An Energy Aware Framework for Mobile Computing

Since their inception, energy dissipation has been a critical issue for mobile computing systems. Although a large research investment in low-energy circuit design and hardware level energy management has led to more energy-efficient architectures, even then, there is a growing realization that the contribution to energy conservation should be more rigorously considered at higher levels of the systems, such as operating systems and applications. This dissertation puts forth the claim that energy-aware compilation to improve appli- cation quality both in terms of execution time and energy consumption is essential for a high performance mobile computing embedded system design. Our work is a design paradigm shift from the logic gate being the basic silicon computation unit, to an in- struction running on an embedded processor. Multimedia DSP processors are the most lucrative choice to a mobile computing system design for their optimal performance de- livery in high data throughput at low energy. They use instruction-level parallelism (ILP) in programs, for executing more than one primitive instruction at a time. In this work, we exploit the parallelism slacks, unraveled by the native multimedia DSP compilers. We propose an iterative compilation environment to optimize a given ’C’ source code. The contributions of our framework are the collaboration of an application profile mon- itor (APM) together with an optimization engine in native multimedia DSP Software Development Environments (SDE). We propose to monitor application behavior at all levels (such as static, compilation, scheduling, linking and during execution). These APMs are later used in an optimization engine to speculate optimal code transformation schemes. These schemes are applied successively, across the basic code blocks. We propose two methods for the selection of optimization schemes, a Gradient Mode Iter- ative Compilation (GMIC) and Multicriteria Stochastic Iterative Compilation (MSIC). Both schemes are tested at several multimedia applications obtained from diversified domains such as video transcodecs (MPEG2, H-264L audio transcodecs (G-723, Mp3) and bioinformatics (Glimmer, Fgene), to name a few. Finally, we propose the characterization of application-architecture correlations that sup- port our claim that an ideal performance of a mobile computing system demands a per- fect match between hardware capability and program behavior. We exposed our results for 20 multimedia applications experimented at the TriMedia DSP 1300, the Blackfin DSP ADSP533, and the PI I I-850 embedded processor.