Programming environments for parallel computing: a comparison of CPS, Linda, P4, PVM, POSYBL, and TCGMSG

Author

Mattson, Timothy G.

Author_Institution

Intel Sci. Comput., Beaverton, OR, USA

Volume

2

fYear

1994

fDate

4-7 Jan. 1994

Firstpage

586

Lastpage

594

Abstract

Six portable parallel programming environments are compared. Results for two-node communication benchmarks are reported for each environment. Results for the more complicated four-node communications tests are reported for all of the environments except CPS. In every case, the benchmarks were run on an isolated Ethernet network of identical SPARCstation 1 workstations to assure reproducibility. Earlier reports based on this work omitted any opinions about the utility of these environments; in essence, the communication times were left to speak for themselves. In this paper, these opinions are included; they are useful to consider since they are based on a unique experience/spl minus/the experience of running two programs written with six different programming environments.<>

Keywords

parallel programming; performance evaluation; programming environments; software portability; CPS; Cooperative Processes Software; Ethernet network; Linda; P4; POSYBL; PVM; SPARCstation 1 workstations; TCGMSG; Theoretical Chemistry Group Message-passing system; communication times; environment utility; four-node communications tests; portable parallel programming environments; reproducibility; two-node communication benchmarks;

fLanguage

English

Publisher

ieee

Conference_Titel

System Sciences, 1994. Proceedings of the Twenty-Seventh Hawaii International Conference on

Conference_Location

Wailea, HI, USA

Print_ISBN

0-8186-5090-7

Type

conf

DOI

10.1109/HICSS.1994.323224

Filename

323224