Stream Compaction for Deferred Shading

Simple item page
dc.contributor.authorHoberock, Jareden_US
dc.contributor.authorLu, Victoren_US
dc.contributor.authorJia, Yuntaoen_US
dc.contributor.authorHart, John C.en_US
dc.contributor.editorDavid Luebke and Philipp Slusalleken_US
dc.date.accessioned2013-10-29T15:48:20Z
dc.date.available2013-10-29T15:48:20Z
dc.date.issued2009en_US
dc.description.abstractThe GPU leverages SIMD efficiency when shading because it rasterizes a triangle at a time, running the same shader on all of its fragments. Ray tracing sacrifices this shader coherence, and the result is that SIMD units often must run different shaders simultaneously resulting in serialization. We study this problem and define a new measure called heterogeneous efficiency to measure SIMD divergence among multiple shaders of different complexities in a ray tracing application. We devise seven different algorithms for scheduling shaders onto SIMD processors to avoid divergence. In all but simply shaded scenes, we show the expense of sorting shaders pays off with better overall shading performance.en_US
dc.description.seriesinformationHigh-Performance Graphicsen_US
dc.identifier.isbn978-1-60558-603-8en_US
dc.identifier.issn2079-8687en_US
dc.identifier.urihttps://doi.org/10.1145/1572769.1572797en_US
dc.publisherThe Eurographics Associationen_US
dc.titleStream Compaction for Deferred Shadingen_US
Files
Collections
High-Performance Graphics 2009