On-the-Fly rendering of losslessly compressed irregular volume data

Very large irregular-grid data sets are represented as tetrahedral meshes and may incur significant disk I/O access overhead in the rendering process. An effective way to alleviate the disk I/O over- head associated with rendering large tetrahedral mesh is to re- duce the I/O bandwidth requirement through compression. Exist- ing tetrahedral mesh compression algorithms focus only on com- pression efficiency and cannot be readily integrated into the mesh rendering process, and thus demand that a compressed tetrahedral mesh be decompressed before it can be rendered into a 2D image. This paper presents an integrated tetrahedral mesh compression and rendering algorithm called Gatun, which allows compressed tetra- hedral meshes to be rendered incrementally as they are being de- compressed, thus leading to an efficient irregular grid rendering pipeline. Both compression and rendering algorithms in Gatun ex- ploit the same local connectivity information among adjacent tetra- hedra, and thus can be tightly integrated into a unified implemen- tation framework. Our tetrahedral compression algorithm is specif- ically designed to facilitate the integration with irregular grid ren- derer without any compromise in compression efficiency. A unique performance advantage of Gatun is its ability to reduce the run- time memory footprint requirement by releasing memory allocated to tetrahedra as early as possible. As a result, Gatun is able to de- crease rendering time by one or two orders of magnitude for very large tetrahedral mesh whose size exceeds the amount of physical memory. At the same time, the smaller working set and better ac- cess locality of Gatun improve the rendering performance by up to 30%, even when the input tetrahedral mesh is entirely memory- resident.