Abstract: A virtual desktop can be remoted to a client device by transmitting a video stream using a video coding format, such as H.264, where higher resolution video can be streamed than natively supported by the encoder or decoder. The encoder framebuffer is divided into a plurality of equal size child buffers, each child buffer is assigned an identifier for identifying the child buffer. Padding pixels can be added to the child buffers to make the child buffer size acceptable for the video coding format. The child buffers are encoded using the video coding format and the encoded frames are transmitted to a client. On the decoder side, the encoded child frames are decoded, padding pixels are removed, and the data is used to update corresponding child buffers in a framebuffer on the client display system.

Abstract: Data generated by one or more data producers may be transmitted via multiple communication paths according to a path transmission scheme that divides transmission of different portions of the data amongst different communication paths. Upon a failure of a communication path, transmission of data may continue for those portions of data that are not assigned to the failed communication path. In some embodiments, modifications to the path transmission scheme may be made to change the division of data amongst remaining communication paths in the event of failure.

Abstract: Methods and devices are provided for communicating data in a wireless channel. In one example, a method includes adapting the transmission time interval (TTI) length of transport container for transmitting data in accordance with a criteria. The criteria may include (but is not limited to) a latency requirement of the data, a buffer size associated with the data, a mobility characteristic of a device that will receive the data. The TTI lengths may be manipulated for a variety of reasons, such as for reducing overhead, satisfy quality of service (QoS) requirements, maximize network throughput, etc. In some embodiments, TTIs having different TTI lengths may be carried in a common radio frame. In other embodiments, the wireless channel may partitioned into multiple bands each of which carrying (exclusively or otherwise) TTIs having a certain TTI length.

Abstract: Described is a computer-implemented method for preventing time out during data transfer to an input/output device. Dummy data is generated and transferred to the input/output device at a time during data transfer, such as when a time out event may occur that would end the data transfer. The transfer of dummy data prevents a time out event from occurring.

Abstract: A print output control device operably connected to a printer, is configured to periodically check a first buffer sequentially storing print data received from the printer; accumulate, when the print data is stored in the first buffer, the stored print data in a second buffer; store, when status information on the printer is included in the print data, the status information in a status storage unit; store, when a first function is executed, in a third buffer, the print data accumulated in the second buffer to send back the stored print data as an acquisition value for the first function; and store, when a second function is executed, in a third buffer, the print data accumulated in the second buffer from when the second function is executed to send back the stored print data as an acquisition value for the second function.

Abstract: Module compressing/encoding plural images for recording, or an image recording apparatus or image recording system including the module. At least two first and second image input module types capture an image of frames from a video signal source, and convert into digital image data for output; an image input arbitration module arbitrates to place digital image data provided by the first type before digital image data provided by the second type. The first type image input module is provided with a real-time image. The apparatus or system further includes: a memory module temporarily storing the real-time image by a processing time for the arbitration module to process digital image data provided by the second type of image input module, an image encoding module compressing and encoding the digital image data, and changing a processing speed to perform a process of compression and encoding more in real time.

Abstract: Aspects of the disclosure include a device for processing media samples. The device includes a frame decoder, a buffer, and a placement manager. The frame decoder is configured to receive a data frame from a source outside the device, extract from the data frame a first sample, and determine a first designated playback time of the first sample. The buffer has memory portions, and addresses of the memory portions are associated with a reference time and time increments of a local sampling period of the device. The placement manager is configured to store the first sample in a first memory portion of the buffer having a first address that is associated with a first time increment that most closely corresponds to the first designated playback time of the first sample.

Abstract: One embodiment is associated with dropping or admitting packets to an output queue using occupancy values of virtual destination queues which are updated according to different independent disciplines upon the enqueuing of a packet to an output queue, and the dequeuing of that packet from an output queue. In one embodiment, a virtual destination queue is determined for a packet. A policing decision is made whether to drop the packet or admit the packet to the output queue based on the occupancy level of the determined virtual destination queue, which is updated upon admission. Packets are dequeued in first-in-first-out order from the output queue. For a dequeued one or more packets, one or more of the occupancy values of the virtual destination queues are updated based a scheduling policy that is independent of the particular virtual destination queue(s) associated with the dequeued packets.

