Realising constant time parallel algorithms with active memory modules

    Research output: Contribution to journalArticleScientificpeer-review

    Abstract

    Recent advances in emulated shared memory architectures have made it possible to exploit the full power of a scalable parallel hardware in an easy-to-program form. Unfortunately, the obtained model of computing does not allow efficient parallel access to a single memory cell leaving the lower bound of the execution time of many important parallel algorithms logarithmic. In this paper, we describe a simple active memory based modification on memory module architecture that eliminates this limitation in many cases. Both algorithmic and real life examples are given. The resulting architecture can be used as a scalable processing infrastructure building block for general purpose applications like e-business, e-education, e-science, and e-medicine on the internet.
    Original languageEnglish
    Pages (from-to)255 - 263
    Number of pages9
    JournalInternational Journal of Electronic Business
    Volume3
    Issue number3-4
    DOIs
    Publication statusPublished - 2005
    MoE publication typeA1 Journal article-refereed

    Fingerprint

    Parallel algorithms
    Data storage equipment
    Memory architecture
    Medicine
    Education
    Internet
    Hardware
    Processing
    Module
    Industry

    Keywords

    • Computer architecture
    • parallel computing
    • active memory
    • memory modules
    • memory systems
    • models of computing
    • parallel algorithms
    • infrastructure for e-business

    Cite this

    @article{e297d7aa02c240febd7857956ab2c35a,
    title = "Realising constant time parallel algorithms with active memory modules",
    abstract = "Recent advances in emulated shared memory architectures have made it possible to exploit the full power of a scalable parallel hardware in an easy-to-program form. Unfortunately, the obtained model of computing does not allow efficient parallel access to a single memory cell leaving the lower bound of the execution time of many important parallel algorithms logarithmic. In this paper, we describe a simple active memory based modification on memory module architecture that eliminates this limitation in many cases. Both algorithmic and real life examples are given. The resulting architecture can be used as a scalable processing infrastructure building block for general purpose applications like e-business, e-education, e-science, and e-medicine on the internet.",
    keywords = "Computer architecture, parallel computing, active memory, memory modules, memory systems, models of computing, parallel algorithms, infrastructure for e-business",
    author = "Martti Forsell",
    year = "2005",
    doi = "10.1504/IJEB.2005.007270",
    language = "English",
    volume = "3",
    pages = "255 -- 263",
    journal = "International Journal of Electronic Business",
    issn = "1470-6067",
    publisher = "Inderscience Publishers",
    number = "3-4",

    }

    Realising constant time parallel algorithms with active memory modules. / Forsell, Martti.

    In: International Journal of Electronic Business, Vol. 3, No. 3-4, 2005, p. 255 - 263.

    Research output: Contribution to journalArticleScientificpeer-review

    TY - JOUR

    T1 - Realising constant time parallel algorithms with active memory modules

    AU - Forsell, Martti

    PY - 2005

    Y1 - 2005

    N2 - Recent advances in emulated shared memory architectures have made it possible to exploit the full power of a scalable parallel hardware in an easy-to-program form. Unfortunately, the obtained model of computing does not allow efficient parallel access to a single memory cell leaving the lower bound of the execution time of many important parallel algorithms logarithmic. In this paper, we describe a simple active memory based modification on memory module architecture that eliminates this limitation in many cases. Both algorithmic and real life examples are given. The resulting architecture can be used as a scalable processing infrastructure building block for general purpose applications like e-business, e-education, e-science, and e-medicine on the internet.

    AB - Recent advances in emulated shared memory architectures have made it possible to exploit the full power of a scalable parallel hardware in an easy-to-program form. Unfortunately, the obtained model of computing does not allow efficient parallel access to a single memory cell leaving the lower bound of the execution time of many important parallel algorithms logarithmic. In this paper, we describe a simple active memory based modification on memory module architecture that eliminates this limitation in many cases. Both algorithmic and real life examples are given. The resulting architecture can be used as a scalable processing infrastructure building block for general purpose applications like e-business, e-education, e-science, and e-medicine on the internet.

    KW - Computer architecture

    KW - parallel computing

    KW - active memory

    KW - memory modules

    KW - memory systems

    KW - models of computing

    KW - parallel algorithms

    KW - infrastructure for e-business

    U2 - 10.1504/IJEB.2005.007270

    DO - 10.1504/IJEB.2005.007270

    M3 - Article

    VL - 3

    SP - 255

    EP - 263

    JO - International Journal of Electronic Business

    JF - International Journal of Electronic Business

    SN - 1470-6067

    IS - 3-4

    ER -