Out-of-core aware multi-GPU rendering for large-scale scene visualization

We introduce an out-of-core method for multi-GPU path tracing of large-scale scenes, leveraging memory access analysis to optimize data distribution. Our approach enables efficient rendering on multi-GPU systems even when the combined GPU memory is smaller than the total scene size. By partitioning the scene between GPU and CPU memory at the memory management level, our method strategically distributes or replicates scene data across GPUs while storing the remaining data in CPU memory. This hybrid memory strategy ensures efficient access patterns and minimizes performance bottlenecks, facilitating high-quality rendering of massive scenes. The main contribution of this rendering approach is that it enables GPUs to perform accelerated path-tracing for massive scenes that would otherwise be rendered only by CPUs. Previous work on this topic has enabled the rendering of massive scenes that are distributed among memories of all GPUs on one server. However, in that method, it is not possible to render scenes larger than the total size of all GPU memories. In our paper, we show how to break this barrier and how to combine the capacity of GPU memories with CPU main memory to render massive scenes with only a minor impact on the performance. When applied to a small system with 4xGPUs, the results are equivalent to a more powerful system with 16xGPUs if using the same number of GPUs as on the smaller system. Therefore, users can use even small systems to render massive scenes.