Energy-Aware Synthesis of Embedded Systems on Multiprocessor Platforms

Principal Investigator: Sanjoy K. Baruah
Funding Agency: National Science Foundation
Agency Number: CNS-0309825

Abstract
Due to recent advances in multiprocessor real-time scheduling theory, it is now possible to design and implement significantly complex embedded applicaions upon multiprocessor platforms. One major advantage of multiprocessor implementations over uniprocessor ones is that multiprocessor designs tend to be more energy efficient since the power consumed by a CMOS processor is approximately proportional to the square of the speed or computing capacity at which the processor executes, the total power consumed by an m-processor multiprocessor platform is approximately 1- times the power consumed by a uniprocessor platform of the same computing capacity. However, several factors (including the non-existence of optimal multiprocessor (in contrast to uniprocessor) scheduling algorithms) combine to prevent all the computing capacity of a multiprocessor platform from being guaranteed available for executing the real-time workload; indeed, the precise relationship between multiprocessor implmentation of a given real-time system., and the energy savings realized, has not yet been studied. It is the purpose of this project to thoroughly explore this relationship, and to use the knowledge thus obtained to propose algorithms and design guidelines for the energy-aware design systhesis of embedded real-time systems upon multiprocessor platforms. The proposed project will build upon current and previous research, performed by both investigators, on multiprocessor real-time scheduling and resource-allocation.