Hyperreconfigurable architectures as flexible control systems

Abstract

Hyperreconfigurable architectures can change their reconfiguration capabilities dynamically at run-time. For reconfiguration they use two types of reconfiguration steps: i) in hyperreconfiguration steps they change their ability for reconfiguration, ii) in ordinary reconfiguration steps they reconfigure the actual contexts of a computation within the limits that have been set by the preceding hyperreconfiguration step. Hyperreconfigurable architectures have originally been introduced to increase the speed of run-time reconfiguration. In this paper we show that the high flexibility with respect to runtime reconfiguration makes hyperreconfigurable architectures well suited for the control of processes that demand varying amounts of supervision. One advantage of hyperreconfiguration is that the run-time of a control task can be influenced without changing the task itself but only by using different variants of other control tasks that run in parallel. To illustrate the concepts we present the results of simulations with a small hyperreconfigurable architecture where counter and adder control tasks run in parallel.