Hierarchical macro-dataflow computation scheme

Masami Okamoto, Kouichirou Yamashita, Hironori Kasahara, Seinosuke Narita

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

    3 Citations (Scopus)

    Abstract

    This paper proposes a hierarchical macro-dataflow computation scheme in a Fortran program. In addition to usually used the parallelism among loop iterations, the hierarchical macro-dataflow computation scheme allows us to hierarchically exploit the near fine grain parallelism among statements inside basic block, and the coarse grain parallelism among basic blocks, loops, or subroutines inside a main routine, subroutines, and loops. This paper describes the hierarchical definition of macrotasks, the parallelism extraction scheme among macrotasks defined inside a higher level layer macrotask and a scheduling scheme that assigns hierarchical macrotasks on hierarchical processor clusters. A result is also described of the performance of hierarchical macro-dataflow computation evaluated on a distributed shared memory and centralized memory multiprocessor system OSCAR.

    Original languageEnglish
    Title of host publicationIEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings
    Place of PublicationPiscataway, NJ, United States
    PublisherIEEE
    Pages44-49
    Number of pages6
    Publication statusPublished - 1995
    EventProceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Victoria, BC, Can
    Duration: 1995 May 171995 May 19

    Other

    OtherProceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing
    CityVictoria, BC, Can
    Period95/5/1795/5/19

    Fingerprint

    Macros
    Subroutines
    Data storage equipment
    Computer systems
    Scheduling

    ASJC Scopus subject areas

    • Signal Processing

    Cite this

    Okamoto, M., Yamashita, K., Kasahara, H., & Narita, S. (1995). Hierarchical macro-dataflow computation scheme. In IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings (pp. 44-49). Piscataway, NJ, United States: IEEE.

    Hierarchical macro-dataflow computation scheme. / Okamoto, Masami; Yamashita, Kouichirou; Kasahara, Hironori; Narita, Seinosuke.

    IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings. Piscataway, NJ, United States : IEEE, 1995. p. 44-49.

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

    Okamoto, M, Yamashita, K, Kasahara, H & Narita, S 1995, Hierarchical macro-dataflow computation scheme. in IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings. IEEE, Piscataway, NJ, United States, pp. 44-49, Proceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing, Victoria, BC, Can, 95/5/17.
    Okamoto M, Yamashita K, Kasahara H, Narita S. Hierarchical macro-dataflow computation scheme. In IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings. Piscataway, NJ, United States: IEEE. 1995. p. 44-49
    Okamoto, Masami ; Yamashita, Kouichirou ; Kasahara, Hironori ; Narita, Seinosuke. / Hierarchical macro-dataflow computation scheme. IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings. Piscataway, NJ, United States : IEEE, 1995. pp. 44-49
    @inproceedings{e33e8ffb5254418ea3c23f965a8af1c8,
    title = "Hierarchical macro-dataflow computation scheme",
    abstract = "This paper proposes a hierarchical macro-dataflow computation scheme in a Fortran program. In addition to usually used the parallelism among loop iterations, the hierarchical macro-dataflow computation scheme allows us to hierarchically exploit the near fine grain parallelism among statements inside basic block, and the coarse grain parallelism among basic blocks, loops, or subroutines inside a main routine, subroutines, and loops. This paper describes the hierarchical definition of macrotasks, the parallelism extraction scheme among macrotasks defined inside a higher level layer macrotask and a scheduling scheme that assigns hierarchical macrotasks on hierarchical processor clusters. A result is also described of the performance of hierarchical macro-dataflow computation evaluated on a distributed shared memory and centralized memory multiprocessor system OSCAR.",
    author = "Masami Okamoto and Kouichirou Yamashita and Hironori Kasahara and Seinosuke Narita",
    year = "1995",
    language = "English",
    pages = "44--49",
    booktitle = "IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings",
    publisher = "IEEE",

    }

    TY - GEN

    T1 - Hierarchical macro-dataflow computation scheme

    AU - Okamoto, Masami

    AU - Yamashita, Kouichirou

    AU - Kasahara, Hironori

    AU - Narita, Seinosuke

    PY - 1995

    Y1 - 1995

    N2 - This paper proposes a hierarchical macro-dataflow computation scheme in a Fortran program. In addition to usually used the parallelism among loop iterations, the hierarchical macro-dataflow computation scheme allows us to hierarchically exploit the near fine grain parallelism among statements inside basic block, and the coarse grain parallelism among basic blocks, loops, or subroutines inside a main routine, subroutines, and loops. This paper describes the hierarchical definition of macrotasks, the parallelism extraction scheme among macrotasks defined inside a higher level layer macrotask and a scheduling scheme that assigns hierarchical macrotasks on hierarchical processor clusters. A result is also described of the performance of hierarchical macro-dataflow computation evaluated on a distributed shared memory and centralized memory multiprocessor system OSCAR.

    AB - This paper proposes a hierarchical macro-dataflow computation scheme in a Fortran program. In addition to usually used the parallelism among loop iterations, the hierarchical macro-dataflow computation scheme allows us to hierarchically exploit the near fine grain parallelism among statements inside basic block, and the coarse grain parallelism among basic blocks, loops, or subroutines inside a main routine, subroutines, and loops. This paper describes the hierarchical definition of macrotasks, the parallelism extraction scheme among macrotasks defined inside a higher level layer macrotask and a scheduling scheme that assigns hierarchical macrotasks on hierarchical processor clusters. A result is also described of the performance of hierarchical macro-dataflow computation evaluated on a distributed shared memory and centralized memory multiprocessor system OSCAR.

    UR - http://www.scopus.com/inward/record.url?scp=0029211846&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0029211846&partnerID=8YFLogxK

    M3 - Conference contribution

    AN - SCOPUS:0029211846

    SP - 44

    EP - 49

    BT - IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Proceedings

    PB - IEEE

    CY - Piscataway, NJ, United States

    ER -