A Job Mapping Strategy for Heterogeneous Multiprogrammed Systems

Piyush Maheshwari

School of Computer Science and Engineering
The University of New South Wales
Sydney NSW 2052 Australia
piyush@cse.unsw.edu.au

Abstract

Mapping and scheduling in multiprogrammed environment has re-
cently 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 Multiprogrammed Map-
ping (HMM), is presented. Due to its complex nature, little work has
been done in this area.