Abstract: A first memory device stores (i) a head part of a FIFO queue structured as a linked list (LL) of LL elements arranged in an order in which the LL elements were added to the FIFO queue and (ii) a tail part of the FIFO queue. A second memory device stores a middle part of the FIFO queue, the middle part comprising a LL elements following, in an order, the head part and preceding, in the order, the tail part. A queue controller retrieves LL elements in the head part from the first memory device, moves LL elements in the middle part from the second memory device to the head part in the first memory device prior to the head part becoming empty, and updates LL parameters corresponding to the moved LL elements to indicate storage of the moved LL elements changing from the second memory device to the first memory device.

Abstract: A method for network communication includes receiving in a network element a packet for forwarding to a destination node. The destination node is reachable via two or more candidate ports of the network element that are connected to respective next-hop network elements. Link-level flow-control credit notifications are received in the network element from the next-hop network elements via the respective candidate ports. An egress port is selected for the packet, from among the candidate ports, based at least on the received link-level flow-control credit notifications. The packet is forwarded toward the destination node over the selected egress port.

Abstract: A computing device is provided configured to compute a data function on a function-input value comprising an electronic storage storing a table network configured for the data function and an electronic processor coupled to the storage and configured to compute the data function by applying the table network, wherein the device is configured to obtain the function-input value as an encoded input value, the encoded input value combines the function-input value together with a state-input value encrypted together into a single value, the table network is configured to take as input the encoded input value and produce as output an encoded output value, the encoded output value combines a function-output value together with a state-output value encrypted data function together into a single value, wherein the function-output value equals the result of applying the data function to the function-input value, and the state-output value equals the result of applying a state function to the state-input value.

Abstract: Embodiments provide a virtual queue management system within the cluster of gateways. When a network message arrives at the gateway cluster, it is processed by one of the gateways within the cluster. The gateway that is processing the network message obtains identifying parameters. The identifying parameters can include, but are not limited to, an Internet Protocol (IP) address, a port number, and/or an HTTP command. The gateway creates a virtual queue identifier based on the obtained identifying parameters. The first gateway to receive a network message with a given virtual queue identifier assumes the role of virtual queue manager for that virtual queue. The virtual queue manager gateway informs other gateways within the cluster of the proper sequence for sending network messages to the server such that messages are transmitted to the server in the proper temporal order.

Abstract: A network device and a method for maintaining a count of network events in a network device are provided. A first memory is configured as a first counter, where the first counter is configured to store a least significant bit (LSb) portion of a count value. A second memory is configured as a second counter, where the second counter is configured to store a most significant bit (MSb) portion of the count value. Update circuitry is configured to (i) selectively increment or decrement the LSb portion of the count value stored in the first memory upon occurrence of an event, and (ii) selectively increment or decrement the MSb portion of the count value stored in the second memory upon occurrence of a wrap-around event in the first memory.

Abstract: Systems and methods cross device application discovery and/or control. Cross device application discovery and/or control can provide for simple detection and activation of applications on remote devices. Cross device application discovery and/or control can provide for the control of remote applications in a master and slave configuration. Responsive to an activation message, an application can execute a task in an application, the task being displayed on a target device. Responsive to an activation message, an application can execute a task in an application on a target device, a task context data for the task being streamed to the source device for presentation on a display. Cross device application discovery and/or control can be enabled on a single operating system, or across a plurality of operating systems.

