An Improved Parallel Technique for Neighbour Search on CUDA

dc.contributor.authorPerea, Juan J.en_US
dc.contributor.authorCordero, Juan M.en_US
dc.contributor.editorFco. Javier Melero and Nuria Pelechanoen_US
dc.date.accessioned2017-06-26T16:32:47Z
dc.date.available2017-06-26T16:32:47Z
dc.date.issued2017
dc.description.abstractIn Computer Graphics is usual the modelling of dynamic systems through particles. The simulation of liquids, cloths, gas, smoke... are highlighted examples of that modelling. In this scope, is particularly relevant the procedure of neighbour particles searching, which represents a bottleneck in terms of computational cost. One of the most used searching techniques is the cell- based spatial division by cubes, where each cell is tagged by a hash value. Thus, all particles located into each cell have the same tag and are the candidate to be neighbours. The most useful feature of this technique is that it can be easily parallelized, what reduces the computational costs. Nevertheless, the parallelizing process has some drawbacks associated with data memory management. Also, during the process of neighbour search, it is necessary to trace into the adjacent cells to find neighbour particles, as a consequence, the computational cost is increased. To solve these shortcomings, we have developed a method that reduces the search space by considering the relative position of each particle in its own cell. This method, parallelized using CUDA, shows improvements in processing time and memory management over other ''standard'' spatial division techniques.en_US
dc.description.sectionheadersGeometry and Animation
dc.description.seriesinformationSpanish Computer Graphics Conference (CEIG)
dc.identifier.doi10.2312/ceig.20171201
dc.identifier.isbn978-3-03868-046-8
dc.identifier.issn-
dc.identifier.pages1-10
dc.identifier.urihttps://doi.org/10.2312/ceig.20171201
dc.identifier.urihttps://diglib.eg.org:443/handle/10.2312/ceig20171201
dc.publisherThe Eurographics Associationen_US
dc.subjectComputing methodologies
dc.subject> Distributed computing methodologies
dc.subjectPhysical simulation
dc.titleAn Improved Parallel Technique for Neighbour Search on CUDAen_US
Files
Original bundle
Now showing 1 - 1 of 1
No Thumbnail Available
Name:
001-010.pdf
Size:
927.21 KB
Format:
Adobe Portable Document Format
Collections