External Facelist Calculation with Data-Parallel Primitives

dc.contributor.authorLessley, Brentonen_US
dc.contributor.authorBinyahib, Robaen_US
dc.contributor.authorMaynard, Roberten_US
dc.contributor.authorChilds, Hanken_US
dc.contributor.editorEnrico Gobbetti and Wes Bethelen_US
dc.date.accessioned2016-06-09T09:43:11Z
dc.date.available2016-06-09T09:43:11Z
dc.date.issued2016en_US
dc.description.abstractExternal facelist calculation on three-dimensional unstructured meshes is used in scientific visualization libraries to efficiently render the results of operations such as clipping, interval volumes, and material boundaries. With this study, we consider the external facelist algorithm on many-core architectures. We design and introduce two novel approaches, one based on sorting and one based on hashing. Both of these algorithms consist entirely of data-parallel primitive operations, in an effort to achieve portable performance across different architectures. We study the performance of the algorithms via experiments varying over data set, hardware, and other factors. Overall, we observe that the hashing-based implementation achieves better runtime performance for the majority of configurations, while also achieving the most-stable performance on highly unstructured data sets.en_US
dc.description.sectionheadersGeometryen_US
dc.description.seriesinformationEurographics Symposium on Parallel Graphics and Visualizationen_US
dc.identifier.doi10.2312/pgv.20161178en_US
dc.identifier.isbn978-3-03868-006-2en_US
dc.identifier.issn1727-348Xen_US
dc.identifier.pages11-20en_US
dc.identifier.urihttps://doi.org/10.2312/pgv.20161178en_US
dc.identifier.urihttps://diglib.eg.org:443/handle/10
dc.publisherThe Eurographics Associationen_US
dc.subjectD.1.3 [Programming Techniques]en_US
dc.subjectConcurrent Programmingen_US
dc.subjectParallel programmingen_US
dc.subjectI.3.3 [Computer Graphics]en_US
dc.subjectPicture/Image Generationen_US
dc.subjectDisplay algorithmsen_US
dc.titleExternal Facelist Calculation with Data-Parallel Primitivesen_US
Files
Original bundle
Now showing 1 - 1 of 1
Loading...
Thumbnail Image
Name:
011-020.pdf
Size:
1.98 MB
Format:
Adobe Portable Document Format