I wrote an non-RTX on-GPU raytracer a while back (naive compared to this) and it's super-interesting to read about the advances in compressing BVH structures.<p>But the changes also highlights a change in focus from just implementing this naively(RDNA3 technically not too much removed from the naive raytracer I wrote) to moving it to something carefully engineered and optimized for memory bandwidth (with savings circuits even built into silicon?).
Smaller data is where it’s at when optimizing nowadays. Less bandwidth required and higher cache hit rate.<p>You can compute a ton per bit transferred from DRAM. On both CPUs and GPUs.
See also:<p><a href="https://news.ycombinator.com/item?id=43548212">https://news.ycombinator.com/item?id=43548212</a><p><a href="https://news.ycombinator.com/item?id=43543933">https://news.ycombinator.com/item?id=43543933</a>