Preceding activation scheme with graph unfolding for the parallel processing system 'Harray'

Hayato Yamana, Takashi Hagiwara, Jun Kohdate, Yoichi Muraoka

Research output: Contribution to conferencePaper

Abstract

The purpose of this work is to propose and evaluate the preceding activation scheme with graph unfolding, which translate a Fortran program into a dataflow graph and executes it efficiently. The problems in restructuring a Fortran program into a dataflow graph are that a Fortran program is not written in a single assignment rule and it has an explicit control flow. These problems result in little parallelism because many gate operations, such as T/F gates, are introduced in the dataflow graph to synchronize the data movement. Therefore, discarding these gate operations is the key to exposing parallelism in a Fortran program. The preceding activation scheme with graph unfolding is proposed to discard these gate operations. The result of the performance evaluation by the 'Harray' software simulator is presented. It is shown that the execution speed with the proposed scheme for flow graphs without backward branches is about 1.5 times as fast as that with the extended activation scheme which initiates the execution only after it is confirmed that a basic block will be selected at a conditional branch. Moreover, the execution speed is 2.7 times as fast as that with the extended activation scheme if a flow graph including backward branches is unfolded by the proposed scheme.

Original languageEnglish
Pages675-684
Number of pages10
Publication statusPublished - 1989 Dec 1
EventProceedings: Supercomputing '89 - Reno, NV, USA
Duration: 1989 Nov 131989 Nov 17

Other

OtherProceedings: Supercomputing '89
CityReno, NV, USA
Period89/11/1389/11/17

    Fingerprint

ASJC Scopus subject areas

  • Engineering(all)

Cite this

Yamana, H., Hagiwara, T., Kohdate, J., & Muraoka, Y. (1989). Preceding activation scheme with graph unfolding for the parallel processing system 'Harray'. 675-684. Paper presented at Proceedings: Supercomputing '89, Reno, NV, USA, .