Abstract: A method of generating a plurality of potential network topologies is provided herein. The method includes receiving parameters that specify a number of servers, a number of switches, and a number of ports in the switches. The parameters are for configuring a network topology. The method also includes generating one or more potential network topologies comprising the set of potential network topologies, for each of a number of dimensions. The number of dimensions is based on the number of switches. The method further includes determining that the set of potential network topologies is structurally feasible. Additionally, the method includes determining an optimal link aggregation (LAG) factor in each dimension of each of the set of potential network topologies.

Abstract: A method of generating a plurality of potential generalized fat tree network (GFT) topologies is provided herein. The method includes receiving parameters that specify a number of servers, a number of switches, and a number of ports in the switches. The parameters are for configuring an GFT topology. The method also includes generating a plurality of potential GFT topologies based on heuristics that favor higher bandwidth and lower latency. Generating the plurality of potential GFT topologies includes generating each level of the potential GFT topologies, recursively, and from a bottom level of a potential GFT topology to a top level.

Abstract: Example methods, apparatus, and articles of manufacture to control generation of memory access requests in processor systems are disclosed. A disclosed example method involves determining at a memory controller whether a memory access queue depth for a memory reference is greater than a first threshold. When the memory access queue depth for the memory reference is greater than the first threshold, an indication is sent to control generation of memory access requests corresponding to the memory reference.

Abstract: Managing a forwarding table in a switch of a computer network includes determining an entry in the forwarding table in a data plane in the switch to replace with a new entry to minimize a future flooding caused by a forwarding table miss of the forwarding table. The managing also includes storing a forwarding information base in the control plane, and the forwarding information base includes entries from the forwarding table.

Abstract: Proactive sending of an IP-to-MAC address binding for a node is performed if a node is determined to be a high fan-in node. If the node is determined to be a high fan-in node, the node periodically sends its IP-to-MAC address binding to nodes in a network. If the node is not determined to be a high fan-in node, the node sends its IP-to-MAC address binding in response to receiving a request for the node's IP-to-MAC address binding.

Abstract: In a method for minimizing pathological flooding of a network using a destination node, a packet is received from a source node at the destination node. The packet is transmitted from the source node to the destination node along a path. A determination is made by a node whether the packet indicates a possibility of pathological flooding. In response to a determination that the packet indicates a possibility of pathological flooding, a dummy packet is forwarded along the path to the source node.

Abstract: A method for routing data on a fat-tree network using network switches includes assigning a customized MAC address to each host device in the network. The customized MAC address has a set of bits for each level in the fat-tree network, each set of bits corresponding to a division of the network in which the host device is located. Each switch applies a MAC subnet mask to a destination MAC address of each received packet and performs at least one hashing function on the masked destination MAC address to determine a forwarding port for the packet.

Abstract: Described is a switch architecture that combines address management with simplified hardware to implement fast route lookup within network switches such as Ethernet switches. A managed address includes a cluster ID which is shared by all endpoints in a cluster, and a member ID which is unique for each node in the cluster. The switch extracts the cluster ID from a target address for a packet and compares it against at least one cluster ID stored in a cluster identification memory. Responsive to a match, the switch generates a port identification for the packet using a fast lookup table. Responsive to no match, the target address is considered an unmanaged address. In one implementation, a slow lookup table can be used to generate a port identification for the unmanaged address.

Abstract: Illustrated is a system for performing Deep Packet Inspection (DPI) that includes a core to prepare a data packet for transmission. Further, the system includes a memory controller to direct the data packet to a DPI core. Additionally, the system includes a Network Interface Card to receive the data packet for transmission after DPI is performed on the data packet by the DPI core. The system includes a Direct Memory Management module to update a descriptor that references a received data packet stored in an Operating System buffer. Moreover, the system includes an Input/Output Memory Management Unit to direct the descriptor to be stored in a DPI memory. Additionally, the system includes an interrupt controller to transmit an interrupt to the DPI core to such that the DPI core retrieves the descriptor from the DPI memory and performs DPI on the data packet stored in the OS buffer.

Abstract: In a method for minimizing pathological flooding of a network using a destination node, a packet is received from a source node at the destination node. The packet is transmitted from the source node to the destination node along a path. A determination is made by a node whether the packet indicates a possibility of pathological flooding. In response to a determination that the packet indicates a possibility of pathological flooding, a dummy packet is forwarded along the path to the source node.

Abstract: A networking packet is to be sent from a first virtual machine of a computing device to a second virtual machine of the computing device. A hardware network interface controller (NIC) of the computing device is to determine whether the networking packet is to be routed from the first virtual machine to the second virtual machine in accordance with a first approach or a second approach, based upon one or more considerations regarding a state of the computing device. The hardware NIC is then to control routing of the networking packet in accordance with the first approach or the second approach.

Abstract: Illustrated is a system for performing Deep Packet Inspection (DPI) that includes a core to prepare a data packet for transmission. Further, the system includes a memory controller to direct the data packet to a DPI core. Additionally, the system includes a Network Interface Card to receive the data packet for transmission after DPI is performed on the data packet by the DPI core. The system includes a Direct Memory Management module to update a descriptor that references a received data packet stored in an Operating System buffer. Moreover, the system includes an Input/Output Memory Management Unit to direct the descriptor to be stored in a DPI memory. Additionally, the system includes an interrupt controller to transmit an interrupt to the DPI core to such that the DPI core retrieves the descriptor from the DPI memory and performs DPI on the data packet stored in the OS buffer.

Abstract: A system and method for implementing a VM to identify a data packet for transmission, the data packet including a QoS the data packet is to receive as compared to another QoS that another data packet is to receive. The system and method further includes a SNIC to pull the data packet from the VM based upon the QoS the data packet is to receive. The system and method may also include a link scheduler module to transmit the data packet based upon the QoS the data packet is to receive. The system and method may also include a receiver to receive a management instruction from a network management device, the management instruction to dictate the QoS the data packet is to receive based upon a SLA.

Abstract: A switch, a system and operational method for packet switching between virtual machines running in a server and a network. The server comprises a switch with swappable, virtual ports. The switch routes packets to and from the various virtual machines resident in the server memory.

Abstract: A process, method, and system that examines a set of services to identify two or more parallel services performed by a common processor. A defined number of data elements are processed to simulate a data flow through the set of services. An element ratio is determined that defines the portion of data elements processed by each of the parallel services.

Abstract: A method for assigning a process to a processor for execution includes determining a value that represents a degree of information sharing between one process and another process, grouping the processes into a process group based on the value, determining if the process group is executable in a memory associated with a processor, and associating the process group, if determined executable, with the memory associated with the processor.

Abstract: A system and method of cache replacement for streaming multimedia is provided. A network system includes a content provider connected to local service providers via an interactive distribution network, such as the Internet. The local service providers facilitate delivery of the content from the content provider to multiple subscribers. For each of the data blocks which make up the multimedia stream requested by a subscriber, the local service provider receiving the request determines whether the request can be serviced locally or whether the requested data blocks must be retrieved from the content provider. In the case where the portion of the requested stream must be retrieved from the content provider, the local service provider attempts to cache the requested blocks in its local cache in addition to streaming the data blocks to the requesting subscriber.