Accelerated isosurface extraction in time-varying fields

摘要

For large time-varying data sets, memory and disk limitations cannlower the performance of visualization applications. Algorithms and datanstructures must be explicitly designed to handle these data sets innorder to achieve more interactive rates. The Temporal Branch-on-NeednOctree (T-BON) extends the three-dimensional branch-on-need octree forntime-varying isosurface extraction. This data structure minimizes thenimpact of the I/O bottleneck by reading from disk only those portions ofnthe search structure and data necessary to construct the currentnisosurface. By performing a minimum of I/O and exploiting thenhierarchical memory found in modern CPUs, the T-BON algorithm achievesnhigh performance isosurface extraction in time-varying fields. The papernextends earlier work on the T-BON data structure by including techniquesnfor better memory utilization, out-of-core isosurface extraction, andnsupport for nonrectilinear grids. Results from testing the T-BONnalgorithm on large data sets show that its performance is similar tonthat of the three-dimensional branch-on-need octree for static data setsnwhile providing substantial advantages for time varying fields