A processing device includes an internal transmitter to receive packets and to forward those packets across a link to an external receiver external to the processing device. The internal transmitter is to receive a portion of a packet and to begin transmitting the portion across the link to the external receiver before the entire overall packet, of which the portion is a part, is received and validated. For a packet determined to have an error, the internal transmitter does not resend the overall packet across the link even if a message is received from the external receiver to resend the overall packet.

At an action implementation layer of a virtual traffic hub, a packet is obtained from a first isolated network. A first action, generated at a decision making layer of the hub based on a first route table of the hub, is performed, resulting in transmission of at least one network packet to a first destination. In response to a second packet, obtained at the action implementation layer from a source outside the first isolated network, a second action is performed, resulting in transmission of at least one packet to a second destination. The second action is generated based on a second route table of the hub.

A slice changing device is disclosed including a circuitry configured to acquire, in a case where a condition for changing a slice is satisfied, a connection destination of a slice after change. The circuitry is further configured to notify a communication device that connects a terminal using a slice and a connection destination of a slice of the acquired connection destination, and to release a resource relating to a slice before change after notification by the notifying means, where a service which is used by the terminal is allocated to a slice, and in a case where a condition in which the slice is changed is satisfied, the service is allocated to a slice after change.

The present invention provides a method and apparatus to route data packets across a torus or higher radix topology that has low latency, increased throughput and traffic distribution to avoid hot spots development. Disclosed is a method of routing packets in a distributed direct interconnect network from a source node to a destination node comprising the steps of: discovering all nodes and associated ports; updating the database to include the nodes and ports in the network topology; calculating the shortest path from every output port on each node to every other node in the topology; segmenting each packet into flits at the output port of the source node; as the flits are segmented, distributing said flits along the shortest path from each output port on the source node to the destination node using wormhole switching, whereby the packets are distributed along alternate maximum disjoint routes in the network topology; and re-assembling and re-ordering the packets at the destination node so that the packets accord with their original order/form.

There is provided a method in a packet based network system for node-to-node transmission of data packets comprising timing packets and non-timing packets, which is directed to a mechanism for providing a delay variation compensation in a timing system or timing sensitive signal transport in a packet based network without participating in the timing signaling of the timing packets or timing sensitive packets themselves. The method comprises associating the data packets with different levels of transmission priority P.sub.r, P.sub.l, assigning highest (or highest available) transmission priority P.sub.r to the timing packets, separately queuing the timing packets in different buffers 401, 402, and providing first opportunity transmission of the timing packets regardless of transmission priority level of non-timing packets waiting to be transmitted. The advantage of the method is that timing-sensitive traffic thereby experiences reduced buffer delay variations.

At an action implementation layer of a virtual traffic hub, a packet is obtained from a first isolated network. A first action, generated at a decision making layer of the hub based on a first route table of the hub, is performed, resulting in transmission of at least one network packet to a first destination. In response to a second packet, obtained at the action implementation layer from a source outside the first isolated network, a second action is performed, resulting in transmission of at least one packet to a second destination. The second action is generated based on a second route table of the hub.

A communication management list generation device 20 generates a communication management list composed of communication management information including time of day information corresponding to a prescribed time of day and communication information indicating a communication process started at a prescribed time of day and not using the same path at the same time. The communication management list generation device is provided with: a determination means 21 for determining, regarding whether information on the communication process can be added to the communication information, each communication management information in descending order of time (early time first) corresponding to the time of day information; and an addition means 22 for adding information on the communication process to the communication information of the communication management information determined at a stage at which it was determined by the determination means 21 that addition is possible.

Provisioning resources into the cloud is a constantly increasing technical challenge as more cloud service providers emerge, each offering disparate computing platforms, services, assets, supported technical components, and other features. A cloud computing provisioning architecture implements a sequence of complex technical analyses that successfully provisions complex cloud computing services. The provisioning architecture disaggregates resources into individual provisioning actions, and also selectively re-aggregates the resources into template blocks which a service provider accepts for native provisioning.

A memory network includes a first local memory group, a second local memory group, and multiple first channels. The first local memory group includes multiple first memory devices that are not directly connected to each other. The second local memory group includes multiple second memory devices that are not directly connected to each other. The first channels are configured to connect the first memory devices to the second memory devices in a one to one relationship.

A method is provided of detecting packet error during a transmission of a flit along a path from a source node through one or more intermediate nodes to a destination node. The method includes identifying a stalled node, from among the source and intermediate nodes, which prevents the transmission of the flit. The method includes generating, by a transmitter of the stalled node, a CRC for the flit and placing the CRC in an IDLE pattern of the flit. The method includes checking, by a receiver of an intermediate node subsequent to the stalled node, the CRC for the flit. The method includes sending, by a transmitter of the intermediate node, an error code to the destination node, and releasing the nodes from the intermediate node to and including the destination node, responsive to a detection, by the intermediate node, of an error in the CRC for the flit.