EGPGV23: Eurographics Symposium on Parallel Graphics and Visualization

Permanent URI for this collection

https://diglib.eg.org/handle/10.2312/2633345

Browse

Browsing EGPGV23: Eurographics Symposium on Parallel Graphics and Visualization by Subject "Scientific visualization"

Now showing 1 - 2 of 2
  • Thumbnail Image
    Item
    Efficient Sphere Rendering Revisited
    (The Eurographics Association, 2023) Gralka, Patrick; Reina, Guido; Ertl, Thomas; Bujack, Roxana; Pugmire, David; Reina, Guido
    Glyphs are an intuitive way of displaying the results of atomistic simulations, usually as spheres. Raycasting of camera-aligned billboards is considered the state-of-the-art technique to render large sets of spheres in a rasterization-based pipeline since the approach was first proposed by Gumhold. Over time various acceleration techniques have been proposed, such as the rendering of point primitives as billboards, which are trivial to rasterize and avoid a high workload in the vertex pipeline. Other techniques attempt to optimize data upload and access patterns in shader programs, both relevant aspects for dynamic data. Recent advances in graphics hardware raise the question of whether these optimizations are still valid. We evaluate several rendering and data access scheme combinations on real-world datasets and derive recommendations for efficient rasterization-based sphere rendering.
  • Thumbnail Image
    Item
    A GPU-based Out-of-core Architecture for Interactive Visualization of AMR Time Series Data
    (The Eurographics Association, 2023) Alexandre-Barff, Welcome; Deleau, Hervé; Sarton, Jonathan; Ledoux, Franck; Lucas, Laurent; Bujack, Roxana; Pugmire, David; Reina, Guido
    This paper presents a scalable approach for large-scale Adaptive Mesh Refinement (AMR) time series interactive visualization. We can define AMR data as a dynamic gridding format of cells hierarchically refined from a computational domain described in this study as a regular Cartesian grid. This adaptive feature is essential for tracking time-dependent evolutionary phenomena and makes the AMR format an essential representation for 3D numerical simulations. However, the visualization of numerical simulation data highlights one critical issue: the significant increases in generated data memory footprint reaching petabytes, thus greatly exceeding the memory capabilities of the most recent graphics hardware. Therefore, the question is how to access this massive data - AMR time series in particular - for interactive visualization on a simple workstation. To overcome this main problem, we present an out-of-core GPU-based architecture. Our proposal is a cache system based on an ad-hoc bricking identified by a Space-Filling Curve (SFC) indexing and managed by a GPU-based page table that loads required AMR data on-the-fly from disk to GPU memory.