Automated Hardware-Independent Scenario Identification

Scenario-based design exploits the time-varying execution behavior of applications by dynamically adapting the system on which they run. This is a particularly interesting design methodology for media applications with soft real-time constraints such as decoders: frames can be classified into scenarios based on their decode complexity, and the system can be configured on a per-scenario basis such that energy consumption is reduced while still meeting the deadlines. At the foundation of scenario-based design lies the ability to identify scenarios, or recurring modes of operation with similar run time characteristics. There are two opposite ends to scenario identification. Some researchers have proposed techniques that, based on domain knowledge, identify hardware-independent scenarios in a media input stream. At the other end, other researchers have proposed techniques that identify hardware-dependent scenarios in a (semi-) automated way. This paper proposes a scenario identification approach that bridges both opposite ends, and finds hardware-independent scenarios in an automated way. It does so by computing execution profiles on a per-frame basis that capture the application's code execution patterns. We find that Edge Vectors (EVs) are more accurate than Basic Block Vectors (BBVs) at capturing the variation in frame-level decode complexity. The complexity of the proposed automated scenario identification is comparable to existing hardware-dependent scenario identification approaches, yet the scenarios can be used across hardware implementations