Proceedings of the 28th International Conference on Real-Time Networks and Systems最新文献_第2页

Scheduling of Synchronous Dataflow Graphs with Partially Periodic Real-Time Constraints 部分周期实时约束的同步数据流图调度

Proceedings of the 28th International Conference on Real-Time Networks and Systems Pub Date : 2020-06-09 DOI: 10.1145/3394810.3394820

Alexandre Honorat, K. Desnos, S. Bhattacharyya, J. Nezan

{"title":"Scheduling of Synchronous Dataflow Graphs with Partially Periodic Real-Time Constraints","authors":"Alexandre Honorat, K. Desnos, S. Bhattacharyya, J. Nezan","doi":"10.1145/3394810.3394820","DOIUrl":"https://doi.org/10.1145/3394810.3394820","url":null,"abstract":"Modern Cyber-Physical Systems (CPSs) are composed of numerous components, some of which require real-time management: for example, management of sensors and actuators requires periodic deadlines while processing parts do not. We refer to these systems as partially periodic. In a partially periodic system, precedence constraints may exist between periodic and aperiodic components. It is notably the case in CPSs where sensors measuring physical variables at a fixed sampling rate are typically feeding data to one or more processing part. A critical challenge for any real-time CPS software is its scheduling on an embedded computing platform. The increasing number of cores in such platforms (as Kalray MPPA Bostan having 288 cores) makes offline non-preemptive scheduling techniques efficient to respect real-time constraints, but requires new analysis and synthesis algorithms. In this paper, we study the schedulability of partially periodic systems modeled as Synchronous Data Flow (SDF) graphs. Our contributions are a few necessary conditions on any live SDF graph, and a linearithmic offline non-preemptive scheduling algorithm on vertices of any directed acyclic task graph. The presented algorithm has been evaluated on a set of randomly generated SDF graphs and on one real use-case. Experiments show that our proposed non-preemptive scheduling algorithm allocates thousands of tasks in less than a second. In the last experiment, the computed schedules achieve a throughput close to that one obtained with global Earliest Deadline First (EDF) scheduling.","PeriodicalId":322095,"journal":{"name":"Proceedings of the 28th International Conference on Real-Time Networks and Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"128126018","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: 3

Justifying the Service Provided to Low Criticality Tasks in a Mixed Criticality System 混合临界系统中为低临界任务提供服务的合理性

Proceedings of the 28th International Conference on Real-Time Networks and Systems Pub Date : 2020-06-09 DOI: 10.1145/3394810.3394814

S. Law, I. Bate, Benjamin Lesage

{"title":"Justifying the Service Provided to Low Criticality Tasks in a Mixed Criticality System","authors":"S. Law, I. Bate, Benjamin Lesage","doi":"10.1145/3394810.3394814","DOIUrl":"https://doi.org/10.1145/3394810.3394814","url":null,"abstract":"Significant work has been presented over the last decade looking at the application of Mixed Criticality Scheduling. The premise being that if a failure occurs the scheduler performs a mode change from normal mode to high-criticality mode. In high-criticality mode, some low criticality tasks are given a reduced service (e.g. not executed or executed at a different period). Recently work has been performed to bound the number of low criticality jobs that might be skipped while the scheduler operates in high-criticality mode. However a significant gap in the analysis is to understand for how long the service to low criticality tasks may be reduced, i.e. how often the system switches to a high-criticality mode and how long the high-criticality mode is sustained. This is essential as part of supporting software certification. In this paper we consider a process, agnostic to the underlying scheduling strategy, designed to allow a system integrator to address this gap by assessing the level of service provided to low criticality tasks. The result is a safety argument with supporting evidence based on a real life case study, taken from a DAL-A certified aircraft engine control system.1","PeriodicalId":322095,"journal":{"name":"Proceedings of the 28th International Conference on Real-Time Networks and Systems","volume":"79 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"125057608","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: 4

TEECheck: Securing Intra-Vehicular Communication Using Trusted Execution TEECheck:使用可信执行保护车内通信

Proceedings of the 28th International Conference on Real-Time Networks and Systems Pub Date : 2020-06-09 DOI: 10.1145/3394810.3394822

Tanmaya Mishra, Thidapat Chantem, Ryan M. Gerdes

{"title":"TEECheck: Securing Intra-Vehicular Communication Using Trusted Execution","authors":"Tanmaya Mishra, Thidapat Chantem, Ryan M. Gerdes","doi":"10.1145/3394810.3394822","DOIUrl":"https://doi.org/10.1145/3394810.3394822","url":null,"abstract":"Modern vehicles have a large number of advanced driver assistance systems (e.g., adaptive cruise control and automatic lane keeping) that depend on the timely availability of data exchanged through the CAN bus from a variety of ECUs and sensors. Considering the large amount of data on the CAN bus, CAN has become a lucrative target for malicious parties wishing to take control of a vehicle. Specifically, an attacker may compromise an ECU to gain access to the bus. It is, thus, imperative that the CAN bus is secured from disruption by compromised ECUs to ensure its correct and timely operation. We design a new system architecture for ECUs that leverages trusted execution environments and propose TEECheck, an on-device message vetting mechanism to proactively contain masquerade and denial-of-service attacks, as well as eliminate information leakage. The uniqueness of our approach is that it require neither authentication at the receiver end adds any overhead if there is no need for CAN bus access. Experiments show that our technique has very low and predictable overhead, regardless of the workload.","PeriodicalId":322095,"journal":{"name":"Proceedings of the 28th International Conference on Real-Time Networks and Systems","volume":"6 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"127544793","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: 7