Abstract: A method comprising: receiving, by a first network packet scheduler, from each other network packet scheduler of a plurality of network packet schedulers, a virtual packet for each traffic class of a plurality of traffic classes defining relative transmission priority of network packets; receiving, by the first network packet scheduler, a network packet of a first traffic class of the plurality of traffic classes; transmitting, by the first network packet scheduler, each virtual packet into a virtual connection of a plurality of virtual connections created for each traffic class; scheduling, by the first network packet scheduler, a network packet or a virtual packet as a next packet in a buffer for transmission; determining, by the first network packet scheduler, that the next packet in the buffer is a virtual packet; and discarding, by the first network packet scheduler, the virtual packet, responsive to the determination that the next packet in the buffer is a virtual packet.

Abstract: One embodiment includes a system. The system includes a receiver configured to extract a timestamp from a header of each packet of a data stream received from a network and to de-packetize the data stream to provide a stream of data blocks. The timestamp can correspond to generation of each data block associated with each respective packet of the data stream according to a global timebase. The system also includes a delay controller configured to measure a delay associated with each packet of the data stream based on the timestamp relative to the global timebase and to control converting the data stream to a corresponding analog output signal for transmission based on the measured delay.

Abstract: A method and apparatus for providing multi-view composed frames uses a single display pipe mechanism. The single display pipe includes, in one example, a memory requestor that fetches multi-view data from a frame buffer using a plurality of viewports. The single display pipe may also include a multi-view packer. Each viewport of the single display pipe has access to a frame buffer holding multi-view frame data, and may be configured to have access to different areas of the frame buffer. In this fashion the single display pipe may fetch data representing more than one view of a multi-view frame. Additionally, the multi-view packer combines the data fetched from one or more of the viewports to form a multi-view frame to be supplied for display.

Abstract: One or more computing devices may comprise congestion management circuitry, one or more client file system request buffers, and DESS interface circuitry. The one or more client file system request buffers is/are operable to queue first client file system requests of a first priority level and second client file system requests of a second priority level, where the first priority level is higher priority than the second priority level. The DESS interface circuitry is operable to determine a choking level according to the load on a plurality of DESS resources. Individual load values of the DESS resources are mapped to a composite load value using a first function. The composite load value is mapped to a congestion contribution using a second function. And, the congestion contribution is mapped to a choking level using a third function.

Abstract: Systems and methods relating to direct bit rate adaptation for end-to-end communication via a cellular communications network are disclosed. In one embodiment, a method of operation of a radio access node in a cellular communications network includes obtaining a bit rate associated with a radio bearer between the radio access node and a wireless device. The radio bearer between the radio access node and the wireless device is part of an end-to-end communication path between the wireless device, as a first end-point of the end-to-end communication path, and a second end-point. The method further includes transmitting the bit rate associated with the radio bearer to the wireless device. By transmitting the bit rate associated with the radio bearer to the wireless device, the radio access node controls a bit rate for the end-to-end communication path between the wireless device and the second end-point.

Abstract: An electronic apparatus and a playout delay adjustment method thereof are provided. The electronic apparatus includes a target playout delay estimator configured to estimate an initial target playout delay of a current frame by using network status information of a played packet and estimate a final target playout delay of the current frame by updating the estimated initial target playout delay based on real delay information of an unplayed packet, and an adaptation controller configured to determine an adaptation method for adjusting a playout delay of the current frame based on the final target playout delay.

Abstract: A first request is received from a window checker, requesting to read cell data from a window buffer or write cell data into the window buffer, where the first request contains at least first cell index. A second request is received from a window releaser, requesting to read cell data from the window buffer or write cell data into the window buffer, where the second request contains at least second cell index. A register stores the first cell index, the second cell index, a first lock flag indicating whether the window checker has read cell data but hasn't written cell data back and a second lock flag indicating whether the window releaser has read cell data but hasn't written cell data back. One of the requests is granted according to the first and second cell indices and the first and second lock flags.

