Download now Free registration required
Energy optimization in software design is gaining importance due to increases in the recurring energy utility bill as well as the high cost of power provisioning and backup infrastructure, along with growing citizen concerns about the carbon footprint of computing There is a significant need and potential for energy optimization as large parts of the IT infrastructure operate at a low average utilization and the idle power consumption of a computer is typically 50-60% of peak power. Techniques have been proposed to reduce processor energy usage through multi-core processors and help the environment from decaying. Designing energy proportional hardware, and increasing the number of performance and sleep states. The contributions of this paper are twofold. The work addresses the research challenges in enabling generic application layer energy optimization, and describes the tools that are needed for application design-time energy profiling and performance scaling. The goal of the paper is to propose the development of automated fine-grained energy profiling tools as an important research area in addressing the significant potential for application layer energy optimization. These tools should be integrated with compilers and integrated development environments to provide visibility into the energy impact of application design choices. Such tools could lead to a significant reduction in the energy cost of the global IT infrastructures with a relatively small additional effort in design.
- Format: PDF
- Size: 460.6 KB