CPU-Style SIMD Ray Traversal on GPUs

dc.contributor.author	Lier, Alexander	en_US
dc.contributor.author	Stamminger, Marc	en_US
dc.contributor.author	Selgrad, Kai	en_US
dc.contributor.editor	Patney, Anjul and Niessner, Matthias	en_US
dc.date.accessioned	2018-11-11T10:46:00Z
dc.date.available	2018-11-11T10:46:00Z
dc.date.issued	2018
dc.identifier.isbn	978-1-4503-5896-5
dc.identifier.issn	2079-8679
dc.identifier.uri	https://doi.org/10.1145/3231578.3231583
dc.identifier.uri	https://diglib.eg.org:443/handle/10.1145/3231578-3231583
dc.description.abstract	In this paper we describe and evaluate an implementation of CPUstyle SIMD ray traversal on the GPU. We show how spreading moderately wide BVHs (up to a branching factor of eight) across multiple threads in a warp can improve performance while not requiring expensive pre-processing. e presented ray-traversal method exhibits improved traversal performance especially for increasingly incoherent rays.	en_US
dc.publisher	ACM	en_US
dc.subject	Computing methodologies
dc.subject	Ray tracing
dc.subject	Shared memory algorithms
dc.subject	Vector / streaming algorithms
dc.subject	Ray tracing
dc.subject	GPU
dc.subject	SIMD
dc.title	CPU-Style SIMD Ray Traversal on GPUs	en_US
dc.description.seriesinformation	Eurographics/ ACM SIGGRAPH Symposium on High Performance Graphics
dc.description.sectionheaders	Ray Traversal, Transparency, and GPU Computing
dc.identifier.doi	10.1145/3231578.3231583