Abstract: A multi-node communications system is provided with communications protocol using both static (11, 12, 13, 18) (pre-determined) and dynamic (51, 52, 53 . . . ) (run-time determined) consecutive communication slots is used. The system has a number of distributed communication nodes, each node being arranged for communicating frames of data with the other nodes during both the static (11, 12, 13 . . . ) and the dynamic (51, 52, 53 . . . ) communication slots. Each node includes a synchronized time base 5 made up of consecutive timeslots (11, 12, 13 . . . , 51, 52, 53 . . . ). The timebase 5 has substantially the same error tolerance in each node. For static communication (10), a predetermined number of timeslots (20) are utilized for each static communication slot. For dynamic communication a dynamically allocated number of timeslots (60) are utilized for each dynamic communication slot. In this way both static and dynamic media arbitration is provided within a periodically recurring communication pattern.

Abstract: A system comprises a first signal processing logic module and at least one further signal processing logic module. The system further comprises mismatch handler logic module arranged to detect a mismatch between outputs of the first and at least one further signal processing logic module, the mismatch between outputs indicating a failed operation. The mismatch handler logic module further arranged, upon detection of a mismatch between outputs of the first and at least one further signal processing logic module, to analyse internal states of the first and at least one further signal processing logic module, determine whether the cause of the output mismatch is due to a transient fault, and upon determination that the cause of the output mismatch is due to a transient fault, to re-synchronise the first and at least one further signal processing logic module.

Abstract: A communication network for providing media arbitration via a communications protocol using consecutive communication slots in a communication network. The communication network comprises a plurality of communication nodes, each node arranged for communicating frames of data with the other nodes during a dynamic segment comprising dynamic communication slots with respective communication slot numbers.

Abstract: A data processing system may include a first data path and a second data path. A set of components may include a system component and a partner component, each having a communication interface for communicating data. The components are operable in a synchronized mode and a non-synchronized mode with respect to each other. The set may further include a configuration control system connected to the system component and the partner component, for controlling the set to be in a synchronized mode configuration or a non-synchronized mode configuration. The configuration control system may include a first path selector module connecting the communication interface of the system component to the first data path and the second data path and a partner path selector module connecting the communication interface of the partner component to the first data path and the second data path.

Abstract: An arrangement and method for interconnecting fail-uncontrolled processor nodes in a dependable distributed system. A node has a bus guardian with input switches which act in combination with a logic element as an input multiplexer under the control of a control unit. This provides the advantage of transferring the problem of fault containment from the output interface of a potentially faulty processing node to the input interface of fault-free processing nodes. By doing so, problems encountered by spatial proximity faults or functional dependencies within a faulty processing node that may jeopardize fault containment at its output interface are mitigated.

Abstract: The invention concerns a network comprising an interconnecting network and several network nodes that are coupled to said interconnecting network and are designed to adapt their local communication time schedule to the communication time schedule of at least one other network mode, prior to being integrated as active network nodes. A network node to be integrated checks the activity of other network nodes and if no activity is identified, sends out positional messages for other network nodes, said message being fixed by predetermination in its communication time schedule. If a network node cannot be integrated as a reference node, it can only be integrated as an active node if it adapts its local communication time schedule to that of the reference node after receiving positional messages and if a check as to whether its own communication time schedule agrees with the communication time schedules of at least some of the active network nodes proves positive.

Abstract: The invention refers to a method for monitoring a communication media access schedule of a communication controller (5) of a communication system (1) by means of a bus guardian (6). The communication system (1) comprises a communication media (2) and nodes (3) connected to the communication media (2). Each node (3) comprises a communication controller (5) and a bus guardian (6) assigned to the communication controller (5). Messages are transmitted among the nodes (3) across the communication media (2) based on a cyclic time triggered communication media access scheme.

Abstract: A self-routing communication network (100) having: a plurality of nodes (N1-N15); a plurality of star couplers (S1-S4) each having a plurality of inputs and a plurality of outputs; and communication paths coupled between the plurality of star couplers and the plurality of nodes for communication therebetween of frames of information, including at least one redundant communication path (L1-L3), and each of the star couplers sensing which of its inputs first receives a frame and passing only the frame first received. The frames each have a fram-start-sequence (FSS), and the star couplers change the fram-start-sequences before outputting the frame of information e.g. by reducing the size of a frame's fram-start-sequence by a predetermined amount (e.g., 2 bits), whereby interconnection failure may be diagnosed by analyzing the frame-start-sequence.

Abstract: A method and a bit stream decoding unit for bit stream decoding has a bit stream comprising a number of consecutive samples. In order to provide for rapid and, in particular, reliable decoding of the bit stream, a detection window comprising a number of samples is defined and the detection window is positioned at certain positions on the bit stream in order to comprise certain samples with respective sample values. A majority voting is applied to the sample values in the detection window and, in dependence on the result of the majority voting, the bit stream is decoded and respective bit values are generated.

Abstract: A computer node comprising a synchronisation unit for comparing network timing information for a first network with network timing information for a second network and for communicating to the first network the sign of the difference between the first network timing information and the second network timing information to allow the first network to alter its network timing information using the sign of the difference to allow the network timing difference between the first network and the second network to be reduced.

Abstract: An arrangement and method for interconnecting fail-uncontrolled processor nodes in a dependable distributed system. A node has a bus guardian with input switches which act in combination with a logic element as an input multiplexer under the control of a control unit. This provides the advantage of transferring the problem of fault containment from the output interface of a potentially faulty processing node to the input interface of fault-free processing nodes. By doing so, problems encountered by spatial proximity faults or functional dependencies within a faulty processing node that may jeopardize fault containment at its output interface are mitigated.

