Real-time ray tracing and rendering method based on GPU (Graphics Processing Unit) aggregate

Abstract

The invention discloses a real-time ray tracing and rendering method based on a GPU (Graphics Processing Unit) aggregate. The method comprises the following steps of pre-dividing each frame task to be rendered into a plurality of sub-tasks in a screen space; distributing the sub-tasks to each rendering machine node in the aggregate by using a dynamic balance mechanism; parallelly performing parallel ray tracing calculation on each pixel of the screen space of each sub-task in each rendering node by using the GPU; and after the sub-task of rendering on each rendering node is completed, sending a middle image to a managing machine node, and after the managing machine node receives rendering result images of all the sub-tasks, splicing all the rendering result images of all the sub-tasks into a final result image. The ray is highly and parallelly traced and calculated by the GPU, meanwhile intersection operation on points and triangular surface sheets is performed by a polar coordinate expression way, so that while a picture with the effect of an actual feeling is achieved, very good rendering performance is obtained, and the real-time requirement of application is met.

Description

technical field [0001] The invention relates to a rendering method in cluster rendering, in particular to a GPU cluster-based real-time ray tracing rendering method. Background technique [0002] At present, high-realistic rendering has been widely used in film special effects production, virtual reality display, interactive tour of cultural heritage and other fields. High-realistic rendering requires a lot of computing power. As the complexity of 3D scenes or models increases (currently, 3D scenes with a size of several G are very common), it is almost impossible to perform high-realistic real-time rendering on a single machine. Using cluster technology to solve this problem is the most commonly used method at present. [0003] At present, the main rendering methods mainly include ray tracing rendering and rasterized rendering, and other renderings such as radiosity. The rasterized rendering method is currently the most widely used rendering method, and it is also the mos...

AI Technical Summary

Problems solved by technology

But the biggest shortcoming of this platform is that it cannot take advantage of cluster hardware to improve efficiency

Although OpenRT supports cluster rendering, the cluster is a CPU-based cluster that does not make full use of the high-speed graphics processing capabilities of the GPU, so the CPU-based cluster cannot meet the real-time requirements of interactive applications in complex scenes; OptiX is a GPU-based rendering system, but only Rendering on a single machine is supported. For more complex 3D scenes or models, it is difficult to achieve real-time rendering speed on a single machine using Optix. The existing cluster rendering systems also have their own deficiencies and defects, which cannot meet the real-time application requirements. need