A receiving circuit of a communications link comprises: a first data buffer configured to input, under control of a first clock signal, data of a first data stream transmitted by a transmitting circuit, and to generate a credit trigger signal indicating when a data value is read from the first data buffer, wherein data is read from the first data buffer, or from a further data buffer coupled to the output of the first data buffer, under control of a second clock signal; and a credit generation circuit configured to generate, based on the credit trigger signal, a credit signal for transmission to the transmitting circuit under control of the first clock signal, the credit signal indicating that one or more further data values of the first data stream can be transmitted by the transmitting circuit.

A method includes storing entries in a first first-in first-out (FIFO) buffer, each entry of the first FIFO buffer includes a respective segment of plural segments of a first data stream and timing attributes corresponding to the respective segment. The method also includes processing the respective segments in entries output from the first FIFO buffer using a first media processing task of a workflow in a network-based media processing (NBMP) system. The respective segments are processed independently from each other and the first media processing task is performed in a cloud computing environment. The method also includes generating a continuous data stream by concatenating the processed segments according to the timing attributes corresponding to the processed segments.

An apparatus with a data input, a data output, a first buffer, a second buffer, and control logic is disclosed. The control logic is equipped to route data packets that are received through the data input to the first buffer or the second buffer and to flag them as valid or invalid, and to provide data packets that are to be output through the data output from the first buffer or the second buffer, equipped to provide a data packet that is to be output through the data output from the first buffer when the data packet is being written into the first buffer at the time of a start of the readout, to provide it from the second buffer when the data packet is being written into the second buffer at the time of a start of the readout.

Some embodiments provide a method of forwarding data messages to a machine that executes on a host computer and has an associated virtual network interface controller (VNIC) also executing on the host computer. The method retrieves data messages from a queue associated with the VNIC and stores these data messages in a first set of buffer data stores associated with the VNIC. When the first buffer set reaches a threshold congestion level, the method stores data messages subsequently retrieved from the VNIC queue in a second set of buffer data stores associated with the VNIC. In some embodiments, a set of one or more processes executing on the machine retrieves the data messages stored in the buffer sets for processing by these processes or other processes.

A convolutional interleaver included in a time interleaver, which performs convolutional interleaving includes: a first switch that switches a connection destination of an input of the convolutional interleaver to one end of one of a plurality of branches; a FIFO memories provided in some of the plurality of branches except one branch, wherein a number of FIFO memories is different among the plurality of branches; and a second switch that switches a connection destination of an output of the convolutional interleaver to another end of one of the plurality of branches. The first and second switches switch the connection destination when the plurality of cells as many as the codewords per frame have passed, by switching a corresponding branch of the connection destination sequentially and repeatedly among the plurality of branches.

A convolutional interleaver included in a time interleaver, which performs convolutional interleaving includes: a first switch that switches a connection destination of an input of the convolutional interleaver to one end of one of a plurality of branches; a FIFO memories provided in some of the plurality of branches except one branch, wherein a number of FIFO memories is different among the plurality of branches; and a second switch that switches a connection destination of an output of the convolutional interleaver to another end of one of the plurality of branches. The first and second switches switch the connection destination when the plurality of cells as many as the codewords per frame have passed, by switching a corresponding branch of the connection destination sequentially and repeatedly among the plurality of branches.

A method of segmented media data processing can include receiving a first sequence of first segments partitioned from a first data stream of a streaming media, and storing the first segments into a first first-in first-out (FIFO) buffer. In the first FIFO buffer, each first segment and attributes associated with each first segment form an entry of the first FIFO buffer. The attributes associated with each first segment can include a start time of the respective first segment, a duration of the respective first segment, and a length of the respective first segment indicating a number of bytes in the respective first segment. The first segments received from the first FIFO buffer can be processed using a first media processing task of a workflow in a network-based media processing (NBMP) system. The first segments received from the first FIFO buffer can be processed independently from each other.

A switch in a slice-based network can be used to enforce quality of service (“QoS”). Agents can run in the switches, such as in the core of each switch. The switches can sort ingress packets into slice-specific ingress queues in a slice-based pool. The slices can have different QoS prioritizations. A switch-wide policing algorithm can move the slice-specific packets to egress interfaces. Then, one or more user-defined egress policing algorithms can prioritize which packets are sent out into the network first based on slice classifications.

There is provided managing a data flow between a source node and a recipient node. A method comprises storing, at the source node, data frames into a buffer for transmission to the recipient node over a host-to-host protocol connection; measuring, at the source node, a connection quality of the host-to-host protocol connection; adjusting, at the source node, one or more target parameters of the transmission on the basis of the measured connection quality; transmitting, by the source node, data frames from the buffer to the recipient node on the basis of a Last-In, First-Out (LIFO) method and the adjusted one or more target parameters.

The present disclosure generally relates to data transfer device for receiving data from a host device and method therefor. The device comprise a plurality of input ports configured to receive input data comprising of a plurality of bytes, an output port configured to provide an output data byte and a plurality of buffer units, each buffer unit coupled to an input port of the plurality of input ports. Each of the plurality of buffer units receives a portion of the input data, wherein an enable bit is associated with the portion of data and each of the buffer devices provides the received portion of data as an output, if the enable bit indicates that the portion of data is not a garbage data.