International Business Machines Corporation

At&t Intellectual Property I, L.p.

At+t Corp.

Karin Hogstedt

Mark N Wegman

Tova Roth

Douglas Neil Kimelman

Vadakkedathu Thomas Rajan

Ranveer Chandra

Christof Fetzer

Vadekkadathu T Rajan

A topology discovery process is used to discover all of the links in an ad hoc network and thereby ascertain the topology of the entire network. One of the nodes of the network, referred to as the coordinator, receives the topology information which can then be used to, for example, distribute a routing table to each other node of the network. The process has a Diffusion phase in which a k-resilient mesh, k&#x3e;1, is created by propagating a topology request message through the network. Through this process, the nodes obtain information from which they are able to discern their local neighbor information. In a subsequent, Gathering phase, the local neighbor information is reported upstream from a node to its parents in the mesh and thence to the parents' parents and so forth back to the coordinator. The robustness of the Diffusion phase is enhanced by allowing a node to have more than one parent as well as by a number of techniques, including use of a so-called diffusion acknowledgement message. The robustness of the Gathering phase is enhanced by a number of techniques including the use of timeouts that ensure that a node will report its neighbor information upstream even if it never receives neighbor information from one or more downstream neighbors and the use of a panic mode that enhances the probability that a node will get its neighbor information, and its descendents' neighbor information, reported upstream even if that node has lost connectivity with all of its parents.

Adaptive topology discovery in communication networks

A task management system, method and computer program product for determining optimal placement of task components on multiple machines for task execution, particularly for placing program components on multiple computers for distributed processing. First, a communication graph is generated representative of the computer program with each program unit (e.g., an object) represented as a node in the graph. Nodes are connected to other nodes by edges representative of communication between connected nodes. A weight is applied to each edge, the weight being a measure of the level of communication between the connected edges. Terminal nodes representative of the multiple computers are attached to the communication graph. Then, the communication graph is divided into independent nets and a min cut is found for each independent net. The min cut for the communication graph is the combination of the min cuts for all of the independent nets. Finally, program components which may be a single program unit or an aggregate of units are placed on computers according to the communication min cut.

Independent net task identification for efficient partition and distribution

The present invention is a task management system, method and computer program product for determining optimal placement of task components on multiple machines for task execution, particularly for placing program components on multiple computers for distributed processing. First, a communication graph is generated representative of the computer program with each program unit (e.g., an object) represented as a node in the graph. Nodes are connected to other nodes by edges representative of communication between connected nodes. A weight is applied to each edge, the weight being a measure of the level of communication between the connected edges. Terminal nodes representative of ones of the multiple computers are attached to the communication graph. Independent nets may be separated out of the communication graph. For each net, non-terminal nodes adjacent to all of terminal nodes on the net and connected to the net by non-zero weighted edges are identified For each identified non-terminal node, the smallest weight for any terminal edge is identified and the weight of each terminal edge is reduced by the value of that smallest weight, the weight of terminal edges having the smallest weight being reduced to zero. After reducing weights on any terminal edges, The min cut solution is obtained from the reduced graph and program components, which may be a single program unit or an aggregate of units, are placed on computers according to the communication graph min cut solution.

Net zeroing for efficient partition and distribution

A task management system, method and computer program product for determining optimal placement of task components on multiple machines for task execution, particularly for placing program components on multiple computers for distributed processing. First, a communication graph is generated representative of the computer program with each program unit (e.g., an object) represented as a node in the graph. Nodes are connected to other nodes by edges representative of communication between connected nodes. A weight is applied to each edge, the weight being a measure of the level of communication between the connected edges. Terminal nodes representative of the multiple computers are attached to the communication graph. Independent nets may be separated out of the communication graph. A cut is made at each terminal node and the weights of the cut edges are summed. The second heaviest terminal is identified from the cut and edges connected to at least one internal node and not connected to the second heaviest edge are compared against the weight of the second heaviest edge. Any edge found in the comparison to be at least as heavy as the second heaviest terminal node need not be included in the min cut for the communication graph and so, is removed from consideration for the final min cut solution. Finally, program components which may be a single program unit or an aggregate of units are placed on computers according to the communication graph min cut solution.

Machine cut task identification for efficient partition and distribution

A task management system, method and computer program product for determining optimal placement of task components on multiple machines for task execution, particularly for placing program components on multiple computers for distributed processing. First, a communication graph is generated representative of the computer program with each program unit (e.g., an object) represented as a node in the graph. Nodes are connected to other nodes by edges representative of communication between connected nodes. A weight is applied to each edge, the weight being a measure of the level of communication between the connected edges. Terminal nodes representative of the multiple computers are attached to the communication graph. Then, dominant edges are identified within the communication graph. For any non-terminal node, a connected edge is dominant if it is at least as heavy (its weight is greater than or equal to) as the sum of the remaining non-terminal edges and the heaviest of the remaining terminal edges. The min cut for the communication graph need not include any dominant edges and so, dominant edges are removed from consideration for the final min cut solution. Finally, program components which may be a single program unit or an aggregate of units are placed on computers according to the communication graph min cut solution.

Growing community of inventors

Chester, NJ, United States of America

Karin Hogstedt