A high-level and accurate energy model of parallel and concurrent workloads

The ability to predict the energy needed by a system to perform a task, or several concurrent parallel tasks, allows the scheduler to enforce energy-aware policies while providing acceptable performance. The approaches in literature to model energy consumption of tasks usually focus on low-level descriptors and require invasive instrumentation of the computational environment. We developed an energy model and a methodology to automatically extract features that characterize the computational environment relying only on a single power meter that measures the energy consumption of the whole system. Once the model has been built, the energy consumption of concurrent tasks can be calculated, with a statistically insignificant error, even without any power meter. We show that our model can predict with high accuracy, even only using the utilization time of the cores in a high-performance computing enclosure, without using performance counters. Hence, the model could be easily applicable to heterogeneous systems, where collecting representative performance counters can be problematic