Dynamic Power Sharing For Higher Job Throughput

Current trends for high-performance systems are leading towards hardware overprovisioning where it is no longer possible to run all components at peak power without exceeding a system-or facility-wide power bound. The standard practice of static power scheduling is likely to lead to inefficiencies with over-and under-provisioning of power to components at runtime. In this paper we investigate the performance and scalability of an application agnostic runtime power scheduler (POWsched) that is capable of enforcing a system-wide power limit. Our experimental results show POWsched is robust, has negligible overhead, and can take advantage of opportunities to shift wasted power to more power-intensive applications, improving overall workload runtime by as much as 14% without job scheduler integration or application specific profiling. In addition, we conduct scalability studies to determine POWsched's overhead for large node counts. Lastly, we contribute a model and simulator (POWsim) for investigating dynamic power scheduling behavior and enforcement at scale.