摘要:
Systems involving generation of a complex node representation of a PNNI peer group are provided. Use is made of a set of restrictive costs, such as a transition matrix, defining the restrictive costs of paths between pairs of border nodes of the peer group. The complex node representation generation method is based on the group evolution process of the logical group representation of a peer group, and use is also made of the spanning tree representation of a network. Complex node representations generated by the disclosed methods are optimal in that they contain the minimum possible number of exception bypasses.
摘要:
An improved access control system for a memory system in which memory locations can be allocated to virtual output queues dedicated to output ports from the system. The virtual queues can be used to handle data of different priorities. Thresholds are defined for the occupancy of the overall memory and of each virtual queue. The access control system regulates the acceptance of data stored in input adapters by determining whether a back pressure situation exists for the data's target output adapter for the class of traffic to which the data belongs. A single-bit access-controlling back pressure signal is generated as a function of the occupancy level of either the overall memory or of the virtual queue defined for the target output adapter.
摘要:
Traffic congestion control is provided for a network node multiport switch capable of switching data packets of different priorities from input lines, via receive adapters, to output lines via transmit adapters. A spacing function is performed to limit the rate of data transfers through the switch in the absence of high priority data at the input lines and in the absence of a backpressure signal indicating the switch is congested at its output. If high priority data is detected or a backpressure signal has been generated, the data transfer rate is increased to deal with possible congestion.
摘要:
In a solid state memory device, codewords stored in a unit of the memory device are decoded using an error correcting iterative decoding process. An average number of iterations needed for successfully decoding codewords of the unit is determined, and the average number of iterations is monitored. The average number of iterations can be taken as a measure of wear of the subject unit.
摘要:
A method for allocating pending requests for data packet transmission at a number of inputs to a number of outputs of a switching system in successive time slots, including a matching method including the steps of providing a first request information in a first time slot indicating data packets at the inputs requesting transmission to the outputs of the switching system, performing a first step in the first time slot depending on the first request information to obtain a first matching information, providing a last request information in a last time slot successive to the first time slot, performing a last step in the last time slot depending on the last request information and depending on the first matching information to obtain a final matching information, and assigning the pending data packets at the number of inputs to the number of outputs based on the final matching information.
摘要:
The present invention relates to a method for reducing data loss comprising a first computing step for computing an intermediate result for each redundancy information entity of a redundancy set by processing respectively associated data information entities of a given data set on at least two main diagonals of a parity check matrix representing an error correction coding scheme. The method further comprises a second computing step for computing the information content of the respective redundancy information entity dependent on the respective intermediate result.
摘要:
The present invention is related to a method for allocating pending requests for data packet transmission at a number of inputs to a number of outputs of a switching system in successive time slots, wherein according to a matching method the allocation of the pending requests is optimized, wherein the matching method includes a number of steps for incrementally allocating the requests, wherein as a result of each step a matching information is provided, wherein in each time slot a request information is provided, the request information indicating the data packets at the inputs requesting transmission to respective outputs, the matching method comprising the steps of providing a first request information in a first time slot, performing a first step in the first time slot depending on the first request information to obtain a first matching information; providing a last request information in a last time slot successive the first time slot; performing a last step in the last time slot depending on the last request information and depending on the first matching information to obtain a final matching information; and assigning the pending data packets at the number of inputs to the number of outputs in dependence on the final matching information.
摘要:
A flow control method is practiced in a first node in a computer network having one or more upstream nodes, each of which can provide data cells to the first node over a connection. Cells are transmitted over a connection during an established transmission period for that connection and at a data rate not exceeding a peak data rate. To determine whether a buffer is sufficient during a given time period starting at the current time, the potential buffer requirements during that time period are established as a function of the current buffer occupancy and the maximum number of cells which may be received during the given time period. If the potential buffer requirements exceed a predetermined buffer threshold, one or more stop signals is sent to upstream sources to limit the number of cells to be provided to the first node.
摘要:
In a communication switch with input and output queueing, which handles different priority classes of traffic (e.g. video and audio applications with a high priority, and file transfers and e-mail as low priority traffic), the invention provides a timed shut-off mechanism at each input queue. This mechanism is activated when an input queue attempting to transmit low-priority traffic gets a backpressure signal. The mechanism interrupts further attempts to transmit low priority traffic for a predetermined period of T switching cell cycles. Hence, during the shut-off periods, the output queue is only used by the high priority traffic. Therefore, the performance of the high priority traffic is preserved.
摘要:
A method and apparatus for managing write operations in memory. The method includes a memory including units, each of the units including subunits. Data updates are written “out-of-place”, in that new data does not overwrite the memory locations (subunits) where the data is currently stored. The at least one subunit containing the outdated data is marked as invalid. As a result, a subunit can contain up to date data in a valid subunit next to invalid subunits. For reclaiming units for erasure, it is searched amongst the units to identify a unit or units that match a predetermined criterion. The data of valid subunits of such identified unit is rewritten to another unit or units.