Abstract: The present invention provides a flexible, tamper-resistant authentication system, or personal authentication device (PAD), which can support applications in authentication, authorization and accounting. The PAD stores at least one public key associated with a certificate authority (CA) and receives one or more digital certificates, which may be authenticated based on the stored CA public keys. The PAD outputs a service key that, depending on the application, may be used to gain access to a controlled space, obtain permission for taking a certain action, or receive some service. The operation of the PAD and the nature of the service key may be determined by digital certificates that it receives during operation. Using a stored PAD private key that is kept secret, the PAD may perform a variety of security-related tasks, including authenticating itself to a user, signing service keys that it generates, and decrypting content on received digital certificates.

Abstract: A hierarchically-organized linked list structure have a first level comprised of sections of sequentially-ordered segments, and a second level comprised of representatives of each of said sections at the first level. A method for maintaining the hierarchically-organized linked list structure to facilitate segment insertion, retrieval and removal.

Abstract: Transport networks are facing new challenges and opportunities because of the explosive growth of data traffic. Besides having to meet the ever increasing bandwidth demand, transport networks need to provide new functionalities for the support of data applications. Novel enhanced transport systems with inherent packet multiplexing to meet these challenges are described. It uses Internet protocols and technologies to implement these packet transport systems, and thereby re-use much of the existing Internet infrastructure already widely deployed.

Abstract: The present invention relates to a switch for processing data units, such as IP data packets. The switch can be implemented as a router that includes a plurality of input ports, a plurality of output ports and a switch fabric capable of establishing logical pathways to interconnect a certain input port with a certain output port. A characterizing element of the router is its ability to control bandwidth usage on a basis of a logical pathway. This prevents congestion to occur in the switch fabric and also at the level of the output ports. For every active logical pathway the router sets-up a bandwidth control mechanism including at least one queue to hold data units received at an input port. The bandwidth control mechanism performs an accounting operation to determine the average bandwidth usage and if less than a threshold requests for releasing data units in the switch fabric are sent to the switch fabric controller.

Abstract: The present invention relates to a switch for processing data units, such as IF data packets. The switch can be implemented as a router that includes a plurality of input ports, a plurality of output ports and a switch fabric capable of establishing logical pathways to interconnect a certain input port with a certain output port. A characterizing element of the router is its ability to control bandwidth usage on a basis of a logical pathway. This prevents congestion to occur in the switch fabric and also at the level of the output ports. For every active logical pathway the router sets-up a bandwidth control mechanism including at least one queue to hold data units received at an input port. The bandwidth control mechanism performs an accounting operation to determine the average bandwidth usage and if less than a threshold requests for releasing data units in the switch fabric are sent to the switch fabric controller.

Abstract: Flow control of packet based traffic by window is known. Novel modification is described which causes the flow control mechanism to reduce sending rate to some configured number rather than just reducing it by a fixed amount such as one half. The description also shows how the flow control mechanism can be constrained to a maximum rate. The configured numbers will assure that the connection can always run at a minimum rate but not more than a maximum rate. If the guaranteed minimum bandwidth is known and the round trip time between the end points is known or has been calculated, then the sender node needs only reduce its window to that which corresponds to a sending rate equal to that configured number. In this way the protocol will still probe for extra, opportunistic bandwidth but will be able to maintain the minimum rate. In a similar way a window that corresponds to the maximum rate can be calculated and used to constrain the maximum rate of sending.

Abstract: Congestion at a network node can be aggravated by having too many TCP connections. A simple method of avoiding the bad effects of too many TCP connections is to limit the number of connections. Limiting the number of connections is achieved by an admission control which delays or even discards the connection set-up packets. TCP traffic flows are monitored to generate packet loss characteristics and when a certain condition is met, a connection request queue is disabled.

Abstract: Transport networks are facing new challenges and opportunities because of the explosive growth of data traffic. Besides having to meet the ever increasing bandwidth demand, transport networks need to provide new functionalities for the support of data applications. Novel enhanced transport systems with inherent packet multiplexing to meet these challenges are described. It uses Internet protocols and technologies to implement these packet transport systems, and thereby re-use much of the existing Internet infrastructure already widely deployed.

Abstract: The invention provides a method and apparatus for re-ordering data traffic units, such as IP data packets, that may have been miss-ordered during a transmission over a multi-pathway link between a source node and a destination node in a network. The re-ordering apparatus includes a storage medium for intercepting the IP data packets and holding the IP data packets to allow IP data packets delayed on slower pathways to catch-up. The IP data packets in the storage medium are re-ordered based on their sequence number in an attempt to restore the original order of the IP data packets. A maximal time delay variable determines how long a certain IP data packet can be held in the storage medium. The TP data packet is released prior to the maximal time delay variable or as the maximal time delay variable is exceeded.

Abstract: The present invention relates to the field of data communication networks. More specifically, it pertains to devices and methods for the management of bandwidth on links between routing nodes in data networks. The system is particularly useful for reducing congestion caused by high volume traffic streams. The invention provides a novel router that separates traffic on the basis of data type into separate queues buffers. The various queue buffers are associated with virtual output ports on a common physical link. A scheduler regulates the data release from the queue buffers into the physical link to control the bandwidth portion that is made available to each type of data.

Abstract: Multi-media networks will require that a data flow be given certain quality-of-service (QOS) for a network connection but pre-negotiation of this sort is foreign to the current data networking model. The real time traffic flow in the data network requires distinct limits on the tolerance to delay, and the variations in that delay. Interactive voice and video demand that the total delay does not exceed the threshold beyond which human interaction is unacceptably impaired. The present invention allows the network to discover the nature of the service for each traffic flow, classifies it dynamically, and exercises traffic conditioning by means of such techniques as admission control and scheduling when delivering the traffic downstream to support the service appropriately.

Abstract: Multi-media networks will require that a data flow be given certain quality-of-service (QOS) for a network connection but pre-negotiation of this sort is foreign to the current data networking model. The real time traffic flow in the data network requires distinct limits on the tolerance to delay, and the variations in that delay. Interactive voice and video demand that the total delay does not exceed the threshold beyond which human interaction is unacceptably impaired. The present invention allows the network to discover the nature of the service for each traffic flow, classifies it dynamically, and exercises traffic conditioning by means of such techniques as admission control and scheduling when delivering the traffic downstream to support the service appropriately.

Abstract: The interconnection chip of the present invention is a custom chip which is designed to serve as an efficient link between system functional modules, such as arithmetic units, register files and input/output ports. The chip includes a crossbar interconnection, a FIFO or programmable delay for each of its inputs and a pipeline register file for each of its outputs. By using pre-stored control patterns, the chip can configure its crossbar and delays while performing other operations. Therefore, the usual functions of busses and register files can be realized with this single chip. Various embodiments and applications for the chip are disclosed.

Abstract: A systolic array system of inner product step processors is provided in the form of a mesh connected network which rhythmically compute and pass data through the system. Each processor in the system regularly feeds data in and out, each time performing some computation, so that a regular flow of data is kept up in the network. Many basic matrix computations can be readily and efficiently pipelined on systolic array network systems according to these inventions. Such arrays enjoy simple and regular communication paths and the individual processors in the networks are substantially all identical. Similar hexagonally connected processors can, for example, optionally perform matrix multiplication and LU-decomposition of a matrix. Linearly connected systolic arrays are useful for performing a variety of other computations.