Energy-Efficient Real-Time Scheduling of DAGs on Clustered Multi-Core Platforms

With the growth of computation-intensive real-time applications on multi-core embedded systems, energy-efficient real-time scheduling becomes crucial. Multi-core processors enable intra-task parallelism, and there has been much progress on exploiting that, while there has been only a little progress on energy-efficient multi-core real-time scheduling as yet. In this work, we study energy-efficient real-time scheduling of constrained deadline sporadic parallel tasks, where each task is represented as a directed acyclic graph (DAG). We consider a clustered multi-core platform where processors within the same cluster run at the same speed at any given time. A new concept named speed-profile is proposed to model per-task and per-cluster energy-consumption variations during run-time to minimize the expected long-term energy consumption. To our knowledge, no existing work considers energy-aware real-time scheduling of DAG tasks with constrained deadlines, nor on a clustered multi-core platform. The proposed energy-aware realtime scheduler is implemented upon an ODROID XU-3 board to evaluate and demonstrate its feasibility and practicality. To complement our system experiments in large-scale, we have also conducted simulations that demonstrate a CPU energy saving of up to 57% through our proposed approach compared to existing methods.

I. Introduction

There is a trend in moving towards multi/many-core processors for real-time systems—they appear as an enabling platform for embedded systems applications that require real-time guarantees, energy efficiency, and high performance. To exploit the capability of the multi-core platform, considering intra-task parallelism, where an individual task can utilize multiple cores simultaneously, is vital. Intra-task parallelism facilitates a balanced distribution of the tasks among the processors, which leads to energy efficiency [1]. One of the most general-ized workload model for representing deterministic intra-task parallelism is Directed Acyclic Graph (DAG) task [2]. Under such method of abstraction, the nodes in a DAG represent various threads of execution while the edges represent their dependencies. In the past five years or so, quite some effort has been spent on developing real-time scheduling strategies and schedulability analysis of DAG tasks [2]–[9].