Abstract: Methods and devices are provided for communicating data in a wireless channel. In one example, a method includes adapting the transmission time interval (TTI) length of transport container for transmitting data in accordance with a criteria. The criteria may include (but is not limited to) a latency requirement of the data, a buffer size associated with the data, a mobility characteristic of a device that will receive the data. The TTI lengths may be manipulated for a variety of reasons; such as for reducing overhead, satisfy quality of service (QoS) requirements, maximize network throughput, etc. In some embodiments, TTIs having different TTI lengths may be carried in a common radio frame. In other embodiments, the wireless channel may partitioned into multiple bands each of which carrying (exclusively or otherwise) TTIs having a certain TTI length.

Abstract: Various embodiments of the invention provide methods, systems, and computer program products for bridging a third party onto a communication such as a telephone call or Web chat that is being conducted between a first party and a second party. Specifically, a contact, such as a telephone number or webpage address, is linked with the communication being conducted between the first and second parties and a text message is sent to the third party that includes the contact. For instance, in particular embodiments, this contact may be embedded in the text message so that the third party can simply select the contact from the text message to initiate being bridged onto the communication. Accordingly, the third party makes use of the contact to be bridged onto the communication so that the third party can converse with the first party and the second party.

Abstract: The present invention provides a hybrid programmable logic device which includes a programmable field programmable gate array logic fabric and a many-core distributed processing subsystem. The device integrates both a fabric of programmable logic elements and processors in the same device, i.e., the same chip. The programmable logic elements may be sized and arranged such that place and route tools can address the processors and logic elements as a homogenous routing fabric. The programmable logic elements may provide hardware acceleration functions to the processors that can be defined after the device is fabricated. The device may include scheduling circuitry that can schedule the transmission of data on horizontal and vertical connectors in the logic fabric to transmit data between the programmable logic elements and processor in an asynchronous manner.

Abstract: A memory-access completion notification associated with a data unit is received from a thread of a pixel shader. A processing status associated with the data unit is obtained from a window buffer. The processing status is updated to indicate that the data unit has not been processed by any thread. The updated processing status is written into the window buffer.

Abstract: A data transfer method executed by a processor included in a parallel processing device including a first node and a second node, the data transfer method includes transmitting, by a first processor included in the first node, data and information of a size of the data to the second node by remote direct memory access (RDMA); receiving, by a second processor included in the second node, the data and the information of the size of the data from the first node; writing the received data in a memory; and performing prefetch of at least a part of the data, based on information of a position of a memory area of the memory in which the received data has been written and the information of the size of the data.

Abstract: A method of registering an optical network unit (ONU) in an optical line terminal (OLT). The OLT determines a lane to be used by the ONU based on a transmission rate supported by the ONU, combines or distributes data of a dataflow based on a rate of the lane by comparing the rate of the lane to a rate of the dataflow of a media access control (MAC) client interface, and, when the OLT and the ONU are connected through multiple lanes, transmits and receives data between the OLT and the ONU through channel bonding for more effective use of a network.

Abstract: System and method of data routing according to a hierarchical scheduling process. Incoming data traffic is allocated to various queues of a buffer. A scheduling tree has a top level for queues, a bottom level for egress ports, and a plurality of intermediate levels corresponding to different granularities with respect to service categories. Each queue is assigned to a particular node in each intermediate level of the scheduling tree. The scheduling tree traverses through multiple scheduling stages from the bottom to the top level to select a winner node in each level based on a variety of fairness and differentiating variables. As a result, a queue associated with the winner nodes in various levels is selected and data from the queue is read out and sent to the selected egress port for transmission.

Abstract: A game apparatus repeatedly switches between a doze state in which a wireless communication function is restricted, and an awake state. The game apparatus stores unicast data and broadcast data acquired in the awake state, in a normal queue, and transmits the pieces of data to air in acquisition order. On the other hand, in the doze state, the game apparatus stores acquired broadcast data in a preferential transmission queue, and stores acquired unicast data in the normal queue. Thereafter, when the game apparatus becomes the awake state again, the game apparatus transmits the broadcast data stored in the preferential transmission queue in preference to the unicast data stored in the normal queue.

