A Shader-Based Parallel Rendering Framework

Abstract

Existing parallel or remote rendering solutions rely on communicating pixels, OpenGL commands, scene-graph changes or application-specific data. We propose an intermediate solution based on a set of independent graphics primitives that use hardware shaders to specify their visual appearance. Compared to an OpenGL based approach, it reduces the complexity of the model by eliminating most fixed function parameters while giving access to the latest functionalities of graphics cards. It also suppresses the OpenGL state machine that creates data dependencies making primitive re-scheduling difficult.Using a retained-mode communication protocol transmitting changes between each frame, combined with the possibility to use shaders to implement interactive data processing operations instead of sending final colors and geometry, we are able to optimize the network load. High level information such as bounding volumes is used to setup advanced schemes where primitives are issued in parallel, routed according to their visibility, merged and re-ordered when received for rendering. Different optimization algorithms can be efficiently implemented, saving network bandwidth or reducing texture switches for instance.We present performance results based on two VTK applications, a parallel iso-surface extraction and a parallel volume renderer. We compare our approach with Chromium. Results show that our approach leads to significantly better performance and scalability, while offering easy access to hardware accelerated rendering algorithms.

Multicamera Real-Time 3D Modeling for Telepresence and Remote Collaboration

“…To distribute efficiently the rendering part, we use FlowVR Render [38]. Existing parallel or remote rendering solutions rely on communicating pixels, OpenGL commands, scene-graph changes or applicationspecific data.…”

A 3d data intensive tele-immersive grid

“…it contains all data (meshes, textures, etc.) and codes (shaders) necessary for rendering, including its position in the scene [1]. Thus, a rendering component just has the responsibility of rendering the primitives it receives.…”

“…To our knowledge, the collaborative geoscience experiment between UC Berkeley and UC Davis is one of the few tele-immersive experiments involving complex data 1 .Two persons are interacting around a scientific data set, one being present through its 3D model computed from a multi-camera system, while the other is immersed in a CAVE. This paper and the attached video show that associating multi-camera 3D modeling, data grid and interactions can lead to a rich 3D multimedia experience.…”

“…It leads to very modular distributed applications, enabling to keep the application complexity under control. A protocol for transferring 3D primitives for rendering enables to forward and combine various 3D data to the rendering hosts [1]. The 3D modeling on Grenoble and Bordeaux is a parallel application running on a cluster to produce meshes at the camera acquisition rate [11].…”

The GrImage Platform: A Mixed Reality Environment for Interactions

“…We use a new framework [2], allowing to use a different scheme for each part of the scene. Large static objects, such as the landscape, use a replicated scheme so that they are sent locally on each PC.…”