Enabling technologies for self-aware adaptive systems

Self-aware computer systems will be capable of adapting their behavior and resources thousands of times a second to automatically find the best way to accomplish a given goal despite changing environmental conditions and demands. Such a capability benefits a broad spectrum of computer systems from embedded systems to supercomputers and is particularly useful for meeting power, performance, and resource-metering challenges in mobile computing, cloud computing, multicore computing, adaptive and dynamic compilation environments, and parallel operating systems. Some of the challenges in implementing self-aware systems are a) knowing within the system what the goals of applications are and if they are meeting them, b) deciding what actions to take to help applications meet their goals, and c) developing standard techniques that generalize and can be applied to a broad range of self-aware systems. This work presents our vision for self-aware adaptive systems and proposes enabling technologies to address these three challenges. We describe a framework called Application Heartbeats that provides a general, standardized way for applications to monitor their performance and make that information available to external observers. Then, through a study of a self-optimizing synchronization library called Smartlocks, we demonstrate a powerful technique that systems can use to determine which optimization actions to take. We show that Heartbeats can be applied naturally in the context of reinforcement learning optimization strategies as a reward signal and that, using such a strategy, Smartlocks are able to significantly improve performance of applications on an important emerging class of multicore systems called asymmetric multicores.