Agon: A Scalable Competitive Scheduler for Large Heterogeneous Systems

2021/09/02 by Prodromou, Andreas, Venkat, Ashish, Tullsen, Dean M.
#FOS: Computer and information sciences #Hardware Architecture (cs.AR)

paper · doi:10.48550/arxiv.2109.00665

Abstract

This work proposes a competitive scheduling approach, designed to scale to large heterogeneous multicore systems. This scheduler overcomes the challenges of (1) the high computation overhead of near-optimal schedulers, and (2) the error introduced by inaccurate performance predictions. This paper presents Agon, a neural network-based classifier that selects from a range of schedulers, from simple to very accurate, and learns which scheduler provides the right balance of accuracy and overhead for each scheduling interval. Agon also employs a de-noising frontend allowing the individual schedulers to be tolerant towards noise in performance predictions, producing better overall schedules. By avoiding expensive scheduling overheads, Agon improves average system performance by 6% on average, approaching the performance of an oracular scheduler (99.1% of oracle performance).

Related

• Mixture-of-Schedulers: An Adaptive Scheduling Agent as a Learned Router for Expert Policies
• Neural Heterogeneous Scheduler
• A Taxonomy of Schedulers -- Operating Systems, Clusters and Big Data Frameworks
• An Adaptive Performance-oriented Scheduler for Static and Dynamic Heterogeneity
• Slim Scheduler: A Runtime-Aware RL and Scheduler System for Efficient CNN Inference