Informatica

Several best effort schemes (next-hop routing) are used to transport the data in the Internet. Some of them do not perform flexible route computations to cope up with the network dynamics. With the recent trends in programmable networks, mobile agent technology seems to support more flexible, adaptable and distributed mechanism for routing. In this paper, we propose a Mobile Agent based Routing (MAR) scheme with the objectives similar to Routing Information Protocol (RIP). A comparative study of both the schemes (MAR and RIP) in terms of communication overheads, convergence time, network bandwidth utilization and average session delays is presented. The results demonstrate that the MAR scheme performs better than RIP. MAR has comparatively less communication overheads and convergence time and also offers more flexibility and adaptability as compared to RIP. In addition, this paper also presents a MAR based network load balancing.

This paper deals with load balancing of parallel algorithms for distributed-memory computers. The parallel versions of BLAS subroutines for matrix-vector product and LU factorization are considered. Two task partitioning algorithms are investigated and speed-ups are calculated. The cases of homogeneous and heterogeneous collections of computers/processors are studied, and special partitioning algorithms for heterogeneous workstation clusters are presented.