Learn More
Two basic approaches are taken when modeling workloads in simulation-based performance evaluation of parallel job scheduling algorithms: (1) a carefully reconstructed trace from a real supercomputer can provide a very realistic job stream, or (2) a exible synthetic model that attempts to capture the behavior of observed workloads can be devised. Both(More)
Current processor allocation techniques for highly parallel systems have thus far been restricted to contiguous allocation strategies for which performance suffers significantly due to the inherent problem of fragmentation. We are investigating processor allocation algorithms which lift the restriction on contiguity of processors in order to address the(More)
We investigate the applicability of k-spanners as shared virtual topologies for intradomain broadcast and multicast on the Internet. A lightweight k-spanner is a spanning subgraph of a network that has both relatively small total edge weight and small multiplicative penalty (at most k) on all point-to-point distances. We deene broadcasting and multicasting(More)
  • 1