Showing papers in "Future Generation Computer Systems in 1996"
••
TL;DR: The design and implementation of a distributed, layered Condor flocking mechanism that represents in each pool idle machines from other pools in the flock and allows job transfers across pool boundaries is described.
343 citations
••
TL;DR: The Metacomputer Adaptive Runtime System (MARS), a framework for minimizing the execution time of distributed applications on a WAN metacomputers, and uses accumulated statistical data on previous execution runs of the same application to derive an improved task-to-process mapping.
87 citations
••
TL;DR: A framework for interfacing PVM, a popular system for parallel programming with Condor, a powerful resource management system is developed, and this combined system is operational, and further developments are made to provide a single coherent environment.
82 citations
••
TL;DR: A new approach to dynamic load balancing of parallel jobs in clusters of workstations is discussed and the implementation into a Unix run-time environment is described.
57 citations
••
TL;DR: An innovative parallel dataflow scheme that requires no global communication except at the pixel level is developed, which combines the benefits of very high memory bandwidth, modularity, and scalability, a result which has not been achieved before.
48 citations
••
6 citations
••
TL;DR: The PIOUS system, a transport independent, scalable I/O framework for parallel and distributed systems is presented, and experiences with its use are reported.
5 citations
••
2 citations
••
IBM1
TL;DR: PVM (Parallel Virtual Machine) is currently a de facto standard in the world of distributed computing based on message passing, but PV Me is a proprietary realization of the PVM programming model which maintains the full compliance with the original programming interface.
••
TL;DR: The Meiko Computing Surface, a multicomputer architecture based on the transputer technology, is enriched with the PVM environment, allowing a user to distribute any application partly on ‘traditional’ PVM nodes, and partly on transputer ones.