Performance evaluation of macrodataflow computation on shared memory multiprocessors

Kento Aida*, Kiyoshi Iwasaki, Hironori Kasahara, Seinosuke Narita

*この研究の対応する著者

研究成果: Paper査読

3 被引用数 (Scopus)

抄録

The coarse grain parallel processing on shared memory multiprocessor systems has been implemented using multi-tasking. However, this scheme has drawbacks such as difficulty in the extraction of parallelism among coarse grain tasks by ordinary users and large dynamic scheduling overhead caused by operating system calls or run-time library calls. On the other hand, in the proposed Fortran macro-dataflow computation scheme, the compiler automatically generates coarse grain tasks called macrotasks, exploits parallelism among macrotasks, and generates a dynamic scheduling routine that schedules macrotasks to processors at run-time with small overhead. This paper presents performance evaluation of macrodataflow computation on shared memory multiprocessor systems. The results on four processors of a KSR1 show that macrodataflow computation reduces execution time to 1/2.81 of sequential execution time while an ordinary multi-threading reduces execution time to 1/2.19 of sequential execution time.

本文言語English
ページ50-54
ページ数5
出版ステータスPublished - 1995 1 1
イベントProceedings of the 1995 IEEE Pacific RIM Conference on Communications, Computers, and Signal Processing - Victoria, BC, Can
継続期間: 1995 5 171995 5 19

Other

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

ASJC Scopus subject areas

  • 信号処理
  • コンピュータ ネットワークおよび通信

フィンガープリント

「Performance evaluation of macrodataflow computation on shared memory multiprocessors」の研究トピックを掘り下げます。これらがまとまってユニークなフィンガープリントを構成します。

引用スタイル