A floorplan aware high-level synthesis algorithm with body biasing for delay variation compensation

    Research output: Contribution to journalArticle

    Abstract

    In this paper, we propose a floorplan aware high-level syn-thesis algorithm with body biasing for delay variation compensation, which minimizes the average leakage energy of manufactured chips. In order to realize floorplan-aware high-level synthesis, we utilize huddle-based dis-tributed register architecture (HDR architecture). HDR architecture divides the chip area into small partitions called a huddle and we can control a body bias voltage for every huddle. During high-level synthesis, we iteratively obtain expected leakage energy for every huddle when applying a body bias voltage. A huddle with smaller expected leakage energy contributes to reducing expected leakage energy of the entire circuit more but can in-crease the latency. We assign control-data flow graph (CDFG) nodes in non-critical paths to the huddles with larger expected leakage energy and those in critical paths to the huddles with smaller expected leakage energy. We expect to minimize the entire leakage energy in a manufactured chip without increasing its latency. Experimental results show that our algorithm reduces the average leakage energy by up to 39.7% without latency and yield degradation compared with typical-case design with body biasing.

    Original languageEnglish
    Pages (from-to)1439-1451
    Number of pages13
    JournalIEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences
    VolumeE100A
    Issue number7
    DOIs
    Publication statusPublished - 2017 Jul 1

    Fingerprint

    High-level Synthesis
    Bias voltage
    Leakage
    Data flow graphs
    Energy
    Latency
    Degradation
    Chip
    Networks (circuits)
    Voltage
    Entire
    Minimise
    Critical Path
    Flow Graphs
    Compensation and Redress
    High level synthesis
    Data Flow
    Divides
    Assign
    Partition

    Keywords

    • Body biasing
    • Delay variation
    • Floorplan
    • High-level synthesis
    • Interconnection delay

    ASJC Scopus subject areas

    • Signal Processing
    • Computer Graphics and Computer-Aided Design
    • Applied Mathematics
    • Electrical and Electronic Engineering

    Cite this

    @article{1a8b72d8a8ac4eb28750087019cbdb82,
    title = "A floorplan aware high-level synthesis algorithm with body biasing for delay variation compensation",
    abstract = "In this paper, we propose a floorplan aware high-level syn-thesis algorithm with body biasing for delay variation compensation, which minimizes the average leakage energy of manufactured chips. In order to realize floorplan-aware high-level synthesis, we utilize huddle-based dis-tributed register architecture (HDR architecture). HDR architecture divides the chip area into small partitions called a huddle and we can control a body bias voltage for every huddle. During high-level synthesis, we iteratively obtain expected leakage energy for every huddle when applying a body bias voltage. A huddle with smaller expected leakage energy contributes to reducing expected leakage energy of the entire circuit more but can in-crease the latency. We assign control-data flow graph (CDFG) nodes in non-critical paths to the huddles with larger expected leakage energy and those in critical paths to the huddles with smaller expected leakage energy. We expect to minimize the entire leakage energy in a manufactured chip without increasing its latency. Experimental results show that our algorithm reduces the average leakage energy by up to 39.7{\%} without latency and yield degradation compared with typical-case design with body biasing.",
    keywords = "Body biasing, Delay variation, Floorplan, High-level synthesis, Interconnection delay",
    author = "Koki Igawa and Masao Yanagisawa and Nozomu Togawa",
    year = "2017",
    month = "7",
    day = "1",
    doi = "10.1587/transfun.E100.A.1439",
    language = "English",
    volume = "E100A",
    pages = "1439--1451",
    journal = "IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences",
    issn = "0916-8508",
    publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
    number = "7",

    }

    TY - JOUR

    T1 - A floorplan aware high-level synthesis algorithm with body biasing for delay variation compensation

    AU - Igawa, Koki

    AU - Yanagisawa, Masao

    AU - Togawa, Nozomu

    PY - 2017/7/1

    Y1 - 2017/7/1

    N2 - In this paper, we propose a floorplan aware high-level syn-thesis algorithm with body biasing for delay variation compensation, which minimizes the average leakage energy of manufactured chips. In order to realize floorplan-aware high-level synthesis, we utilize huddle-based dis-tributed register architecture (HDR architecture). HDR architecture divides the chip area into small partitions called a huddle and we can control a body bias voltage for every huddle. During high-level synthesis, we iteratively obtain expected leakage energy for every huddle when applying a body bias voltage. A huddle with smaller expected leakage energy contributes to reducing expected leakage energy of the entire circuit more but can in-crease the latency. We assign control-data flow graph (CDFG) nodes in non-critical paths to the huddles with larger expected leakage energy and those in critical paths to the huddles with smaller expected leakage energy. We expect to minimize the entire leakage energy in a manufactured chip without increasing its latency. Experimental results show that our algorithm reduces the average leakage energy by up to 39.7% without latency and yield degradation compared with typical-case design with body biasing.

    AB - In this paper, we propose a floorplan aware high-level syn-thesis algorithm with body biasing for delay variation compensation, which minimizes the average leakage energy of manufactured chips. In order to realize floorplan-aware high-level synthesis, we utilize huddle-based dis-tributed register architecture (HDR architecture). HDR architecture divides the chip area into small partitions called a huddle and we can control a body bias voltage for every huddle. During high-level synthesis, we iteratively obtain expected leakage energy for every huddle when applying a body bias voltage. A huddle with smaller expected leakage energy contributes to reducing expected leakage energy of the entire circuit more but can in-crease the latency. We assign control-data flow graph (CDFG) nodes in non-critical paths to the huddles with larger expected leakage energy and those in critical paths to the huddles with smaller expected leakage energy. We expect to minimize the entire leakage energy in a manufactured chip without increasing its latency. Experimental results show that our algorithm reduces the average leakage energy by up to 39.7% without latency and yield degradation compared with typical-case design with body biasing.

    KW - Body biasing

    KW - Delay variation

    KW - Floorplan

    KW - High-level synthesis

    KW - Interconnection delay

    UR - http://www.scopus.com/inward/record.url?scp=85021781782&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=85021781782&partnerID=8YFLogxK

    U2 - 10.1587/transfun.E100.A.1439

    DO - 10.1587/transfun.E100.A.1439

    M3 - Article

    VL - E100A

    SP - 1439

    EP - 1451

    JO - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

    JF - IEICE Transactions on Fundamentals of Electronics, Communications and Computer Sciences

    SN - 0916-8508

    IS - 7

    ER -