Abstract: A method and an apparatus of transmitting media content in a multimedia system are provided. The method includes determining a transmission unit for transmitting at least one multimedia source related to the media content, generating a data stream including header information and the at least one multimedia source according to the determined transmission unit, and transmitting the data stream through a communication network.

Abstract: Elastic message tracking apparatus and methods are provided that opportunistically improve on the latency of a message processing system and increase the accuracy of a consolidated message stream generated from message streams received from multiple message sources. The elastic message tracking apparatus and methods reduce that latency in situations where the actual latency of all the message streams is lower than a predetermined latency value.

Abstract: In one embodiment, a system includes a processor and logic integrated with and/or executable by the processor. The logic is configured to cause the processor to receive an overlay-encapsulated packet comprising one or more underlay packets. The logic is also configured to cause the processor to decapsulate the one or more underlay packets from the overlay-encapsulated packet. Moreover, the logic is configured to cause the processor to derive a priority for each of the one or more underlay packets based on a priority of the overlay-encapsulated packet, a transport header of the overlay-encapsulated packet, or the priority and the transport header of the overlay-encapsulated packet. In addition, the logic is configured to cause the processor to set the priority of the one or more underlay packets.

Abstract: A computer-implemented method is disclosed to enhance command burst tolerance in a SCSI system. The method starts with receiving an initiator timeout value at a SCSI target, where the SCSI target is communicatively coupled with a SCSI initiator through a set of communication links, and where the initiator timeout value is associated with a timeout duration after which the SCSI initiator times out if receiving no response from the SCSI target after sending a SCSI command. After receiving the initiator timeout value, the SCSI target determines how long a SCSI command has been pending to be processed at the SCSI target. The SCSI target then returns a response for the SCSI command to the SCSI initiator within the timeout duration associated with the initiator timeout value even if the SCSI command is pending to be processed at the SCSI target.

Abstract: A system, such as a System-on-Chip includes an interface component or PLUG which generates transactions over an IP block, such as an interconnect serving one or more clients via virtual channels. The client or clients are mapped onto the virtual channels via client/virtual channel mappings. The virtual channels are provided as a first set of virtual channels in the interface component which cooperate with a second set of virtual channels in the IP block. First and second client/virtual channel mappings for the first set of virtual channels and the second set of virtual channels are provided. The first and second client/virtual channel mappings are separately programmable and mutually decoupled from one another.

Abstract: In some embodiments, an apparatus comprises a schedule module within a switch fabric system. At a first time, the schedule module is configured to access a list of status indicators associated with a group of egress port indicators. The list of status indicators includes a set of status indicators each of which has a value greater than a threshold. The schedule module is configured to randomly select a status indicator from the set of status indicators and configured to reduce the value of the selected status indicator. The schedule module is then configured to send the egress port indicator associated with the selected status indicator such that a data cell is sent from an egress port associated with that egress port indicator. At a second time, when the value of every status indicator from the list of status indicators is not greater than the threshold, the schedule module is configured to increase the value of every status indicator above the threshold.

Abstract: Memory systems may include a plurality of queues, a queue ready indicator suitable for grouping the plurality of queues into a predefined number of queue ranges, each queue range having associated with it a queue range ready signal, and setting a queue range ready signal to ready when each queue in the queue range associated with the queue range ready signal is ready for processing, and a queue process sequencer suitable for determining a queue range ready for processing based on the queue range ready signals, and processing a queue within the queue range determined to be ready for processing.

Abstract: Methods and systems for implementing client isolation in a distributed queue are disclosed. Messages are enqueued in one or more logical queues. Individual messages comprise respective values for an isolation parameter. A respective value for the isolation parameter is assigned to individual queue clients. Messages are sent to the queue clients based at least in part on the values for the isolation parameter. The queue clients are configured to attempt message processing for the messages. Messages having different values for the isolation parameter are isolated among different queue clients.

