Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models

Philip Sebastian Kurtin, Marco Jan Gerrit Bekooij

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    49 Downloads (Pure)

    Abstract

    Real-time streaming applications with cyclic data dependencies that are executed on multiprocessor systems with processor sharing usually require a temporal analysis to give guarantees on their temporal behavior at design time. Current accurate analysis techniques for cyclic applications that are scheduled with Static Priority Preemptive (SPP) schedulers are however limited to the analysis of applications that can be expressed with Homogeneous Synchronous Dataflow (HSDF) models, i.e. in which all tasks operate at a single rate. Moreover, it is required that both input and output buffers synchronize atomically at the beginnings and finishes of task executions, which is difficult to realize on many existing hardware platforms. This paper presents a temporal analysis approach for cyclic real-time streaming applications executed on multiprocessor systems with processor sharing and SPP scheduling that can be expressed using Cyclo-Static Dataflow (CSDF) models. This allows to model tasks with multiple phases and changing rates and furthermore resolves the problematic restriction that buffer synchronization must occur atomically at the boundaries of task executions. For that purpose a joint interference characterization over multiple phases is introduced, which realizes a significant accuracy improvement compared to an isolated consideration of interference. Applicability, efficiency and accuracy of the presented approach are evaluated in a case study using a WLAN 802.11p transceiver application. Thereby different use-cases of CSDF modeling are discussed, including a CSDF model relaxing the requirement of atomic synchronization.
    Original languageUndefined
    Title of host publication2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia)
    Place of PublicationNew York
    PublisherAssociation for Computing Machinery (ACM)
    Pages94-103
    Number of pages10
    ISBN (Print)978-1-4503-4543-9
    DOIs
    Publication statusPublished - 7 Oct 2016
    Event14th ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia, ESTIMedia 2016 - Pittsburgh, United States
    Duration: 6 Oct 20167 Oct 2016
    Conference number: 14
    http://www.estimedia.org/past/ESTIMedia2016/index.html

    Publication series

    Name
    PublisherACM

    Conference

    Conference14th ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia, ESTIMedia 2016
    Abbreviated titleESTIMedia
    CountryUnited States
    CityPittsburgh
    Period6/10/167/10/16
    Internet address

    Keywords

    • IR-101816
    • METIS-318555
    • Real Time
    • Joint Interference Characterization
    • Processor Sharing
    • Multi-Rate Applications
    • Multi-Phase Tasks
    • Dataflow Modeling
    • MPSoCs
    • Abstraction
    • CSDF
    • Temporal Analysis
    • Streaming Applications
    • Static Priority Preemptive Scheduling
    • EWI-27311
    • Cyclic Applications

    Cite this

    Kurtin, P. S., & Bekooij, M. J. G. (2016). Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models. In 2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia) (pp. 94-103). New York: Association for Computing Machinery (ACM). https://doi.org/10.1145/2993452.2993564
    Kurtin, Philip Sebastian ; Bekooij, Marco Jan Gerrit. / Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models. 2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia). New York : Association for Computing Machinery (ACM), 2016. pp. 94-103
    @inproceedings{259c3576d5b94f91a5f1b9ca5b4b3a17,
    title = "Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models",
    abstract = "Real-time streaming applications with cyclic data dependencies that are executed on multiprocessor systems with processor sharing usually require a temporal analysis to give guarantees on their temporal behavior at design time. Current accurate analysis techniques for cyclic applications that are scheduled with Static Priority Preemptive (SPP) schedulers are however limited to the analysis of applications that can be expressed with Homogeneous Synchronous Dataflow (HSDF) models, i.e. in which all tasks operate at a single rate. Moreover, it is required that both input and output buffers synchronize atomically at the beginnings and finishes of task executions, which is difficult to realize on many existing hardware platforms. This paper presents a temporal analysis approach for cyclic real-time streaming applications executed on multiprocessor systems with processor sharing and SPP scheduling that can be expressed using Cyclo-Static Dataflow (CSDF) models. This allows to model tasks with multiple phases and changing rates and furthermore resolves the problematic restriction that buffer synchronization must occur atomically at the boundaries of task executions. For that purpose a joint interference characterization over multiple phases is introduced, which realizes a significant accuracy improvement compared to an isolated consideration of interference. Applicability, efficiency and accuracy of the presented approach are evaluated in a case study using a WLAN 802.11p transceiver application. Thereby different use-cases of CSDF modeling are discussed, including a CSDF model relaxing the requirement of atomic synchronization.",
    keywords = "IR-101816, METIS-318555, Real Time, Joint Interference Characterization, Processor Sharing, Multi-Rate Applications, Multi-Phase Tasks, Dataflow Modeling, MPSoCs, Abstraction, CSDF, Temporal Analysis, Streaming Applications, Static Priority Preemptive Scheduling, EWI-27311, Cyclic Applications",
    author = "Kurtin, {Philip Sebastian} and Bekooij, {Marco Jan Gerrit}",
    note = "eemcs-eprint-27311",
    year = "2016",
    month = "10",
    day = "7",
    doi = "10.1145/2993452.2993564",
    language = "Undefined",
    isbn = "978-1-4503-4543-9",
    publisher = "Association for Computing Machinery (ACM)",
    pages = "94--103",
    booktitle = "2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia)",
    address = "United States",

    }

    Kurtin, PS & Bekooij, MJG 2016, Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models. in 2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia). Association for Computing Machinery (ACM), New York, pp. 94-103, 14th ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia, ESTIMedia 2016, Pittsburgh, United States, 6/10/16. https://doi.org/10.1145/2993452.2993564

    Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models. / Kurtin, Philip Sebastian; Bekooij, Marco Jan Gerrit.

