Dynamic Caustic Generation for Transparent Geometry in Virtualized GPU Environment

Abstract

Cloud computing permits a significant improvement of the computational performance due to its integration of resources. Virtualization technology has an important impact on how the resources are integrated. In cloud computing, virtualization of Graphics Processing Unit (GPU) is the key technology for GPU intensive workloads such as game rendering, film production, etc. This paper proposes a strategy of the global illumination, specifically the effect of caustic of transparent geometries in virtualized framework platform. An GPU scheduling method (DGC) on different VMs was proposed to reduce the computation complexity. The feasibility of the algorithm is verified by ray tracing algorithm under OptiX frame work. We demonstrate the effectiveness of our approach with several simulated and fabricated examples under the virtualization framework.