DAS: Dynamic Adaptive Scheduling for Energy-Efficient Heterogeneous SoCs

TL;DR

This paper introduces DAS, a dynamic adaptive scheduling framework for heterogeneous SoCs that balances fast and sophisticated scheduling to optimize energy efficiency and performance across various workloads.

Contribution

The paper presents a novel DAS framework that dynamically combines fast and high-performance schedulers to improve energy efficiency and performance in DSSoCs.

Findings

DAS outperforms individual schedulers in real-world applications.

Achieves 1.29x speedup and 45% lower EDP on average.

Effective across diverse workload complexities.

Abstract

Domain-specific systems-on-chip (DSSoCs) aim at bridging the gap between application-specific integrated circuits (ASICs) and general-purpose processors. Traditional operating system (OS) schedulers can undermine the potential of DSSoCs since their execution times can be orders of magnitude larger than the execution time of the task itself. To address this problem, we propose a dynamic adaptive scheduling (DAS) framework that combines the benefits of a fast (low-overhead) scheduler and a slow (sophisticated, high-performance but high-overhead) scheduler. Experiments with five real-world streaming applications show that DAS consistently outperforms both the fast and slow schedulers. For 40 different workloads, DAS achieves on average 1.29x speedup and 45% lower EDP compared to the sophisticated scheduler at low data rates and 1.28x speedup and 37% lower EDP than the fast scheduler when the workload complexity increases.