Rendering Complex Scenes on Clusters with Limited Precomputation

Abstract

This paper presents a parallel ray-tracing algorithm in order to compute very large models (more than 100 million triangles) with distributed computer architecture. On a single computer, the size of the used dataset generates an out of core computation. Cluster architectures designed with off-the-shelf components offer extended capacities which allow to keep the large dataset inside the aggregated main memories. Then, to achieve scalability of operational applications, the real challenge is to exploit efficiently the amount of available memory and computing power. Ray-tracing, for high quality image rendering, spawns non-coherent rays which generate irregular tasks difficult to distribute on such architectures. In this paper we present a cache mechanism for main memory management distributed on each parallel computer and we implement a load balancing solution based on an auto adaptive algorithm to distribute the computation efficiently.

Parallel Domain Decomposition Methods for Ray-Tracing on Multi-cores and Multi-processors

“…However the additional complexity and slowdown are often not worth it, so ray-tracing is largely preferred. Ray-tracing of large scale models got also some attention [17], [21], [22]. However these results are not directly applicable to acoustics due to the assumptions made.…”

Beam-Tracing Domain Decomposition Method for Urban Acoustic Pollution

“…Efficient generation of hierarchical partitioning of good quality [39,41] for the handling of intersection detection, the use of vectorial instructions [42,41], and graphics processing unit (GPU) [15,17] allowed to accelerate the ray-tracing. Large scale models got some attention too [42,5,20]. However, these optimized methods are very efficient when the rays follow similar trajectories, which is rarely the case in acoustic analysis.…”

Ray‐tracing domain decomposition methods for real‐time simulation on multi‐core and multi‐processor systems

“…The use of vectorial instructions and graphics processing units allowed to accelerate the ray‐tracing algorithm. Many experiments were run on large‐scale models too .…”

“…The use of vectorial instructions [30,31] and graphics processing units [32,33] allowed to accelerate the ray-tracing algorithm. Many experiments were run on large-scale models too [31,34,35].The main challenge beyond the present work is to find the best compromise between both lighting and acoustics simulation and real-time rendering. In the following, we first describe the geometrical method implemented for this study.…”