Patent classifications
H04L47/23
System and method for supporting SMA level abstractions at router ports for GRH to LRH mapping tables in a high performance computing environment
Systems and methods for supporting SMA level abstractions at router ports for GRH to LRH mapping tables in a high performance computing environment. Ingress port mapping of GRH to new LRH can be reduced to minimally include DGID to DLID mapping. By further reducing the complexity by assuming all packets received at a subnet are addressed to a correct subnet (and also taking into account that correct subnet destination can be checked independently of the individual mapping entries), the DGID address can be simplified to a DGUID address, allowing for additional mappings within a same memory size.
Power gains and capacity gains for a relaxed frame erasure rate
A method of controlling frame transmissions includes determining, at a first device, a frame erasure rate for a communication session between the first device and at least a second device. The method also includes comparing the frame erasure rate to an erasure threshold. The method further includes discarding an active speech frame if the frame erasure rate satisfies the erasure threshold.
Fabric-wide bandth management
In one embodiment, a method includes measuring a rate of traffic received at a leaf node, marking a plurality of packets in the flow as protected at the leaf node to match the rate of traffic with a configured rate of traffic for the flow at the leaf node, and dropping a plurality of non-protected packets at the leaf node when a queue at the leaf node is congested. A minimum bandwidth is provided for the flow based on the configured rate of traffic at the leaf node. The leaf node comprises an ingress node or an egress node connected to a fabric. An apparatus is also disclosed herein.
System and method for supporting unique multicast forwarding across multiple subnets in a high performance computing environment
Systems and methods for supporting unique multicast forwarding across multiple connected subnets in a high performance computing environment. In accordance with an embodiment, by enforcing that incoming (i.e., incoming on a router port of a subnet) multicast packets have SGIDs (source global identifiers) that correspond to a restricted set of source subnet numbers when entering the ingress router ports to a local subnet, it is possible to ensure that multicast packets sent from one subnet are never returned to the same subnet through a different set of connected router ports (i.e., avoid looping multicast packets).
SYSTEM AND METHOD FOR SUPPORTING RESOURCE QUOTAS FOR INTRA AND INTER SUBNET MULTICAST MEMBERSHIP IN A HIGH PERFORMANCE COMPUTING ENVIRONMENT
Systems and methods for supporting resource quotas for multicast group creation and membership in a high performance computing environment. In accordance with an embodiment, multicast group membership can present an issue in that inter-subnet partitions can, if left unchecked, runaway with multicast group creation within any given connected subnet. This can starve address map resources at router ports. A quota can be supplied that provides a maximum number of multicast groups any given inter-subnet partition is allowed to create within any given subnet.
Method and apparatus for controlling media delivery in multimedia transport network
A method and an apparatus for controlling media delivery in a multimedia transport network. The method includes transmitting composition information (CI) on media assets within a media package to be transmitted, to a user equipment (UE), packetizing the media assets of the media package to packets, transmitting some of the packets to the UE, receiving a feedback message including information on an available bitrate determined by the UE from the UE while the some of the packets are transmitted, selecting media data, which can be transmitted according to the available bitrate, from the media package by using asset delivery characteristics (ADCs) of the media assets within the media package, and packetizing the selected media data to packets and transmitting the packets to the UE.
Credit mechanisms for packet policing
Provided are systems and methods for packet policing for controlling the rate of a packet flows. In some implementations, an integrated circuit is provided. The integrated circuit may comprise a memory, a counter, and a pipeline. The integrated circuit may be operable to, upon receiving packet information describing a packet, determine, using the pipeline, a drop status for the packet. Determining the drop status may include determining a previous number of credits available, a number of new credits available, a current number of credits available, and a number of credits needed to transmit the packet. The drop status may be determined by comparing the number of credits needed to transmit the packet against the current number of credits available. The integrated circuit may further update the information stored for a policing context in the memory based on the drop status and the number of credits needed to transmit the packet.
System and method for supporting resource quotas for intra and inter subnet multicast membership in a high performance computing environment
Systems and methods for supporting resource quotas for multicast group creation and membership in a high performance computing environment. In accordance with an embodiment, multicast group membership can present an issue in that inter-subnet partitions can, if left unchecked, runaway with multicast group creation within any given connected subnet. This can starve address map resources at router ports. A quota can be supplied that provides a maximum number of multicast groups any given inter-subnet partition is allowed to create within any given subnet.
EXTENDING BERKELEY PACKET FILTER SEMANTICS FOR HARDWARE OFFLOADS
Examples include registering a device driver with an operating system, including registering available hardware offloads. The operating system receives a call to a hardware offload, inserts a binary filter representing the hardware offload into a hardware component and causes the execution of the binary filter by the hardware component when the hardware offload is available, and executes the binary filter in software when the hardware offload is not available.
Data processing device, receiving device, data processing method, and program
The present disclosure relates to a data processing device, a receiving device, a data processing method, and a program capable of suppressing degradation in quality in a case of reproducing data. In one example, a packet selection units selects one service stream from a multiplexed stream obtained by multiplexing a plurality of service streams. An insertion unit inserts null packets with time information, in which predetermined time information has been given to payloads, to spaces that become empty when the packet selection unit generates the one service stream. Thereafter, in the streams which have been demultiplexed after being multiplexed, the timing to output the null packets is adjusted with reference to the time information inserted in-to the null packets.