Abstract: An acoustic imaging system coupled to a sensing plate to define an imaging surface. The acoustic imaging system includes an array of piezoelectric acoustic transducers coupled to the sensing plate opposite the imaging surface and formed using a thin-film manufacturing process over an application-specific integrated circuit that, in turn, is configured to leverage the array of piezoelectric actuators to generate an image of an object at least partially wetting to the imaging surface.

Abstract: A method and apparatus for routing frames through a fiber channel fabric to make the most efficient possible use of redundant inter-switch links between neighboring switches. The inter-switch links may have different bandwidths. The flow between adjacent switches is monitored to determine various local usage statistics and periodically adjust routing tables to move data flows from congested links to lightly loaded links.

Abstract: A method and apparatus for routing frames through a fibre channel fabric to make the most efficient possible use of redundant inter-switch links between neighboring switches. The inter-switch links may have different bandwidths. The flow between adjacent switches is monitored to determine various local usage statistics and periodically adjust routing tables to move data flows from congested links to lightly loaded links.

Abstract: A method and apparatus for routing frames through a fibre channel fabric to make the most efficient possible use of redundant inter-switch links between neighboring switches. The inter-switch links may have different bandwidths. The flow between adjacent switches is monitored to determine various local usage statistics and periodically adjust routing tables to move data flows from congested links to lightly loaded links.

Abstract: A switch for use in a communications system having multiple local area networks interconnected by multiple switches so as to be configurable into different types of virtual local area networks includes first and second communication ports. The first communication port is connected directly to a local area network and the second communication port interconnects with other system switches. A switch control detects a communication from the local area network and identifies a virtual local area network over which the communication is to be transmitted based upon rules of precedence for different types of virtual local area networks. The communication is appended with a VLAN tag representing the identified virtual local area network so as to form a VLAN communication that is directed to the second communication port for transmission over the identified virtual local area network.

Abstract: A switchable interface for conveniently coupling a network station of the CSMA/CD type to a network having any of a variety of communication media. The invention provides a single interface connector through which connection may be made directly to a twisted-pair medium, using the 10BASE-T protocol, or to a medium of a different type, through an AUI protocol and an appropriate media attachment unit. The interface connector has pin assignments chosen to minimize adverse effects of misconfiguring the station by connecting to a network having a protocol that is different from the one selected in the switchable interface. In one form of the invention, the switchable interface has the ability to determine the protocol being used by the network to which it is connected, and to switch the interface accordingly. Use of the common interface reduces station equipment cost and provides for increased user convenience, since only a single connector is needed to connect to a variety of media types.

Abstract: The invention improves the efficiency of buffer descriptor processing by performing descriptor prefetches, where multiple descriptors are read within the same descriptor bus transaction. The invention reads multiple buffer descriptors each time the bus is accessed. This allows for a smaller FIFO in a cut-through network adapter because it reduces the number of bus transactions needed to transfer data.

Abstract: A network adapter for interfacing between a communication network and a host computer operating as a network device, and a method of operation of these components. The adapter is initially conditioned to transmit at a lower of two possible speeds, such as 10 Mbps instead of 100 Mbps, and then senses at which speed the network is operating, before matching to this sensed speed, either the higher speed or the lower speed. If the sensed speed is the lower speed, the adapter transmits a burst of high-speed signals and senses again for high-speed operation. If the network has not switched to high-speed operation, the adapter is conditioned for low-speed operation. After the adapter is conditioned for low-speed or high-speed operation, the network speed is continually sensed and, if the network is not operating at the selected speed for some preselected period of time, the adapter is returned to its initial low-speed state to begin network speed sensing over again.

Abstract: An arbiter of an I/O controller implements an arbitration process for controlling bi-directional data flow between a local area network and a main memory connected to a system bus having variable latency. A receive state machine of the controller manages inbound data bursts from the network by temporarily storing the data in a receive buffer before transfer to the main memory. Outbound data bursts from the main memory are managed by a transmit state machine of the controller, and are temporarily stored in a transmit buffer prior to transmission onto the network. The arbitration process assigns each of the receive and transmit state machines priority for accessing the system bus depending upon certain status conditions of the controller.

Abstract: A technique for modifying the IEEE 802.3 standard for selecting transmit-to-transmit interpacket gap (IPG) intervals in a Carrier Sense Multiple Access with Collision Detection (CSMA/CD) network, to provide fairness and good channel utilization in the event that a node has captured the network communication channel. If there is a small number of active nodes on the network, one node may capture the channel and the standard backoff algorithm makes it increasingly unlikely for another node to transmit. The new technique provides for use of a longer interpacket gap (IPG) interval to be used by a node that has been initially unsuccessful in contention for the channel, thereby ensuring that the other node may continue to transmit back-to-back data packets without interruption or collision. After a preselected time interval, the nodes reverse their roles by selecting the opposite IPG intervals. The initial receiver now selects the shorter IPG interval and captures the channel for the preselected time interval.

Abstract: Frame processing apparatus, and a related method for its operation, for use in a station connected to a token ring network, to ensure rapid stripping of frames from the network without reference to source addresses in the frames, and in spite of the possible presence of extraneous no-owner frames on the network. The adverse effects of extraneous no-owner frames are avoided by any of three techniques. First, transmitted information frames are preceded by a start strip delimiter frame and followed by an end strip delimiter frame. The process strips all incoming frames (except tokens and ring initialization frames, which are specially handled), but does not count the stripped frames until the start strip delimiter frame is detected. Therefore, extraneous frames preceding the transmitted information frames will be stripped but not counted, and all of the transmitted frames will be stripped. In another approach, an estimated stripping time is used to terminate stripping.

