External Facelist Calculation with Data-Parallel Primitives

Lessley, Brenton; Binyahib, Roba; Maynard, Robert; Childs, Hank

External Facelist Calculation with Data-Parallel Primitives

Files

011-020.pdf (1.98 MB)

Date

2016

Authors

Lessley, Brenton
Binyahib, Roba
Maynard, Robert
Childs, Hank

Publisher

The Eurographics Association

Abstract

External 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.

        @inproceedings{10.2312:pgv.20161178
,
booktitle = {Eurographics Symposium on Parallel Graphics and Visualization
},
editor = {Enrico Gobbetti and Wes Bethel
},
title = {{External Facelist Calculation with Data-Parallel Primitives
}},
author = {Lessley, Brenton and 
Binyahib, Roba and 
Maynard, Robert and 
Childs, Hank
},
year = {2016
},
publisher = {The Eurographics Association
},
ISSN = {1727-348X
},
ISBN = {978-3-03868-006-2
},
DOI = {10.2312/pgv.20161178
}
}