For future embedded applications, computing infrastructures will increasingly consist of dynamically assembled sets of portable and handheld devices. Key problems include that such devices differ in capabilities and resources, often depending on current operating conditions, and that they have limited energy budgets. The MORPH project is creating methods and techniques for deploying self-modifying (morphable) application services onto cooperating devices, so as to continuously meet applications' Quality of Service (QoS) requirements within existing platform resources and energy budgets.

Two applications drive this research: one being autonomous robots operating in an emergency response scenario, the other involving the use of handheld devices in a collaborative scientific application. The project's technical approach spans the domains of middleware, operating systems, compilers, and hardware. In the middleware domain, we are developing an overlay infrastructure that can dynamically deploy and re-deploy services onto pervasive computing platforms. Systems-level research associates new dynamic quality management methods with middleware-based end user applications. The goal is to ensure that applications meet their current requirements with current platform and energy resources. Using standard Linux-based platforms, the idea of kernel-level support, termed Q-Fabric, is to span all machines and devices that currently cooperate, when such cooperation is established and while it is ongoing. Platform virtualization is a key element in separating Q-Fabric's management and monitoring support from end user operating systems and applications. The compiler methods to be developed address the manner in which application code implements the services needed by end users, including migration support, power-efficient representatios of current application code, and methods to protect and distribute critical application state to reduce its exposure to intrusions. Hardware research serves to further extend the 'optimization space' available to compiler- and system-based methods for service morphing, by providing novel ways of configuring hardware for improved power efficiency and security.