2021 IEEE Real-Time Systems Symposium (RTSS)最新文献_第6页

Joint Model and Data Adaptation for Cloud Inference Serving 云推理服务的联合模型与数据自适应

2021 IEEE Real-Time Systems Symposium (RTSS) Pub Date : 2021-12-01 DOI: 10.1109/rtss52674.2021.00034

Jingyan Jiang, Ziyue Luo, Chenghao Hu, Zhaoliang He, Zhi Wang, Shutao Xia, Chuan Wu

{"title":"Joint Model and Data Adaptation for Cloud Inference Serving","authors":"Jingyan Jiang, Ziyue Luo, Chenghao Hu, Zhaoliang He, Zhi Wang, Shutao Xia, Chuan Wu","doi":"10.1109/rtss52674.2021.00034","DOIUrl":"https://doi.org/10.1109/rtss52674.2021.00034","url":null,"abstract":"Real-time deep learning inference serving systems often require prohibitive resources and diverse user requirements. The existing design of inference serving systems mainly focusing on computation resource efficiency, largely ignoring the trade-off between computation and bandwidth resources in need. Sub-optimal resource utilization usually leads to huge serving cost waste. In this paper, we tackle the dual challenge of computation-bandwidth trade-off and cost-effectiveness by proposing sys, an efficient joint Adaptive model, and Adaptive data deep learning serving solution across the geo-datacenters. Inspired by the insight that a trade-off between computational cost and bandwidth cost in achieving the same accuracy, we design a real-time inference serving framework, which selectively places different \"versions\" of the deep learning models at different geo-locations, and schedules different data sample versions to be sent to those model versions for inference. The goal is to minimize the total serving cost while meeting latency and accuracy demand for the serving requests. We formulate a joint placement and serving problem and propose an efficient approximation algorithm to solve it with a theoretical performance guarantee. We deploy sys on Amazon EC2 for experiments, which shows that sys achieves 30%-50% serving cost reduction under the same required latency and accuracy as compared to baselines.","PeriodicalId":102789,"journal":{"name":"2021 IEEE Real-Time Systems Symposium (RTSS)","volume":"48 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"134031848","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

TimeWall: Enabling Time Partitioning for Real-Time Multicore+Accelerator Platforms TimeWall:为实时多核+加速器平台启用时间分区

2021 IEEE Real-Time Systems Symposium (RTSS) Pub Date : 2021-12-01 DOI: 10.1109/rtss52674.2021.00048

Tanya Amert, Zelin Tong, Sergey Voronov, Joshua Bakita, F. D. Smith, James H. Anderson

引用次数: 10

Balancing Energy Efficiency and Real-Time Performance in GPU Scheduling GPU调度中的能效与实时性平衡

2021 IEEE Real-Time Systems Symposium (RTSS) Pub Date : 2021-12-01 DOI: 10.1109/rtss52674.2021.00021

Yidi Wang, Mohsen Karimi, Yecheng Xiang, Hyoseung Kim

{"title":"Balancing Energy Efficiency and Real-Time Performance in GPU Scheduling","authors":"Yidi Wang, Mohsen Karimi, Yecheng Xiang, Hyoseung Kim","doi":"10.1109/rtss52674.2021.00021","DOIUrl":"https://doi.org/10.1109/rtss52674.2021.00021","url":null,"abstract":"General-purpose graphics processing units (GPUs) made available on embedded platforms have gained much interest in real-time cyber-physical systems. Despite the fact that GPUs generally outperform CPUs on many compute-intensive tasks in a multitasking environment, high power consumption remains a challenging problem. In this paper, we first analyze the power and energy consumption of GPU kernels scheduled with spatial multitasking, which is found to be advantageous for schedulability in recent studies, and prove that its use, however, degrades energy efficiency even in the latest commercially available embedded GPUs like NVIDIA Jetson Xavier AGX. Then, based on our observations, we propose sBEET, a real-time energy-efficient GPU scheduling framework that makes scheduling decisions at runtime to optimize the energy consumption while utilizing spatial multitasking to improve real-time performance. We evaluate the performance of the proposed sBEET framework using well-known GPU benchmarks and randomly-generated timing parameters on real hardware. The results indicate that sBEET reduces deadline misses up to 13% when the system is overloaded, and also achieves 15% to 21% lower energy consumption when the tasksets are schedulable compared to the existing works.","PeriodicalId":102789,"journal":{"name":"2021 IEEE Real-Time Systems Symposium (RTSS)","volume":"34 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-12-01","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"121370080","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 9

Composite Resource Scheduling for Networked Control Systems 网络控制系统的复合资源调度

2021 IEEE Real-Time Systems Symposium (RTSS) Pub Date : 2021-09-27 DOI: 10.1109/rtss52674.2021.00025

Peng Wu, Chenchen Fu, Tianyu Wang, Minming Li, Yingchao Zhao, C. Xue, Song Han

{"title":"Composite Resource Scheduling for Networked Control Systems","authors":"Peng Wu, Chenchen Fu, Tianyu Wang, Minming Li, Yingchao Zhao, C. Xue, Song Han","doi":"10.1109/rtss52674.2021.00025","DOIUrl":"https://doi.org/10.1109/rtss52674.2021.00025","url":null,"abstract":"Real-time end-to-end task scheduling in networked control systems (NCSs) requires the joint consideration of both network and computing resources to guarantee the desired quality of service (QoS). This paper introduces a new model for composite resource scheduling (CRS) in real-time networked control systems, which considers a strict execution order of sensing, computing, and actuating segments based on the control loop of the target NCS. We prove that the general CRS problem is NP-hard and study two special cases of the CRS problem. The first case restricts the computing and actuating segments to have unit-size execution time while the second case assumes that both sensing and actuating segments have unit-size execution time. We propose an optimal algorithm to solve the first case by checking the intervals with 100% network resource utilization and modify the deadlines of the tasks within those intervals to prune the search. For the second case, we propose another optimal algorithm based on a novel backtracking strategy to check the time intervals with the network resource utilization larger than 100% and modify the timing parameters of tasks based on these intervals. For the general case, we design a greedy strategy to modify the timing parameters of both network segments and computing segments within the time intervals that have network and computing resource utilization larger than 100%, respectively. The correctness and effectiveness of the proposed algorithms are verified through extensive experiments.","PeriodicalId":102789,"journal":{"name":"2021 IEEE Real-Time Systems Symposium (RTSS)","volume":"137 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2021-09-27","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122061181","PeriodicalName":null,"FirstCategoryId":null,"ListUrlMain":null,"RegionNum":0,"RegionCategory":"","ArticlePicture":[],"TitleCN":null,"AbstractTextCN":null,"PMCID":"","EPubDate":null,"PubModel":null,"JCR":null,"JCRName":null,"Score":null,"Total":0}

引用次数: 1

Response-Time Analysis and Optimization for Probabilistic Conditional Parallel DAG Tasks 概率条件并行DAG任务的响应时间分析与优化

2021 IEEE Real-Time Systems Symposium (RTSS) Pub Date : 2021-01-26 DOI: 10.1109/rtss52674.2021.00042

Niklas Ueter, Mario Günzel, Jian-Jia Chen

引用次数: 5