多核处理器正越发广泛地应用到现代嵌入式系统的设计与实现当中，其强大的计算能力为将多个不同关键性级别的功能子系统集成到统一的共享资源平台提供了支持.混合关键性系统的调度问题即便在单处理器平台中都极具挑战性，在多处理器平台则更为困难.将目前资源利用率最高的单处理器混合关键性调度算法EY-VD扩展到多处理器平台中.首先，结合传统的划分调度策略提出了适用于多处理器混合关键性系统的MC-PEDF(mixedcriticality partitioned earliest deadline first)划分调度算法.尽管比之前的算法有更好的可调度性能，但传统的划分策略不能有效地平衡不同关键性级别下的负载，故其不完全适用于混合关键性系统.为了克服传统策略的不足，提出了划分调度策略OCOP(one criticality one partition).OCOP允许系统在关键性模式切换时对实时任务集进行重新划分，进而更好地平衡各个处理器在不同关键性模式中的资源利用率.基于OCOP，提出了第2种划分调度算法MC-MP-EDF(mixed-criticality multi-partitioned EDF).基于随机生成任务集的仿真实验结果表明，与MC-PEDF和已有的算法相比，MC-MP-EDF能够显著地提高系统的可调度性，尤其是在处理器数量较多的系统中.

Multi-Core processors are more and more widely used in embedded systems as they provide great computing capacities to integrate multiple functionalities with different criticality levels into a shared platform. The scheduling problem of mixed-criticality systems appears to be challenging, even on single-processor platforms. This work extends the state-of-the-art single-processor mixedcriticality scheduling algorithm EY-VD to multi-processor systems. To begin with, it integrates EY-VD into traditional workload partitioning schemes to get a multiprocessor mixed-criticality scheduling algorithm MC-PEDF (mixed-criticality partitioned earliest deadline first). Although MC-PEDF performs better than previous solutions, the study finds that the traditional workload partitioning schemes are not suitable for mixed-criticality systems as it does not explore the asymmetricity of workload on different criticality levels. To overcome this problem, a workload partitioning policy OCOP (one criticality one partition) is proposed. OCOP allows tasks to be reassigned to a different processor when criticality mode switch occurs, thus can better balance the resource utilization among processors on different criticality levels. Based on OCOP, the second partitioned scheduling algorithm MC-MP-EDF (mixed-criticality multi-partitioned EDF) is constructed. Experiments with randomly generated workload show that MC-MP-EDF can drastically improve the system schedulability comparing with MC-PEDF and other previous algorithms, especially for systems with more processors.

国家科技支撑计划（2012BAF13B08）；中央高校基本科研业务费项目（FRFCUN100204001, FRFCUN110804003）；国家自然科学基金（61300022）