Abstract: Methods of updating b-tree data structures (e.g., b*tree data structure) using search key insertion and deletion operations proceed from respective known states (e.g., respective canonical forms). These insertion operations include inserting a first search key into the b-tree by reconfiguring (e.g., pre-processing) a plurality of sibling nodes of the b-tree into a predetermined overloaded form having a shape that is independent of a value of the first search key to be inserted therein. An operation is then performed to split the sibling nodes by redistributing the first and other search keys among an expanded plurality of the sibling nodes. These insertion operations use a process that trades off possibly performing additional memory accesses (e.g., to shift search keys (and/or handles or pointers) to the predetermined overloaded form) for the certainty that the same key movements are ultimately performed during operations to split sibling nodes.

Abstract: The invention relates to an EPON bridge apparatus and a forwarding method thereof. In a case of receiving a frame from the network port or the PON port, the apparatus associates the port having the received frame inputted with a source MAC address of the received frame to learn the information in an FDB table, which manages port information for the learned MAC address. Then the apparatus refers to the FDB table to remove an LLID from upstream frame, and then forwards the upstream frame to the network port, while attaching an LLID corresponding to a destination MAC address to the downstream frame to transmit to the PON port. Bridging between ONUs is possible with flooding capability using an anti-LLID. VLAN-LLID translation mode is provided with support for VLAN tag addition/removal at the ONU side. A multicast pruning function is provided for the downstream.

Abstract: A method may include receiving a packet associated with a flow of packets, the packet including a destination address; selecting one of a plurality of memory banks, the selected memory bank being associated with the flow of packets, wherein each of the plurality of memory banks stores the same next-hop information for forwarding the packet to the destination address; accessing, in the selected memory bank, the next-hop information for forwarding the packet to the destination address; and forwarding the packet to the destination address based on the next-hop information.

Abstract: In one embodiment, a system comprises a plurality of nodes that are communicatively coupled to one another. Each of the plurality of nodes, in the absence of any faults, is communicatively coupled to at least a first neighbor node and a first neighbor's neighbor node and a second neighbor node and a second neighbor's neighbor node. When at least a first clique and a second clique exist within the plurality of nodes and a first node included in the first clique successfully receives a synchronization message associated with the second clique from the first neighbor node of the first node and the first neighbor's neighbor node of the first node, the first node does the following. The first node defects to the second clique and synchronizes to the synchronization message. The first node also communicates a join message to at least the second neighbor node of the first node and the second neighbor's neighbor node of the first node.

Abstract: In one embodiment, the present invention includes an apparatus that has multiple buffers, including a first buffer dedicated to a first virtual channel of a first virtual network and a second buffer shared among virtual channels of a second virtual network. The shared buffer may be implemented as a shared adaptive buffer, and the buffers can be controlled using different flow control schemes, such as on a packet and flit basis. Other embodiments are described and claimed.

Abstract: The message switching system (51) comprises at least two inputs (52, 53, 54, 55) and at least one output (56), first arbitration means (62) dedicated to said output (56), and management means (64) designed to determine a relative order OR(i,j) of one input relative to the other, for any pair of separate inputs belonging to the system (51) and having sent requests for the assignment of said output (56), and designed to assign said output (56). Said management means (64) comprise storage means (70) designed to store said relative orders OR(i,j), initialization means (66) designed to initialize said relative orders OR(i,j) such that only one of said inputs takes priority on initialization, and updating means (68) designed to update all of said relative orders when a new request arrives at said first arbitration means (62), or when said output is assigned to one of said inputs.

Abstract: A transmitter forms each subcarrier group of only frequency locations of subcarriers to which at least one pilot signal is allocated, and conducts transmission by allocating a macro-diversity signal into the subcarrier group and allocating a non-macro-diversity signal to other frequencies (outside the subcarrier group). As for the macro-diversity signal, a receiver conducts channel estimation on the basis of the pilot signal in the same subcarrier group as the macro-diversity signal. As for the non-macro-diversity signal outside the subcarrier group, the receiver conducts channel estimation on the basis of the pilot signal, and results of channel estimations of the macro-diversity signal and other non-macro-diversity signals.

Abstract: The invention relates to a device and a method for retrieving/storing electronic data in a system with a plurality of data processing units, which each implement a functionality of a read-write memory. The device comprises a system of a plurality of data processing units, which each comprise a read-write memory for recording/outputting objects comprising electronic data with processor means and storage means, and physical data exchange links between the plurality of data processing units, wherein a virtual network is formed in the system, in which network the plurality of data processing units are provided as a series arrangement with a sequence of a plurality of memories (S0, . . . , Sn; n>2), in which a first memory (S0) is arranged next to a last memory (Sn), and, in which in each of the plurality of memories (S0, . . .

Abstract: A host device connected to a network includes a storage unit configured to store first identification information dynamically assigned to a device connected to the network and second identification information unique to the device, and an updating unit acquiring the first identification information and the second identification information from the device and updating the first identification information stored in the storage unit with the acquired first identification information based on the acquired second identification information.

Abstract: A method assigns addresses to nodes in a wireless network. An address space is defined as an n-dimensional grid. Each grid intersection has coordinates of a corresponding possible node of a wireless network. A number of components of each coordinate is equal to a dimensionality of the grid, and the coordinates form a logical address of the corresponding node. A parent node assigns an unallocated logical address as a child node address to a child node joining the wireless network such that one component of the child node address is one larger than a corresponding component of the parent node.