Abstract: A novel method of handling network traffic for cable service flows in a distributed cable system is presented. Such a cable systems use remote distribution nodes in the fields to handle RF communications with cable modems in a distributed fashion. A packet engine is configured to assign a logical interface to each cable service flow in the cable system. Each logical interface in the packet engine is uniquely identifiable by a compound identifier that includes the identifier of the corresponding service flow and the identifier of the remote distribution node. Each service flow is assigned a class of service (CoS) at the packet engine and guarantee a certain level of quality of service (QoS). In some embodiments, each cable service flow is assigned a CoS priority number. For each possible CoS priority number, the packet engine is configured to provide certain resources at certain quality level, i.e., certain level of QoS.

Abstract: Techniques are disclosed for multi-tenant cloud-based queuing. Certain techniques are disclosed herein that provide for interactions and observability between tenant queues within a multi-tenant cloud-based queuing database. In some embodiments, the queues may be utilized by both users and merchants for both online and point-of-service interactions. Multiple queues for multiple tenants are hosted by a cloud computing system. Each queue may include one more queue entries, each of which includes a ticket value, and may further include a ticket alias. The ticket values and/or ticket aliases may be decoupled from a queue position for the entry. In some embodiments, the queue entries may be swapped within a queue or between queues, and the system may enable searching in or automated actions between queues and/or tenants based in part upon queue conditions.

Abstract: A method for adaptively performing video decoding includes: performing decoding complexity management based upon parameter representing processing capability related to the adaptive complexity video decoder, in order to determine whether to reduce decoding complexity of at least one component of a plurality of components within an adaptive complexity video decoder; and selectively reducing decoding complexity of a portion of components within the adaptive complexity video decoder. An associated adaptive complexity video decoder and an associated adaptive audio/video playback system are also provided. In particular, the adaptive complexity video decoder includes a plurality of components and a decoding complexity manager. When needed, the decoding complexity manager delays audio playback of audio information.

Abstract: Method and systems for adaptive scheduling of packets in a wireless broadband network are disclosed. In one embodiment, the method comprises receiving the packets from applications. The method further comprises analyzing the packets to obtain one or more packet parameters. The method further comprises determining a Dynamic-Packet-Level-Priority (DPLP) value for each of the packets based on the one or more packet parameters. The method further comprises placing each of the packets in priority queues based on the DPLP value. The method further comprises scheduling the packets present in the priority queues based on scheduling parameters and the DPLP value. The method further comprises performing dynamic configuration adaptation for the packet parameters, scheduling parameters and the DPLP value.

Abstract: Provided is an apparatus for controlling a data flow for multiple paths in a receiving node of a communication system. The apparatus includes a receiver configured to receive data for a specific sub-flow among a plurality of sub-flows; a controller configured to calculate an optimal transmission rate of the received data, determine a window reference value for generating the optimal transmission rate, and generate an artificial response message if a window size for the specific sub-flow is greater than or equal to the window reference value; and a transmitter configured to transmit the artificial response message to a transmitting node.

Abstract: A novel Macro-assisted Multi-Connectivity (MC) mobility scheme for UEs traversing clusters of (mmWave) small cells (small-BS or SBS) under the coverage of the same 5G or LTE Macro-cell (macro-BS or MBS) is proposed. It keeps the same Control/User split scheme and C-Plane anchor at MBS, same as in LTE Dual Connectivity (DuCo or DC), yet extending DuCo with a multi-connectivity split bearer user plane. For example, MBS adopts a multi-way packet data convergence protocol (PDCP) bearer split based on routing weighted by channel quality, SBS's resource availability, etc. with or without inter-BS flow control. Utilizing the MC user plane, a macro-assisted make-before-break MC mobility can be enabled.

