Parallel processing scheme of a basic block in a Fortran program on OSCAR

Hiroki Honda, Hironori Kasahara, Seinosuke Narita, Satoshi Mizuno

    Research output: Contribution to journalArticle

    Abstract

    With the development of the supercomputer with multiprocessors, the parallel processing of a Fortran program on the multiprocessor system is considered interesting. This paper proposes a parallel processing scheme for the Fortran program where the assignment unit (task) to the processor is the processing of an arithmetic substitution statement. The implementation and performance evaluation of the proposed scheme on the actual system are reported. In the proposed scheme, the arithmetic substitution statement in the basic block is defined as the task, and the precedence constraints among the tasks due to data dependencies are determined. Based on the derived constraints, the allocation of the tasks to the processors as well as the execution order are determined at the compiling stage, using the multiprocessor scheduling algorithm. Then the codes for the processors are generated and the parallel processing is executed. The proposed scheme was implemented on an actual system and the performance was evaluated. The effect of the parallel processing is manifested. In the conventional loop parallel processing, the effect of the parallel processing cannot be expected for the basic block in the loop or for the basic block of the scalar operation unit outside the loop. On the other hand, it was verified that the parallel processing of those blocks can be realized by applying the proposed method.

    Original languageEnglish
    Pages (from-to)1-13
    Number of pages13
    JournalSystems and Computers in Japan
    Volume22
    Issue number11
    Publication statusPublished - 1991

    Fingerprint

    Parallel Processing
    Processing
    Substitution
    Substitution reactions
    Multiprocessor Scheduling
    Data Dependency
    Precedence Constraints
    Unit
    Multiprocessor Systems
    Supercomputer
    Multiprocessor
    Supercomputers
    Scheduling Algorithm
    Scheduling algorithms
    Performance Evaluation
    Assignment
    Scalar

    ASJC Scopus subject areas

    • Computational Theory and Mathematics
    • Hardware and Architecture
    • Information Systems
    • Theoretical Computer Science

    Cite this

    Parallel processing scheme of a basic block in a Fortran program on OSCAR. / Honda, Hiroki; Kasahara, Hironori; Narita, Seinosuke; Mizuno, Satoshi.

    In: Systems and Computers in Japan, Vol. 22, No. 11, 1991, p. 1-13.

    Research output: Contribution to journalArticle

    Honda, Hiroki ; Kasahara, Hironori ; Narita, Seinosuke ; Mizuno, Satoshi. / Parallel processing scheme of a basic block in a Fortran program on OSCAR. In: Systems and Computers in Japan. 1991 ; Vol. 22, No. 11. pp. 1-13.
    @article{14fee2edf0b14f2c991ddcf09e71f34c,
    title = "Parallel processing scheme of a basic block in a Fortran program on OSCAR",
    abstract = "With the development of the supercomputer with multiprocessors, the parallel processing of a Fortran program on the multiprocessor system is considered interesting. This paper proposes a parallel processing scheme for the Fortran program where the assignment unit (task) to the processor is the processing of an arithmetic substitution statement. The implementation and performance evaluation of the proposed scheme on the actual system are reported. In the proposed scheme, the arithmetic substitution statement in the basic block is defined as the task, and the precedence constraints among the tasks due to data dependencies are determined. Based on the derived constraints, the allocation of the tasks to the processors as well as the execution order are determined at the compiling stage, using the multiprocessor scheduling algorithm. Then the codes for the processors are generated and the parallel processing is executed. The proposed scheme was implemented on an actual system and the performance was evaluated. The effect of the parallel processing is manifested. In the conventional loop parallel processing, the effect of the parallel processing cannot be expected for the basic block in the loop or for the basic block of the scalar operation unit outside the loop. On the other hand, it was verified that the parallel processing of those blocks can be realized by applying the proposed method.",
    author = "Hiroki Honda and Hironori Kasahara and Seinosuke Narita and Satoshi Mizuno",
    year = "1991",
    language = "English",
    volume = "22",
    pages = "1--13",
    journal = "Systems and Computers in Japan",
    issn = "0882-1666",
    publisher = "John Wiley and Sons Inc.",
    number = "11",

    }

    TY - JOUR

    T1 - Parallel processing scheme of a basic block in a Fortran program on OSCAR

    AU - Honda, Hiroki

    AU - Kasahara, Hironori

    AU - Narita, Seinosuke

    AU - Mizuno, Satoshi

    PY - 1991

    Y1 - 1991

    N2 - With the development of the supercomputer with multiprocessors, the parallel processing of a Fortran program on the multiprocessor system is considered interesting. This paper proposes a parallel processing scheme for the Fortran program where the assignment unit (task) to the processor is the processing of an arithmetic substitution statement. The implementation and performance evaluation of the proposed scheme on the actual system are reported. In the proposed scheme, the arithmetic substitution statement in the basic block is defined as the task, and the precedence constraints among the tasks due to data dependencies are determined. Based on the derived constraints, the allocation of the tasks to the processors as well as the execution order are determined at the compiling stage, using the multiprocessor scheduling algorithm. Then the codes for the processors are generated and the parallel processing is executed. The proposed scheme was implemented on an actual system and the performance was evaluated. The effect of the parallel processing is manifested. In the conventional loop parallel processing, the effect of the parallel processing cannot be expected for the basic block in the loop or for the basic block of the scalar operation unit outside the loop. On the other hand, it was verified that the parallel processing of those blocks can be realized by applying the proposed method.

    AB - With the development of the supercomputer with multiprocessors, the parallel processing of a Fortran program on the multiprocessor system is considered interesting. This paper proposes a parallel processing scheme for the Fortran program where the assignment unit (task) to the processor is the processing of an arithmetic substitution statement. The implementation and performance evaluation of the proposed scheme on the actual system are reported. In the proposed scheme, the arithmetic substitution statement in the basic block is defined as the task, and the precedence constraints among the tasks due to data dependencies are determined. Based on the derived constraints, the allocation of the tasks to the processors as well as the execution order are determined at the compiling stage, using the multiprocessor scheduling algorithm. Then the codes for the processors are generated and the parallel processing is executed. The proposed scheme was implemented on an actual system and the performance was evaluated. The effect of the parallel processing is manifested. In the conventional loop parallel processing, the effect of the parallel processing cannot be expected for the basic block in the loop or for the basic block of the scalar operation unit outside the loop. On the other hand, it was verified that the parallel processing of those blocks can be realized by applying the proposed method.

    UR - http://www.scopus.com/inward/record.url?scp=0026386687&partnerID=8YFLogxK

    UR - http://www.scopus.com/inward/citedby.url?scp=0026386687&partnerID=8YFLogxK

    M3 - Article

    VL - 22

    SP - 1

    EP - 13

    JO - Systems and Computers in Japan

    JF - Systems and Computers in Japan

    SN - 0882-1666

    IS - 11

    ER -