> Thanks for the link. This is an interesting topic. I had a student > work on ray reordering two years ago: > https://sites.google.com/site/vascocosta/GRAPP2017.pdf
Cool interesting. This sounds a bit like one of the ray streaming papers I read a few years ago (which had a sorting component) but rather structurally different. Do you think there was a significant finding applicable to librt? > He wasn't concerned with material sorting because we did not have > complex material evaluators in our rendering pipeline. So he focused > on sorting rays spatially. I kind of think you’d likely want to use spatial sorting even with complex shaders because you’ll likely hit the same shader spatially... of course not going to give the absolute best performance coherencywise, but probably good balance for the general case where there’s an ad hoc mixture. > You usually spend a lot of time performing the sort if you have a lot > of rays. Scene complexity is a minor issue. > > You might also find this one interesting: > http://research.nvidia.com/publication/megakernels-considered-harmful-wavefront-path-tracing-gpus Thanks! Cheers, Sean ------------------------------------------------------------------------------ Check out the vibrant tech community on one of the world's most engaging tech sites, Slashdot.org! http://sdm.link/slashdot _______________________________________________ BRL-CAD Developer mailing list brlcad-devel@lists.sourceforge.net https://lists.sourceforge.net/lists/listinfo/brlcad-devel