Design and Analysis of Programming Platform for Accelerated GPU-Like Architectures 加速类gpu架构编程平台的设计与分析

Proceedings of the 28th International Conference on Real-Time Networks and Systems Pub Date : 2020-06-09 DOI: 10.1145/3394810.3394826

H. Zahaf, G. Lipari

{"title":"Design and Analysis of Programming Platform for Accelerated GPU-Like Architectures","authors":"H. Zahaf, G. Lipari","doi":"10.1145/3394810.3394826","DOIUrl":"https://doi.org/10.1145/3394810.3394826","url":null,"abstract":"Many recent computing platforms combine CPUs with different types of accelerators such as Graphical Processing Units (GPUs), to cope with the increasing computation needs of complex realtime applications. However, most hardware accelerators have not been designed to provide predictable timing-behavior to support real-time tasks. Moreover, they do not provide efficient preemption mechanisms. In this work, we present the design of a software library to program and execute real-time tasks onto hardware accelerators (e.g. GPUs) that exhibit limited-preemption capabilities with variables costs. The library provides: 1) parallel execution for real-time applications within the same accelerator; 2) the choice of different partitioned scheduling algorithms (FP, EDF, Gang-EDF); 3) support for (limited) task preemption. We describe a user space implementation of the library as a proof of concept. We also present a schedulability analysis for real-time tasks programmed using this platform, in particular for partitioned EDF and GANG-EDF. The effectiveness of the proposed scheduling strategies and their analyses is demonstrated through 1) actual measurements on a GPU platform, and 2) through synthetic task sets.","PeriodicalId":322095,"journal":{"name":"Proceedings of the 28th International Conference on Real-Time Networks and Systems","volume":"4 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-06-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122079011","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: 2

Workload assignment for global real-time scheduling on unrelated multicore platforms 非相关多核平台上全局实时调度的工作负载分配

Proceedings of the 28th International Conference on Real-Time Networks and Systems Pub Date : 2020-04-06 DOI: 10.1145/3394810.3394823

A. Bertout, J. Goossens, E. Grolleau, Xavier Poczekajlo

引用次数: 8

Adaptive Routing with Guaranteed Delay Bounds using Safe Reinforcement Learning 基于安全强化学习的有保证延迟界自适应路由

Proceedings of the 28th International Conference on Real-Time Networks and Systems Pub Date : 2020-03-09 DOI: 10.1145/3394810.3394815

Gautham Nayak Seetanadi, Karl-Erik Årzén, M. Maggio

{"title":"Adaptive Routing with Guaranteed Delay Bounds using Safe Reinforcement Learning","authors":"Gautham Nayak Seetanadi, Karl-Erik Årzén, M. Maggio","doi":"10.1145/3394810.3394815","DOIUrl":"https://doi.org/10.1145/3394810.3394815","url":null,"abstract":"Time-critical networks require strict delay bounds on the transmission time of packets from source to destination. Routes for transmissions are usually statically determined, using knowledge about worst-case transmission times between nodes. This is generally a conservative method, that guarantees transmission times but does not provide any optimization for the typical case. In real networks, the typical delays vary from those considered during static route planning. The challenge in such a scenario is to minimize the total delay from a source to a destination node, while adhering to the timing constraints. For known typical and worst-case delays, an algorithm was presented to (statically) determine the policy to be followed during the packet transmission in terms of edge choices. In this paper we relax the assumption of knowing the typical delay, and we assume only worst-case bounds are available. We present a reinforcement learning solution to obtain optimal routing paths from a source to a destination when the typical transmission time is stochastic and unknown. Our reinforcement learning policy is based on the observation of the state-space during each packet transmission and on adaptation for future packets to congestion and unpredictable circumstances in the network. We ensure that our policy only makes safe routing decisions, thus never violating pre-determined timing constraints. We conduct experiments to evaluate the routing in a congested network and in a network where the typical delays have a large variance. Finally, we analyze the application of the algorithm to large randomly generated networks.","PeriodicalId":322095,"journal":{"name":"Proceedings of the 28th International Conference on Real-Time Networks and Systems","volume":"51 1","pages":"0"},"PeriodicalIF":0.0,"publicationDate":"2020-03-09","publicationTypes":"Journal Article","fieldsOfStudy":null,"isOpenAccess":false,"openAccessPdf":"","citationCount":null,"resultStr":null,"platform":"Semanticscholar","paperid":"122422131","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: 7