A data optimized I/O middleware for accessing heterogeneous storage hierarchies in high performance computing and cloud environments

Ruonan Wang

    Research output: ThesisDoctoral Thesis

    Abstract

    One of the future world's largest data generators, the Square Kilometre Array telescope (SKA), is currently approaching the construction phase. As a budget-limited project, the efficiency of the data system limits its final scope. This thesis identifies bottlenecks and potential solutions. A generic I/O framework SHORE has been designed and implemented. SHORE addresses two main points, which have not been in the focus previously. One is the recognition of the fact that one data format does not fit all requirements. The other point is the separation of user application specific data models from I/O specific and data flow optimisation techniques.
    LanguageEnglish
    QualificationDoctor of Philosophy
    Awarding Institution
    • The University of Western Australia
    Award date3 Jul 2017
    DOIs
    StateUnpublished - 2017

    Fingerprint

    Middleware
    Telescopes
    Data structures

    Cite this

    @phdthesis{9a488a80e6fc41fe8f3841ebbd38a7b8,
    title = "A data optimized I/O middleware for accessing heterogeneous storage hierarchies in high performance computing and cloud environments",
    abstract = "One of the future world's largest data generators, the Square Kilometre Array telescope (SKA), is currently approaching the construction phase. As a budget-limited project, the efficiency of the data system limits its final scope. This thesis identifies bottlenecks and potential solutions. A generic I/O framework SHORE has been designed and implemented. SHORE addresses two main points, which have not been in the focus previously. One is the recognition of the fact that one data format does not fit all requirements. The other point is the separation of user application specific data models from I/O specific and data flow optimisation techniques.",
    keywords = "Data I/O, Data storage, Radio astronomy, Middleware, Square kilometre array, Performance optimization",
    author = "Ruonan Wang",
    year = "2017",
    doi = "10.4225/23/5987b9f1a7898",
    language = "English",
    school = "The University of Western Australia",

    }

    TY - THES

    T1 - A data optimized I/O middleware for accessing heterogeneous storage hierarchies in high performance computing and cloud environments

    AU - Wang,Ruonan

    PY - 2017

    Y1 - 2017

    N2 - One of the future world's largest data generators, the Square Kilometre Array telescope (SKA), is currently approaching the construction phase. As a budget-limited project, the efficiency of the data system limits its final scope. This thesis identifies bottlenecks and potential solutions. A generic I/O framework SHORE has been designed and implemented. SHORE addresses two main points, which have not been in the focus previously. One is the recognition of the fact that one data format does not fit all requirements. The other point is the separation of user application specific data models from I/O specific and data flow optimisation techniques.

    AB - One of the future world's largest data generators, the Square Kilometre Array telescope (SKA), is currently approaching the construction phase. As a budget-limited project, the efficiency of the data system limits its final scope. This thesis identifies bottlenecks and potential solutions. A generic I/O framework SHORE has been designed and implemented. SHORE addresses two main points, which have not been in the focus previously. One is the recognition of the fact that one data format does not fit all requirements. The other point is the separation of user application specific data models from I/O specific and data flow optimisation techniques.

    KW - Data I/O

    KW - Data storage

    KW - Radio astronomy

    KW - Middleware

    KW - Square kilometre array

    KW - Performance optimization

    U2 - 10.4225/23/5987b9f1a7898

    DO - 10.4225/23/5987b9f1a7898

    M3 - Doctoral Thesis

    ER -