Analysis of Divisible Load Scheduling with result collection on HETerogeneous Systems

Abhay Ghatpande, Hidenori Nakazato, Olivier Beaumont, Hiroshi Watanabe

    Research output: Contribution to journalArticle

    4 Citations (Scopus)

    Abstract

    Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Result Collection on HETerogeneous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.

    Original languageEnglish
    Pages (from-to)2234-2243
    Number of pages10
    JournalIEICE Transactions on Communications
    VolumeE91-B
    Issue number7
    DOIs
    Publication statusPublished - 2008

    Fingerprint

    Scheduling

    Keywords

    • Divisible Load Scheduling
    • HETerogeneous Systems
    • Result collection

    ASJC Scopus subject areas

    • Electrical and Electronic Engineering
    • Computer Networks and Communications
    • Software

    Cite this

    Analysis of Divisible Load Scheduling with result collection on HETerogeneous Systems. / Ghatpande, Abhay; Nakazato, Hidenori; Beaumont, Olivier; Watanabe, Hiroshi.

    In: IEICE Transactions on Communications, Vol. E91-B, No. 7, 2008, p. 2234-2243.

    Research output: Contribution to journalArticle

    @article{7f0b513745a74b75bcd25b9f8f0b3aaa,
    title = "Analysis of Divisible Load Scheduling with result collection on HETerogeneous Systems",
    abstract = "Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Result Collection on HETerogeneous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.",
    keywords = "Divisible Load Scheduling, HETerogeneous Systems, Result collection",
    author = "Abhay Ghatpande and Hidenori Nakazato and Olivier Beaumont and Hiroshi Watanabe",
    year = "2008",
    doi = "10.1093/ietcom/e91-b.7.2234",
    language = "English",
    volume = "E91-B",
    pages = "2234--2243",
    journal = "IEICE Transactions on Communications",
    issn = "0916-8516",
    publisher = "Maruzen Co., Ltd/Maruzen Kabushikikaisha",
    number = "7",

    }

    TY - JOUR

    T1 - Analysis of Divisible Load Scheduling with result collection on HETerogeneous Systems

    AU - Ghatpande, Abhay

    AU - Nakazato, Hidenori

    AU - Beaumont, Olivier

    AU - Watanabe, Hiroshi

    PY - 2008

    Y1 - 2008

    N2 - Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Result Collection on HETerogeneous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.

    AB - Divisible Load Theory (DLT) is an established framework to study Divisible Load Scheduling (DLS). Traditional DLT ignores the result collection phase, and specifies no solution to the general case where both the network speed and computing capacity of the nodes are heterogeneous. In this paper, the DLS with Result Collection on HETerogeneous Systems (DLSRCHETS) problem is formulated as a linear program and analyzed. The papers to date that have dealt with result collection, proposed simplistic LIFO (Last In, First Out) and FIFO (First In, First Out) type of schedules as solutions. The main contributions of this paper are: (a) A proof of the Allocation Precedence Condition, which is inconsequential in LIFO or FIFO, but is important in a general schedule. (b) A proof of the Idle Time Theorem, which states that irrespective of whether load is allocated to all available processors, in the optimal solution to the DLSRCHETS problem, at the most one processor that is allocated load has idle time, and that the idle time exists only when the result collection begins immediately after the completion of load distribution.

    KW - Divisible Load Scheduling

    KW - HETerogeneous Systems

    KW - Result collection

    UR - http://www.scopus.com/inward/record.url?scp=67651065501&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=67651065501&partnerID=8YFLogxK

    U2 - 10.1093/ietcom/e91-b.7.2234

    DO - 10.1093/ietcom/e91-b.7.2234

    M3 - Article

    VL - E91-B

    SP - 2234

    EP - 2243

    JO - IEICE Transactions on Communications

    JF - IEICE Transactions on Communications

    SN - 0916-8516

    IS - 7

    ER -