High-level synthesis with post-silicon delay tuning for RDR architectures

Yuta Hagio, Masao Yanagisawa, Nozomu Togawa

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    2 Citations (Scopus)

    Abstract

    In this paper, we propose a high-level synthesis algorithm with post-silicon delay tuning for RDR architectures. We first obtain a non-delayed scheduling/binding result and a delayed scheduling/binding result. By adding several extra functional units to vacant RDR islands, we have a delayed scheduling/binding result so that its latency cannot be increased compared with the non-delayed one. After that, we similarize the two scheduling/binding results by repeatedly modifying their results. We can finally realize non-delayed and delayed scheduling/binding results simultaneously on RDR architecture with almost no area/performance overheads and we can select either one of them depending on post-silicon delay variation. Experimental results show that our algorithm successfully reduces delayed scheduling/binding latency by up to 42.9% compared with the conventional approach.

    Original languageEnglish
    Title of host publicationISOCC 2013 - 2013 International SoC Design Conference
    PublisherIEEE Computer Society
    Pages194-197
    Number of pages4
    ISBN (Print)9781479911417
    DOIs
    Publication statusPublished - 2013
    Event2013 International SoC Design Conference, ISOCC 2013 - Busan
    Duration: 2013 Nov 17 → 2013 Nov 19

    Other

    Other2013 International SoC Design Conference, ISOCC 2013
    CityBusan
    Period13/11/17 → 13/11/19

    Fingerprint

    Tuning
    Scheduling
    Silicon
    High level synthesis

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Electrical and Electronic Engineering

    Cite this

    Hagio, Y., Yanagisawa, M., & Togawa, N. (2013). High-level synthesis with post-silicon delay tuning for RDR architectures. In ISOCC 2013 - 2013 International SoC Design Conference (pp. 194-197). [6863970] IEEE Computer Society. https://doi.org/10.1109/ISOCC.2013.6863970

    High-level synthesis with post-silicon delay tuning for RDR architectures. / Hagio, Yuta; Yanagisawa, Masao; Togawa, Nozomu.

    ISOCC 2013 - 2013 International SoC Design Conference. IEEE Computer Society, 2013. p. 194-197 6863970.

    Research output: Chapter in Book/Report/Conference proceeding › Conference contribution

    Hagio, Y, Yanagisawa, M & Togawa, N 2013, High-level synthesis with post-silicon delay tuning for RDR architectures. in ISOCC 2013 - 2013 International SoC Design Conference., 6863970, IEEE Computer Society, pp. 194-197, 2013 International SoC Design Conference, ISOCC 2013, Busan, 13/11/17. https://doi.org/10.1109/ISOCC.2013.6863970
    Hagio Y, Yanagisawa M, Togawa N. High-level synthesis with post-silicon delay tuning for RDR architectures. In ISOCC 2013 - 2013 International SoC Design Conference. IEEE Computer Society. 2013. p. 194-197. 6863970 https://doi.org/10.1109/ISOCC.2013.6863970
    Hagio, Yuta ; Yanagisawa, Masao ; Togawa, Nozomu. / High-level synthesis with post-silicon delay tuning for RDR architectures. ISOCC 2013 - 2013 International SoC Design Conference. IEEE Computer Society, 2013. pp. 194-197
    @inproceedings{7f8f2523e2d2406d800c79352a5c8cfa,
    title = "High-level synthesis with post-silicon delay tuning for RDR architectures",
    abstract = "In this paper, we propose a high-level synthesis algorithm with post-silicon delay tuning for RDR architectures. We first obtain a non-delayed scheduling/binding result and a delayed scheduling/binding result. By adding several extra functional units to vacant RDR islands, we have a delayed scheduling/binding result so that its latency cannot be increased compared with the non-delayed one. After that, we similarize the two scheduling/binding results by repeatedly modifying their results. We can finally realize non-delayed and delayed scheduling/binding results simultaneously on RDR architecture with almost no area/performance overheads and we can select either one of them depending on post-silicon delay variation. Experimental results show that our algorithm successfully reduces delayed scheduling/binding latency by up to 42.9{\%} compared with the conventional approach.",
    author = "Yuta Hagio and Masao Yanagisawa and Nozomu Togawa",
    year = "2013",
    doi = "10.1109/ISOCC.2013.6863970",
    language = "English",
    isbn = "9781479911417",
    pages = "194--197",
    booktitle = "ISOCC 2013 - 2013 International SoC Design Conference",
    publisher = "IEEE Computer Society",

    }

    TY - GEN

    T1 - High-level synthesis with post-silicon delay tuning for RDR architectures

    AU - Hagio, Yuta

    AU - Yanagisawa, Masao

    AU - Togawa, Nozomu

    PY - 2013

    Y1 - 2013

    N2 - In this paper, we propose a high-level synthesis algorithm with post-silicon delay tuning for RDR architectures. We first obtain a non-delayed scheduling/binding result and a delayed scheduling/binding result. By adding several extra functional units to vacant RDR islands, we have a delayed scheduling/binding result so that its latency cannot be increased compared with the non-delayed one. After that, we similarize the two scheduling/binding results by repeatedly modifying their results. We can finally realize non-delayed and delayed scheduling/binding results simultaneously on RDR architecture with almost no area/performance overheads and we can select either one of them depending on post-silicon delay variation. Experimental results show that our algorithm successfully reduces delayed scheduling/binding latency by up to 42.9% compared with the conventional approach.

    AB - In this paper, we propose a high-level synthesis algorithm with post-silicon delay tuning for RDR architectures. We first obtain a non-delayed scheduling/binding result and a delayed scheduling/binding result. By adding several extra functional units to vacant RDR islands, we have a delayed scheduling/binding result so that its latency cannot be increased compared with the non-delayed one. After that, we similarize the two scheduling/binding results by repeatedly modifying their results. We can finally realize non-delayed and delayed scheduling/binding results simultaneously on RDR architecture with almost no area/performance overheads and we can select either one of them depending on post-silicon delay variation. Experimental results show that our algorithm successfully reduces delayed scheduling/binding latency by up to 42.9% compared with the conventional approach.

    UR - http://www.scopus.com/inward/record.url?scp=84906895281&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=84906895281&partnerID=8YFLogxK

    U2 - 10.1109/ISOCC.2013.6863970

    DO - 10.1109/ISOCC.2013.6863970

    M3 - Conference contribution

    AN - SCOPUS:84906895281

    SN - 9781479911417

    SP - 194

    EP - 197

    BT - ISOCC 2013 - 2013 International SoC Design Conference

    PB - IEEE Computer Society

    ER -

    Access to Document