An Efficient Scheduling Algorithm for Interdependent Tasks in Heterogeneous Multi-core Systems

Due to the increasing demand for computing power in many industries, heterogeneous multi-core processors are needed to solve the problem. In order to make full use of multi-core computing resources, an effective scheduling strategy for heterogeneous multi-core processor tasks is required. Directed acyclic graph (DAG) is usually used to represent data dependencies between tasks. Each task needs to be executed in the order of its data dependencies. Research under this model has made great progress. In this article, we study and improve the DAG-based task model, taking into account the fact that not only one-way data transmission is possible between tasks, but also two-way data exchange. Based on this model, we propose two scheduling strategies, overall cutting scheduling (OCS) and greedy selection scheduling (GSS). As far as we know, there is currently no work considering the existence of a special task model of two-way transmission between tasks, nor has it considered task scheduling in two-way transmission. In order to evaluate and demonstrate its feasibility and practicability, we proposed a reference method and supplemented with large-scale system experiments. These experiments show that the scheduling efficiency of the proposed method is greatly improved.