Abstract: Systems and methods of the present disclosure relate to allocating ports for packets distributed via a computer network. A packet engine on a core of a multicore device intermediary between a client and a server receives a first packet from the client. The first packet includes an outer header of an encapsulation protocol encapsulating a payload with an inner header. The first packet is directed by a packet distributor of the device to the first core selected based on a first tuple of the outer header. A port allocator of the packet engine determines a source port number to cause the packet distributor to identify the first core based on a second tuple of the inner header. The packet engine modifies the inner header of the payload to include the determined source port number. The device forwards the first packet including the modified inner header to the server.

Abstract: An Ethernet switch includes at least two interconnected Ethernet switch modules, with each of the Ethernet switch modules having a number of ingress/egress ports configured to receive or output Ethernet packets from and to end systems and interconnected Ethernet switch modules, and a forwarding function configured to modify a packet header of received Ethernet packets by encoding the identity of the ingress port at which the respective Ethernet packet has been received in identification bits of the packet header.

Abstract: A system and method are disclosed for steering incoming packets to receive queues of virtual machines (VMs). In one embodiment, a hypervisor executed by a processing device receives an incoming packet for a VM, where the incoming packet identifies an incoming flow to the VM. The hypervisor determines that a data store has no entries for the incoming flow and indicates to the VM that the data store has no entries for the incoming flow. The hypervisor receives an outgoing packet from the VM identifying a first receive queue and obtains from the outgoing packet an incoming flow identifier that identifies the incoming flow The hypervisor stores in the data store an entry associating the incoming flow identifier with the first receive queue. The hypervisor receives a second incoming packet for the VM specifying the incoming flow identifier, and the second incoming packet is inserted into the first receive queue in view of the data store.

Abstract: Implementations of the present disclosure involve an apparatus and/or method for an efficient packet queue depth sorting scheme for a ‘longest queue first’ based switch fabric device. In general, the sorting scheme compares a data queue length on an incoming port to a sorted queue of available ports based on longest queue. Based at least on the results of the comparison of the data queue length on the input port, a port designator is inserted into a re-sorted longest queue available port list in the proper position based on the incoming or outgoing port data length. The remaining entries are then sorted around the inserted port designator. Because the comparison and insertion of the port designator can occur in one clock cycle of the switch fabric device, efficiency of the switch is improved.

Abstract: Communication apparatus includes multiple interfaces connected to a packet data network. A memory is coupled to the interfaces and configured as a buffer to contain packets received through ingress interfaces while awaiting transmission to the network via respective egress interfaces. Packet processing logic is configured, upon receipt of a multicast packet through an ingress interface, to identify a number of the egress interfaces through which respective copies of the multicast packet are to be transmitted, to allocate a space in the buffer for storage of a single copy of the multicast packet, to replicate and transmit multiple copies of the stored copy of the multicast packet through the egress interfaces, to maintain a count of the replicated copies that have been transmitted, and when the count reaches the identified number, to release the allocated space in the buffer.

Abstract: An injection descriptor corresponding to a destination node may be stored in memory. A network interface controller (NIC) may determine that one or more messages added to the injection descriptor are to be transmitted to the destination node. The NIC may then lock the injection descriptor so that no additional message can be added to the injection descriptor, and the NIC may load the one or more messages. The NIC may then generate a network packet that includes the one or more messages, and the NIC may transmit the network packet to the destination node.

Abstract: The present application discloses a flow forwarding method, device, and system. The method includes: receiving, by an edge node, an intelligent routing service request packet, and the packet includes a constraint condition required for establishing the intelligent routing service; if the edge node does not find, in a flow table, a corresponding matching flow table entry of characteristic information, sending, by the edge node, a first message to a controller, where the first message includes identification information of the edge node and the characteristic information and the edge node is an ingress edge-node or an egress edge-node that receives the packet; receiving, a first flow table entry sent by the controller, where the first flow table entry is generated according to the first message and meets the constraint condition; and processing, according to the first flow table entry, a packet sent by the user side device.