Practical performance prediction under Dynamic Voltage Frequency Scaling

Predicting performance under Dynamic Voltage Frequency Scaling (DVFS) remains an open problem. Current best practice explores available performance counters to serve as input to linear regression models that predict performance. However, the inaccuracies of these models require that large-scale DVFS runtime algorithms predict performance conservatively in order to avoid significant consequences of mispredictions. Recent theoretical work based on interval analysis advocates a more accurate and reliable solution based on a single new performance counter, Leading Loads. In this paper, we evaluate a processor-independent analytic framework for existing performance counters based on this interval analysis model. We begin with an analysis of the counters used in many published models. We then briefly describe the Leading Loads architectural model and describe how we can use Leading Loads Cycles to predict performance under DVFS. We validate this approach for the NAS Parallel Benchmarks and SPEC CPU 2006 benchmarks, demonstrating an order of magnitude improvement in both error and standard deviation compared to the best existing approaches.