Guided self-scheduling: A practical scheduling scheme for parallel supercomputers
IEEE Transactions on Computers
Factoring: a method for scheduling parallel loops
Communications of the ACM
A Case for NOW (Networks of Workstations)
IEEE Micro
Trapezoid Self-Scheduling: A Practical Scheduling Scheme for Parallel Compilers
IEEE Transactions on Parallel and Distributed Systems
Hi-index | 0.00 |
Heterogeneous Networks of Workstations (NOWs) offer a cost-effective solution for parallel processing. The completion time of a parallel task over NOWs depends on how the task is divided and distributed among the heterogeneous workstations. In this paper we present a distribution scheme which attempts to minimize the task's completion time over a heterogeneous NOWs. The scheme is based on the idea of distributing fixed time slices of work as opposed to fixed work slices. Our simulations show that the proposed scheme outperforms both fixed and variable work distribution schemes commonly in use. The scheme is very simple and requires no active monitoring of the network. Furthermore it is adaptive and copes very well with the changes in background loads on workstations and network interference.