A distributed-data implementation of the perspective shear-warp volume rendering algorithm for visualisation of large astronomical cubes

Publications of the Astronomical Society of Australia, Volume 20, Number 3, 2003

Brett Beeson1 David G. Barnes2 Paul D. Bourke1


1. Centre for Astrophysics and Supercomputing, Swinburne University of Technology, PO Box 218, Hawthorn, Australia, 3122

2. School of Physics, The University of Melbourne, Parkville, Australia 3010 barnesd@unimelb.edu.au


Abstract

We describe the first distributed-data implementation of the perspective shear-warp volume rendering algorithm, and explore its applications to large astronomical data cubes and simulation realisations. Our system distributes sub-volumes of 3-dimensional images to leaf nodes of a Beowulf-class cluster, where the rendering takes place. Junction nodes composite the sub-volume renderings together and pass the combined images upwards for further compositing or display. We demonstrate that our system out-performs other software solutions, and can render a "worst-case" 512 x 512 x 512 data volume in less than four seconds using 16 rendering and 15 compositing nodes. Our system also performs very well compared to much more expensive hardware systems. With appropriate commodity hardware, such as Swinburne's Virtual Reality Theatre or a 3Dlabs Wildcat graphics card, stereoscopic display is possible.

Keywords: methods: data analysis, techniques: image processing, surveys

PDF file