. If a port in the UP state cannot be determined for the unicast packet, then the packet is dropped.

Abstract: In a communications network, a cluster switch is provided, where the cluster switch has plural individual switches. An abstraction layer is provided in the cluster switch, such that an interface having a set of ports is provided to upper layer logic in the cluster switch. The set of ports includes a collection of ports of the individual switches. Control traffic and data traffic are communicated over virtual tunnels between individual switches of the cluster switch, where each virtual tunnel has an active channel and at least one standby channel.

Abstract: A network element disposed at an edge of a connectivity fault management (CFM) domain includes a switch fabric, a central processor (CP) card, and a line card in communication with the CP card through the switch fabric. The line card includes an Ethernet interface for transmitting and receiving Ethernet CFM frames over a network and circuitry configured to generate new continuity check messages (CCMs) periodically, to process CCMs received on each connection supported by the line card, and to detect a loss of continuity for any of the connections supported by the line card. The line card maintains a list of supported connections. A generate timer and an age counter are associated with each connection in the list. The line card generates a CCM for a given connection when the generate timer expires and detects a loss of continuity for the given connection when its age counter exceeds a threshold.

Abstract: Improved systems and methods for processing data traveling in a network in an efficient manner are provided. In many network implementations input/output ports have one or a small number of bandwidths. These ports sometimes lead to higher bandwidth ports than the source or destination needs. A method and system are provided wherein some of the input and output ports are known to be underutilized. Only a relatively small number of output ports require a complicated merge scheduler that provides configurable data transmission “fairness” between input ports. Accordingly, a method and system are provided wherein preprocessing of input data reduces the cost of the merge circuits required at the outputs.

Abstract: In a communications network, a cluster switch is provided, where the cluster switch has plural individual switches. An abstraction layer is provided in the cluster switch, such that an interface having a set of ports is provided to upper layer logic in the cluster switch. The set of ports includes a collection of ports of the individual switches. Control traffic and data traffic are communicated over virtual tunnels between individual switches of the cluster switch, where each virtual tunnel has an active channel and at least one standby channel.

Abstract: The present invention provides a dynamically scalable edge router, wherein multiple data cards are connected to multiple input/output (I/O) cards via a dynamically configurable cross point. The cross point can be reconfigured to establish different connections between the data cards and the I/O cards, as well as change or establish new connections when additional data cards or I/O cards are added to the edge router. Accordingly, the cross point cooperates with the I/O cards to establish specific connections to the various data cards. The data cards may be connected to each other through a packet fabric, wherein the I/O cards, the cross point, the data cards, and the packet fabric form a significant portion of the forwarding plane of the edge router. The control plane is substantially provided by control cards, which are connected to the data cards through an internal network, which may be a switched network.

Abstract: A network element includes a plurality of Input/Output Cards (IOCs), a plurality of Datapath Service Cards (DSCs); and at least one crosspoint switch card (XPC) configured to be able to selectively interconnect each of the IOCs with each of the DSCs. Enabling full interconnectivity between all the IOCs and DSCs enables greater sparing options within the network element. Additionally, network element is configured to enable the XPCs to be spared, thus eliminating the XPCs as a potential single source of failure in the network element.

Abstract: A computer graphics method of and apparatus for normalizing vector-based terms for a plurality of display pixels associated with a polygon representing a surface of an object being imaged, the vector-based terms being determined from predetermined vectors at vertices of the polygon. The square (.eta.) of the magnitude of a vector associated with each vector-based term is determined for each display pixel from the predetermined vectors at the vertices of the polygon. The quantity 1/.sqroot..eta. is approximated for each vector-based term using a series expansion employing .eta., and each vector based term is multiplied by the corresponding approximation of 1/.sqroot..eta. to produce a normalized vector-based term for each display pixel.

Abstract: Computer graphics apparatus including a host computer, a plurality of pixel-processors and associated respective frame buffers controlled by the host computer to permit simultaneous pixel-processing, a device for displaying a graphics image described by pixel data stored in the frame buffers, and switching circuitry connected for simultaneously receiving pixel data from source pixel-processors and returning the pixel data to selected destination pixel-processors.