Hybrid computational model for efficient parallel volume visualization


Kose C.

International Conference on Parallel and Distributed Processing Techniques and Applications (PDPTA 99), Nevada, Amerika Birleşik Devletleri, 28 Haziran - 01 Temmuz 1999, ss.3079-3085 identifier

  • Yayın Türü: Bildiri / Tam Metin Bildiri
  • Cilt numarası:
  • Basıldığı Şehir: Nevada
  • Basıldığı Ülke: Amerika Birleşik Devletleri
  • Sayfa Sayıları: ss.3079-3085

Özet

Volume visualization is a powerful engineering tool, however, the visualization of a three: dimensional volume is computationally expensive taking significant amounts of time to produce the images on conventional computers. Parallel processing offers the possibility of rendering the volume in acceptable times. This paper discusses various strategies, which are used to cope with very large distribution of data sets associated with the ray casting algorithm used for volume visualization. Volume and image space software solutions are developed that use dynamic image and volume partitioning. Volume partitioning with clustering and image partitioning are used in combination with dynamic data management and task management strategies. A hybrid approach which selects the most efficient computational strategy as the volume is manipulated on a large distributed memory multiprocessor system.