中文摘要：

任务调度是并行处理的一个非常关键的方面。目前的调度算法大多假定处理器完全互连、可以并行接收数据，而没有考虑实际应用中通信链路的竞争及延迟，进而导致调度算法在具体应用中效率较低。论文研究异构计算环境下具有依赖关系任务的边调度问题，结合传统任务调度问题中的有效策略，提出一种新的调度算法，该算法通过串行化通信边使通信竞争集成化。实验结果表明，与各种经典调度方案相比，该算法显著地改善了精确性和效率。

英文摘要：

Task scheduling is an essential aspect of parallel processing.However,many previous works assume fully connected processors and concurrent communication,while ignoring the contention and delay on data links in real applications,which leads to low efficiency.This paper focuses on the issue of edge scheduling for dependent tasks in heterogeneous environment.Combining with classically efficient heuristics,this paper proposes a new scheduling algorithm that integrates communication contention by se- rializing the communications edges,which produces significantly more accurate and efficient schedules than classic schedule schemes in experiments.