A job scheduling strategy for heterogeneous multiprogrammed systems

Mapping and scheduling in multiprogrammed environment has recently attracted more attention of the researchers. Most of the past algorithms use the First Come First Serve (FCFS) strategy, using time-sharing, space-sharing or the combination of both. However, there are limitations when FCFS is implemented in a real system. In order to overcome those drawbacks, we propose a new scheme, called First Input First Output-Best Fit (FIFO-BF), which is used in a mapping policy, Adaptive Multiprogrammed Mapping (AMM). Taking heterogeneity into account, another mapping policy, Heterogeneous Multiprograrnmed Mapping (HMM), is presented. Due to its complex nature, little work has been done in this area.