Abstract: A technique for modifying the IEEE 802.3 standard for selecting backoff times in a Carrier Sense Multiple Access with Collision Detection (CSMA/CD) network, in the event that a collision is sensed by a node that has captured the network communication channel. If there is a small number of active nodes on the network, one node may capture the channel and the standard backoff algorithm makes it increasingly unlikely for another node to transmit. The new technique provides for less aggressive, i.e. longer, backoff times before at least the first retransmission attempt made by a node that has captured the channel, and in addition provides for the use of a stopped backoff algorithm. Three specific examples of methods to choose a backoff time and two methods of using a stopped backoff algorithm are disclosed.

Abstract: A technique for modifying the IEEE 802.3 standard for selecting transmit-to-transmit interpacket gap (IPG) intervals in a Carrier Sense Multiple Access with Collision Detection (CSMA/CD) network, in the event that a node has captured the network communication channel. If there is a small number of active nodes on the network, one node may capture the channel and the standard backoff algorithm makes it increasingly unlikely for another node to transmit. The new technique provides for less aggressive, i.e. longer, interpacket gap (IPG) intervals to be used by a node that has captured the channel, thereby increasing the likelihood that another node will gain access.

Abstract: A technique for establishing and maintaining full duplex communication between two stations connected to a token ring network, without physically reconfiguring the station connections or otherwise disturbing the network. Each station continually performs a two node test to ascertain whether there are only two active stations on the network, and updates a two node flag that indicates whether or only two active stations are present. The two node test uses both upstream neighbor and downstream neighbor addresses to update the two node flag, and requires validation of either one of these addresses if the other one of them appears to have changed since the previous observation. A concurrently running full duplex control process uses the two node flag and other conditions to decide whether to initiate or continue transition to full duplex mode.

Abstract: Method and apparatus for automatically switching an Ethernet station interface to choose between two protocols and, possibly, two external connector configurations, to adapt the station automatically to the correct one of two communication media types, such as the twisted-pair medium served by the 10BASE-T protocol, and other media types, served by the attachment unit interface (AUI). The invention continually tests for proper operation in the currently selected protocol, and switches to the other protocol upon failure of a test. If one of two available external connectors is used to connect the station to a network, the invention chooses between the connectors automatically, such that manual switching between them is not required.

Abstract: A technique for controlling access to a bridge connected to at least two networks, such that network collisions are reduced, transmit live-lock conditions are eliminated, and buffer memory requirements are minimized. For at least one target network of the two networks, two dynamic lists are maintained, to keep track of data packets received from the target network and not yet forwarded, and to keep track of data packets stored for forwarding to the target network, but not yet forwarded. The target network uses a half-duplex medium and a CSMA/CD (Carrier Sense Multiple Access with Collision Detection) protocol. The invention operates by dynamically adjusting an inter packet gap (IPG) betweens data packets forwarded to the target network, such that stations on the target network are, under selected conditions, given an extended opportunity to transmit.

Abstract: A plurality of physical addresses are derived from address information stored in an address memory of a bridge or other multi-port communication device, wherein the stored address information does not directly specify all the addresses. In a first embodiment, the stored addressing information specifies a single address value from a first block of preferably consecutive address values. A processor uses the first address value to derive a second address value from a second, different block of preferably consecutive address values, and then assigns both as, e.g., port addresses. In a second embodiment of the invention, the address memory stores address information which specifies a range of preferably consecutive address values, for instance, the first and last address values of the range. A processor fetches these address values from the address memory, identifies all address values within the range, and assigns them as, e.g., port addresses.

Abstract: A duplicate address condition in a computer network may be detected by a station of the type for attachment to a computer communications network, the network capable of maintaining communications among a plurality of stations, the station having means for receiving a frame, the frame having a source address field and a frame control field; means for maintaining an individual address of the station; means for maintaining a source address list of address, the source address list not containing the individual address; means for determining that a contents of the source address field in the frame matches at least one address in the source address list; means for determining that the frame control field of the frame has a predetermined contents; and, means, responsive to the source address of the frame matching at least one address in the source address list and the frame control field of the frame having the predetermined value, for setting an indicator that a duplicate address condition exists.

Abstract: A circuit for incorporation into LAN-compatible devices uses both the link integrity test (LIT) pulses and the end of frame delimiter (EOF) waveform information in received data transmissions to detect polarity errors on the twisted-pair media to which the devices are connected. The circuit integrates this information and a new auto-polarity detection/correction algorithm with the LIT algorithm of the IEEE 10 Base T standard to provide a stable and reliable twisted-pair link operation. Also, once the circuit is in its normal operational stage, it will not declare that a link is faulty unless it fails to receive a LIT pulse or an EOF waveform within a time-out period that is in accord with the IEEE standard. Therefore, the circuit is quite insensitive to line noise.

Abstract: A technique for establishing and maintaining full duplex communication between two stations connected to a token ring network, without physically reconfiguring the station connections or otherwise disturbing the network. In an auto-configuration full duplex mode of operation, each station ascertains whether there are only two active stations on the network and, if so, performs an exchange of frames with the other station to establish full duplex communication. One way to ascertain whether only two stations are active is for each station to transmit periodically a neighbor information frame, which contains the identities of the source station and the source station's nearest upstream neighbor. Once established, full duplex communication can proceed at a greater bandwidth than communication in a token ring network, and without latency delays and distance limitations associated with token ring networks.