Analyzing and understanding energy consumption of applications is an important task which allows researchers to develop novel strategies for optimizing and conserving energy. A typical methodology is to reduce the complexity of real systems and applications by developing a simplified performance model from observed behavior. In the literature, many of these models are known; however, inherent to any simplification is that some measured data cannot be explained well. While analyzing a models accuracy, it is highly important to identify the properties of such prediction errors. Such knowledge can then be used to improve the model or to optimize the benchmarks used for training the model parameters. For such a benchmark suite, it is important that the benchmarks cover all the aspects of system behavior to avoid overfitting of the model for certain scenarios. It is not trivial to identify the overlap between the benchmarks and answer the question if a benchmark causes different hardware behavior. Inspection of all the available hardware and software counters by humans is a tedious task given the large amount of real-time data they produce. In this paper, we utilize statistical techniques to foster understand and investigate hardware counters as potential indicators of energy behavior. We capture hardware and software counters including power with a fixed frequency and analyze the resulting timelines of these measurements. The concepts introduced can be applied to any set of measurements in order to compare them to another set of measurements. We demonstrate how these techniques can aid identifying interesting behavior and significantly reducing the number of features that must be inspected. Next, we propose counters that can potentially be used for building linear models for predicting with a relative accuracy of 3%. Finally, we validate the completeness of a benchmark suite, from the point of view of using the available architectural components, for generating accurate models.

@article{UHASMWRTPC17,
	author	 = {Julian Kunkel and Manuel F. Dolz},
	title	 = {{Understanding Hardware and Software Metrics with respect to Power Consumption}},
	year	 = {2017},
	month	 = {11},
	editor	 = {Ishfaq Ahmad},
	publisher	 = {Elsevier},
	journal	 = {Sustainable Computing: Informatics and Systems},
	series	 = {Sustainable Computing},
	issn	 = {2210-5379},
	doi	 = {https://doi.org/10.1016/j.suscom.2017.10.016},
	abstract	 = {Analyzing and understanding energy consumption of applications is an important task which allows researchers to develop novel strategies for optimizing and conserving energy. A typical methodology is to reduce the complexity of real systems and applications by developing a simplified performance model from observed behavior. In the literature, many of these models are known; however, inherent to any simplification is that some measured data cannot be explained well. While analyzing a models accuracy, it is highly important to identify the properties of such prediction errors. Such knowledge can then be used to improve the model or to optimize the benchmarks used for training the model parameters. For such a benchmark suite, it is important that the benchmarks cover all the aspects of system behavior to avoid overfitting of the model for certain scenarios. It is not trivial to identify the overlap between the benchmarks and answer the question if a benchmark causes different hardware behavior. Inspection of all the available hardware and software counters by humans is a tedious task given the large amount of real-time data they produce. In this paper, we utilize statistical techniques to foster understand and investigate hardware counters as potential indicators of energy behavior. We capture hardware and software counters including power with a fixed frequency and analyze the resulting timelines of these measurements. The concepts introduced can be applied to any set of measurements in order to compare them to another set of measurements. We demonstrate how these techniques can aid identifying interesting behavior and significantly reducing the number of features that must be inspected. Next, we propose counters that can potentially be used for building linear models for predicting with a relative accuracy of 3\%. Finally, we validate the completeness of a benchmark suite, from the point of view of using the available architectural components, for generating accurate models.},
	url	 = {http://www.sciencedirect.com/science/article/pii/S2210537916300865},
}