Energy-aware Task Scheduling with Deadline Constraint in DVFS-enabled Heterogeneous Clusters

TL;DR

This paper proposes an energy-aware task scheduling approach for CPU-GPU clusters using DVFS, achieving significant energy savings while respecting task deadlines through an analytical model and heuristic algorithms.

Contribution

It introduces a nonlinear model for GPU energy consumption and a scheduling method that effectively minimizes energy use under deadline constraints.

Findings

Achieves 33-35% energy savings in real-world tests.

Model accurately predicts energy consumption considering GPU nonlinear behavior.

Scheduling algorithm performs close to the theoretical energy saving upper bound.

Abstract

Energy conservation of large data centers for high-performance computing workloads, such as deep learning with big data, is of critical significance, where cutting down a few percent of electricity translates into million-dollar savings. This work studies energy conservation on emerging CPU-GPU hybrid clusters through dynamic voltage and frequency scaling (DVFS). We aim at minimizing the total energy consumption of processing a batch of offline tasks or a sequence of real-time tasks under deadline constraints. We derive a fast and accurate analytical model to compute the appropriate voltage/frequency setting for each task and assign multiple tasks to the cluster with heuristic scheduling algorithms. In particular, our model stresses the nonlinear relationship between task execution time and processor speed for GPU-accelerated applications, for more accurately capturing real-world GPU energy consumption. In performance evaluation driven by real-world power measurement traces, our scheduling algorithm shows comparable energy savings to the theoretical upper bound. With a GPU scaling interval where analytically at most 36% of energy can be saved, we record 33-35% of energy savings. Our results are applicable to energy management on modern heterogeneous clusters.