Cisco Technology, Inc.

Kent H Hoult

Kenneth Harvey Potter, Jr

David Richard Barach

Jeffery B Scott

John Mitten

Michael G Curcio

Kevin T Mortimer

Christopher G Riedle

Guy Fedorkow

John A Joyce

Vijay J Savla

Nagarajan Swaminathan

Michael B Milano

An apparatus includes a carry chain circuit and a detector circuit. The carry chain circuit includes a plurality of stages. Each stage of the plurality of stages includes a plurality of lookup table elements coupled in sequence. The carry chain circuit propagates a clock signal through the plurality of lookup table elements of the plurality of stages. The detector circuit determines, based on a value of the clock signal stored by a final lookup table element of each stage of the plurality of stages, which stage of the plurality stages contains an edge of the clock signal. The detector circuit then outputs a zero if the determined stage is assigned to a first group of the plurality of stages and a one if the determined stage is assigned to a second group of the plurality of stages.

Random number generator

An apparatus includes a ring oscillator, a carry chain circuit, and a detector circuit. The ring oscillator produces a clock signal. The carry chain circuit includes a plurality of stages. Each stage of the plurality of stages includes a plurality of lookup table elements coupled in sequence. The carry chain circuit propagates the clock signal through the plurality of lookup table elements of the plurality of stages. The detector circuit determines, based on a value of the clock signal stored by a final lookup table element of each stage of the plurality of stages, which stage of the plurality stages contains an edge of the clock signal. The detector circuit then outputs a zero if the determined stage is assigned to a first group of the plurality of stages and a one if the determined stage is assigned to a second group of the plurality of stages.

A data path protocol eliminates most of the conventional read transactions required to transfer data between devices interconnected by a split transaction bus, such as a HyperTransport (HPT) bus. To that end, each device is configured to manage its own set of buffer descriptors, unlike previous data path protocols in which only one device managed all the buffer descriptors. As such, neither device has to perform a read transaction to retrieve a 'free' buffer descriptor from the other device. As a result, only write transactions are performed for transferring descriptors across the HPT bus, thereby decreasing the amount of traffic over the bus and eliminating conventional latencies associated with read transactions. In addition, because descriptors are separately managed in each device, the data path protocol also conserves processing bandwidth that is traditionally consumed by managing ownership of the buffer descriptors within a single device.

Hypertransport data path protocol

A buffer-management technique efficiently manages a set of data buffers accessible to first and second devices interconnected by a split transaction bus, such as a Hyper-Transport (HPT) bus. To that end, a buffer manager controls access to a set of 'free' buffer descriptors, each free buffer descriptor referencing a corresponding buffer in the set of data buffers. Advantageously, the buffer manager ensures that the first and second devices are allocated a sufficient number of free buffer descriptors for use in a HPT data path protocol in which the first and second devices have access to respective sets of free buffer descriptors. Because buffer management over the HPT bus is optimized by the buffer manager, the amount of processing bandwidth traditionally consumed managing descriptors can be reduced.

Buffer management technique for a hypertransport data path protocol

To ensure fair access to upstream trunk bandwidth among a plurality of interface units, a plurality of queues is provided in a first unit. One of the queues is associated with the first interface unit. Each of the remaining queues is associated with one of a plurality of second interface units. Local data is received by the first interface unit and forwarded to the associated queue. Data received from a second, subtended interface unit is forwarded to a queue which associated with the second interface unit. Data is then issued from the queues according to a fairness algorithm. A unique identifier is assigned to each interface unit. Associating a queue with an interface unit is done by associating the queue with the respective interface unit's identifier. In each interface unit, local data is tagged with the instant interface unit's identifier, and received data is forwarded to a queue according to the data's tag. For ATM traffic, data can be tagged by inserting the receiving interface unit's identifier into the generic flow control (GFC) field. Alternatively, a table of associations between virtual channel identifiers (VCIs) and interface unit identifiers may be maintained, and the received data is forwarded to a queue according to the interface unit identifier associated with the data's VCI.

Growing community of inventors

Lunenburg, MA, United States of America

Kent H Hoult