Exploring the Spectrum of Dynamic Scheduling Algorithms for Scalable Distributed-MemoryRay Tracing

Abstract

Abstract-This paper extends and evaluates a family of dynamic ray scheduling algorithms that can be performed in-situ on large distributed memory parallel computers. The key idea is to consider both ray state and data accesses when scheduling ray computations. We compare three instances of this family of algorithms against two traditional statically scheduled schemes. We show that our dynamic scheduling approach can render datasets that are larger than aggregate system memory and that cannot be rendered by existing statically scheduled ray tracers. For smaller problems that fit in aggregate memory but are larger than typical shared memory, our dynamic approach is competitive with the best static scheduling algorithm.

Data Parallel Multi‐GPU Path Tracing using Ray Queue Cycling

“…Ray forwarding has been looked at by several different researchers (e.g., [SG89, NCFL14, Nav10, Rei95]. Fouladi et al [FSP*22] proposed this for low‐cost (offline‐)rendering in the cloud.…”

Scalable Ray Tracing Using the Distributed FrameBuffer

“…Navrátil et al [NFLC12] proposed a scheduler that combines static image and data decompositions for ray tracing, roughly similar to sort-first and sort-last, respectively. However, a key difference of their approach when compared to a sort-last rasterizer is that rays will be sent between nodes, similar to Reinhard et al [RCJ99], to compute reflections and shadows.…”