A Simulation Framework for Reconfigurable Processors in Large-Scale Distributed Systems

Abstract

The inclusion of reconfigurable processors in distributed grid systems promises to offer increased performance without compromising flexibility. Consequently, these large-scale distributed grid systems (such as TeraGrid) are utilizing reconfigurable computing resources next to general-purpose processors (GPPs) in their computing nodes. The near-optimal utilization of resources in such distributed systems considerably depends on the resource management and the application task scheduling. Many state-of-the-art simulators for application scheduling simulation in distributed computing systems have been proposed. However, there is no dedicated simulation framework to study the behavior of reconfigurable nodes in grids. The incorporation of reconfigurable nodes in these systems requires to take into account reconfigurable hardware characteristics, such as, area utilization, performance increase, reconfiguration time, and time to transfer configuration bit streams, execution code, and data. Many of these characteristics are not taken into account by traditional simulators. In this paper, we present a simulation framework for reconfigurable processors in large-scale distributed systems. It is capable of modeling reconfigurable nodes, processor configurations, and tasks in a distributed system. Furthermore, as part of the verification of the framework, we implemented a dynamic task scheduling algorithm with support for the scheduling of tasks on reconfigurable nodes. A number of experiments with various simulation parameters were conducted. The results show an expected trend. We also present a thorough discussion of the results.