Performance study of core2duo desktop processors

Abduljalil R A Saif, Kasmiran Bin Jumari

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Abstract

    The multicore processors turned out to open the doors to make the desktop to have parallel and high performance capability. In this paper, the performance study for these systems is presented, in which the studies were carried out on the Intel's Core2Duo processor with an OpenMP programming integrated into Microsoft visual studio C++ 2005 and Intel C++ 10.1.020 compiler. Using multithreaded programming, this paper provides the performance measurement for dual core over a single core and assessing the performance of the OpenMP multithreaded programming on a Core2Duo processor. The speedup of dual-core over a single core and the behaviour of Core2Duo processor with OpenMP programming are reported. Our results reveal that the Core2Duo performance with OpenMP multithreaded programming falls behind the Core2Duo performance in a sequential mode when the workload exceeds the size of the L2 cache, also the dual core speedup drops drastically to about 1.1. Finally we measured the performance using the Stream and Stream2 benchmarks and analyse the running results.

    Original languageEnglish
    Title of host publicationProceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009
    Pages532-536
    Number of pages5
    Volume2
    DOIs
    Publication statusPublished - 2009
    Event2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009 - Selangor
    Duration: 5 Aug 20097 Aug 2009

    Other

    Other2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009
    CitySelangor
    Period5/8/097/8/09

    Fingerprint

    Studios

    Keywords

    • Benchmarks
    • Core2Duo
    • Memory performance
    • OpenMP

    ASJC Scopus subject areas

    • Information Systems
    • Software
    • Energy Engineering and Power Technology
    • Electrical and Electronic Engineering

    Cite this

    Saif, A. R. A., & Jumari, K. B. (2009). Performance study of core2duo desktop processors. In Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009 (Vol. 2, pp. 532-536). [5254756] https://doi.org/10.1109/ICEEI.2009.5254756

    Performance study of core2duo desktop processors. / Saif, Abduljalil R A; Jumari, Kasmiran Bin.

    Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009. Vol. 2 2009. p. 532-536 5254756.

    Research output: Chapter in Book/Report/Conference proceedingConference contribution

    Saif, ARA & Jumari, KB 2009, Performance study of core2duo desktop processors. in Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009. vol. 2, 5254756, pp. 532-536, 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009, Selangor, 5/8/09. https://doi.org/10.1109/ICEEI.2009.5254756
    Saif ARA, Jumari KB. Performance study of core2duo desktop processors. In Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009. Vol. 2. 2009. p. 532-536. 5254756 https://doi.org/10.1109/ICEEI.2009.5254756
    Saif, Abduljalil R A ; Jumari, Kasmiran Bin. / Performance study of core2duo desktop processors. Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009. Vol. 2 2009. pp. 532-536
    @inproceedings{b7f8726d792c477dbe6a72e28c6faca0,
    title = "Performance study of core2duo desktop processors",
    abstract = "The multicore processors turned out to open the doors to make the desktop to have parallel and high performance capability. In this paper, the performance study for these systems is presented, in which the studies were carried out on the Intel's Core2Duo processor with an OpenMP programming integrated into Microsoft visual studio C++ 2005 and Intel C++ 10.1.020 compiler. Using multithreaded programming, this paper provides the performance measurement for dual core over a single core and assessing the performance of the OpenMP multithreaded programming on a Core2Duo processor. The speedup of dual-core over a single core and the behaviour of Core2Duo processor with OpenMP programming are reported. Our results reveal that the Core2Duo performance with OpenMP multithreaded programming falls behind the Core2Duo performance in a sequential mode when the workload exceeds the size of the L2 cache, also the dual core speedup drops drastically to about 1.1. Finally we measured the performance using the Stream and Stream2 benchmarks and analyse the running results.",
    keywords = "Benchmarks, Core2Duo, Memory performance, OpenMP",
    author = "Saif, {Abduljalil R A} and Jumari, {Kasmiran Bin}",
    year = "2009",
    doi = "10.1109/ICEEI.2009.5254756",
    language = "English",
    isbn = "9781424449132",
    volume = "2",
    pages = "532--536",
    booktitle = "Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009",

    }

    TY - GEN

    T1 - Performance study of core2duo desktop processors

    AU - Saif, Abduljalil R A

    AU - Jumari, Kasmiran Bin

    PY - 2009

    Y1 - 2009

    N2 - The multicore processors turned out to open the doors to make the desktop to have parallel and high performance capability. In this paper, the performance study for these systems is presented, in which the studies were carried out on the Intel's Core2Duo processor with an OpenMP programming integrated into Microsoft visual studio C++ 2005 and Intel C++ 10.1.020 compiler. Using multithreaded programming, this paper provides the performance measurement for dual core over a single core and assessing the performance of the OpenMP multithreaded programming on a Core2Duo processor. The speedup of dual-core over a single core and the behaviour of Core2Duo processor with OpenMP programming are reported. Our results reveal that the Core2Duo performance with OpenMP multithreaded programming falls behind the Core2Duo performance in a sequential mode when the workload exceeds the size of the L2 cache, also the dual core speedup drops drastically to about 1.1. Finally we measured the performance using the Stream and Stream2 benchmarks and analyse the running results.

    AB - The multicore processors turned out to open the doors to make the desktop to have parallel and high performance capability. In this paper, the performance study for these systems is presented, in which the studies were carried out on the Intel's Core2Duo processor with an OpenMP programming integrated into Microsoft visual studio C++ 2005 and Intel C++ 10.1.020 compiler. Using multithreaded programming, this paper provides the performance measurement for dual core over a single core and assessing the performance of the OpenMP multithreaded programming on a Core2Duo processor. The speedup of dual-core over a single core and the behaviour of Core2Duo processor with OpenMP programming are reported. Our results reveal that the Core2Duo performance with OpenMP multithreaded programming falls behind the Core2Duo performance in a sequential mode when the workload exceeds the size of the L2 cache, also the dual core speedup drops drastically to about 1.1. Finally we measured the performance using the Stream and Stream2 benchmarks and analyse the running results.

    KW - Benchmarks

    KW - Core2Duo

    KW - Memory performance

    KW - OpenMP

    UR - http://www.scopus.com/inward/record.url?scp=70449637814&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=70449637814&partnerID=8YFLogxK

    U2 - 10.1109/ICEEI.2009.5254756

    DO - 10.1109/ICEEI.2009.5254756

    M3 - Conference contribution

    AN - SCOPUS:70449637814

    SN - 9781424449132

    VL - 2

    SP - 532

    EP - 536

    BT - Proceedings of the 2009 International Conference on Electrical Engineering and Informatics, ICEEI 2009

    ER -