Hardware-accelerated direct visualization of unstructured volumetric meshes

buir.advisorGüdükbay, Uğur
dc.contributor.authorŞahıstan, Alper
dc.date.accessioned2022-08-15T10:32:07Z
dc.date.available2022-08-15T10:32:07Z
dc.date.copyright2022-07
dc.date.issued2022-07
dc.date.submitted2022-07-27
dc.descriptionCataloged from PDF version of article.en_US
dc.descriptionThesis (Master's): Bilkent University, Department of Computer Engineering, İhsan Doğramacı Bilkent University, 2022.en_US
dc.descriptionIncludes bibliographical references (leaves 43-51).en_US
dc.description.abstractComputational fluid dynamic simulations often produce large clusters of finite ele-ments with non-trivial, non-convex boundaries and uneven distributions among com-pute nodes, posing challenges to compositing during interactive volume rendering. Correct, in-place visualization of such clusters becomes difficult because viewing rays straddle domain boundaries across multiple compute nodes. We propose a GPU-based, scalable, memory-efficient direct volume visualization framework suitable for in situ and post hoc usage. Our approach reduces memory usage of the unstructured volume elements by leveraging an exclusive or-based index reduction scheme and provides fast ray-marching-based traversal without requiring large external data structures built over the elements. Moreover, we present a GPU-optimized deep compositing scheme that allows correct order compositing of intermediate color values accumulated across different ranks that works even for non-convex clusters. Furthermore, we illustrate that we can achieve secondary effects such as shadows and gradient shading using our method for single GPU setups. Our approach scales well on large data-parallel sys-tems and achieves interactive frame rates during visualization. We can interactively render Fun3D Small Mars Lander (14 GB / 798.4 million finite elements) and Huge Mars Lander (111.57 GB / 6.4 billion finite elements) data sets at 14 and 10 frames per second using 72 and 80 GPUs, respectively, on the Frontera supercomputer at The Texas Advanced Computing Center (TACC).en_US
dc.description.provenanceSubmitted by Betül Özen (ozen@bilkent.edu.tr) on 2022-08-15T10:32:07Z No. of bitstreams: 1 B161115.pdf: 25844538 bytes, checksum: 2a0114d6a82287b9a9a29f72551de5ca (MD5)en
dc.description.provenanceMade available in DSpace on 2022-08-15T10:32:07Z (GMT). No. of bitstreams: 1 B161115.pdf: 25844538 bytes, checksum: 2a0114d6a82287b9a9a29f72551de5ca (MD5) Previous issue date: 2022-07en
dc.description.statementofresponsibilityby Alper Şahıstanen_US
dc.embargo.release2023-01-28
dc.format.extentx, 51 leaves : illustrations, charts (some color) ; 30 cm.en_US
dc.identifier.itemidB161115
dc.identifier.urihttp://hdl.handle.net/11693/110438
dc.language.isoEnglishen_US
dc.rightsinfo:eu-repo/semantics/openAccessen_US
dc.subjectDirect volume visualizationen_US
dc.subjectUnstructured volumetric meshen_US
dc.subjectRay tracingen_US
dc.subjectAcceleration structureen_US
dc.subjectTetrahedralizationen_US
dc.subjectBounding volume hierarchyen_US
dc.subjectk-d treeen_US
dc.subjectHardware-accelerationen_US
dc.subjectGraphics Processing Uniten_US
dc.titleHardware-accelerated direct visualization of unstructured volumetric meshesen_US
dc.title.alternativeDüzensiz hacimsel ağların donanımsal hızlandırıcı yöntemleri ile doğrudan görüntülenmesien_US
dc.typeThesisen_US
thesis.degree.disciplineComputer Engineering
thesis.degree.grantorBilkent University
thesis.degree.levelMaster's
thesis.degree.nameMS (Master of Science)

Files

Original bundle

Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
B161115.pdf
Size:
24.65 MB
Format:
Adobe Portable Document Format
Description:
Full printable version

License bundle

Now showing 1 - 1 of 1
No Thumbnail Available
Name:
license.txt
Size:
1.69 KB
Format:
Item-specific license agreed upon to submission
Description: