Impact analysis of performance faults in modern microprocessors

Naghmeh Karimi, Mihalis Maniatakos, Chandra Tirumurti, Abhijit Jas, Yiorgos Makris

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

    Abstract

    Towards improving performance, modern microprocessors incorporate a variety of architectural features, such as branch prediction and speculative execution, which are not critical to the correctness of their operation. While faults in the corresponding hardware may not necessarily affect functional correctness, they may, nevertheless, adversely impact performance. In this paper, we investigate quantitatively the performance impact of such faults using a superscalar, dynamicallyscheduled, out-of-order, Alpha-like microprocessor, on which we execute SPEC2000 integer benchmarks. We provide extensive fault simulation-based experimental results and we discuss how this information may guide the inclusion of additional hardware for performance loss recovery and yield enhancement.

    Original languageEnglish (US)
    Title of host publication2009 IEEE International Conference on Computer Design, ICCD 2009
    Pages91-96
    Number of pages6
    DOIs
    StatePublished - Dec 1 2009
    Event2009 IEEE International Conference on Computer Design, ICCD 2009 - Lake Tahoe, CA, United States
    Duration: Oct 4 2009Oct 7 2009

    Other

    Other2009 IEEE International Conference on Computer Design, ICCD 2009
    CountryUnited States
    CityLake Tahoe, CA
    Period10/4/0910/7/09

    Fingerprint

    Microprocessor chips
    Hardware
    Recovery

    ASJC Scopus subject areas

    • Hardware and Architecture
    • Electrical and Electronic Engineering

    Cite this

    Karimi, N., Maniatakos, M., Tirumurti, C., Jas, A., & Makris, Y. (2009). Impact analysis of performance faults in modern microprocessors. In 2009 IEEE International Conference on Computer Design, ICCD 2009 (pp. 91-96). [5413171] https://doi.org/10.1109/ICCD.2009.5413171

    Impact analysis of performance faults in modern microprocessors. / Karimi, Naghmeh; Maniatakos, Mihalis; Tirumurti, Chandra; Jas, Abhijit; Makris, Yiorgos.

    2009 IEEE International Conference on Computer Design, ICCD 2009. 2009. p. 91-96 5413171.

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

    Karimi, N, Maniatakos, M, Tirumurti, C, Jas, A & Makris, Y 2009, Impact analysis of performance faults in modern microprocessors. in 2009 IEEE International Conference on Computer Design, ICCD 2009., 5413171, pp. 91-96, 2009 IEEE International Conference on Computer Design, ICCD 2009, Lake Tahoe, CA, United States, 10/4/09. https://doi.org/10.1109/ICCD.2009.5413171
    Karimi N, Maniatakos M, Tirumurti C, Jas A, Makris Y. Impact analysis of performance faults in modern microprocessors. In 2009 IEEE International Conference on Computer Design, ICCD 2009. 2009. p. 91-96. 5413171 https://doi.org/10.1109/ICCD.2009.5413171
    Karimi, Naghmeh ; Maniatakos, Mihalis ; Tirumurti, Chandra ; Jas, Abhijit ; Makris, Yiorgos. / Impact analysis of performance faults in modern microprocessors. 2009 IEEE International Conference on Computer Design, ICCD 2009. 2009. pp. 91-96
    @inproceedings{5a3b5fca8ba5417e964b166f83bf090c,
    title = "Impact analysis of performance faults in modern microprocessors",
    abstract = "Towards improving performance, modern microprocessors incorporate a variety of architectural features, such as branch prediction and speculative execution, which are not critical to the correctness of their operation. While faults in the corresponding hardware may not necessarily affect functional correctness, they may, nevertheless, adversely impact performance. In this paper, we investigate quantitatively the performance impact of such faults using a superscalar, dynamicallyscheduled, out-of-order, Alpha-like microprocessor, on which we execute SPEC2000 integer benchmarks. We provide extensive fault simulation-based experimental results and we discuss how this information may guide the inclusion of additional hardware for performance loss recovery and yield enhancement.",
    author = "Naghmeh Karimi and Mihalis Maniatakos and Chandra Tirumurti and Abhijit Jas and Yiorgos Makris",
    year = "2009",
    month = "12",
    day = "1",
    doi = "10.1109/ICCD.2009.5413171",
    language = "English (US)",
    isbn = "9781424450282",
    pages = "91--96",
    booktitle = "2009 IEEE International Conference on Computer Design, ICCD 2009",

    }

    TY - GEN

    T1 - Impact analysis of performance faults in modern microprocessors

    AU - Karimi, Naghmeh

    AU - Maniatakos, Mihalis

    AU - Tirumurti, Chandra

    AU - Jas, Abhijit

    AU - Makris, Yiorgos

    PY - 2009/12/1

    Y1 - 2009/12/1

    N2 - Towards improving performance, modern microprocessors incorporate a variety of architectural features, such as branch prediction and speculative execution, which are not critical to the correctness of their operation. While faults in the corresponding hardware may not necessarily affect functional correctness, they may, nevertheless, adversely impact performance. In this paper, we investigate quantitatively the performance impact of such faults using a superscalar, dynamicallyscheduled, out-of-order, Alpha-like microprocessor, on which we execute SPEC2000 integer benchmarks. We provide extensive fault simulation-based experimental results and we discuss how this information may guide the inclusion of additional hardware for performance loss recovery and yield enhancement.

    AB - Towards improving performance, modern microprocessors incorporate a variety of architectural features, such as branch prediction and speculative execution, which are not critical to the correctness of their operation. While faults in the corresponding hardware may not necessarily affect functional correctness, they may, nevertheless, adversely impact performance. In this paper, we investigate quantitatively the performance impact of such faults using a superscalar, dynamicallyscheduled, out-of-order, Alpha-like microprocessor, on which we execute SPEC2000 integer benchmarks. We provide extensive fault simulation-based experimental results and we discuss how this information may guide the inclusion of additional hardware for performance loss recovery and yield enhancement.

    UR - http://www.scopus.com/inward/record.url?scp=77951017726&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=77951017726&partnerID=8YFLogxK

    U2 - 10.1109/ICCD.2009.5413171

    DO - 10.1109/ICCD.2009.5413171

    M3 - Conference contribution

    SN - 9781424450282

    SP - 91

    EP - 96

    BT - 2009 IEEE International Conference on Computer Design, ICCD 2009

    ER -