摘要:
A method according to one embodiment may include receiving, by an integrated circuit of a switch, a plurality of packets, monitoring a rate of the plurality of packets received at the integrated circuit, and adjusting a power consumption of at least a part of the integrated circuit in response to the rate of the plurality of packets received at the integrated circuit. A switch may include a plurality of ports configured to receive a plurality of packets, and an integrated circuit configured to monitor a rate of the plurality of packets received at the switch. The integrated circuit may be configured to adjust a power consumption of at least part of the switch in response to the rate of the plurality of packets received at the switch.
摘要:
A cascadable AGC amplifier in a signal distribution system includes a low noise cascadable amplifier having a through path and a cascadable output. The cascadable amplifier is also configured to provide AGC over a predetermined input power range. The cascadable AGC amplifier can be configured to provide gain or attenuation. When the cascadable AGC amplifier is implemented in a signal distribution system, typically as part of a signal distribution device, an input signal can be gain controlled and supplied to multiple signal paths without distortion due to degradation of signal to noise ratio or distortion due to higher order amplifier products. The distributed signal is not significantly degraded by distortion regardless of the number of cascadable AGC amplifiers connected in series or the position of the cascadable AGC amplifier in the signal distribution system.
摘要:
Method and apparatus are provided for improved connection of devices and lower latency of communications between devices of a massively parallel network. In particular, method and apparatus are provided for cross-bar switches, a multiple protocol interface device, a low latency upper communication protocol layer, addressing and remote direct memory access over a massively parallel network.
摘要:
A switching element including first, second and third ports each comprising a plurality of lines is disclosed. A first memory cell includes a storage element, a first pass gate for selectively coupling a first line of the first port to the storage element, a second pass gate for selectively coupling a first line of the second port to the storage element, and a third pass gate for selectively coupling a first line of the third port to the storage element. A second memory cell includes a storage element, a first gate for selectively coupling a second line of the first port to the storage element, a second pass gate for selectively coupling a second line of the second port to the storage element, and a third pass gate for selectively coupling a second line of the third port to the storage element.
摘要:
A single-stage grooming switch is provided for switching streams of multiplexed traffic, such as SONET STS-48, in both time and space domains. In particular, the switch implements a distributed demultiplexing architecture for switching between any input timeslot to any output timeslot at a reduced layout size. Furthermore, the distributed demultiplexing architecture results in low latencies being associated with reconfiguration of output permutations on the order of nanoseconds.
摘要:
Two or more cross-connect ICs are interconnected. Each IC directly receives some, but not all, of the system inputs, and outputs to some, but not all, outputs. Each cross-connect IC has a switch matrix that has the same number of inputs as the system, and a lesser number of outputs that matches the number of outputs of the IC. Each cross-connect IC provides fanout of its direct inputs to a link to each other cross-connect IC. Thus, each IC receives inputs either directly, or from a fanout on another IC.
摘要:
A transmission lines arrangement comprising a first plurality of transmission lines each transmission line having an effective characteristic impedance. The arrangement further comprises a second plurality of transmission lines, said first plurality of transmission lines being coupled to a plurality of switching elements. The plurality of switching elements are conceived to redirect an input signal from one transmission line of the first plurality of transmission lines to at least one transmission line of the second plurality of transmission lines. The arrangement is characterized in that each of the switching elements of the plurality of switching elements have a relatively high input impedance in comparison with the effective characteristic impedance and a relatively high output impedance in comparison with the effective characteristic impedance. Furthermore, each transmission line of the first plurality of transmission lines is further coupled to an impedance that is substantially equal to the effective characteristic impedance of said transmission line.
摘要:
A single-stage grooming switch is provided for switching streams of multiplexed traffic, such as SONET STS-48, in both time and space domains. In particular, the switch implements a distributed demultiplexing architecture for switching between any input timeslot to any output timeslot at a reduced layout size. Furthermore, the distributed demultiplexing architecture results in low latencies being associated with reconfiguration of output permutations on the order of nanoseconds.
摘要:
A programmable logic device architecture having a matrix of smaller functional units, each of which being a programmable logic array, and a set of fixed conductive lines connected to the functional unit inputs and outputs, the conductive lines forming programmable interconnection matrices. The input pins can be programmably connected to any input of any functional unit, and the outputs of functional units can be programmably connected to any input of any functional unit or any output pin. The interconnection matrices may be a simple array of crossing conductive lines with crossings connected by fuses, EPROM, or EEPROM switches or may have additional series switches to limit the effective impedance so as to speed propagation through these matrices. A fast path through one functional unit bypassing the interconnection matrices is available for a limited number of input and output pins. Multiplexers and other structures may be provided at ends of the fixed conductive lines to enable exhaustive testing of individual functional units, interconnections and logic, and structure may also be provided for on-chip monitoring of state information and providing the information to the external world when certain preselected events happen.
摘要:
In a broadband signal switching matrix network having a cross-point matrix in FET technology whose switching elements, controlled by a holding memory cell, are each formed with a series circuit of a switching transistor and of an input transistor. Matrix output lines thereof are respectively connected to one terminal of the operating voltage source via a pre-charging transistor that is controlled by a pre-charging clock, that side of the series circuit connected opposite from the matrix output line being permanently connected to the other terminal of the operating voltage source (directly or via a transistor controlled by the output signal and individually associated to the matrix output line) in order to avoid sample clock lines that lead to the switching elements.