    2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia). New York : Association for Computing Machinery (ACM), 2016. p. 94-103.

    Research output: Chapter in Book/Report/Conference proceedingConference contributionAcademicpeer-review

    TY - GEN

    T1 - Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models

    AU - Kurtin, Philip Sebastian

    AU - Bekooij, Marco Jan Gerrit

    N1 - eemcs-eprint-27311

    PY - 2016/10/7

    Y1 - 2016/10/7

    N2 - Real-time streaming applications with cyclic data dependencies that are executed on multiprocessor systems with processor sharing usually require a temporal analysis to give guarantees on their temporal behavior at design time. Current accurate analysis techniques for cyclic applications that are scheduled with Static Priority Preemptive (SPP) schedulers are however limited to the analysis of applications that can be expressed with Homogeneous Synchronous Dataflow (HSDF) models, i.e. in which all tasks operate at a single rate. Moreover, it is required that both input and output buffers synchronize atomically at the beginnings and finishes of task executions, which is difficult to realize on many existing hardware platforms. This paper presents a temporal analysis approach for cyclic real-time streaming applications executed on multiprocessor systems with processor sharing and SPP scheduling that can be expressed using Cyclo-Static Dataflow (CSDF) models. This allows to model tasks with multiple phases and changing rates and furthermore resolves the problematic restriction that buffer synchronization must occur atomically at the boundaries of task executions. For that purpose a joint interference characterization over multiple phases is introduced, which realizes a significant accuracy improvement compared to an isolated consideration of interference. Applicability, efficiency and accuracy of the presented approach are evaluated in a case study using a WLAN 802.11p transceiver application. Thereby different use-cases of CSDF modeling are discussed, including a CSDF model relaxing the requirement of atomic synchronization.

    AB - Real-time streaming applications with cyclic data dependencies that are executed on multiprocessor systems with processor sharing usually require a temporal analysis to give guarantees on their temporal behavior at design time. Current accurate analysis techniques for cyclic applications that are scheduled with Static Priority Preemptive (SPP) schedulers are however limited to the analysis of applications that can be expressed with Homogeneous Synchronous Dataflow (HSDF) models, i.e. in which all tasks operate at a single rate. Moreover, it is required that both input and output buffers synchronize atomically at the beginnings and finishes of task executions, which is difficult to realize on many existing hardware platforms. This paper presents a temporal analysis approach for cyclic real-time streaming applications executed on multiprocessor systems with processor sharing and SPP scheduling that can be expressed using Cyclo-Static Dataflow (CSDF) models. This allows to model tasks with multiple phases and changing rates and furthermore resolves the problematic restriction that buffer synchronization must occur atomically at the boundaries of task executions. For that purpose a joint interference characterization over multiple phases is introduced, which realizes a significant accuracy improvement compared to an isolated consideration of interference. Applicability, efficiency and accuracy of the presented approach are evaluated in a case study using a WLAN 802.11p transceiver application. Thereby different use-cases of CSDF modeling are discussed, including a CSDF model relaxing the requirement of atomic synchronization.

    KW - IR-101816

    KW - METIS-318555

    KW - Real Time

    KW - Joint Interference Characterization

    KW - Processor Sharing

    KW - Multi-Rate Applications

    KW - Multi-Phase Tasks

    KW - Dataflow Modeling

    KW - MPSoCs

    KW - Abstraction

    KW - CSDF

    KW - Temporal Analysis

    KW - Streaming Applications

    KW - Static Priority Preemptive Scheduling

    KW - EWI-27311

    KW - Cyclic Applications

    U2 - 10.1145/2993452.2993564

    DO - 10.1145/2993452.2993564

    M3 - Conference contribution

    SN - 978-1-4503-4543-9

    SP - 94

    EP - 103

    BT - 2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia)

    PB - Association for Computing Machinery (ACM)

    CY - New York

    ER -

    Kurtin PS, Bekooij MJG. Temporal analysis of static priority preemptive scheduled cyclic streaming applications using CSDF models. In 2016 ACM/IEEE Symposium on Embedded Systems for Real-Time Multimedia (ESTIMedia). New York: Association for Computing Machinery (ACM). 2016. p. 94-103 https://doi.org/10.1145/2993452.2993564