Eurographics Digital Library now runs dspace7. Some settings need to be completed in the next few days. Please report any problems to eg-support@eg.org. (The old server is still available at https://dlold.eg.org/ )
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.