RankMap提升异构嵌入式设备上多DNN任务的吞吐与优先级控制。
RankMap: Priority-Aware Multi-DNN Manager for Heterogeneous Embedded Devices
- 通过随机搜索与性能估计优化多DNN映射策略。
- 平均吞吐量提升3.6倍，关键DNN优先级提高57.5%。
- 适合需要高优先级保障的边缘AI部署场景。
现代边缘数据中心需同时处理多个深度神经网络（DNN），对工作负载管理带来巨大挑战。为此，当前管理系统必须利用新型嵌入式系统的架构异构性，高效处理多DNN工作负载。本文提出RankMap，一种专为异构嵌入式设备上的多DNN任务设计的优先级感知管理器。RankMap通过随机空间探索结合性能估计，应对多DNN映射的庞大解空间。实验结果表明，与现有方法相比，RankMap在重负载下平均吞吐量提升3.6倍，有效防止DNN饥饿，并使指定DNN的优先级提升57.5%。
原文摘要 · Abstract (English)
Modern edge data centers simultaneously handle multiple Deep Neural Networks (DNNs), leading to significant challenges in workload management. Thus, current management systems must leverage the architectural heterogeneity of new embedded systems to efficiently handle multi-DNN workloads. This paper introduces RankMap, a priority-aware manager specifically designed for multi-DNN tasks on heterogeneous embedded devices. RankMap addresses the extensive solution space of multi-DNN mapping through stochastic space exploration combined with a performance estimator. Experimental results show that RankMap achieves x3.6 higher average throughput compared to existing methods, while preventing DNN starvation under heavy workloads and improving the prioritization of specified DNNs by x57.5.
Thank you to arXiv for use of its open access interoperability. PaperDance 不是 arXiv 官方产品；中文卡片由大模型生成，请以原文为准。