Federated scheduling for Typed DAG tasks scheduling analysis on heterogeneous multi-cores

Abstract Heterogeneous multi-cores utilize the strength of different architectures for executing particular types of workload, and usually offer higher performance and energy efficiency. In this paper, we study a federated scheduling. Federated scheduling is a promising approach to schedule non-typed parallel real-time tasks, where each heavy task exclusively executes on a number of dedicated processors, while light tasks are treated as sequential sporadic tasks and share the remaining processors. We are the first considering federated scheduling for typed DAG tasks. In this paper, we first propose a method to show how to assign cores for heavy tasks. Second, we propose a response time analysis method for the light tasks. Experiments with randomly generated workload show that our proposed method are more precise than the only known global scheduling method of typed DAG tasks.