OUT-OF-CORE STREAMLINE VISUALIZATION ON LARGE UNSTRUCTURED MESHES

This paper presents an out-oi-core approach for interactive streamline construction on large unstructured tetrahedral meshes containing mill ions of elements. The out-of-core algorithm uses an octree to partitio n and restructure the raw data into subsets stored into disk flies for fast data retrieval. A memory management policy tailored to the strea mline calculations is used such that, during the streamline constructi on, only a very small amount of data are brought into the main memory on demand. By carefully scheduling computation and data fetching, the overhead oi reading data from the disk is significantly reduced and go od memory performance results. This out-of-core algorithm makes possib le interactive streamline visualization of large unstructured-grid dat a sets on a single mid-range workstation with relatively low main-memo ry capacity: 5-15 megabytes. We also demonstrate that this approach is much more efficient than relying on virtual memory and operating syst em's paging algorithms.