Parallel implementation of VolVis on a network of workstations (NOWs)

Author

Teck, Lui Meng ; Prakash, Edmond C.

Author_Institution

Sch. of Appl. Sci., Nanyang Technol. Inst., Singapore

Volume

1

fYear

1999

fDate

1999

Firstpage

486

Abstract

Analyzing the computational bottlenecks for parallel implementation of a huge interactive volume visualisation (VolVis) software (Avila et al., 1992; 1994) was a really challenging task. We have explored the possibility of using Cilk, PVM and MPI for parallel processing. Task partitioning has been achieved by computing the pixels of an image in parallel. We also report the parallel code developed for VolVis to run on NOWs consisting of 12 SGI O2 machines. Finally we present some experimental results and the parallel performance of VolVis for various datasets

Keywords

data visualisation; message passing; parallel processing; software performance evaluation; solid modelling; workstation clusters; Cilk; MPI; PVM; SGI O2 machines; VolVis; computational bottleneck; datasets; experimental results; interactive volume visualisation; network of workstations; parallel implementation; performance; pixels; task partitioning; Casting; Chromium; Computer graphics; Concurrent computing; Data visualization; Image generation; Parallel processing; Parallel programming; Pixel; Software performance;

fLanguage

English

Publisher

ieee

Conference_Titel

TENCON 99. Proceedings of the IEEE Region 10 Conference

Conference_Location

Cheju Island

Print_ISBN

0-7803-5739-6

Type

conf

DOI

10.1109/TENCON.1999.818457

Filename

818457