Abstract: Previously conducted conversations in real-time collaboration messages are persistently stored, either by client or a server, and then are associated with conversational items presented to a user (e.g. contact names, topics, etc.). An icon is provided near each listed item, which when selected, displays to the user summaries or titles of all transcripts to which the selected item pertains or relates. The user may select one or more summaries or titles for which the conversation is to be resumed, causing the system to retrieve the stored transcript and resume appending new conversational entries to it, so that the user recovers conversational context effortlessly and accurately. Enhanced versions of the invention include sharing of transcripts so that all participants receive the context of the conversation, and server-side or client-side implementations.

Abstract: A multi-node communications system is provided with communications protocol using both static (11, 12, 13, 18) (pre-determined) and dynamic (51, 52, 53 . . . ) (run-time determined) consecutive communication slots is used. The system has a number of distributed communication nodes, each node being arranged for communicating frames of data with the other nodes during both the static (11, 12, 13 . . . ) and the dynamic (51, 52, 53 . . . ) communication slots. Each node includes a synchronized time base 5 made up of consecutive timeslots (11, 12, 13 . . . , 51, 52, 53 . . . ). The timebase 5 has substantially the same error tolerance in each node. For static communication (10), a predetermined number of timeslots (20) are utilized for each static communication slot. For dynamic communication a dynamically allocated number of timeslots (60) are utilized for each dynamic communication slot. In this way both static and dynamic media arbitration is provided within a periodically recurring communication pattern.

Abstract: A self-routing communication network (100) having: a plurality of nodes (N1-N15); a plurality of star couplers (S1-S4) each having a plurality of inputs and a plurality of outputs; and communication paths coupled between the plurality of star couplers and the plurality of nodes for communicaton therebetween of frames of information, including at least one redundant communication path (L1-L3), and each of the star couplers sensing which of its inputs first receives a frame and passing only the frame first received. The frames each have a fram-start-sequence (FSS), and the star couplers change the fram-start-sequences before outputting the frame of information e.g. by reducing the size of a frame's fram-start-sequence by a predetermined amount (e.g., 2 bits), whereby interconnection failure may be diagnosed by analysing the frame-start-sequence.

Abstract: The invention concerns a network comprising an interconnecting network and several network nodes that are coupled to said interconnecting network and are designed to adapt their local communication time schedule to the communication time schedule of at least one other network mode, prior to being integrated as active network nodes. A network node to be integrated checks the activity of other network nodes and if no activity is identified, sends out positional messages for other network nodes, said message being fixed by predetermination in its communication time schedule. If a network node cannot be integrated as a reference node, it can only be integrated as an active node if it adapts its local communication time schedule to that of the reference node after receiving positional messages and if a check as to whether its own communication time schedule agrees with the communication time schedules of at least some of the active network nodes proves positive.

Abstract: A communication network (300, 400), and (D1-D3, D11-D13, 500) for use therein, comprising a plurality of nodes (N1-N4, N11-N13), a communication medium for communicating between the plurality of nodes; and communication diode arrangement(s) (D1-D3, D11-D13, 500) for controlledly enabling/disabling access of the node(s) to the communication medium by control external to the node(s). The communication diode arrangement(s) can enforce fail-silence in the time domain within a distributed computer system, showing resilience against spatial proximity faults. The communication diode arrangement(s) may be controllable not only by time but also by commands embedded in frames. This allows isolation of a faulty processing node and/or subnets within an embedded distributed real-time communication system, such as for automotive by-wire applications (FlexRay, TTP), under consideration of spatial proximity faults.

Abstract: The invention refers to one of a number of nodes of a communication system. The nodes are connected to a communication media for transmitting data among the nodes. Said one node comprises a communication controller, across which the node is connected to the communication media, and a bus guardian for controlling access of the communication controller to the communication media. In order to provide a cheap but nevertheless reliable way for monitoring the synchronized clock signal of a node of a communication system and in particular for detecting deviations of the synchronized clock signal it is suggested that a synchronized clock signal from the communication controller is made available to the bus guardian, and that the bus guardian comprises means for monitoring the synchronized clock signal using a bus guardian internal clock signal, which is generated by means of an electronic circuit and which is less accurate than the synchronized clock signal to be monitored.

Abstract: A method and a bit stream decoding unit for bit stream decoding has a bit stream comprising a number of consecutive samples. In order to provide for rapid and, in particular, reliable decoding of the bit stream, a detection window comprising a number of samples is defined and the detection window is positioned at certain positions on the bit stream in order to comprise certain samples with respective sample values. A majority voting is applied to the sample values in the detection window and, in dependence on the result of the majority voting, the bit stream is decoded and respective bit values are generated.

Abstract: Method for transmitting data within a communication system, the communication system comprising a communication media and a number of nodes connected to the communication media, the data being transmitted across the communication media within a communication cycle comprising a number of time slots assigned to one or more nodes of the communication system. In order to provide a possibility for a data transmission within communication cycles, which can satisfy the demands in communication systems for safety critical applications, too, it is suggested, that the communication cycle is initiated by an external event. The external event can be caused by manually setting a bit by a host, by a configurable timer in a controller host interface (CHI) or by an external trigger.

Abstract: The invention refers to a method for monitoring a communication media access schedule of a communication controller (5) of a communication system (1) by means of a bus guardian (6). The communication system (1) comprises a communication media (2) and nodes (3) connected to the communication media (2). Each node (3) comprises a communication controller (5) and a bus guardian (6) assigned to the communication controller (5). Messages are transmitted among the nodes (3) across the communication media (2) based on a cyclic time triggered communication media access scheme.