Out-of-core streamline visualization on large unstructured meshes

Abstract

It's advantageous for computational scientists to have the capability to perform interactive visualization on their desktop workstations. For data on large unstructured meshes, this capability is not generally available. In particular, particle tracing on unstructured grids can result in a high percentage of non-contiguous memory accesses and therefore may perform very poorly with virtual memory paging schemes. The alternative of visualizing a lower resolution of the data degrades the original high-resolution calculations. This paper presents an out-of-core approach for interactive streamline construction on large unstructured tetrahedral meshes containing millions of elements. The out-of-core algorithm uses an octree to partition and restructure the raw data into subsets stored into disk les for fast data retrieval. A memory management policy tailored to the streamline calculations is used such that during the streamline construction only a very small amount of data are brought i n to the main memory on demand. By carefully scheduling computation and data fetching, the overhead of reading data from the disk is signicantly reduced and good memory performance results. This out-of-core algorithm makes possible interactive streamline visualization of large unstructured-grid data sets on a single mid-range workstation with relatively low main-memory capacity: 5-20 megabytes. Our test results also show that this approach i s m uch more ecient than relying on virtual memory and operating system's paging algorithms.

A modular extensible visualization system architecture for culled prioritized data streaming

“…4,17,25 In addition, Vitter presents a general introduction to out-of-core/streaming algorithms. 27 These algorithms typically read the data from disk, execute the algorithm, and write the data back to disk incrementally.…”

External memory management and simplification of huge meshes

“…Our system is based on a hierarchical data structure, called Octree-based External Memory Mesh (OEMM). Hierarchical schemes [25] have been often used in geometric processing and interactive visualization [1], [8], [9], [13], [15], [22], [24], [29], but in all these cases the hierarchical structure sets strong limitation on how and where processing can be performed. For example, the hierarchical simplification approach [13], [8], [22] simplifies some boundary elements only in the very last step of the bottom-up simplification process (i.e.…”

“…The design of EM solutions is a very active research area, and many groups are working on this issue in the graphics community as well. Recent results are: EM isosurfaces fitting [4], EM reconstruction of surfaces from point clouds [2], EM visualization [29], or EM solutions for the simplification of huge meshes [13], [17], [7], [18], [28]. Let us focus on the mesh simplification task.…”

Visualization of particle traces in virtual environments

“…During the encoding step, the maximum amount of particles per injector is calculated, and all active injectors are sorted by their Morton code 3 . Based on the final order, the particle lists for each injector are traversed.…”