Architecture exploration for embedded processors

Abstract

In this paper we will discuss the emerging application of “low-power” computing in bio-medical systems, both for ultra-low-energy and low heat producing embedded implantable devices, as well as for low power dissipation but high performance embedded computing platforms which process the large data sets collected from the sensors and implants in real-time. We will discuss the power and real-time performance requirements of the embedded platforms. We will outline the path to developing and analyzing bio-medical benchmark suite and identify the computational and data characteristics of a selected application - both for implantable devices and for external portable data processing platforms. This paper will also include an in-depth look at available simulation and design space exploration tools for different processor micro-architectures which can be used to design the green bio-medical computation platform.